How often may a laundry robot's opening detector aim wrong before blind pinching is faster?
research/hanger-misaim
How often may a laundry robot's opening detector aim wrong before blind pinching is faster? In the stylised hanger-pick model each 10 points of detector error cost about 1 s of look-time budget: 9.2 s per pick when perfect, 4.5 s at 50% wrong, none when always wrong. Stylised.
What it found
In the stylised hanger-pick model a wrong aim costs one wasted grasp and then the same regrasp hunt as a blind pinch. The look-time budget of the detector falls almost linearly with its error: 9.2 s per pick when perfect, 6.3 s at 30% wrong, 4.5 s at 50%, about 0 when always wrong (300 paired piles, assumed times). At a 1 s look aiming still wins until about 88% of aims are wrong; at 5 s the limit is 43%, at 9 s 3%, and an 11 s look loses even when perfect. Stylised: every time and probability is an assumed placeholder; error is independent per pick.
A figure from its own output
Paper, code and results
More in Laundry-hanging robots
- Does the 2D hanger result survive in 3D, with front and back panels and a hanger arm of finite depth?Does the 2D hanger result survive in 3D? With an arm as deep as the garment a 3D cloth sheet matches the 2D drape (within 0.05 cm for round-ended hangers) and the best width is again 1 cm over the half shoulder; a shallow arm lets the front and back panels fall 5–8 cm and raises a wooden hanger's error from 0.4 to 2.0 cm. Stylised.
- Does a 3D-designed hanger keep improving when the end-radius cap is lifted past 6 cm?No: with caps of 10 and 15 cm the whole-sheet error is 1.08 and 1.21 cm against 1.12 cm at 6 cm (8 seeds each, p = 0.77 and 0.57), so the optimum sat on a flat ridge. Stylised.
- Is a hanger designed in 3D really better than one designed on the 2D centre line, once seed noise is counted?Yes, by 0.26 cm on the whole sheet with hanger-fit's bounds (8 seeds each, p = 0.03) and by 0.68 cm once the end-radius and bow limits are widened (p < 0.001), but the 3D-designed hangers have a worse centre line. Stylised.
- Does a second laundry-hanging arm lose less if it picks a free garment instead of waiting?Does a second laundry-hanging arm lose less if it picks a free garment instead of waiting? At 0.30 m clearance blind pinching recovers 9.5 of its 28 lost garments an hour (151 to 161), aiming about 2 of 10; at 0.45 m nothing. Stylised: clearance and spacing assumed.
- Is a laundry-hanging arm's gain from picking a free garment real? A paired test on 2000 loadsIs a laundry-hanging arm's gain from picking a free garment real? Paired on 2000 loads at 0.30 m: aiming +1.25 an hour (0.60 to 1.92), sweeping +4.4, pinching +10.0; at 0.45 m aiming gains nothing. Stylised: inputs are placeholders.
- How many dryers can one laundry-hanging arm serve once the pick is simulated, not assumed?How many dryers can one laundry-hanging arm serve once the pick is simulated, not assumed? A one-arm cell drops from 169 to 147 garments an hour (5.1 to 4.4 dryers) with look-then-aim picking and to 104 with blind pinching; with two arms the fold table is the limit. Stylised.
All 25 Laundry-hanging robots projects →
Other research topics
Proper scoring & elicitation28Effort & peer prediction9Verification games & slashing19Detection & tolerances14Markets as routers13Prediction-market design9Paying contributors8Decentralised training systems23Digital twins & sim-to-real164LLM chip design loops40Robot manufacturing loops53Ambient AI assistant46Self-replicating manufacturing34Simulation-first design64Engineered clothing45Task-specific AI accelerators40Algorithmic chip-design loops42Open-source purpose-built robots44The software-engineering loop43Adversarial human imitation41Open-source residential construction41Autonomous multi-angle capture34Sensing, imaging and 3D31Energy supply and dense energy storage39Robot societies among people31Agentic co-design of low-cost robots27Laundry-hanging robots25Machine learning on qualitative data23Robots on the building site27Civilizations & group psychology1History & human sciences1
Produced with AI assistance (Claude). Results are from the code in this repository and are simulated or stylised unless the abstract says otherwise; nothing here implies affiliation with or endorsement by any lab, researcher or company cited. MIT licensed.