Learning to Recover: Dynamic Reward Shaping with Wheel-Leg Coordination for Fallen Robots

Learning to recover with wheel-leg coordination

This paper presents a learning-based framework integrating Episode-based Dynamic Reward Shaping and curriculum learning, which dynamically balances exploration of diverse recovery maneuvers with precise posture refinement. We further demonstrate that synergistic wheel-leg coordination reduces joint torque consumption by 15.85%–26.2% and improves stabilization through energy transfer mechanisms. Extensive evaluations on two distinct platforms achieve recovery success rates up to 99.1% and 97.8% without platform-specific tuning.

The strategy can learn effective recovery actions and demonstrates remarkable robustness.

We show that our DS-policy can recover from the falling postures of the baseline.