{"key":"care","title":"Robots that maintain","kanji":"守","one_line":"Make the building the robot's map and fixture, swap whole organs, and keep a remote human for exceptions.","thesis":"A fully automated habitat does not mean a humanoid fixing everything; it means few, captive robots doing scheduled tasks on fixtures the building provides, organ-level swaps instead of repairs, a fleet ledger that learns real failure rates, and a remote operator for the few percent of exceptions. The most scaled autonomous maintenance robots today (row-captive waterless PV cleaners with billions of cleanings) succeed because they are mechanically constrained, not because they are smart. Space shows the same pattern: Canadarm2/Dextre work because ORUs were designed for robots, and Astrobee needed crew for only about 20% of its console time. The non-obvious insight is that design for robot maintenance is mostly the building's job: datum sockets, rails, one handle standard, and coarse ORU granularity turn hard perception and manipulation into easy positioning. General-purpose home manipulators (NEO, Helix, LBMs) are improving fast, but in 2026 they still run on teleoperation, so ORIJO should treat them as an upgrade path, not a dependency.","subsystems":[{"id":"CARE-S1","name":"Sense and patrol (inspection)","function":"Detect degradation (leaks, hot joints, corrosion, cracks, loose latches, soiling) before it becomes failure, on a schedule and on demand.","how_it_works":"A sensor head is carried past every asset on a repeatable route, and each reading is registered to the asset's ID so trends, not snapshots, drive work orders. Thermal imagers read emitted long-wave IR to find resistive hot spots and blocked flow; ultrasonic microphones (to hundreds of kHz) pick up gas leaks and partial discharge that are inaudible; contact ultrasonic transducers measure wall thickness by time-of-flight on steel. The carrier choice is a trade between access and repeatability: fixed sensors are cheapest per reading but blind between points; legged robots climb stairs built for humans; magnetic crawlers hold contact for UT on steel; drones see envelopes and roofs. In ORIJO the building's own crease rails and 910 mm datum sockets make the route mechanically repeatable, so a rail-captive head returns to within the socket tolerance every time and image differencing becomes trivial.","options":[{"name":"Legged inspector (ANYmal, Spot)","principle":"Quadruped carrying thermal, zoom, ultrasonic-acoustic and gas payloads on autonomous routes with dock recharge","maturity":"COMMERCIAL","trl":9,"trl_why":"Sold and operated on offshore, energy and manufacturing sites; >1,500 Spot units in customer hands (claimed).","key_numbers":[{"label":"ANYmal runtime","value":"90 (90-120 min walking, 2 km)","unit":"min","basis":"reported","sources":["src-anymal-spec"]},{"label":"ANYmal 70% quick charge","value":100,"unit":"min","basis":"reported","sources":["src-anymal-spec"]},{"label":"ANYmal ultrasonic mic range","value":"0-384","unit":"kHz","basis":"reported","sources":["src-anymal-spec"]},{"label":"Spot runtime / recharge","value":"90 / 60","unit":"min","basis":"reported","sources":["src-spot-spec"]},{"label":"Spot payload","value":14,"unit":"kg","basis":"reported","sources":["src-spot-spec"]}],"best_for":["E7 steppe/farm clusters","E3 desert sites with many modules","hotel clusters (rented per visit)"],"limits":"Runtime 90 min sets a duty cycle of roughly 1:1 run:charge for Spot; IP54 (Spot) is marginal for driving rain and snow; capital cost too high to dedicate to one home."},{"name":"Rail-captive sensor head (TSURU / crease rail)","principle":"Robot locks to datum sockets on the ridge rails; the structure is the map","maturity":"EXPERIMENTAL","trl":3,"trl_why":"Concept from v3 M09 with analogues (ARMADAS lattice robots, BMU gantries, Ecoppia row robots) but no ORIJO hardware built.","key_numbers":[{"label":"TSURU target mass","value":"25-35","unit":"kg","basis":"target","sources":["src-v3-concept"]},{"label":"TSURU target avg power","value":60,"unit":"W","basis":"target","sources":["src-v3-concept"]}],"best_for":["all ORIJO environments with YOSHI ridges","E4 polar and E5 mountain where walking outside is unsafe"],"limits":"Sees only what is ridge-adjacent; one robot per contiguous rail network; untested in icing."},{"name":"Magnetic / climbing crawler (Gecko TOKA class)","principle":"Magnetic wheels hold sensor arrays (UT, EMAT, visual) against steel walls, tanks, boiler tubes","maturity":"COMMERCIAL","trl":9,"trl_why":"Gecko serves US Navy, power and refinery customers at unicorn scale; $300M Navy IDIQ (claimed).","key_numbers":[{"label":"Gecko Series D","value":125,"unit":"USD million","basis":"reported","sources":["src-gecko-trr"]},{"label":"Gecko valuation","value":1.25,"unit":"USD billion","basis":"reported","sources":["src-gecko-trr"]}],"best_for":["steel tanks, ASHI steel legs, battery cabinet enclosures (rare in ORIJO)"],"limits":"Needs ferrous substrate; ORIJO panels are LVL/composite, so relevance is limited to steel legs and tanks."},{"name":"Inspection drone","principle":"Photogrammetry and IR thermography of envelopes and roofs","maturity":"COMMERCIAL","trl":8,"trl_why":"Widely used for building energy audits (Rakha 2018 review); autonomous dock-in-a-box products exist but regulation limits unattended BVLOS flight.","key_numbers":[{"label":"Robotic built-environment inspection papers reviewed","value":269,"unit":"papers","basis":"measured","sources":["src-halder"]}],"best_for":["E1 rooftop","E7 farmland clusters","post-storm envelope surveys"],"limits":"Wind, snow, rules on unattended flight; sees surfaces only, cannot touch or fix."},{"name":"Intra-vehicular free flyer (Astrobee)","principle":"Fan-propelled cube robots that dock to recharge and survey a habitat interior","maturity":"PILOT","trl":7,"trl_why":"Operating on ISS since 2019 for research; not an operational caretaker yet.","key_numbers":[{"label":"Astrobee flying time","value":"up to 2","unit":"h","basis":"reported","sources":["src-astrobee-tfr"]}],"best_for":["E8 lunar / TSUKI interiors"],"limits":"Microgravity only; localization in a changing interior was its biggest continuing challenge."}]},{"id":"CARE-S2","name":"Surface keeping (PV, glazing, facade)","function":"Keep energy and daylight surfaces clean and keep envelopes inspected without people on ladders or ropes.","how_it_works":"Soiling is a deposition process whose rate depends on dust load, humidity (cementation after dew) and tilt; losses grow roughly linearly until rain or cleaning resets them, so the optimum is frequent light cleaning when water is scarce. The most mature autonomous answer is the row-captive robot: it rides rails on the PV row, sweeps a rotating microfibre cylinder whose helical fins create a directional airflow that pushes dust off the low edge, and parks in a dock at the row end each morning. Because it is captive to the row, it needs no perception beyond end-stops and gap sensors, which is why it reached billions of cleanings. Facades are the opposite case: a building maintenance unit (BMU) gantry positions an industrial arm with force-torque control against glass, with a human supervising from the roof.","options":[{"name":"Row-captive waterless PV robot (Ecoppia class)","principle":"Microfibre + airflow cylinder on a row-mounted frame, nightly, docked","maturity":"COMMERCIAL","trl":9,"trl_why":"Fleet counters claim 3.89 billion panel cleanings across 5 GW+; operating since 2014.","key_numbers":[{"label":"Panels cleaned (cumulative)","value":3890000000,"unit":"panels","basis":"claimed","sources":["src-ecoppia-site"]},{"label":"Autonomous cleaning sessions","value":10510000,"unit":"sessions","basis":"claimed","sources":["src-ecoppia-site"]},{"label":"Coverage rate per robot (Ketura 2014)","value":"~100","unit":"ft2/min (about 9.3 m2/min)","basis":"reported","sources":["src-ecoppia-ketura"]},{"label":"Water used","value":0,"unit":"L","basis":"reported","sources":["src-ecoppia-ketura"]},{"label":"Helix vs straight fin motor power saving","value":"20-30","unit":"%","basis":"claimed","sources":["src-pat-evermore"]}],"best_for":["E3 desert","E7 steppe","MIURA PV wings and BYOBU fences laid out as straight rows"],"limits":"Needs straight continuous rows with a rail edge; module vibration from cleaning has been studied as a microcrack risk (Figgis 2023, not verified in detail)."},{"name":"BMU-mounted robotic arm (Skyline Ozmo)","principle":"Industrial arm on a gondola with lidar, ultrasonic, force-torque sensing (sill sensors unverified); human supervisor on roof","maturity":"PILOT","trl":7,"trl_why":"Operating on one 45-storey Manhattan tower; claims ~3x faster than manual.","key_numbers":[{"label":"Speed vs traditional cleaning","value":"~3x","unit":"ratio","basis":"claimed","sources":["src-ozmo-trr"]}],"best_for":["E1 rooftop towers (not low ORIJO modules)"],"limits":"Needs a BMU; lidar struggles on transparent glass; still supervised."},{"name":"Brush crawler / hand-portable PV robot","principle":"Battery crawler with rotating brush moved row to row by a person","maturity":"COMMERCIAL","trl":9,"trl_why":"Several vendors sell them (e.g. SolarCleano); specs not verified here.","key_numbers":[],"best_for":["irregular arrays, slopes, KUMO racks"],"limits":"Human carries it between rows; not autonomous between arrays (specs unverified in this sweep)."},{"name":"Fixed-gantry facade robot (Fraunhofer SIRIUSc)","principle":"Fully automated roof gantry secures, powers and positions a facade-walking robot","maturity":"PILOT","trl":6,"trl_why":"Demonstrated on an 80 m, 4,000 m2 facade (2008); no evidence of commercial scale.","key_numbers":[{"label":"Fraunhofer HQ facade area","value":4000,"unit":"m2","basis":"reported","sources":["src-sirius"]}],"best_for":["reference for gantry + robot pairing"],"limits":"Bespoke to one building; cost not reported."}]},{"id":"CARE-S3","name":"Swap-in maintenance (organ / ORU replacement)","function":"Repair by replacement: remove a failed unit as a whole, install a spare, repair the old unit at a depot.","how_it_works":"Orbital replacement units (ORUs) concentrate failure-prone parts into boxes with robot-compatible grapple fixtures, alignment guides and captive fasteners, so a manipulator with a tool changer (Dextre) can do what used to need a spacewalk. The physics is constraint: a coarse cone or V-guide removes position error mechanically, then a fine kinematic seat fixes all six degrees of freedom, then a single driven fastener preloads it. Connectors must be blind-mate and dry-break so fluids and power survive misalignment. NASA's Astrobee team found the trap: making many small components into ORUs added captive fasteners, access geometry, mass and size, and in retrospect they would have made only a few larger subassemblies replaceable. ORIJO's JO-PORT already sets the right granularity: the organ (water unit, battery cabinet, farm cassette) is the ORU.","options":[{"name":"Manipulator with tool changer on grapple fixtures (Canadarm2 + Dextre)","principle":"Relocatable 7-joint arm walks end over end between power-data grapple fixtures; dexterous two-arm robot swaps ORUs, mostly ground-commanded","maturity":"COMMERCIAL","trl":9,"trl_why":"Operational on ISS since 2001 (arm) and 2008 (Dextre). Note: an operational agency system, not a commercially sold product; 'COMMERCIAL' here means flight-proven in routine operations.","key_numbers":[{"label":"Canadarm2 length","value":17.6,"unit":"m","basis":"reported","sources":["src-mss-wiki"]},{"label":"Canadarm2 joints","value":7,"unit":"joints","basis":"reported","sources":["src-mss-wiki"]},{"label":"Canadarm2 max payload","value":116000,"unit":"kg","basis":"reported","sources":["src-mss-wiki"]}],"best_for":["E8 lunar","reference for TSURU end-over-end walking"],"limits":"Space-qualified cost; slow, scripted, ground-supervised operations."},{"name":"Organ-level JO-PORT swap (v3 M04)","principle":"Quasi-kinematic ball/V-block datum, floating port box, dry-break couplers; robot or two people roll organ in","maturity":"EXPERIMENTAL","trl":3,"trl_why":"All parts commercial (ISO 16028 couplers, kinematic mounts); integrated socket untested.","key_numbers":[{"label":"Port box float","value":"+/-3","unit":"mm","basis":"target","sources":["src-v3-concept"]}],"best_for":["all ORIJO typologies"],"limits":"Organs up to hundreds of kg exceed TSURU payload; needs cart or crane for heavy organs."},{"name":"Component-level ORUs everywhere","principle":"Every board, fan and sensor is field-replaceable","maturity":"PILOT","trl":7,"trl_why":"Astrobee flew it; its own team judged it over-applied.","key_numbers":[],"best_for":["avoid except for wear parts"],"limits":"Mass, captive fasteners and access geometry grow; interfaces you forget (EMI, acoustics) break modularity."