Phase-Aware Policy Learning for Skateboard Riding of Quadruped Robots via Feature-wise Linear Modulation

TL;DR

This paper introduces a phase-aware reinforcement learning framework for quadruped robots to skateboard effectively, leveraging phase-conditioned modulation to handle multi-phase control and transfer from simulation to real-world.

Contribution

The novel PAPL framework integrates phase-conditioned feature modulation into RL networks, enabling unified, phase-aware skateboarding policies for quadruped robots.

Findings

Validated command-tracking accuracy in simulation

Demonstrated real-world transferability of learned policies

Quantified component contributions through ablation studies

Abstract

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.