Thermal cameras on humanoids - any real use case beyond novelty?

[rebecca_lefe]

Not sure if this has been discussed before, but here goes. IMU drift over time (bias instability) is usually the real culprit behind slowly diverging state estimates, not noise - it's typically handled with sensor fusion against other references (visual odometry, joint kinematics) rather than trying to eliminate drift at the source. Sensor fusion mostly earns its keep by covering for each individual sensor's weaknesses - vision struggles with occlusion and lighting, IMUs drift, force/torque sensors are noisy at low loads - fusing them gives a more robust estimate than any one source alone, independent of raw compute. Feel free to tell me I'm overthinking this.

[park44]

@rebecca_lefe Worth being a little skeptical of the marketing angle here. Tactile skin arrays have improved a lot, but 'good enough to matter' really depends on the task - coarse contact detection across a large area is fairly mature, while fine, high-resolution force distribution sensing (like a human fingertip) is still the harder problem. This whole thread is a good reminder how young this field still is.

[young58]

I'd take that specific number with a grain of salt, honestly. SLAM in a working warehouse is harder than in a controlled lab mainly because the map keeps changing - pallets move, people walk through, lighting shifts near dock doors - so a lot of production systems lean on semi-static maps refreshed periodically rather than pure continuous SLAM.

[chloe_jack]

Pretty much this. One thing to add: Depth sensing range and reliability both degrade outdoors in direct sunlight for most structured-light and active stereo cameras, since the ambient IR washes out the projected pattern - it's a real limitation for humanoids intended for anything beyond indoor, controlled environments. Kind of makes me think about how different this all looked even three years ago.

[ramirez77]

Genuine beginner question - Event cameras (which report per-pixel brightness changes rather than full frames) are still more of a research curiosity than a production sensor for humanoids, mainly because the software ecosystem and processing pipelines around them are far less mature than for standard frame-based cameras. Vibration is one of the most underrated sources of noisy IMU and tactile readings - mounting matters as much as sensor quality, and a poorly isolated mount can add more noise than the sensor's own datasheet specs would suggest. This whole thread is a good reminder how young this field still is.

[erik_novi]

Yeah, this tracks with what I've read as well. Estimating joint torque from motor current draw is cheap and requires no extra sensor, but it's less accurate than a dedicated torque sensor because it doesn't capture friction losses through the gearbox - good enough for coarse control, not always for precise force-controlled tasks.

[green28]

@erik_novi This is exactly the kind of context I was looking for. LiDAR gives reliable, lighting-independent range data but is heavier, pricier, and gives sparser point clouds up close than stereo or depth cameras, which is why a lot of humanoids lean on stereo/depth cameras for near-field manipulation and reserve LiDAR (if present at all) for longer-range navigation.

[larrysokolov]

Sorry if this is a basic question, but Unitree's Dex3-1 dexterous hand packs around 33 pressure/tactile sensors per hand across the fingers and palm, capable of sensing pressure roughly in the 10g-2500g range - a useful reference point for what 'production tactile sensing' looks like right now.

[karen.chen3]

@larrysokolov Appreciate the detailed answer. Force/torque sensors near the ankle give a direct read on ground reaction forces, which is valuable for balance control, but they add cost, a failure point, and routing complexity right at a joint that already takes the most mechanical abuse. This whole thread is a good reminder how young this field still is.

[choi98]

@karen.chen3 This is exactly the kind of context I was looking for. Latency between a perceived event (like a slip) and a corrective control response matters enormously for balance - even 50-100ms of extra perception latency can be the difference between a smooth recovery and a fall, which is part of why a lot of balance-critical sensing is proprioceptive rather than vision-based. Multi-camera calibration drifts over time from thermal expansion, vibration, and mechanical wear, which is why production systems typically run periodic recalibration routines rather than assuming a one-time factory calibration holds forever.