Camera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm
Overview
This research paper investigates how varying room illuminance affects visuomotor policies trained on a low-cost robotic rig.
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · rollouts: 40 other · reported trials · Differing source assertions
“s run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera”
Exact source · revision 1Source owner not reported
Reported quantity · placements: 19 other · reported trials · Differing source assertions
“s run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera”
Exact source · revision 1Source owner not reported
Reported quantity · placements: 20 other · reported trials · Differing source assertions
“s run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera”
Exact source · revision 1Source owner not reported
Reported quantity · rollouts: 10 other · reported trials · Differing source assertions
“s run for ten rollouts at about 520 lux and again at about 45 lux, an 11.5x reduction. Success was 20/40 in normal light and 19/40 in low light: a change of -2.5 percentage points (95% CI -23 to +19), with no evidence that the policies differed in sensitivity (interaction p = 0.86). The recorded video shows why: mean image brightness was only 3% lower in low light on the front camera and 19% lower on the wrist camera”
Exact source · revision 1Source owner not reported
Reported quantity · placements: 7 other · reported trials · Differing source assertions
“. Both cameras were set to automatic exposure and white balance, which most likely absorbed the difference; exposure was not locked in this experiment. An accidental repeat of one 10-rollout block reproduced its success count (7/10) but matched the first block at only 6 of 10 placements, consistent with chance. We conclude that lux alone does not describe what a policy sees. Camera settings, and image statistics comp”
Exact source · revision 1Source owner not reported
Reported quantity · demonstrations: 50 other · Basis not reported
“arXiv:2611.13810v1 Announce Type: new Abstract: Real-robot benchmarks of learned visuomotor policies often record room illuminance as the lighting condition. We show that, on a typical low-cost rig, room light and image light can be almost unrelated. Four imitation-learning policies (ACT, SmolVLA, Diffusion Policy and pi0.5) were trained on the same 50 demonstrations of a pick-and-place task on an SO-101 arm. Each wa”
Exact source · revision 1Source owner not reported
Reported quantity · rollouts: 10 other · reported trials · Differing source assertions
“. Both cameras were set to automatic exposure and white balance, which most likely absorbed the difference; exposure was not locked in this experiment. An accidental repeat of one 10-rollout block reproduced its success count (7/10) but matched the first block at only 6 of 10 placements, consistent with chance. We conclude that lux alone does not describe what a policy sees. Camera settings, and image statistics comp”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalCamera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm
This research paper investigates how varying room illuminance affects visuomotor policies trained on a low-cost robotic rig.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).