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

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.

arXiv comment6 pages, 6 figures, 2 tables, submitted to RA-L/IROS

References in corpus (8)

• Trust Region Policy Optimization
• Emergence of Locomotion Behaviours in Rich Environments
• Solving Rubik's Cube with a Robot Hand
• maplab: An Open Framework for Research in Visual-inertial Mapping and Localization
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
• Whole-Body MPC for a Dynamically Stable Mobile Manipulator
• Benchmarking Reinforcement Learning Algorithms on Real-World Robots
• Deep Value Model Predictive Control

Cited by in corpus (4)

• N${}^2$M${}^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments
• A Versatile Door Opening System with Mobile Manipulator through Adaptive Position-Force Control and Reinforcement Learning
• Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations
• Improved Reinforcement Learning Coordinated Control of a Mobile Manipulator using Joint Clamping