Whole-Body Control of a Mobile Manipulator using End-to-End Reinforcement Learning

TL;DR

This paper introduces an end-to-end reinforcement learning approach for whole-body control of mobile manipulators, improving efficiency and obstacle avoidance compared to traditional methods, validated through simulation and real-world tests.

Contribution

The paper presents a novel RL-based WBC method that overcomes kinematic limitations and enables reactive obstacle avoidance, outperforming existing sampling-based approaches.

Findings

Faster mission completion in simulation.

Successful real-world validation in narrow corridors.

Enhanced reactive obstacle avoidance capabilities.

Abstract

Mobile manipulation is usually achieved by sequentially executing base and manipulator movements. This simplification, however, leads to a loss in efficiency and in some cases a reduction of workspace size. Even though different methods have been proposed to solve Whole-Body Control (WBC) online, they are either limited by a kinematic model or do not allow for reactive, online obstacle avoidance. In order to overcome these drawbacks, in this work, we propose an end-to-end Reinforcement Learning (RL) approach to WBC. We compared our learned controller against a state-of-the-art sampling-based method in simulation and achieved faster overall mission times. In addition, we validated the learned policy on our mobile manipulator RoyalPanda in challenging narrow corridor environments.