}]},{"id":"CARE-S4","name":"Mobile manipulation and housekeeping","function":"Do the open-ended indoor physical tasks: tidy, carry, wipe, load, fetch, reset a room.","how_it_works":"Three hardware classes exist: wheeled carts that only carry (Relay, Servi), wheeled single-arm manipulators (Stretch), and humanoids (NEO, Figure 03, Digit). The 2023-2026 change is in the policy: diffusion policies generate action chunks by iteratively denoising from noise conditioned on camera images, which handles multimodal demonstrations; large behaviour models pretrain one diffusion transformer on hundreds to thousands of hours of teleoperated demos, then finetune a new task with a fraction of the data; VLA models (Helix, pi0.5) split a slow vision-language planner (7-9 Hz) from a fast visuomotor controller (200 Hz). Reliability is still the gap: real deployments run with a human teleoperator who takes over unfamiliar tasks, and every takeover becomes training data.","options":[{"name":"Delivery cart robot (Relay, Bear Servi)","principle":"Wheeled AMR with lidar navigation, lockable bin, elevator integration","maturity":"COMMERCIAL","trl":9,"trl_why":"Deployed in hotels and restaurants, plus 10 hospitals at Relay's 2022 launch; LG took 51% of Bear Robotics (Jan 2025).","key_numbers":[{"label":"LG stake in Bear Robotics","value":51,"unit":"%","basis":"reported","sources":["src-bear-rave"]}],"best_for":["large hotels; not a 6-key ORIJO hotel"],"limits":"Carries only; value scales with corridor length, which ORIJO lacks."},{"name":"Wheeled single-arm manipulator (Hello Robot Stretch 3)","principle":"Telescoping arm on a lift mast, two-wheel base, dexterous wrist","maturity":"PILOT","trl":6,"trl_why":"Sold for research; vendor says consumer homes are not its market yet.","key_numbers":[{"label":"Stretch 3 price","value":24950,"unit":"USD","basis":"reported","sources":["src-stretch-spectrum"]},{"label":"Stretch 3 mass","value":24.5,"unit":"kg","basis":"reported","sources":["src-stretch-spectrum"]}],"best_for":["KURA core and farm bays with level floors"],"limits":"No stairs; low payload; needs level thresholds (fits ORIJO's flat jo floor)."},{"name":"Home humanoid with teleoperation fallback (1X NEO)","principle":"Tendon-driven humanoid; remote 'Expert Mode' operator guides unknown tasks","maturity":"PILOT","trl":6,"trl_why":"Preorders 2025, US deliveries planned 2026; WSJ found it teleoperated for most of the visit.","key_numbers":[{"label":"NEO price","value":"20,000 or 499/month","unit":"USD","basis":"claimed","sources":["src-neo-newatlas","src-neo-kalil"]},{"label":"NEO mass","value":30,"unit":"kg","basis":"claimed","sources":["src-neo-newatlas"]},{"label":"NEO battery","value":"~4","unit":"h","basis":"claimed","sources":["src-neo-newatlas"]},{"label":"NEO noise","value":22,"unit":"dB","basis":"claimed","sources":["src-neo-newatlas"]}],"best_for":["future home and hotel back-of-house"],"limits":"Autonomy share undisclosed; privacy of remote viewing; unit economics of teleoperators."},{"name":"Industrial humanoid (Agility Digit)","principle":"Bipedal tote handler with independent safety controller and fast-charge dock","maturity":"PILOT","trl":7,"trl_why":">65,000 operating hours at customer sites (claimed) in warehouses.","key_numbers":[{"label":"Digit 5 charge time","value":9,"unit":"min","basis":"claimed","sources":["src-digit5"]},{"label":"Digit 5 run:charge","value":"10:1","unit":"ratio","basis":"claimed","sources":["src-digit5"]},{"label":"Digit 4 totes at GXO","value":">100,000 at ~98% accuracy","unit":"totes","basis":"claimed","sources":["src-digit5"]}],"best_for":["farm logistics (crate moving) in larger HATA-MURA sites"],"limits":"Warehouse-structured tasks only."},{"name":"Learned policies (Diffusion Policy, TRI LBM, Helix, pi0.5)","principle":"Imitation learning from teleop demos with diffusion/flow heads and VLM planners","maturity":"EXPERIMENTAL","trl":5,"trl_why":"Strong lab and pilot results; no published long-run home reliability data.","key_numbers":[{"label":"Diffusion Policy average improvement over prior SOTA","value":46.9,"unit":"%","basis":"measured","sources":["src-dp"]},{"label":"LBM finetune data to match single-task (sim, unseen tasks)","value":"<30","unit":"% of task data","basis":"calculated","sources":["src-lbm"]},{"label":"LBM pretraining mixture","value":1695,"unit":"h of demos","basis":"reported","sources":["src-lbm"]},{"label":"Helix teleop training data","value":"~500","unit":"h","basis":"reported","sources":["src-figure-helix"]}],"best_for":["fixed-geometry repeated tasks: cartridge swaps at identical JO-PORTs"],"limits":"Success rates vary by task; distribution shift still degrades; evaluation is expensive (~1,800 real trials in the LBM study)."}]},{"id":"CARE-S5","name":"Prognostics: digital twin and failure ledger","function":"Turn telemetry and inspection data into predicted failures, spare-part counts and work orders.","how_it_works":"Rule-based fault detection (e.g. APAR rules for air handling units) flags known fault signatures; machine-learning condition models estimate remaining useful life; a planner schedules the swap before failure. The spares side is Bayesian: each unit type starts with a prior failure rate and an error factor; every hour without failure and every failure updates the posterior, as NASA's ISS logistics team does for ECLSS ORUs. Fleet data matters more than per-site intelligence: ISS experience moved estimates both ways (26% of ORUs proved twice as reliable, 18% worse than predicted, one 7.8x worse) and the corrected rates cut Mars-class spares mass by 3.9-6.0 t. ORIJO's advantage is identical organs across many sites, so the ledger converges quickly.","options":[{"name":"BIM/IoT digital twin with AFDD (Hosamo 2022)","principle":"APAR rule FDD + ML condition prediction + maintenance planning on BIM","maturity":"PILOT","trl":6,"trl_why":"Tested on a real Norwegian building with Aug 2019-Oct 2021 data.","key_numbers":[{"label":"Field data span","value":"26","unit":"months","basis":"measured","sources":["src-hosamo"]}],"best_for":["KURA HVAC/HRV, heat pump"],"limits":"BIM integration effort; site-specific tuning."},{"name":"Bayesian fleet failure-rate ledger (ISS MADS approach)","principle":"Prior + operating hours + failures -> posterior failure rate -> spares and swap interval","maturity":"COMMERCIAL","trl":9,"trl_why":"Used operationally by ISS logistics (MADS); the method is mature but has no off-the-shelf product for building fleets, so ORIJO's DAICHO implementation is TRL ~4.","key_numbers":[{"label":"ISS ECLSS ORUs worse than predicted","value":18,"unit":"%","basis":"measured","sources":["src-owens-iss"]},{"label":"ORUs >4x worse than predicted","value":6,"unit":"%","basis":"measured","sources":["src-owens-iss"]},{"label":"ORUs at least 2x more reliable than predicted","value":26,"unit":"%","basis":"measured","sources":["src-owens-iss"]},{"label":"Spares mass saved, 1,200-day Mars mission","value":"3.9-6.0","unit":"t","basis":"calculated","sources":["src-owens-iss"]}],"best_for":["every ORIJO organ, all environments, especially remote E4/E5"],"limits":"Needs honest failure logging and enough identical units."},{"name":"Acoustic and thermal anomaly mapping","principle":"Beam-forming microphones or ultrasonic mics locate leaks and failing mechanisms; IR finds hot joints","maturity":"PILOT","trl":7,"trl_why":"ANYmal ships acoustic imaging option; SoundSee flew on Astrobee.","key_numbers":[],"best_for":["hinge and fan bearing wear, water leaks, DC connector heating"],"limits":"Needs baselines per asset; noisy environments."}]},{"id":"CARE-S6","name":"Remote operations and teleoperation fallback","function":"Provide a human in the loop only for exceptions, from a centre that serves many sites.","how_it_works":"Every autonomous task has a confidence gate; below it the robot pauses in a safe state and pages an operator, who either issues a goal-level command ('go to this pose', as Astrobee operators do because of latency) or takes direct teleoperation. The operator's attention is the scarce resource, so a scheduler ranks which robot needs help most (scaled autonomy). Each intervention is logged as a demonstration and fed back into policy training, which is how 1X and Figure gather data. Astrobee shows the target shape: over 1,200 h of console support with only ~220 h needing crew, i.e. nearly 80% of operations needed no person at the site.","options":[{"name":"Ground-operator model (Astrobee/ISS)","principle":"Plans run autonomously; ground teleoperates simple tasks and recovery","maturity":"PILOT","trl":8,"trl_why":"Routine on ISS since 2019 but as a NASA research facility, not a commercial service; ~20% of console hours still needed crew. Terrestrial multi-site remote ops for homes is a transfer, not the same system.","key_numbers":[{"label":"Astrobee real-time operations","value":">165","unit":"operations","basis":"measured","sources":["src-astrobee-tfr"]},{"label":"Console hours / crew hours","value":">1,200 / ~220","unit":"h","basis":"measured","sources":["src-astrobee-tfr"]},{"label":"Share of console time without crew","value":"~80","unit":"%","basis":"calculated","sources":["src-astrobee-tfr"]}],"best_for":["all ORIJO remote sites via Starlink-class links"],"limits":"Latency forces goal-level commands, not joystick control."},{"name":"Consumer teleop fallback (1X Expert Mode)","principle":"Company operator sees through robot cameras and guides tasks","maturity":"PILOT","trl":6,"trl_why":"Announced 2025; operating share undisclosed.","key_numbers":[],"best_for":["home and hotel interior tasks"],"limits":"Privacy, trust (WSJ: 'noticeably teleoperated for most of her visit'), labour cost per robot."},{"name":"Remote supervision in assisted living (MoveCare field study)","principle":"Remote supervisors monitor robots in private homes","maturity":"PILOT","trl":7,"trl_why":"130-week, 10-apartment deployment.","key_numbers":[{"label":"Field study length","value":130,"unit":"weeks","basis":"measured","sources":["src-luperto"]},{"label":"Apartments","value":10,"unit":"homes","basis":"measured","sources":["src-luperto"]}],"best_for":["homes with elderly residents"],"limits":"Supervision raises acceptance but costs staff time."}]},{"id":"CARE-S7","name":"Passive durability and self-healing materials","function":"Reduce the number of maintenance tasks to begin with.","how_it_works":"Bacteria-based concrete carries alkali-tolerant spores (e.g. Bacillus) plus a calcium-lactate nutrient; when a crack lets water in, spores germinate and metabolise lactate into CO2, which precipitates as calcium carbonate and seals the crack. Intrinsic self-healing polymers reform reversible bonds (Diels-Alder, hydrogen bonds, disulfides) when warmed or pressed; extrinsic ones release healing agent from microcapsules. These heal cracks and scratches, not structural failure, and capacity is limited to a few cycles or sub-millimetre gaps. In ORIJO, concrete appears only in ASHI ground pads and some ballast; self-healing elastomers are more relevant to hinge membranes and coupler seals.","options":[{"name":"Bacteria-based self-healing concrete (Basilisk)","principle":"Spores + calcium lactate precipitate CaCO3 in water-exposed cracks","maturity":"COMMERCIAL","trl":8,"trl_why":"Sold as admixture, mortar and liquid repair; field uses in a wastewater settling tank and a bus lane.","key_numbers":[{"label":"Crack width healed","value":"up to 1","unit":"mm","basis":"claimed","sources":["src-basilisk"]},{"label":"Bus-lane life extension","value":15,"unit":"years","basis":"claimed","sources":["src-basilisk"]}],"best_for":["ASHI pads, KUMO water tanks, E7 farm slabs"],"limits":"Needs water to activate; cost premium not stated; heals non-structural cracks."},{"name":"Self-healing polymers and coatings","principle":"Reversible covalent/supramolecular bonds or microcapsules","maturity":"PILOT","trl":5,"trl_why":"Coatings exist commercially in niches; structural use remains research (Goyal 2022 review).","key_numbers":[],"best_for":["KASANE hinge membranes, gasket faces"],"limits":"Healing often needs heat or contact pressure; UV and cold resistance unproven for architecture."},{"name":"Sacrificial wear parts by design","principle":"Put wear into cheap swappable parts (wipers, seals, brushes, filters) sized to a fixed interval","maturity":"COMMERCIAL","trl":9,"trl_why":"Standard industrial practice.","key_numbers":[],"best_for":["every ORIJO organ"],"limits":"Requires logistics of consumables."