Detecting and Explaining Robot Policy Failures from Sparse Internal Features
Overview
This research presents MIND (Mechanistic Interpretability for Neural Diagnosis), a method that utilizes sparse autoencoders to analyze the internal activations of trained visuomotor policies. By linking these features to the robot's position, movement, and surroundings, MIND identifies specific internal concepts contributing to failures during execution. The approach flags deviations from learned patterns in both successful and failed runs, providing explanations for policy breakdowns based on meaningful feature changes. Experiments conducted in simulation and on a physical robot demonstrate that monitoring these internal features effectively detects and explains failures, connecting failure signals to understandable shifts within the policy architecture.
Generated from attributed reports · Updated 13 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.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalDetecting and Explaining Robot Policy Failures from Sparse Internal Features
This research presents MIND (Mechanistic Interpretability for Neural Diagnosis), a method that utilizes sparse autoencoders to analyze the internal activations of trained visuomotor policies. By linking these features to the robot's position, movement, and surroundings, MIND identifies specific internal concepts contributing to failures during execution. The approach flags deviations from learned patterns in both successful and failed runs, providing explanations for policy breakdowns based on meaningful feature changes. Experiments conducted in simulation and on a physical robot demonstrate that monitoring these internal features effectively detects and explains failures, connecting failure signals to understandable shifts within the policy architecture.
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).