NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environments

TL;DR

This paper explores how unsupervised learning can enhance reinforcement learning for robot navigation in dynamic environments, demonstrating competitive results and providing open-source tools for reproducibility.

Contribution

It introduces novel unsupervised learning architectures for reinforcement learning in robot navigation and provides comprehensive benchmarks and open-source resources.

Findings

Unsupervised methods are competitive with end-to-end approaches.

Input representation and latent features significantly impact performance.

Open-source models and environments facilitate reproducibility and comparison.

Abstract

Robot navigation is a task where reinforcement learning approaches are still unable to compete with traditional path planning. State-of-the-art methods differ in small ways, and do not all provide reproducible, openly available implementations. This makes comparing methods a challenge. Recent research has shown that unsupervised learning methods can scale impressively, and be leveraged to solve difficult problems. In this work, we design ways in which unsupervised learning can be used to assist reinforcement learning for robot navigation. We train two end-to-end, and 18 unsupervised-learning-based architectures, and compare them, along with existing approaches, in unseen test cases. We demonstrate our approach working on a real life robot. Our results show that unsupervised learning methods are competitive with end-to-end methods. We also highlight the importance of various components such as input representation, predictive unsupervised learning, and latent features. We make all our models publicly available, as well as training and testing environments, and tools. This release also includes OpenAI-gym-compatible environments designed to emulate the training conditions described by other papers, with as much fidelity as possible. Our hope is that this helps in bringing together the field of RL for robot navigation, and allows meaningful comparisons across state-of-the-art methods.