}]},{"id":"CARE-S8","name":"Robot docks and energy for the robots","function":"Keep robots charged, sheltered, calibrated and reachable without people.","how_it_works":"A dock is a precision fixture: cones or V-guides bring the robot to charging contacts, and the dock doubles as the localization reference and weather shelter. The economics are set by the run-to-charge ratio: Spot runs ~90 min and recharges ~60 min (about 1.5:1), ANYmal needs 100 min for 70%, and Digit 5 claims 9 min charge for 90 min run (10:1) through high-rate cells. Higher ratios mean fewer robots per job. In ORIJO, docks live at JO-PORTs on the 48-60 V DC spine so charging draws from the house battery and can be scheduled to PV surplus.","options":[{"name":"Autonomous charging dock (Spot, ANYmal, Astrobee)","principle":"Mechanically guided contacts; robot returns at low battery","maturity":"COMMERCIAL","trl":9,"trl_why":"Shipped with commercial inspection robots and on ISS.","key_numbers":[{"label":"Spot run:charge","value":"~1.5:1","unit":"ratio","basis":"calculated","sources":["src-spot-spec"]},{"label":"Digit 5 run:charge","value":"10:1","unit":"ratio","basis":"claimed","sources":["src-digit5"]}],"best_for":["all"],"limits":"Outdoor docks need heating, ice clearing and drainage."},{"name":"JO-PORT dock on DC spine","principle":"Dock built into the tatami socket; 48-60 V DC, data, NFC handshake","maturity":"EXPERIMENTAL","trl":3,"trl_why":"Design only (v3 M04).","key_numbers":[],"best_for":["all ORIJO typologies"],"limits":"Untested."}]}],"projects":[{"id":"PRJ-01","name":"TOKA / Komodo crawlers + Cantilever","org":"Gecko Robotics","country":"US","year_or_period":"2013-2026","what":"Wall-climbing inspection robots and an analytics platform for power, refining and naval assets","status":"active","outcome_or_lesson":"Data platform plus robots won defence contracts ($71M, expanded to a $300M IDIQ) and a $1.25B valuation; the money is in the data layer, not the robot alone.","sources":["src-gecko-trr","src-gecko-site"]},{"id":"PRJ-02","name":"ANYmal / ANYmal X","org":"ANYbotics (ETH Zurich spin-off)","country":"CH","year_or_period":"2016-2026","what":"Autonomous quadruped inspector with thermal, acoustic and gas payloads; Ex-proof variant","status":"active","outcome_or_lesson":"Offshore HVDC field trials showed legged robots can patrol human-built plants; product runtime still ~90 min, so docks are essential.","sources":["src-anymal-spec","src-anymal-hvdc","src-anybotics-60m"]},{"id":"PRJ-03","name":"Spot","org":"Boston Dynamics (Hyundai)","country":"US","year_or_period":"2020-2026","what":"Commercial quadruped for inspection, data capture and manipulation","status":"shipped","outcome_or_lesson":">1,500 units in customer hands (claimed); AB InBev cut average repair times from months to 13 days (claimed). Value comes from repeatable routes feeding work orders.","sources":["src-spot-spec","src-spot-retro"]},{"id":"PRJ-04","name":"E4 / T4 / H4 waterless PV cleaning","org":"Ecoppia","country":"IL","year_or_period":"2014-2026","what":"Row-captive nightly microfibre + airflow PV cleaning robots","status":"active","outcome_or_lesson":"The most scaled fully autonomous maintenance robot found: captive to fixed geometry, so perception is minimal. Template for ORIJO surface robots.","sources":["src-ecoppia-site","src-ecoppia-ketura","src-yt-ecoppia"]},{"id":"PRJ-05","name":"Ketura solar park","org":"Ecoppia / Arava Power","country":"IL","year_or_period":"2014","what":"100 robots clean a 20-acre PV park nightly without water","status":"shipped","outcome_or_lesson":"Replaced roughly nine water washes a year (each up to five days) with zero-water nightly cleaning.","sources":["src-ecoppia-ketura"]},{"id":"PRJ-06","name":"Ozmo","org":"Skyline Robotics","country":"US/IL","year_or_period":"2019-2026","what":"KUKA arm on a building maintenance unit cleaning a 45-storey Manhattan facade","status":"pilot","outcome_or_lesson":"Claims ~3x speed but still needs a rooftop supervisor; lidar struggles on transparent glass, so ultrasonic sensors were added.","sources":["src-ozmo-trr","src-yt-ozmo"]},{"id":"PRJ-07","name":"SIRIUSc","org":"Fraunhofer IFF","country":"DE","year_or_period":"2004-2008","what":"Fully automated gantry + facade robot for an 80 m, 4,000 m2 facade","status":"research","outcome_or_lesson":"Showed that the gantry (positioning, power, safety) is half the system; no scale-up evidence found.","sources":["src-sirius"]},{"id":"PRJ-08","name":"Henn-na Hotel","org":"H.I.S. Group","country":"JP","year_or_period":"2015-2026","what":"Robot-staffed hotel with 243 robots","status":"active (scaled back)","outcome_or_lesson":"Decommissioned about half of 243 robots in 2019 because they created more work for humans; the chain survived by keeping robots as novelty/check-in features with human staff behind them (25 locations listed in Oct 2026). Guest-facing robots without a human backup fail; robots as an attraction plus humans as the service can persist.","sources":["src-henn-futurism","src-henn-verge","src-henn-bhimasta","src-henn-site"]},{"id":"PRJ-09","name":"Relay (ex-Savioke)","org":"Relay Robotics","country":"US","year_or_period":"2013-2026","what":"Hotel and hospital delivery robot","status":"active","outcome_or_lesson":"Savioke's assets were acquired by an undisclosed buyer and relaunched as Relay Robotics in May 2022; hospitality stayed the core market, with hospitals (10 at launch) and real estate as adjacent markets. Single-task delivery needed new verticals to grow.","sources":["src-relay-trr"]},{"id":"PRJ-10","name":"Servi","org":"Bear Robotics (LG Electronics 51%)","country":"US/KR","year_or_period":"2017-2026","what":"Restaurant and hospitality serving robots","status":"active","outcome_or_lesson":"Consolidated into a large manufacturer (LG call option to 51% exercised 2025-01-22); KED Global reports it sounding out PE firms for up to 400 billion won (~$300M) pre-IPO funding ahead of a potential Nasdaq listing (2026-09-07, reported, not confirmed by the company).","sources":["src-bear-rave","src-bear-ked"]},{"id":"PRJ-11","name":"Roomba","org":"iRobot","country":"US","year_or_period":"2002-2026","what":"Consumer floor-cleaning robots","status":"restructured (bankruptcy; acquired by contract manufacturer)","outcome_or_lesson":"Filed Chapter 11 on 2025-12-14; emerged by Jan 2026 as a privately held, wholly owned subsidiary of its contract manufacturer and lender Shenzhen Picea, still selling and supporting Roombas. The independent company failed; the product survived as a commodity. Lesson: a one-task home robot is a manufacturing-cost game.","sources":["src-irobot-md","src-irobot-trr"]},{"id":"PRJ-12","name":"NEO","org":"1X Technologies","country":"NO/US","year_or_period":"2023-2026","what":"Home humanoid sold at $20,000 or $499/month with remote 'Expert Mode' teleoperation","status":"pilot","outcome_or_lesson":"Teleoperation openly offered as the bridge to autonomy; WSJ found it mostly teleoperated. Honesty about remote operators is now a product feature.","sources":["src-neo-newatlas","src-neo-kalil","src-yt-neo-wsj"]},{"id":"PRJ-13","name":"Helix / Figure 03","org":"Figure AI","country":"US","year_or_period":"2025-2026","what":"Dual-system VLA (7B planner at 7-9 Hz, 80M controller at 200 Hz) for humanoids","status":"pilot","outcome_or_lesson":"~500 h of teleop data trained a generalist upper-body controller; no public success-rate numbers.","sources":["src-figure-helix"]},{"id":"PRJ-14","name":"Stretch 3","org":"Hello Robot","country":"US","year_or_period":"2020-2026","what":"Lightweight wheeled mobile manipulator","status":"shipped","outcome_or_lesson":"Sold to research ($24,950); vendor says consumer home market is not ready yet. Shows a low-mass, low-force design that is safe in homes.","sources":["src-stretch-spectrum"]},{"id":"PRJ-15","name":"Large Behavior Models","org":"Toyota Research Institute","country":"US","year_or_period":"2023-2026","what":"Multitask diffusion-transformer policies pretrained on ~1,700 h of demos","status":"research","outcome_or_lesson":"Finetuning needs under 30% of task data in sim to match single-task (interpolated estimate); the paper cites ~1,800 controlled real-world trials (elsewhere ~2,700 rollouts) to evaluate rigorously. Published in Science Robotics (2026-04-15).","sources":["src-lbm"]},{"id":"PRJ-16","name":"pi0.5","org":"Physical Intelligence","country":"US","year_or_period":"2025","what":"VLA co-trained on heterogeneous robots and web data, tested cleaning unseen homes","status":"research","outcome_or_lesson":"Open-world generalisation to new homes is now demonstrated in research; reliability for unattended use is not.","sources":["src-pi05"]},{"id":"PRJ-17","name":"Digit","org":"Agility Robotics","country":"US","year_or_period":"2023-2026","what":"Bipedal tote-handling humanoid at GXO, Schaeffler, Amazon, Toyota","status":"active","outcome_or_lesson":">65,000 operating hours; Digit 5 claims a 9-minute charge. Fast charging changes how many robots a job needs.","sources":["src-digit5"]},{"id":"PRJ-18","name":"Canadarm2 + Dextre (Mobile Servicing System)","org":"CSA / MDA / NASA","country":"CA","year_or_period":"2001-2026","what":"Relocatable arm and two-armed dexterous robot that replace ORUs outside the ISS","status":"active","outcome_or_lesson":"Most robotic ops are ground-commanded; ORU design (grapple fixtures, standard bolts) is what made robot maintenance possible.","sources":["src-mss-wiki","src-yt-dextre","src-oos-ma"]},{"id":"PRJ-19","name":"Astrobee","org":"NASA Ames","country":"US","year_or_period":"2019-2026","what":"Three free-flying IVR robots with dock recharge on ISS","status":"active","outcome_or_lesson":">165 operations; ~80% of console time without crew; biggest problem was localization in a changing interior; too many ORUs hurt the design.","sources":["src-astrobee-nasa","src-astrobee-tfr"]},{"id":"PRJ-20","name":"ISAAC","org":"NASA","country":"US","year_or_period":"2019-2023","what":"Integrated autonomous caretaking: robots + spacecraft systems + ground","status":"research","outcome_or_lesson":"Frames caretaking for uncrewed phases; Gateway planned to be uncrewed >85% of the time.","sources":["src-isaac","src-astrobee-tfr"]},{"id":"PRJ-21","name":"Canadarm3 / Gateway","org":"CSA / MDA / NASA","country":"CA/US","year_or_period":"2020-2029+","what":"8.5 m arm plus dexterous arm and ORU/tool caddy, some tasks autonomous","status":"research","outcome_or_lesson":"Delivery no earlier than 2029; CSA states intent to repurpose investments to the next lunar phase, so the Gateway path is uncertain.","sources":["src-canadarm3","src-gateway-nasa"]},{"id":"PRJ-22","name":"ISS ECLSS logistics and maintenance (MADS)","org":"NASA","country":"US","year_or_period":"2000-2026","what":"Bayesian failure-rate updating for ORUs","status":"active","outcome_or_lesson":"Operations revealed underestimated failure rates (one ORU 7.8x) and saved 3.9-6.0 t spares for Mars-class missions.","sources":["src-owens-iss"]},{"id":"PRJ-23","name":"Basilisk self-healing concrete","org":"Basilisk (TU Delft spin-off)","country":"NL","year_or_period":"2015-2026","what":"Bacteria-based healing agent, repair mortar and liquid repair","status":"active","outcome_or_lesson":"Commercial for sub-millimetre cracks in water-exposed concrete; field projects claimed.","sources":["src-basilisk","src-wiktor"]},{"id":"PRJ-24","name":"Ecuador irrigation canal","org":"TU Delft / partners","country":"EC","year_or_period":"2014","what":"First field application of bacterial self-healing concrete with natural fibres","status":"research","outcome_or_lesson":"Field use in an Andean canal where about 70% of water was lost through unlined walls.","sources":["src-jonkers-ecuador"]},{"id":"PRJ-25","name":"MoveCare","org":"EU H2020 consortium","country":"EU","year_or_period":"2017-2020","what":"Assistive robots in 10 older adults' apartments for 130 weeks","status":"research","outcome_or_lesson":"Remote supervision increased acceptance. Long-term autonomy needs a human channel.","sources":["src-luperto"]},{"id":"PRJ-26","name":"Hobbit","org":"TU Wien et al.","country":"AT","year_or_period":"2015-2016","what":"Assistive manipulation robot in 16 private homes","status":"research","outcome_or_lesson":"Real homes exposed misinterpretation failures that never appeared in labs.","sources":["src-hobbit"]},{"id":"PRJ-27","name":"SYMPARTNER","org":"TU Ilmenau / MetraLabs","country":"DE","year_or_period":"2015-2018","what":"Companion robots in 20 senior households, one week each, unsupervised","status":"research","outcome_or_lesson":"Seniors adapted quickly; robustness under domestic conditions was the hard part.","sources":["src-sympartner"]},{"id":"PRJ-28","name":"Walden Robotics","org":"Walden Robotics (origin claim 'spun out of a Toyota lab' unverified)","country":"US","year_or_period":"2026","what":"General-purpose industrial robots; $300M seed","status":"unverified","outcome_or_lesson":"Headline only: a Business Wire release (2026-07-15) title says it launched with $300M; the page returned 403 and the round type, investors and founders could not be verified. Do not cite as evidence.","sources":["src-walden"]}],"papers":[{"id":"PAP-01","title":"Robots in Inspection and Monitoring of Buildings and