Multi-Modal Legged Locomotion Framework with Automated Residual Reinforcement Learning

TL;DR

This paper introduces a multi-modal legged robot framework that combines a handcrafted transition with a novel automated residual reinforcement learning algorithm, enabling quadruped robots to walk bipedally with successful real-world implementation.

Contribution

It presents a new multi-modal locomotion framework with a novel reinforcement learning algorithm for bipedal control, allowing quadruped robots to switch modes and walk bipedally.

Findings

Algorithms perform best in simulation

Maintain good real-world performance

Successfully switch between quadruped and biped modes

Abstract

While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller -- learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/.