Learning Decentralized Multi-Biped Control for Payload Transport

TL;DR

This paper introduces a decentralized reinforcement learning-based control method for multi-biped robot carriers, enabling effective payload transport over rough terrain with varying robot configurations, demonstrated both in simulation and real-world experiments.

Contribution

It presents the first scalable multi-biped payload transport system with a transferable decentralized controller that adapts to different robot configurations without retraining.

Findings

Effective payload transport over rough terrain demonstrated in simulation.

Successful real-world deployment with two and three Cassie robots.

Controller adapts to various configurations without retraining.

Abstract

Payload transport over flat terrain via multi-wheel robot carriers is well-understood, highly effective, and configurable. In this paper, our goal is to provide similar effectiveness and configurability for transport over rough terrain that is more suitable for legs rather than wheels. For this purpose, we consider multi-biped robot carriers, where wheels are replaced by multiple bipedal robots attached to the carrier. Our main contribution is to design a decentralized controller for such systems that can be effectively applied to varying numbers and configurations of rigidly attached bipedal robots without retraining. We present a reinforcement learning approach for training the controller in simulation that supports transfer to the real world. Our experiments in simulation provide quantitative metrics showing the effectiveness of the approach over a wide variety of simulated transport scenarios. In addition, we demonstrate the controller in the real-world for systems composed of two and three Cassie robots. To our knowledge, this is the first example of a scalable multi-biped payload transport system.