If a thermostat infrared-gating band is tuned on some rooms, does it still help in rooms it never saw?

What it found

A stylised, preliminary follow-up to garment-twonodemet. A skin-temperature gate band is tuned by exhaustive grid search on rest-to-walk and walk-to-rest steps in 22, 24 and 26 C rooms, then scored unchanged on held-out rooms (23, 25, 20 and 28 C). The tuned band (a narrow 33.6–33.7 C) beats the untuned 33.2–34.2 C band and both fixed states on both held-out sets under both choice sets, by 0.01 to 0.06 C against the untuned band. It also beats the four-schedule oracle on training scenarios, because the oracle is restricted, and it chatters (up to 24 switches in 180 min) with instant, free switching, so the gain may not survive actuation lag or cost. Six training and eight held-out scenarios from one model; no real fabric or person.

A figure from its own output

Paper, code and results

• README and method
• Experiments and results
• Code
• Tests

More in Engineered clothing

• Does a tuned infrared-gating thermostat survive an actuation lag and a cost per switch?Retuning the thermostat infrared-gating band with an actuation lag (0 to 10 min) and a cost per switch: lag cuts the gain over never switching from 0.23 to 0.15 C (stylised), a switch penalty widens the band and stops the chatter, and under one choice set the tuned band can lose to the untuned one.
• Does a proportional infrared-gating textile beat the on/off thermostat gate?A proportional infrared-gating transmittance against the tuned on/off thermostat gate: a negative result, within 0.010 C in every cell because the tuned ramp collapses to nearly on/off, and a softer ramp costs 0.02 to 0.07 C (stylised).
• At what switching penalty does a proportional infrared gate beat the on/off thermostat gate?Prices actuation in equal units (one full close-open swing = 1) and asks when a proportional infrared gate beats the on/off gate: it wins in 52 of 80 held-out cells, by tenths of a degree at most, and the gain reverses in the outside rooms at the highest penalty (stylised, preliminary).
• Is the outside-room reversal of the proportional infrared gate a training-range artefact?Retunes both infrared gates on a wider set of rooms: the proportional gate's outside-room reversal is partly a training-range artefact
• Does an infrared-gating band tuned for one person and clothing level still work for other clothing and body sizes?Tunes both infrared gates on one person and clothing level and scores them on other clothing and body sizes; clothing matters, body size barely does
• How far is the thermostat-driven infrared-gating textile from the best possible switching schedule when the room temperature steps?A grid search for the best open/closed switching schedule under a room-temperature step shows one toggle suffices and the thermostat gate sits within 0.02 °C of it after a step up, but up to 0.11 °C after a step down (stylised).

All 45 Engineered clothing 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.