Infrastructure: A Systematic Review","authors":"Halder, Afsari","year":2023,"venue":"Applied Sciences","doi_or_url":"10.3390/app13042304","finding":"A content analysis of 269 papers found nine robot types, with UAVs most common, then UGVs.","type":"review"},{"id":"PAP-02","title":"Review of UAS applications in the built environment: towards automated building inspection procedures using drones","authors":"Rakha, Gorodetsky","year":2018,"venue":"Automation in Construction","doi_or_url":"10.1016/J.AUTCON.2018.05.002","finding":"Proposes a standard drone IR energy-audit procedure, tested on the Syracuse University campus (465 citations).","type":"review"},{"id":"PAP-03","title":"Climbing robots for maintenance and inspections of vertical structures: a survey","authors":"Schmidt, Berns","year":2013,"venue":"Robotics and Autonomous Systems","doi_or_url":"10.1016/j.robot.2013.09.002","finding":"Landmark survey of adhesion and locomotion principles for climbing robots (282 citations); not read in full here.","type":"review"},{"id":"PAP-04","title":"ANYmal in the Field: Solving Industrial Inspection of an Offshore HVDC Platform with a Quadrupedal Robot","authors":"Gehring, Fankhauser, Isler et al.","year":2021,"venue":"Field and Service Robotics (FSR 2019), Springer Proceedings in Advanced Robotics 2021","doi_or_url":"10.1007/978-981-15-9460-1_18","finding":"First North Sea HVDC platform trial of autonomous legged inspection (abstract only; numbers not verified).","type":"field-trial"},{"id":"PAP-05","title":"Techno-Economic Assessment of Soiling Losses and Mitigation Strategies for Solar Power Generation","authors":"Ilse, Micheli, Figgis et al.","year":2019,"venue":"Joule","doi_or_url":"10.1016/j.joule.2019.08.019","finding":"Even with optimized cleaning, soiling cuts global solar output by at least 3-4%, worth 3-5 billion EUR a year in 2018, projected to rise to 4-7% by 2023.","type":"model"},{"id":"PAP-06","title":"PV module vibration by robotic cleaning","authors":"Figgis, Bermudez, Garcia","year":2023,"venue":"Solar Energy","doi_or_url":"https://www.sciencedirect.com/science/article/pii/S0038092X2200929X","finding":"Field measurement at Qatar's QEERI of module vibration induced by cleaning robots (full text not accessed; values not verified).","type":"field-trial"},{"id":"PAP-07","title":"Kinematics, sensors and control of the fully automated facade-cleaning robot SIRIUSc","authors":"Elkmann, Lucke, Kruger et al.","year":2008,"venue":"Industrial Robot","doi_or_url":"10.1108/01439910810868543","finding":"A fully automated gantry plus robot system was built for an 80 m, 4,000 m2 facade.","type":"field-trial"},{"id":"PAP-08","title":"What causes the adoption failure of service robots? A case of Henn-na Hotel","authors":"Bhimasta, Kuo","year":2019,"venue":"UbiComp/ISWC Adjunct","doi_or_url":"10.1145/3341162.3350843","finding":"A thematic analysis of 250 negative reviews found six failure themes, including the need for human intervention, usefulness and embodiment.","type":"field-trial"},{"id":"PAP-09","title":"Her Name Was Chloe and She Delivers Stuff to Your Room","authors":"Salminen, Milenkovic","year":2020,"venue":"NordiCHI","doi_or_url":"10.1145/3419249.3420084","finding":"Of 1,289 TripAdvisor reviews of six robot hotels, 92% were positive, mostly about novelty; failures show human backup is needed.","type":"field-trial"},{"id":"PAP-10","title":"The perils of hotel technology: The robot usage resistance model","authors":"Fu, Zheng, Wong","year":2022,"venue":"Int. J. Hospitality Management","doi_or_url":"10.1016/j.ijhm.2022.103174","finding":"Staff resistance comes from excessive robot-related workload, techno-insecurity and low usability, so robots get shelved after adoption.","type":"model"},{"id":"PAP-11","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","authors":"Chi, Xu, Feng et al.","year":2023,"venue":"RSS / IJRR","doi_or_url":"10.1177/02783649241273668","finding":"Across 15 tasks from 4 benchmarks (IJRR version; 12 tasks in the RSS 2023 version), it averages 46.9% better than the prior state of the art.","type":"experiment"},{"id":"PAP-12","title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","authors":"TRI LBM Team (Barreiros et al.)","year":2025,"venue":"arXiv 2507.05331 / Science Robotics 2026","doi_or_url":"10.1126/scirobotics.aea6201","finding":"Finetuned LBMs match single-task performance on unseen sim tasks with under 30% of the task data (interpolated estimate), using about 1,695 h of pretraining demos (~545 h TRI + ~1,150 h OXE).","type":"experiment"},{"id":"PAP-13","title":"pi0.5: a Vision-Language-Action Model with Open-World Generalization","authors":"Physical Intelligence (Black, Brown et al.)","year":2025,"venue":"arXiv","doi_or_url":"10.48550/arXiv.2504.16054","finding":"Co-training on heterogeneous robot and web data lets the model do multi-step tasks in homes not seen in training (no single headline number).","type":"experiment"},{"id":"PAP-14","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","authors":"Khazatsky, Pertsch, Nair et al.","year":2024,"venue":"RSS","doi_or_url":"10.48550/arXiv.2403.12945","finding":"The dataset holds 76k demonstrations collected in diverse real environments, improving policy robustness.","type":"experiment"},{"id":"PAP-15","title":"Scaled Autonomy: Enabling Human Operators to Control Robot Fleets","authors":"Swamy, Reddy, Levine, Dragan","year":2020,"venue":"ICRA","doi_or_url":"10.1109/ICRA40945.2020.9196792","finding":"Learning which robot most needs a human lets one operator supervise more robots than unaided attention allows.","type":"experiment"},{"id":"PAP-16","title":"User feedback and remote supervision for assisted living with mobile robots: long-term autonomy field study","authors":"Luperto, Romeo, Monroy et al.","year":2022,"venue":"Robotics and Autonomous Systems","doi_or_url":"10.1016/j.robot.2022.104170","finding":"A 130-week study in 10 older adults' apartments found remote supervision increased acceptance.","type":"field-trial"},{"id":"PAP-17","title":"Results of Field Trials with a Mobile Service Robot for Older Adults in 16 Private Households","authors":"Bajones, Fischinger, Weiss et al.","year":2019,"venue":"ACM THRI","doi_or_url":"10.1145/3368554","finding":"All 16 users interacted with Hobbit daily over multiple weeks; real homes exposed misinterpretation failures.","type":"field-trial"},{"id":"PAP-18","title":"Living with a Mobile Companion Robot in your Own Apartment: 20-week field study with 20 seniors","authors":"Gross, Scheidig, Muller et al.","year":2019,"venue":"ICRA","doi_or_url":"10.1109/ICRA.2019.8793693","finding":"Two robots served 20 single-person households (ages 62-94) for a week each with no on-site support.","type":"field-trial"},{"id":"PAP-19","title":"The Robot Household Marathon Experiment","authors":"Kazhoyan, Stelter, Kenfack et al.","year":2021,"venue":"ICRA","doi_or_url":"10.1109/ICRA48506.2021.9560774","finding":"Tested extended fully autonomous pick-and-place and container opening in a household and reported the limits hit.","type":"experiment"},{"id":"PAP-20","title":"Astrobee: Free-Flying Robots for the International Space Station","authors":"Alexandrov, Barlow, Bualat, Fong, Smith et al.","year":2026,"venue":"IEEE Trans. Field Robotics","doi_or_url":"https://ntrs.nasa.gov/citations/20260001396","finding":"Over 1,200 h of console support needed only ~220 h of crew (~80% crew-free); 4 hardware problems across ~379 robot and dock sessions.","type":"field-trial"},{"id":"PAP-21","title":"International Space Station Operational Experience and its Impacts on Future Mission Supportability","authors":"Owens, de Weck","year":2018,"venue":"ICES-2018-198","doi_or_url":"https://ntrs.nasa.gov/citations/20200002558","finding":"18% of ECLSS ORUs fail more often than predicted (6% by more than 4x) and 26% are twice as reliable; corrected rates save 3.9-6.0 t of Mars spares.","type":"model"},{"id":"PAP-22","title":"Crew maintenance lessons learned from ISS and considerations for future manned missions","authors":"Bertels","year":2006,"venue":"SpaceOps 2006","doi_or_url":"10.2514/6.2006-5952","finding":"Search snippet says ISS crews had spent over 4,000 hours on maintenance by 2006 (full text not accessed; treat as unverified).","type":"field-trial"},{"id":"PAP-23","title":"On-orbit service (OOS) of spacecraft: A review of engineering developments","authors":"Li, Cheng, Liu et al.","year":2019,"venue":"Progress in Aerospace Sciences","doi_or_url":"10.1016/J.PAEROSCI.2019.01.004","finding":"Reviews OOS from Hubble's five servicing missions through ETS-VII and Orbital Express (384 citations).","type":"review"},{"id":"PAP-24","title":"Advances in Space Robots for On-Orbit Servicing: A Comprehensive Review","authors":"Ma, Jiang, Liu, Xie","year":2023,"venue":"Advanced Intelligent Systems","doi_or_url":"10.1002/aisy.202200397","finding":"Names five key challenges, including multifunctional end-effectors and ground teleoperation with long delays.","type":"review"},{"id":"PAP-25","title":"A Digital Twin predictive maintenance framework of air handling units based on AFDD","authors":"Hosamo, Svennevig, Svidt, Han","year":2022,"venue":"Energy and Buildings","doi_or_url":"10.1016/j.enbuild.2022.111988","finding":"Combines APAR fault rules, ML condition prediction and maintenance planning, validated on Aug 2019-Oct 2021 data from a Norwegian building.","type":"field-trial"},{"id":"PAP-26","title":"Application of an adapted FMEA framework for robot-inclusivity of built environments","authors":"Ng, Yeo, Ng, Budig et al.","year":2022,"venue":"Scientific Reports","doi_or_url":"10.1038/s41598-022-06902-4","finding":"Most service-robot failures trace to poor furniture design, missing clearances and hazard indicators, and sub-optimal interior planning.","type":"model"},{"id":"PAP-27","title":"Quantification of crack-healing in novel bacteria-based self-healing concrete","authors":"Wiktor, Jonkers","year":2011,"venue":"Cement and Concrete Composites","doi_or_url":"10.1016/j.cemconcomp.2011.03.012","finding":"Landmark bacterial healing study (1,177 citations); the healed crack-width values were not verified here.","type":"experiment"},{"id":"PAP-28","title":"A review on self-healing polymers for applications in spacecraft and construction of roads","authors":"Goyal, Agarwal, Bhatnagar","year":2022,"venue":"J. Applied Polymer Science","doi_or_url":"10.1002/app.52816","finding":"Compares the healing efficiency and limits of extrinsic and intrinsic self-healing polymers for space and roads.","type":"review"},{"id":"PAP-29","title":"ISAAC: An integrated system for autonomous and adaptive caretaking","authors":"Smith, Bualat et al.","year":2021,"venue":"ISS R&D Conference","doi_or_url":"https://ntrs.nasa.gov/citations/20210020134","finding":"Uses Astrobee and Robonaut as analogues to integrate IVR robots with spacecraft systems for uncrewed caretaking (no metrics given).","type":"experiment"}],"numbers":[{"id":"NUM-01","label":"Global solar output lost to soiling even with optimized cleaning","value":"3-4 (4-7 projected for 2023)","unit":"% of production","basis":"calculated","context":"Worth 3-5 billion EUR a year; sets the value of PV cleaning robots","sources":["src-ilse-joule"]},{"id":"NUM-02","label":"Ecoppia cumulative panels cleaned / sessions","value":"3.89e9 / 10.51e6","unit":"panels / sessions","basis":"claimed","context":"Company counters on 35+ sites and 5,000+ MW; an embedded figure says 4,000 MW (inconsistent)","sources":["src-ecoppia-site"]},{"id":"NUM-03","label":"Ketura robot coverage rate (per robot)","value":"~100 (about 9.3)","unit":"ft2/min (m2/min)","basis":"reported","context":"Times of Israel: each robot covers about 100 ft2 of panel per minute; 100 robots clean the 20-acre park nightly with zero water, replacing about nine water washes a year (each up to five days)","sources":["src-ecoppia-ketura"]},{"id":"NUM-04","label":"Dust efficiency loss quoted by Ecoppia (2014)","value":"up to 35","unit":"%","basis":"claimed","context":"Upper-bound desert claim; contrast with the 3-4% global average in NUM-01","sources":["src-ecoppia-ketura"]},{"id":"NUM-05","label":"Spot runtime / recharge / payload","value":"90 / 60 / 14","unit":"min / min / kg","basis":"reported","context":"IP54, -20 to 55 C; run:charge about 1.5:1","sources":["src-spot-spec"]},{"id":"NUM-06","label":"Spot units in customer hands","value":">1,500","unit":"robots","basis":"claimed","context":"Company page 2026","sources":["src-spot-spec"]},{"id":"NUM-07","label":"Spot industrial assets inspected in 2022","value":">130,000","unit":"assets","basis":"claimed","context":"AB InBev: average repair time from 'a few months' to 13 days","sources":["src-spot-retro"]},{"id":"NUM-08","label":"ANYmal battery runtime and quick charge","value":"90 run / 100 to 70% / 180 full","unit":"min","basis":"reported","context":"10 