Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion

TL;DR

This paper introduces a reinforcement learning method enhanced by an evolving foot trajectory generator, enabling quadrupedal robots to learn complex gaits from scratch and perform challenging tasks efficiently.

Contribution

It presents a novel RL approach with an adaptive trajectory generator that improves sample efficiency and task performance in quadrupedal locomotion.

Findings

Successfully learned walking on a balance beam in simulation

Crawled through a cave environment in simulation

Deployed controller on real robot for challenging scenarios

Abstract

Recently reinforcement learning (RL) has emerged as a promising approach for quadrupedal locomotion, which can save the manual effort in conventional approaches such as designing skill-specific controllers. However, due to the complex nonlinear dynamics in quadrupedal robots and reward sparsity, it is still difficult for RL to learn effective gaits from scratch, especially in challenging tasks such as walking over the balance beam. To alleviate such difficulty, we propose a novel RL-based approach that contains an evolutionary foot trajectory generator. Unlike prior methods that use a fixed trajectory generator, the generator continually optimizes the shape of the output trajectory for the given task, providing diversified motion priors to guide the policy learning. The policy is trained with reinforcement learning to output residual control signals that fit different gaits. We then optimize the trajectory generator and policy network alternatively to stabilize the training and share the exploratory data to improve sample efficiency. As a result, our approach can solve a range of challenging tasks in simulation by learning from scratch, including walking on a balance beam and crawling through the cave. To further verify the effectiveness of our approach, we deploy the controller learned in the simulation on a 12-DoF quadrupedal robot, and it can successfully traverse challenging scenarios with efficient gaits.