Learning Skateboarding for Humanoid Robots through Massively Parallel Reinforcement Learning

TL;DR

This paper explores using massively parallel reinforcement learning to teach humanoid robots to skateboard, extending existing locomotion methods with a focus on simulation and initial hardware testing.

Contribution

It introduces a novel application of RL for skateboarding in humanoid robots, utilizing Brax/MJX for fast simulation-based training.

Findings

Successful initial simulation results

Framework for applying RL to skateboarding

Hardware experiments are underway

Abstract

Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work extends the periodic reward formulation of locomotion to skateboarding for the REEM-C robot. Brax/MJX is used to implement the RL problem to achieve fast training. Initial results in simulation are presented with hardware experiments in progress.