kg extra payload; IP67; customer claims +1.5% production uptime","sources":["src-anymal-spec"]},{"id":"NUM-09","label":"Digit 5 charge time / runtime / run:charge","value":"9 min; ~90 min; 10:1","unit":"min; min; ratio","basis":"claimed","context":"Digit 4 for comparison: 1-2 h charge, ~4 h runtime, 2:1. Digit 4: >65,000 operating hours at customer sites and >100,000 totes at ~98% task accuracy at GXO Flowery Branch","sources":["src-digit5"]},{"id":"NUM-10","label":"Gecko Robotics valuation / Series D","value":"1.25 / 0.125","unit":"USD billion","basis":"reported","context":"Series D and valuation reported by The Robot Report 2025-06-12. Navy figures are company press releases (claimed): $71M deal 2026-03-17; IDIQ expanded to $300M 2026-10-20 with 'savings up to $8M per ship'","sources":["src-gecko-trr","src-gecko-site"]},{"id":"NUM-11","label":"Henn-na Hotel robots decommissioned","value":"about half of 243","unit":"robots","basis":"reported","context":"Luggage robots could reach only about a quarter of rooms; in-room assistant woke guests on snoring","sources":["src-henn-futurism"]},{"id":"NUM-12","label":"Robot-hotel reviews that were positive","value":92,"unit":"% of 1,289 reviews","basis":"measured","context":"Mostly novelty-driven; failures stress human backup","sources":["src-chloe"]},{"id":"NUM-13","label":"Ozmo speed vs manual window cleaning","value":"~3x","unit":"ratio","basis":"claimed","context":"45-storey tower, rooftop supervisor still present","sources":["src-ozmo-trr"]},{"id":"NUM-14","label":"1X NEO price / mass / battery / noise","value":"20,000 USD or 499 USD/month; 30 kg; ~4 h; 22 dB","unit":"mixed","basis":"claimed","context":"Remote 'Expert Mode' teleoperation; WSJ: mostly teleoperated during visit","sources":["src-neo-newatlas","src-neo-kalil"]},{"id":"NUM-15","label":"Helix model split","value":"7B @ 7-9 Hz planner; 80M @ 200 Hz controller; ~500 h teleop data; 35 DoF","unit":"params / Hz / h","basis":"reported","context":"Runs on two onboard embedded GPUs","sources":["src-figure-helix"]},{"id":"NUM-16","label":"LBM data needed to match single-task performance on unseen sim tasks","value":"<30","unit":"% of task-specific data","basis":"calculated","context":"Interpolated from sim data-fraction sweeps (paper's own wording), not a direct real-world measurement. Pretraining ~1,695 h (~545 h TRI + ~1,150 h OXE); real SetBreakfastTable: LBM with 15% of the data beat single-task with 100% (single-task empirical success was 0)","sources":["src-lbm"]},{"id":"NUM-17","label":"Diffusion Policy average improvement","value":46.9,"unit":"%","basis":"measured","context":"15 tasks, 4 benchmarks (IJRR 2024 version; the RSS 2023 arXiv version reports 12 tasks with the same 46.9%)","sources":["src-dp"]},{"id":"NUM-18","label":"Astrobee console hours vs crew hours","value":">1,200 / ~220","unit":"h","basis":"measured","context":"Nearly 80% of console time without crew; >165 real-time operations, >90 guest-science sessions","sources":["src-astrobee-tfr"]},{"id":"NUM-19","label":"Astrobee hardware problems per session","value":"4 / 379 (about 1.1); 4 / 566 (about 0.7) if all Table X rows are counted","unit":"problems / sessions (%)","basis":"calculated","context":"Table X: Dock 164 sessions/2 problems, Batteries 164/0, Bumble 135/0, Honey 59/1, Perching Arms 23/0, Queen 21/1. 379 counts Dock + 3 robots only; sessions overlap across rows, so treat as an indicative rate, not an MTBF","sources":["src-astrobee-tfr"]},{"id":"NUM-20","label":"Astronaut time per SPHERES session (pre-Astrobee)","value":"~4","unit":"h","basis":"reported","context":"Astrobee's dock-recharge, fan propulsion design was driven by removing this burden","sources":["src-astrobee-tfr"]},{"id":"NUM-21","label":"Planned Gateway uncrewed share (as cited by Astrobee team)","value":">85","unit":"% of time","basis":"reported","context":"Stated in the Astrobee TFR paper (its ref. [29]); NASA's Gateway page (2026-07-23) gives no percentage and notes Artemis architecture updates of Feb 2026, so the programme is uncertain","sources":["src-astrobee-tfr"]},{"id":"NUM-22","label":"ISS ECLSS ORU failure-rate surprises","value":"18% worse; 6% >4x worse; 26% >=2x better; max 7.8x worse","unit":"% of ORUs","basis":"measured","context":"Bayesian updates of on-orbit data","sources":["src-owens-iss"]},{"id":"NUM-23","label":"Spares mass saved by ISS-informed failure rates (1,200-day Mars mission)","value":"3.9-6.0","unit":"t","basis":"calculated","context":"Also uncovered underestimates worth an order of magnitude in risk","sources":["src-owens-iss"]},{"id":"NUM-24","label":"Canadarm2 length / joints / max payload","value":"17.6 / 7 / 116,000","unit":"m / joints / kg","basis":"reported","context":"Walks end over end between grapple fixtures (analogue for TSURU)","sources":["src-mss-wiki"]},{"id":"NUM-25","label":"Canadarm3 large arm length; delivery","value":"8.5 m; NET 2029","unit":"m; year","basis":"reported","context":"Includes ORU and tool caddy; some tasks autonomous","sources":["src-canadarm3"]},{"id":"NUM-26","label":"Self-healing concrete crack width","value":"up to 1","unit":"mm","basis":"claimed","context":"Basilisk; activation needs water","sources":["src-basilisk"]},{"id":"NUM-27","label":"Long-term home robot field study length","value":"130","unit":"weeks (10 apartments)","basis":"measured","context":"Remote supervision raised acceptance","sources":["src-luperto"]},{"id":"NUM-28","label":"iRobot Chapter 11 filing; Picea unsecured claim","value":"2025-12-14; 98.9","unit":"date; USD million","basis":"reported","context":"Combined debt and assets 480.3 M USD at 2025-06-28; taken over by its contract manufacturer","sources":["src-irobot-md"]},{"id":"NUM-29","label":"Stretch 3 price / mass","value":"24,950 / 24.5","unit":"USD / kg","basis":"reported","context":"Research market; vendor says consumer homes are not its market yet","sources":["src-stretch-spectrum"]},{"id":"NUM-30","label":"Remote-operator capacity for ORIJO homes","value":"~200","unit":"homes per operator FTE","basis":"calculated","context":"Formula in sizing_reference.home_4p; assumes 5% intervention rate at 5 min each (target, unvalidated)","sources":["src-astrobee-tfr","src-scaled-aut"]},{"id":"NG-13","label":"Spot Explorer kit list price","value":74500,"unit":"USD (2020)","basis":"reported","context":"Robot, two batteries, charger, tablet, cases, SDK; US commercial/industrial sale only at launch; current pricing is by quote","sources":["src-spot-slashdot"]}],"failures":[{"what":"Henn-na Hotel decommissioned about half of its 243 robots (2019)","why":"Guest-facing robots handled only scripted cases (foreign passports, local questions); luggage robots reached about a quarter of rooms; failures created more human work.","lesson_for_anyground":"Keep robots back-of-house and out of guest moments; budget a human runner for the hotel; never deploy a robot whose failure mode is a guest waiting."},{"what":"iRobot filed Chapter 11 (Dec 2025) and was taken over by its contract manufacturer","why":"A narrow single-task consumer robot commoditised; the Amazon acquisition collapsed in 2024 and competitors undercut it.","lesson_for_anyground":"Do not sell the robot; sell uptime of the building (lease/service). Robots are cost lines inside the SHIKINEN lease."},{"what":"Savioke relaunched as Relay Robotics after acquisition (2022)","why":"Undisclosed acquirer formed a new entity; hotel delivery alone was a small market, so it expanded into hospitals and real estate while keeping hospitality as core.","lesson_for_anyground":"Single-task hotel robots need long corridors and volume; a 6-key ORIJO hotel has neither."},{"what":"1X NEO revealed as heavily teleoperated in the WSJ test (2025)","why":"General home autonomy is not ready; the company openly uses remote operators.","lesson_for_anyground":"Design for teleoperation from day one, with consent, privacy zones and logged interventions; market honest 'robot plus remote human' service."},{"what":"Astrobee: too many components designed as ORUs","why":"Captive fasteners, access geometry, mass and size grew; team judged that a few larger replaceable sub-assemblies would capture most of the benefit.","lesson_for_anyground":"Swap at organ level (one JO-PORT organ = one ORU) and at wear-part level only."},{"what":"Astrobee: modularity broken by unspecified interface properties (EMI on power bus, nozzle noise amplified by plenum)","why":"Power-quality and acoustic requirements were never defined at the module interface.","lesson_for_anyground":"JO-PORT spec must include DC ripple/EMI limits, acoustic and thermal limits, not just geometry and connectors."},{"what":"Astrobee: localization was the biggest continuing challenge","why":"The ISS interior changes constantly, so maps went stale faster than planned.","lesson_for_anyground":"Use fixtures (datum sockets, rails, docks) as the map; never rely on visual maps of rooms that guests rearrange."},{"what":"ISS ECLSS: some ORU failure rates were badly underestimated (one ~7.8x)","why":"Pre-flight reliability predictions lacked operating data.","lesson_for_anyground":"Start each organ type with pessimistic priors, log every failure across the fleet, and size site spares from posteriors."},{"what":"Hotel staff shelve robots after adoption (robot usage resistance)","why":"Robot-related extra workload, low usability, techno-insecurity.","lesson_for_anyground":"Measure staff minutes added by robots, not only saved; a robot that adds work is removed."},{"what":"Gateway/Canadarm3 programme uncertainty (2025-2026)","why":"Artemis architecture changes; CSA states intent to repurpose Canadarm3 investments.","lesson_for_anyground":"Do not anchor the TSUKI roadmap to a single agency programme; reuse terrestrial service grammar."},{"what":"Ozmo still needs a rooftop supervisor; lidar failed on glass","why":"Transparent surfaces defeat lidar; safety at height requires a human.","lesson_for_anyground":"Add contact or ultrasonic sensing for glazing (YOSHI-6G); keep facade work on rails, not free-flying."}],"interfaces":[{"with_layer":"energy","exchange":"kWh to robots (about 0.2-0.5 kWh/week for a TSURU-class patrol at 60 W); PV yield recovered by cleaning (3-4% average, more in deserts)","design_rule":"Docks on the 48-60 V DC spine; charge only on PV surplus; clean PV when the soiling loss times the remaining-day yield exceeds the cleaning energy and wear cost."},{"with_layer":"water","exchange":"Filter, membrane, UV and sorbent cartridge swaps; leak detection data; zero water for PV cleaning","design_rule":"Every MIZU/KUMO consumable is a front-loading cartridge with a robot handle, a cone lead-in and dry-break couplers; no tool inside the wet zone."},{"with_layer":"build","exchange":"Datum sockets, crease rails, grapple handles, as-built survey","design_rule":"Install rails and sockets at the micro-factory and survey them after unfolding; the as-built survey is the robot's map."},{"with_layer":"grow","exchange":"Maintenance of HATA rail robot and grow cassettes; shared rail and dock hardware","design_rule":"Farm and care robots share one rail profile, one dock and one cartridge handle standard."},{"with_layer":"loop","exchange":"Swap of waste cartridges (urine/zeolite, larvae digester trays); labour minutes","design_rule":"Waste organs are sealed swap cassettes; the robot never opens a waste stream."},{"with_layer":"mind","exchange":"Telemetry, inspection imagery, failure ledger, remote-operator sessions, policy updates","design_rule":"Every organ has a passport ID; every intervention is logged as a demonstration; fleet Bayesian failure rates update weekly."},{"with_layer":"structure","exchange":"Hinge thermal scans, latch close-and-verify, seal inspection, anchor-leg checks","design_rule":"Latches have a robot-readable state (sensor or visual flag) and are actuable from the ridge rail."},{"with_layer":"care","exchange":"Robots maintain robots: dock self-check, brush and wiper swaps","design_rule":"Robot wear parts are themselves cartridges at the same handle standard."