EFGCL: Learning Dynamic Motion through Spotting-Inspired External Force Guided Curriculum Learning

TL;DR

This paper introduces EFGCL, a reinforcement learning method that uses external forces inspired by gymnastics spotting to improve learning efficiency for complex robot motions, successfully transferring learned skills to real robots.

Contribution

EFGCL is a novel guided RL approach that incorporates external assistive forces for efficient exploration in dynamic robot motion learning, without relying on reward shaping or reference trajectories.

Findings

EFGCL doubles the learning speed for the Jump task.

It enables learning of complex motions that standard RL methods cannot achieve.

Policies learned with EFGCL transfer effectively to real robots.

Abstract

Learning dynamic whole-body motions for legged robots through reinforcement learning (RL) remains challenging due to the high risk of failure, which makes efficient exploration difficult and often leads to unstable learning. In this paper, we propose External Force Guided Curriculum Learning (EFGCL), a guided RL approach based on the principle of physical guidance, in which external assistive forces are introduced during training. Inspired by spotting in artistic gymnastics, EFGCL enables agents to physically experience successful motion executions without relying on task-specific reward shaping or reference trajectories. Experiments on a quadrupedal robot performing Jump, Backflip, and Lateral-Flip tasks demonstrate that EFGCL accelerates learning of the Jump task by approximately a factor of two and enables the acquisition of complex whole body motions that conventional RL methods fail to learn. We further show that the learned policies can be deployed on real robot, reproducing motions consistent with those observed in simulation. These results indicate that physically guided exploration, which allows agents to experience success early in training, is an effective and general strategy for improving learning efficiency in dynamic whole-body motion tasks.