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

2026-02-10

AI Summary

This work addresses the challenge of quadrupedal robots manipulating skateboards, which involves complex multi-stage dynamic interactions and coordinated control. The authors propose a phase-aware policy learning framework that, for the first time, integrates Feature-wise Linear Modulation (FiLM) into a reinforcement learning policy network. By dynamically modulating feature representations conditioned on motion phase, the approach unifies the modeling of distinct behavioral modes across different phases of skateboard locomotion while sharing underlying robotic knowledge. Evaluated in simulation, the method achieves high-precision command tracking and demonstrates significantly improved locomotion efficiency compared to legged and wheeled-legged baselines. Furthermore, the policy successfully transfers to a real-world robot system, validating its generalization capability and effectiveness in coordinating multimodal control strategies.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Multimodal Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• skateboard riding
• quadruped robots
• policy learning
• multi-modal control
• phase-awareness

Innovation

• Phase-Aware Policy Learning
• Feature-wise Linear Modulation
• quadruped robot
• skateboard riding
• reinforcement learning