}],"autonomy_ladder":[{"level":"L0","description":"All inspection, cleaning and repair done by residents or tradespeople on call.","human_minutes_per_week":"~120-180 (estimate for an off-grid home with PV, water treatment and farm; unsourced, to be measured)","enabling_tech":"Manuals, tools"},{"level":"L1","description":"Sensors and alarms: fixed IoT sensors and a dashboard tell people what to do.","human_minutes_per_week":"~90 (estimate)","enabling_tech":"IoT sensors, rule-based FDD"},{"level":"L2","description":"Captive single-task robots: PV/glazing row robots, robot vacuum, scheduled cartridge reminders.","human_minutes_per_week":"~60 (estimate)","enabling_tech":"Ecoppia-class row robots, docks"},{"level":"L3","description":"Rail-captive service robot does inspections and organ/cartridge swaps at standard ports; remote operator handles exceptions.","human_minutes_per_week":"~20 on site + ~6 remote (target, see sizing)","enabling_tech":"TSURU, JO-PORT, failure ledger, remote ops centre"},{"level":"L4","description":"Mobile manipulator handles open-ended indoor tasks with learned policies; teleop fallback below 1% of tasks.","human_minutes_per_week":"~10 on site + ~3 remote (target)","enabling_tech":"LBM/VLA policies, Stretch/humanoid, fleet learning"},{"level":"L5","description":"Self-maintaining: robots swap organs, receive drone resupply and service each other; humans only for depot repair and renewal.","human_minutes_per_week":"~0 on site; depot time per swapped organ (speculative)","enabling_tech":"Heavy-lift drone resupply, robot-serviceable robots, self-healing seals"}],"orijo_design":{"recommended_stack":[{"subsystem":"CARE-S1 Sense and patrol","choice":"Fixed sensors at every JO-PORT + TSURU-mounted thermal/acoustic head on crease rails; rent legged inspectors per cluster visit","why":"Rail-captive gives repeatable viewpoints without mapping; legged robots are COMMERCIAL but too costly per home."},{"subsystem":"CARE-S2 Surface keeping","choice":"Ecoppia-style waterless helix-microfibre crawler on MIURA/BYOBU rows, docked at hinge ends","why":"Most proven autonomous maintenance robot; zero water fits desert sites."},{"subsystem":"CARE-S3 Swap-in maintenance","choice":"Organ-level ORUs at JO-PORT + wear-part cartridges with one handle standard","why":"ISS/Dextre shows ORUs enable robot maintenance; Astrobee shows the right granularity is coarse."},{"subsystem":"CARE-S4 Mobile manipulation","choice":"No humanoid in v1; wheeled Stretch-class manipulator only in KURA and farm bays from the Catalogue phase; hotel housekeeping stays human","why":"Home autonomy is still teleop-heavy (NEO); Henn-na shows guest-facing failure costs."},{"subsystem":"CARE-S5 Prognostics","choice":"Fleet Bayesian failure ledger (DAICHO) + rule-based FDD for HRV/heat pump","why":"Identical organs across sites make posteriors converge fast; ISS saved tonnes of spares this way."},{"subsystem":"CARE-S6 Remote ops","choice":"MADOGUCHI remote ops desk with goal-level commands and intervention logging","why":"Astrobee: ~80% of operations need no person on site; logged interventions become training data."},{"subsystem":"CARE-S7 Passive durability","choice":"Bacterial self-healing concrete for ASHI pads and tanks; sacrificial wipers/seals elsewhere","why":"Cheap reduction in task count; self-healing polymers are not yet proven outdoors."},{"subsystem":"CARE-S8 Docks","choice":"JO-PORT docks on DC spine; prefer fast-charge chemistries","why":"Run:charge ratio sets robot count; Digit 5 shows 10:1 is possible."}],"new_mechanisms_or_modules":[{"name":"KAWARI handle (替わり, 'replacement')","what":"One robot-graspable handle and lead-in standard for every swappable organ, cartridge and robot wear part across water, energy, grow and loop layers.","how_it_works":"A 60-degree cone pin plus a flat-faced T-handle sits on the cartridge's front face. TSURU or a person pushes it into a socket whose cone gives about 15 mm capture, after which two balls seat in V-grooves to fix position and a quarter-turn captive bolt preloads it. Dry-break couplers mate only after the datum is seated. An NFC tag in the handle carries the passport ID, and a reed switch confirms lock. The design follows ISS ORU/grapple practice at organ granularity, not component granularity.","prototype_12mo":{"build":"3 socket variants (water filter, sorbent tray, battery module dummy) and 20 cartridges; a UR-class arm and a human test both","bom_usd":"8,000-12,000 (estimate)","test":"2,000 insert/remove cycles by arm with +/-10 mm and +/-3 deg initial error; 200 human swaps by untrained users; leak test at couplers","pass":">=99.5% first-try seat by arm; median human swap <=90 s; zero coupler leaks at 3 bar","kill":"<98% arm seat rate after two design iterations, or human swap >3 min"}},{"name":"HOKI crease broom (箒, 'broom')","what":"Waterless PV and glazing crawler that rides the MIURA wing hinge rail, parks in a JO-PORT dock at the wing root.","how_it_works":"A helical microfibre cylinder (Ecoppia/Evermore principle) rotates while the carriage travels along the fold line, generating a directional airflow that pushes dust to the low edge. The rail is the hinge line, so the crawler needs only end-stops and a gap sensor. Because MIURA wings fold, the crawler docks before folding and the dock doubles as its storm shelter. Cleaning is triggered when a reference cell shows a soiling ratio below a threshold.","prototype_12mo":{"build":"One 6 m MIURA-wing mock-up with 6 PV modules and reference cell; crawler with 1.8 m helical microfibre cylinder","bom_usd":"6,000-9,000 (estimate)","test":"Desert dust deposition chamber or field site, 90 nights; measure soiling ratio, module vibration (accelerometer) and brush wear","pass":"Keeps soiling loss <2% between cycles; module acceleration below manufacturer limit; brush life >=6 months","kill":"Soiling loss >4% or visible microcracks in EL imaging after 90 nights"}},{"name":"DAICHO ledger (台帳, 'register')","what":"A fleet-wide Bayesian failure-rate ledger and spares planner for every ORIJO organ passport.","how_it_works":"Each organ type starts with a pessimistic prior failure rate and error factor (ISS MADS practice). Operating hours without failure and each failure update a gamma-Poisson posterior. Site spares are sized so that the probability of sufficiency over the resupply interval is at least 99%, and swap intervals move with the posterior. Remote-operator interventions and robot task failures are logged in the same ledger, so robots get MTBF too.","prototype_12mo":{"build":"Software on existing telemetry from 2 pavilion sites plus bench rigs; import ISS-style priors","bom_usd":"15,000-30,000 (engineering time, estimate)","test":"Back-test on bench failure data; compare spares predicted vs consumed over 12 months","pass":"Predicted spares cover >=99% of demand with <30% excess mass","kill":"Insufficient failure events to update priors (keep as a manual log until the fleet is >20 sites)"}},{"name":"MADOGUCHI desk (窓口, 'service window')","what":"Remote operations centre where one operator supervises many sites' robots with goal-level commands.","how_it_works":"Robots stop in a safe state below a confidence threshold and post a ticket with video and a suggested action. A scaled-autonomy scheduler ranks tickets by urgency and expected operator time. The operator issues goal-level commands (pose, which cartridge, abort) rather than joystick control, which tolerates satellite latency. Every resolved ticket is stored as a demonstration for policy finetuning, and residents can see and veto camera access through privacy zones.","prototype_12mo":{"build":"One desk, 3 test robots (TSURU mock, HOKI, rented quadruped), Starlink link","bom_usd":"20,000-40,000 excluding robots (estimate)","test":"8 weeks of 24/7 operation across 2 sites; log interventions, latency, resolution time","pass":"Intervention rate <=5% of tasks; median resolution <=5 min; zero privacy-zone violations","kill":"Interventions >20% of tasks after 8 weeks, or operator load >30 min per site per week"}},{"name":"MIMAMORI head (見守り, 'watching over')","what":"A 3 kg sensor head (thermal camera, ultrasonic microphone, VOC/NH3 gas, RGB) carried by TSURU along ridge rails twice a day.","how_it_works":"At each datum socket the head captures a fixed-pose thermal and acoustic frame. Because the pose repeats to within socket tolerance, frame-to-frame differencing reveals new hot joints, leaks and latch gaps without a learned map. Anomalies above baseline create a DAICHO ticket.","prototype_12mo":{"build":"Head on a manual rail trolley over a YOSHI mock-up with seeded faults (heated connector, 0.5 L/h leak, loose latch)","bom_usd":"4,000-7,000 (estimate)","test":"60 days, 2 patrols/day, randomised seeded faults","pass":"Detects >=90% of seeded faults within 24 h with <1 false alarm per week","kill":"<70% detection or >5 false alarms per week"}}],"sizing_reference":{"home_4p":{"formula":"H_site = sum(tasks_human x min) ; R_robot = patrols/day x 7 x t_patrol + swaps/week x t_swap + PV passes/week x A_pv / r_clean ; H_remote = N_tasks x p_int x t_int ; homes_per_operator = (2,400 min/week x utilisation) / H_remote","inputs":{"patrols_per_day":"2 (target)","t_patrol_min":"15 (target)","swaps_per_week":"1.5 (assume 12 consumables, mean interval 8 weeks; target)","t_swap_robot_min":"10 (target)","A_pv_m2":"25 (assumed home array; set by energy layer)","r_clean_m2_per_min":"9.3 (Ketura, reported)","PV_passes_per_week":"7 in desert, 1 elsewhere","p_int":"0.05 (target)","t_int_min":"5 (target)","operator_utilisation":"0.5 (target)"},"results":{"robot_minutes_per_week":"210 patrol + 15 swaps + ~19 PV (desert) = ~245 min (calculated)","robot_energy_kWh_per_week":"~0.25 at 60 W (calculated)","remote_operator_min_per_week":"~23 tasks x 0.05 x 5 = ~6 min (calculated)","resident_min_per_week":"~20: receive and stow consumables delivery, approve swaps (target, matches KURA-3 crew_minutes_week 20)","homes_per_operator_FTE":"2,400 x 0.5 / 6 = ~200 (calculated)"},"basis":"calculated from targets; only r_clean is a reported external number"},"hotel_6key":{"formula":"turnovers/week = keys x occupancy x 7 / mean_stay ; H_housekeeping = turnovers x t_turn ; plus home-style care stack for the building","inputs":{"keys":6,"occupancy":"0.7 (assumed)","mean_stay_nights":"2 (assumed)","t_turn_min":"25 (target for a one-jo room designed for fast turnover; industry benchmarks not verified in this sweep)"},"results":{"turnovers_per_week":"6 x 0.7 x 7 / 2 = 14.7 (calculated)","housekeeping_human_min_per_week":"14.7 x 25 = ~370 (calculated); robots do not remove this in 2026","building_care_human_min_per_week":"~30 on site + ~10 remote (target)","robot_role":"Back-of-house only: patrol, PV, cartridge swaps, night floor vacuum; no guest-facing robots (Henn-na lesson)"},"basis":"calculated from assumptions; housekeeping time is the dominant term and must be measured at the Pavilion phase"},"farm_module":{"formula":"H = HATA robot service + cassette swaps + inspection exceptions ; robot uptime A = MTBF / (MTBF + MTTR)","inputs":{"HATA_robot_MTBF_h":"unknown; start prior 500 h (pessimistic target)","MTTR_h_with_swap":"0.5 (target via KAWARI organ swap)","MTTR_h_with_repair_on_site":"24-72 (estimate, remote site)"},"results":{"availability_with_swap":"500 / 500.5 = 99.9% (calculated)","availability_with_on_site_repair":"500 / (500 + 48) = ~91% (calculated)","human_min_per_week":"~30 (target)"},"basis":"calculated; the point is that swap-based MTTR, not MTBF, dominates availability at remote sites"}}},"open_problems":["No public long-run reliability data (MTBF, interventions per hour) for home mobile manipulators or humanoids; vendors publish demos, not failure logs.","Rail-captive robots in icing, snow load and sand: no field data for crease-rail locomotion (TSURU) in E3/E4/E5.","PV cleaning-induced module vibration and microcracks: the trade-off between cleaning frequency and module life is not quantified for lightweight folding PV wings.","Hotel room turnover remains human; bed-making and bathroom cleaning robots are not commercial. Real minutes per turnover must be measured in the Pavilion phase.","Teleoperation economics and privacy: the cost per remote intervention, latency tolerance over satellite links, and consent models for cameras in homes and guest rooms.","Interface specifications beyond geometry (EMI, ripple, acoustic, thermal) for JO-PORT, the gap Astrobee hit.","Self-healing polymers for outdoor hinge membranes: UV, cold-cycling and multi-cycle healing are unproven.","Fleet failure ledger needs enough identical units (>20 sites) before posteriors beat priors; early sites will run on pessimistic guesses.","Regulatory status of unattended drone inspection and heavy-lift resupply varies by country.","Gateway's uncertainty removes the main near-term public testbed for IVR caretaking; terrestrial analogues (ORIJO polar stations) may be the better testbed."],"sources":[{"id":"src-gecko-trr","title":"Gecko Robotics reaches unicorn status with latest funding (The Robot Report, 2025-06-12)","url":"https://www.therobotreport.com/gecko-robotics-reaches-unicorn-status-with-latest-funding/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-gecko-site","title":"Gecko Robotics home page (news items: US Navy $71M deal, IDIQ expansion to $300M)","url":"https://www.geckorobotics.com/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-gecko-cnbc","title":"Gecko Robotics raises $125 million in deal valuing startup over $1 billion (CNBC)","url":"https://www.cnbc.com/2025/06/12/gecko-robotics-raises-125-million-surpassing-billion-dollar-valuation.html","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-pat-gecko","title":"EP3974823B1 