Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration

TL;DR

This paper introduces 'human-robot gym', a benchmark suite for safe reinforcement learning in human-robot collaboration, featuring realistic tasks and a safety guarantee, bridging the gap between theory and real-world deployment.

Contribution

The paper presents a novel benchmark suite with safety guarantees for training RL agents in human-robot collaboration tasks, enabling fair comparison and real-world applicability.

Findings

Diverse tasks challenge current RL methods.

Expert knowledge can improve RL performance.

Agents show minimal overfitting.

Abstract

Deep reinforcement learning (RL) has shown promising results in robot motion planning with first attempts in human-robot collaboration (HRC). However, a fair comparison of RL approaches in HRC under the constraint of guaranteed safety is yet to be made. We, therefore, present human-robot gym, a benchmark suite for safe RL in HRC. Our benchmark suite provides eight challenging, realistic HRC tasks in a modular simulation framework. Most importantly, human-robot gym includes a safety shield that provably guarantees human safety. We are, thereby, the first to provide a benchmark suite to train RL agents that adhere to the safety specifications of real-world HRC. This bridges a critical gap between theoretic RL research and its real-world deployment. Our evaluation of six tasks led to three key results: (a) the diverse nature of the tasks offered by human-robot gym creates a challenging benchmark for state-of-the-art RL methods, (b) incorporating expert knowledge in RL training in the form of an action-based reward can outperform the expert, and (c) our agents negligibly overfit to training data.