Phase-Aware Policy Learning for Skateboard Riding of Quadruped Robots via Feature-wise Linear Modulation
This work addresses the challenge of controlling legged robots on skateboards, a novel domain with multi-modal control objectives, but the approach is tailored to this specific task.
The paper introduces Phase-Aware Policy Learning (PAPL), a reinforcement-learning framework for quadruped robots to ride skateboards. It achieves command-tracking accuracy and real-world transferability, outperforming leg and wheel-leg baselines in locomotion efficiency.
Skateboards offer a compact and efficient means of transportation as a type of personal mobility device. However, controlling them with legged robots poses several challenges for policy learning due to perception-driven interactions and multi-modal control objectives across distinct skateboarding phases. To address these challenges, we introduce Phase-Aware Policy Learning (PAPL), a reinforcement-learning framework tailored for skateboarding with quadruped robots. PAPL leverages the cyclic nature of skateboarding by integrating phase-conditioned Feature-wise Linear Modulation layers into actor and critic networks, enabling a unified policy that captures phase-dependent behaviors while sharing robot-specific knowledge across phases. Our evaluations in simulation validate command-tracking accuracy and conduct ablation studies quantifying each component's contribution. We also compare locomotion efficiency against leg and wheel-leg baselines and show real-world transferability.