Inspection robot (Gecko Robotics, priority 2016)","url":"https://patents.google.com/patent/EP3974823B1/en","type":"patent","accessed":"2026-10-29","read_primary":false},{"id":"src-anymal-spec","title":"ANYbotics ANYmal product page","url":"https://www.anybotics.com/robotics/anymal/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-anybotics-60m","title":"ANYbotics raises $60M to expand inspection robot deployments worldwide (The Robot Report, 2024-12-12)","url":"https://www.therobotreport.com/anybotics-raises-60m-expands-inspection-robot-deployments-worldwide/","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-anymal-hvdc","title":"Gehring et al., ANYmal in the Field: Solving Industrial Inspection of an Offshore HVDC Platform with a Quadrupedal Robot (FSR 2019)","url":"https://doi.org/10.1007/978-981-15-9460-1_18","type":"paper","accessed":"2026-10-29","read_primary":false},{"id":"src-spot-spec","title":"Boston Dynamics Spot product page","url":"https://bostondynamics.com/products/spot/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-spot-retro","title":"A Retrospective on Uses of Boston Dynamics' Spot Robot (Boston Dynamics blog, 2024)","url":"https://bostondynamics.com/blog/retrospective-on-boston-dynamics-spot-robot-uses/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-ecoppia-site","title":"Ecoppia home page (fleet counters)","url":"https://www.ecoppia.com/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-ecoppia-ketura","title":"World's first self-cleaning solar park in the Arava Valley (Times of Israel, 2014-03-25)","url":"https://www.timesofisrael.com/worlds-first-self-cleaning-solar-park-in-the-arava-valley/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-pat-evermore","title":"WO2023181015A1 Waterless solar panel cleaning robot with helix shaped microfiber elements (Evermore United SA)","url":"https://patents.google.com/patent/WO2023181015A1/en","type":"patent","accessed":"2026-10-29","read_primary":true},{"id":"src-pat-ecoppia-pid","title":"WO2019186347A1 Solar panel waterless cleaning system with PID recovery","url":"https://patents.google.com/patent/WO2019186347A1/en","type":"patent","accessed":"2026-10-29","read_primary":false},{"id":"src-ilse-joule","title":"Ilse et al., Techno-Economic Assessment of Soiling Losses and Mitigation Strategies for Solar Power Generation, Joule 2019","url":"https://doi.org/10.1016/j.joule.2019.08.019","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-figgis-vib","title":"Figgis, Bermudez, Garcia, PV module vibration by robotic cleaning, Solar Energy 2023","url":"https://www.sciencedirect.com/science/article/pii/S0038092X2200929X","type":"paper","accessed":"2026-10-29","read_primary":false},{"id":"src-ozmo-trr","title":"Skyline Robotics deploys Ozmo window cleaning robot in New York City (The Robot Report, 2024-08-28)","url":"https://www.therobotreport.com/skyline-robotics-deploys-ozmo-window-cleaning-robot-new-york-city/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-sirius","title":"Elkmann et al., Kinematics, sensors and control of the fully automated facade-cleaning robot SIRIUSc for the Fraunhofer headquarters, Industrial Robot 2008","url":"https://doi.org/10.1108/01439910810868543","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-henn-futurism","title":"Japan's Robot Hotel Just Laid Off Half Its Robots (Futurism, 2019-01-15)","url":"https://futurism.com/japan-robot-hotel","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-henn-verge","title":"Japan's robot hotel lays off half the robots after they created more work for humans (The Verge, 2019-01-15)","url":"https://www.theverge.com/2019/1/15/18184198/japans-robot-hotel-lay-off-work-for-humans","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-henn-bhimasta","title":"Bhimasta & Kuo, What causes the adoption failure of service robots? A case of Henn-na Hotel in Japan (UbiComp Adjunct 2019)","url":"https://doi.org/10.1145/3341162.3350843","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-chloe","title":"Salminen & Milenkovic, 'Her Name Was Chloe and She Delivers Stuff to Your Room' (NordiCHI 2020)","url":"https://doi.org/10.1145/3419249.3420084","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-rurm","title":"Fu, Zheng, Wong, The perils of hotel technology: The robot usage resistance model (IJHM 2022)","url":"https://doi.org/10.1016/j.ijhm.2022.103174","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-relay-trr","title":"Savioke is now Relay Robotics (The Robot Report, 2022-05-02)","url":"https://www.therobotreport.com/savioke-is-now-relay-robotics/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-bear-rave","title":"LG Buys Most of Bear Robotics (rAVe Pubs, 2025-01-30)","url":"https://ravepubs.com/lg-bear-robotics-acquisition-ai-robots/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-bear-ked","title":"LG Electronics-owned Bear Robotics eyes up to $300 mn pre-IPO funding (KED Global, 2026-09-07)","url":"https://www.kedglobal.com/pre-ipos/newsView/ked202609070001","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-irobot-md","title":"Roomba maker files for Chapter 11 bankruptcy (Manufacturing Dive, 2025-12)","url":"https://www.manufacturingdive.com/news/roomba-braava-maker-irobot-chapter-11-bankruptcy-acquisition-picea-china/807997/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-irobot-trr","title":"iRobot emerges from Chapter 11 as restructured Picea U.S. subsidiary (The Robot Report, 2026-01-23)","url":"https://www.therobotreport.com/irobot-emerges-from-chapter-11-picea-u-s-subsidiary/","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-neo-newatlas","title":"1X's first robot housekeeper is available to pre-order in the US (New Atlas, 2025-10-29)","url":"https://newatlas.com/ai-humanoids/1x-neo-housekeeper-humanoid-pre-order/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-neo-kalil","title":"Is 1X's $20K Humanoid Robot for Home Too Good to Be True? (mikekalil.com, 2025-10-29)","url":"https://mikekalil.com/blog/1x-neo-humanoid-robot-for-sale/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-yt-neo-wsj","title":"I Tried the First Humanoid Home Robot. It Got Weird. (WSJ, YouTube)","url":"https://www.youtube.com/watch?v=f3c4mQty_so","type":"video","accessed":"2026-10-29","read_primary":false},{"id":"src-figure-helix","title":"Helix: A Vision-Language-Action Model for Generalist Humanoid Control (Figure, 2025-02-20)","url":"https://www.figure.ai/news/helix","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-stretch-spectrum","title":"Stretch 3 Brings Us Closer to Realistic Home Robots (IEEE Spectrum, 2024-02-15)","url":"https://spectrum.ieee.org/hello-robot-stretch-3","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-digit5","title":"Agility Robotics Unveils Digit 5 (AI Insider, 2026-09-15)","url":"https://theaiinsider.tech/2026/09/15/agility-robotics-unveils-digit-5-with-higher-payload-faster-charging-and-new-safety-system/","type":"news","accessed":"2026-10-29","read_primary":true},{"id":"src-lbm","title":"TRI LBM Team, A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation (arXiv 2507.05331; Science Robotics 2026)","url":"https://arxiv.org/abs/2507.05331","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-dp","title":"Chi et al., Diffusion Policy: Visuomotor Policy Learning via Action Diffusion (RSS 2023 / IJRR 2024)","url":"https://doi.org/10.1177/02783649241273668","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-pi05","title":"Physical Intelligence, pi0.5: a Vision-Language-Action Model with Open-World Generalization (arXiv 2504.16054)","url":"https://arxiv.org/abs/2504.16054","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-droid","title":"Khazatsky et al., DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset (RSS 2024)","url":"https://arxiv.org/abs/2403.12945","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-scaled-aut","title":"Swamy, Reddy, Levine, Dragan, Scaled Autonomy: Enabling Human Operators to Control Robot Fleets (ICRA 2020)","url":"https://doi.org/10.1109/ICRA40945.2020.9196792","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-luperto","title":"Luperto et al., User feedback and remote supervision for assisted living with mobile robots: a field study in long-term autonomy (RAS 2022)","url":"https://doi.org/10.1016/j.robot.2022.104170","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-hobbit","title":"Bajones et al., Results of Field Trials with a Mobile Service Robot for Older Adults in 16 Private Households (ACM THRI 2019)","url":"https://doi.org/10.1145/3368554","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-sympartner","title":"Gross et al., Living with a Mobile Companion Robot in your Own Apartment: 20-week field study with 20 seniors (ICRA 2019)","url":"https://doi.org/10.1109/ICRA.2019.8793693","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-marathon","title":"Kazhoyan et al., The Robot Household Marathon Experiment (ICRA 2021)","url":"https://doi.org/10.1109/ICRA48506.2021.9560774","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-astrobee-nasa","title":"NASA Ames Astrobee page","url":"https://www.nasa.gov/ames/astrobee/","type":"agency","accessed":"2026-10-29","read_primary":true},{"id":"src-astrobee-tfr","title":"Alexandrov et al., Astrobee: Free-Flying Robots for the International Space Station (IEEE Trans. Field Robotics 2026, NTRS 20260001396)","url":"https://ntrs.nasa.gov/api/citations/20260001396/downloads/astrobee_IEEE_TFR_2026_compressed.pdf","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-isaac","title":"Smith et al., ISAAC: An integrated system for autonomous and adaptive caretaking (ISSRDC 2021, NTRS 20210020134)","url":"https://ntrs.nasa.gov/citations/20210020134","type":"agency","accessed":"2026-10-29","read_primary":true},{"id":"src-gateway-nasa","title":"NASA Gateway Space Station reference page (updated 2026-07-23) [no uncrewed-share figure on page]","url":"https://www.nasa.gov/reference/gateway-about/","type":"agency","accessed":"2026-10-29","read_primary":true},{"id":"src-canadarm3","title":"About Canadarm3 (Canadian Space Agency)","url":"https://www.asc-csa.gc.ca/eng/canadarm3/about.asp","type":"agency","accessed":"2026-10-29","read_primary":true},{"id":"src-mss-wiki","title":"Mobile Servicing System (Wikipedia; secondary summary of NASA/CSA data)","url":"https://en.wikipedia.org/wiki/Mobile_Servicing_System","type":"agency","accessed":"2026-10-29","read_primary":true},{"id":"src-yt-dextre","title":"Dextre changes a pump on the International Space Station (CSA animation, YouTube 2015)","url":"https://www.youtube.com/watch?v=7iJUtfTjUVo","type":"video","accessed":"2026-10-29","read_primary":false},{"id":"src-owens-iss","title":"Owens & de Weck, International Space Station Operational Experience and its Impacts on Future Mission Supportability (ICES-2018-198, NTRS 20200002558)","url":"https://ntrs.nasa.gov/api/citations/20200002558/downloads/20200002558.pdf","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-bertels","title":"Bertels, Crew maintenance lessons learned from ISS and considerations for future manned missions (SpaceOps 2006)","url":"https://arc.aiaa.org/doi/pdf/10.2514/6.2006-5952","type":"paper","accessed":"2026-10-29","read_primary":false},{"id":"src-oos-li","title":"Li et al., On-orbit service (OOS) of spacecraft: A review of engineering developments (Prog. Aerospace Sci. 2019)","url":"https://doi.org/10.1016/J.PAEROSCI.2019.01.004","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-oos-ma","title":"Ma et al., Advances in Space Robots for On-Orbit Servicing: A Comprehensive Review (Adv. Intell. Syst. 2023)","url":"https://doi.org/10.1002/aisy.202200397","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-halder","title":"Halder & Afsari, Robots in Inspection and Monitoring of Buildings and Infrastructure: A Systematic Review (Appl. Sci. 2023)","url":"https://doi.org/10.3390/app13042304","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-rakha","title":"Rakha & Gorodetsky, Review of UAS applications in the built environment: towards automated building inspection (Autom. Constr. 2018)","url":"https://doi.org/10.1016/J.AUTCON.2018.05.002","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-hosamo","title":"Hosamo et al., A Digital Twin predictive maintenance framework of air handling units based on AFDD (Energy & Buildings 2022)","url":"https://doi.org/10.1016/j.enbuild.2022.111988","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-rifmea","title":"Ng et al., Application of an adapted FMEA framework for robot-inclusivity of built environments (Sci. Rep. 2022)","url":"https://www.nature.com/articles/s41598-022-06902-4","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-schmidt-berns","title":"Schmidt & Berns, Climbing robots for maintenance and inspections of vertical structures: a survey (RAS 2013)","url":"https://doi.org/10.1016/j.robot.2013.09.002","type":"paper","accessed":"2026-10-29","read_primary":false},{"id":"src-basilisk","title":"Basilisk self-healing concrete product site","url":"https://www.basiliskconcrete.com/en/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-wiktor","title":"Wiktor & Jonkers, Quantification of crack-healing in novel bacteria-based self-healing concrete (Cem. Concr. Compos. 