Event
AWARE: Predicting Robot Dynamics and Identifying Anomalies Using Only External Cameras
1 reports · 1 sources
AWARE is a world-model framework that monitors robots using only external cameras, achieving anomaly detection through system dynamics estimation and state prediction without requiring onboard sensors such as motor encoders. On 240 real robot crane trajectories (including payload collisions and motor degradation), its anomaly classification improves by 26% over the strongest baseline; the inferred dynamics parameters can also be decoded to localize the source of faults, with 88% accuracy in localizing degraded motors.
Report timeline
- AWARE: A world-model framework that predicts robot dynamics and identifies anomalies using only external cameras
AWARE is a world-model framework that relies solely on external camera monitoring, performing anomaly detection through system dynamics estimation and state prediction without onboard sensors such as motor encoders. On 240 real-world robotic crane trajectories (including payload collisions and motor degradation), its anomaly classification improves by 26% over the strongest baseline; the inferred dynamics parameters can also be decoded to localize the source of faults, achieving 88% accuracy in localizing degrading motors.
arXiv cs.RO ·