Robot learns to walk better after leg damage without resetting
Persistent Profile-Guided Reset-Free Recovery Improves Final Gait Selection after Irreversible Leg Damage
Robotics
Summary
Robots sometimes get damaged legs and need to find new ways to walk. The authors created a method called PGRR that helps robots try different walking styles continuously without restarting from the same spot each time. This method uses careful predictions to pick better movements and avoids choosing gaits that seem good only for a short time. Testing in many simulated damaged leg scenarios, PGRR found stronger walking styles more reliably than previous methods. This helps robots adapt better to serious leg damage while moving.
What this means in practice
- •For robot developers: Improve robot locomotion after leg damage by enabling continuous gait adaptation without resets.
- •For robot control engineers: Use uncertainty-aware predictions to guide real-time testing of walking styles in damaged robots.
Authors
Minjoong Kim
Abstract
Damage-recovery algorithms often rank gaits from short trials, yet a gait that performs well briefly may not remain effective during continued execution. In reset-free recovery, each trial also changes the physical state inherited by the next. We introduce persistent profile-guided reset-free recovery (PGRR), which predicts multiple outcomes over repeated gait execution and uses conservative uncertainty-aware estimates to guide short online probes without resetting the robot. Across 108 matched MuJoCo tasks spanning leg amputation, distal fracture, and joint lock, PGRR improves final quality by 0.106 and slot-averaged recovery quality (SRQ) by 0.044 relative to an IT&E-inspired Gaussian-process baseline, while reducing low-quality failures by 27.8 percentage points. Final-quality gains occur in all three damage classes. Against no adaptation, PGRR also improves final quality and reduces low-quality failures, whereas the aggregate SRQ difference is inconclusive. Development ablations identify conservative uncertainty handling as the clearest supported contributor to the observed gains. These results show that PGRR can identify stronger post-damage gaits under continuous physical state and that final-gait quality and recovery-summary performance provide complementary evidence for evaluating reset-free recovery.