2011)","url":"https://doi.org/10.1016/j.cemconcomp.2011.03.012","type":"paper","accessed":"2026-10-29","read_primary":false},{"id":"src-jonkers-ecuador","title":"Sierra Beltran, Jonkers et al., Field application of self-healing concrete with natural fibres as linings for irrigation canals in Ecuador (2015)","url":"https://www.semanticscholar.org/search?q=Field%20application%20of%20self-healing%20concrete%20with%20natural%20fibres%20irrigation%20canals%20Ecuador","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-shp-review","title":"Goyal et al., A review on self-healing polymers for applications in spacecraft and construction of roads (J. Appl. Polym. Sci. 2022)","url":"https://doi.org/10.1002/app.52816","type":"paper","accessed":"2026-10-29","read_primary":true},{"id":"src-yt-ecoppia","title":"Ecoppia H4: autonomous robotic cleaning for fixed tilt and single axis trackers (YouTube)","url":"https://www.youtube.com/watch?v=ZSOy8JZF4Dw","type":"video","accessed":"2026-10-29","read_primary":false},{"id":"src-yt-ozmo","title":"Meet Ozmo: The World's First Robotic-armed Window-Cleaning Robot (YouTube)","url":"https://www.youtube.com/watch?v=SdZOZ2E0YAU","type":"video","accessed":"2026-10-29","read_primary":false},{"id":"src-yt-anymal-dock","title":"Prototype Docking Station for ANYmal (YouTube)","url":"https://www.youtube.com/watch?v=FwE_ioI2SYA","type":"video","accessed":"2026-10-29","read_primary":false},{"id":"src-spot-dhl","title":"Hyundai to buy 'tens of thousands' of Boston Dynamics robots (The Robot Report, 2025-04-04)","url":"https://www.therobotreport.com/hyundai-purchase-tens-of-thousands-boston-dynamics-robots/","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-walden","title":"Walden Robotics Launches with $300 Million (Business Wire, 2026-07-15) [page blocked (403); unverified]","url":"https://www.businesswire.com/news/home/20260715089377/en/Walden-Robotics-Launches-with-%24300-Million-to-Put-General-Purpose-Robots-to-Work-Today","type":"news","accessed":"2026-10-29","read_primary":false},{"id":"src-v3-concept","title":"Anyground ORIJO v3 concept.json (M04 JO-PORT, M09 TSURU, TSURU-1, KURA-3)","url":"research/v3/concept.json","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-henn-site","title":"Henn na Hotel official site (hotel list, technology section)","url":"https://www.hennnahotel.com/","type":"company","accessed":"2026-10-29","read_primary":true},{"id":"src-spot-slashdot","title":"Slashdot (16 Jun 2020) Boston Dynamics starts selling its Spot robot for $74,500 (Spot Explorer kit contents)","url":"https://hardware.slashdot.org/story/20/06/16/1954218/boston-dynamics-starts-selling-its-spot-robot----for-74500","type":"news","accessed":"2026-10-29","read_primary":true,"added_by":"gaps-2026-10-29"}],"verification":{"date":"2026-10-29","method":"Adversarial check of load-bearing claims against primary pages via WebFetch, Crossref/Semantic Scholar DOI metadata, and full-text PDF extraction (Astrobee TFR 2026, Owens ICES-2018). Layer SERP cap was exhausted (48/48) so one search returned nothing useful.","checked":34,"confirmed":27,"confirmed_items":["NUM-01 Ilse Joule 3-4% / 3-5 bn EUR / 4-7% 2023 (abstract)","NUM-02 Ecoppia counters 3.89B / 10.51M / 35+ sites / 5,000 MW (embedded 4,000 MW inconsistency confirmed)","NUM-04 up to 35% dust loss (CEO claim)","NUM-05/06 Spot 90/60 min, 14 kg, IP54, -20..55 C, >1,500 units","NUM-07 Spot >130,000 assets 2022; AB InBev 13 days","NUM-08 ANYmal 90 min, 100 min to 70%, 3 h full, 10 kg, IP67, +1.5% uptime; 0-384 kHz mic","NUM-10 Gecko $125M Series D, $1.25B, 2025-06-12; $71M and $300M IDIQ on company site","NUM-11 Henn-na half of 243 robots, quarter of rooms, snoring","NUM-12 Chloe 1,289 reviews, 92% positive","NUM-13 Ozmo 3x, 45 storeys, rooftop supervisor","NUM-14 NEO $20,000 / $499 mo, 30 kg, 4 h, 22 dB, WSJ mostly teleoperated","NUM-15 Helix 7B 7-9 Hz / 80M 200 Hz / ~500 h / 35 DoF / 2 GPUs","NUM-17 Diffusion Policy 46.9%","NUM-18 Astrobee >1,200 h console, ~220 h crew, >165 ops, >90 GS sessions","NUM-20 SPHERES ~4 h astronaut time","NUM-22/23 Owens 18% / 6% >4x / 26% <half / 7.8x / 3.9-6.0 t for 1,200 days","NUM-25 Canadarm3 8.5 m, NET 2029, repurposing statement","NUM-26 Basilisk up to 1 mm; 15-year bus lane (claimed)","NUM-27 Luperto 130 weeks, 10 apartments","NUM-28 iRobot 2025-12-14, $98.9M Picea claim, $480.3M","NUM-29 Stretch 3 $24,950, 24.5 kg, consumer-market quote","Canadarm2 17.6 m / 7 joints / 116,000 kg (Wikipedia)","SYMPARTNER 20 households, one week each","DROID 76k trajectories","Evermore patent helix 20-30% motor power","Astrobee up to 2 h flying time; EMI and ORU lessons","All 29 paper DOIs resolve to the stated titles (Crossref)"],"corrected":[{"item":"NUM-03","was":"Ketura robot coverage rate (ambiguous whether park or robot rate)","now":"per-robot rate, ~100 ft2/min (~9.3 m2/min); sizing r_clean is therefore per robot","source":"src-ecoppia-ketura"},{"item":"NUM-09","was":"9 min; 10:1","now":"9 min charge; ~90 min runtime; 10:1 (Digit 4: ~4 h run, 2:1) - runtime added so the ratio is not read as longer endurance","source":"src-digit5"},{"item":"NUM-10 context","was":"June 2025; US Navy IDIQ expanded to $300M with claimed savings up to $8M per ship","now":"Series D and valuation reported by The Robot Report 2025-06-12. Navy figures are company press releases (claimed): $71M deal 2026-03-17; IDIQ expanded to $300M 2026-10-20 with 'savings up to $8M per ship'","source":"src-gecko-trr; src-gecko-site"},{"item":"NUM-16 basis","was":"measured","now":"calculated (interpolated, sim only)","source":"src-lbm (arXiv 2507.05331 sec. 3.2, 4.4)"},{"item":"NUM-17 context","was":"15 tasks, 4 benchmarks","now":"15 tasks, 4 benchmarks (IJRR 2024 version; the RSS 2023 arXiv version reports 12 tasks with the same 46.9%)","source":"src-dp; arXiv 2303.04137 abstract"},{"item":"NUM-19","was":"From Table X: Dock 164 sessions/2, Bumble 135/0, Honey 59/1, Queen 21/1 (omitted Batteries and Perching Arms rows)","now":"4 / 379 (about 1.1); 4 / 566 (about 0.7) if all Table X rows are counted","source":"src-astrobee-tfr Table X"},{"item":"NUM-21 sources","was":"['src-astrobee-tfr', 'src-gateway-nasa']","now":"['src-astrobee-tfr'] only - NASA Gateway page does not state >85%","source":"src-astrobee-tfr; src-gateway-nasa (checked, figure absent)"},{"item":"PRJ-06 sensors","was":"Claims ~3x speed but still needs a rooftop supervisor; lidar fails on glass and needed extra ultrasonic and sill sensors.","now":"Claims ~3x speed but still needs a rooftop supervisor; lidar struggles on transparent glass, so ultrasonic sensors were added.","source":"src-ozmo-trr"},{"item":"PRJ-08 status","was":"failed / 2015-2019","now":"active (scaled back) / 2015-2026: Henn na Hotel chain lists 25 locations with front-desk and dinosaur robots in Oct 2026","source":"src-henn-site"},{"item":"PRJ-09","was":"Savioke was acquired and relaunched as Relay in 2022 and pivoted toward hospitals; single-task hotel delivery was not enough on its own.","now":"Savioke's assets were acquired by an undisclosed buyer and relaunched as Relay Robotics in May 2022; hospitality stayed the core market, with hospitals (10 at launch) and real estate as adjacent markets. Single-task delivery needed new verticals to grow.","source":"src-relay-trr"},{"item":"failures: Savioke why","was":"Hotel delivery alone did not sustain the business; pivot to hospitals.","now":"Undisclosed acquirer formed a new entity; hotel delivery alone was a small market, so it expanded into hospitals and real estate while keeping hospitality as core.","source":"src-relay-trr"},{"item":"PRJ-10","was":"Consolidated into a large manufacturer (LG 51% in Jan 2025); pursuing ~$300M pre-IPO round (2026, not verified).","now":"Consolidated into a large manufacturer (LG call option to 51% exercised 2025-01-22); KED Global reports it sounding out PE firms for up to 400 billion won (~$300M) pre-IPO funding ahead of a potential Nasdaq listing (2026-09-07, reported, not confirmed by the company).","source":"src-bear-rave; src-bear-ked (read 2026-10-29)"},{"item":"PRJ-11 status","was":"failed / 2002-2025","now":"restructured: emerged from Chapter 11 as Picea subsidiary (TRR 2026-01-23); Roomba line continues","source":"src-irobot-md; src-irobot-trr"},{"item":"PRJ-15","was":"Finetuning needs under 30% of task data in sim to match single-task; ~1,800 real-world trials needed to evaluate rigorously.","now":"Finetuning needs under 30% of task data in sim to match single-task (interpolated estimate); the paper cites ~1,800 controlled real-world trials (elsewhere ~2,700 rollouts) to evaluate rigorously. Published in Science Robotics (2026-04-15).","source":"src-lbm; Crossref 10.1126/scirobotics.aea6201"},{"item":"PRJ-28","was":"Spun out of a Toyota lab / active","now":"status unverified; Toyota origin and 'seed' removed as unverified","source":"src-walden (title only)"},{"item":"PAP-04 year","was":"2019","now":"2021 (published; conference 2019)","source":"Crossref 10.1007/978-981-15-9460-1_18"},{"item":"CARE-S6 Ground-operator model maturity","was":"COMMERCIAL 9","now":"PILOT 8","source":"src-astrobee-tfr"},{"item":"CARE-S3 Canadarm2+Dextre trl_why","was":"Operational on ISS since 2001 (arm) and 2008 (Dextre).","now":"added caveat: operational agency system, not commercially sold","source":"src-mss-wiki"},{"item":"CARE-S5 Bayesian ledger trl_why","was":"Used operationally by ISS logistics and maintenance.","now":"Used operationally by ISS logistics (MADS); the method is mature but has no off-the-shelf product for building fleets, so ORIJO's DAICHO implementation is TRL ~4.","source":"src-owens-iss"}],"removed":[{"item":"PRJ-06 / Ozmo 'sill sensors'","reason":"not in the cited source; replaced with 'ultrasonic sensors added'"},{"item":"NUM-21 src-gateway-nasa as support for >85%","reason":"page has no such figure"},{"item":"PRJ-28 'spun out of a Toyota lab' and 'seed'","reason":"unverifiable"}],"unverifiable":[{"item":"PRJ-28 Walden Robotics $300M seed / Toyota origin","reason":"Business Wire page blocked (403); layer SERP budget exhausted; only the URL title supports $300M"},{"item":"PAP-06 Figgis 2023 vibration values","reason":"full text not accessed (already flagged)"},{"item":"PAP-22 Bertels >4,000 crew maintenance hours","reason":"DOI resolves, full text not accessed (already flagged)"},{"item":"Brush-crawler PV robot specs (SolarCleano)","reason":"no source in file"}],"internal_consistency":"Every src- id cited in projects, numbers and options exists in sources (69 after adding src-henn-site). 15 sources are listed but not cited by id (papers cite them by DOI, or they are background): src-pat-gecko, src-droid, src-pat-ecoppia-pid, src-bertels, src-marathon, src-gecko-cnbc, src-rakha, src-spot-dhl, src-shp-review, src-rurm, src-oos-li, src-figgis-vib, src-yt-anymal-dock, src-schmidt-berns, src-rifmea. Sizing formulas recomputed: patrol 2x7x15=210, swaps 1.5x10=15, PV 7x25/9.3=18.8 -> ~244 min/week; 4.07 h x 60 W = 0.24 kWh; remote 22.5 tasks x 0.05 x 5 = 5.6 min; 2,400x0.5/6 = 200 homes/FTE; hotel 6x0.7x7/2=14.7 turnovers, x25 = 368 min; farm 500/500.5=99.9%, 500/548=91.2%. All match. r_clean 9.3 m2/min is a per-robot rate, so the PV term assumes one robot - consistent.","verdict":"Substantially sound. No fabricated sources or DOIs found; numbers match primary sources with correct units. Corrections were about status currency (Henn-na still operating, iRobot restructured not dead), one overstated pivot (Relay), one unsupported detail (Ozmo sill sensors), one basis downgrade (LBM <30% is an interpolated sim estimate), one maturity downgrade (Astrobee ground ops PILOT 8), and the Walden item, which stays unverified."},"certification":[{"id":"C-C1","regime":"ISO 13482:2014 (personal care robots), ISO 10218-1/-2:2025 (industrial robots)","jurisdiction":"international","status":"ISO 13482 predates learned behaviours","applies_to":"Home mobile manipulators (13482); fixed farm/factory arms (10218)","requirement":"Hazard analysis, speed/force limits, protective stops","implication_for_orijo":"Rail-captive TSURU and tray shuttles are easier to certify than free-roaming humanoids: fixed paths, guarded zones.","sources":["mind:src-iso13482","mind:src-iso10218-2025"]}],"revision_log":[{"date":"2026-10-29","by":"gaps-2026-10-29","change":"Added certification paths, new sources/numbers/papers/projects from the completeness-critic pass; see research/v4/gaps-log.md"}]}