Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty

TL;DR

This paper introduces a zero-shot transfer learning framework for autonomous robot exploration using graph neural networks and deep reinforcement learning, enabling effective decision-making under uncertainty across different environments.

Contribution

It presents a novel graph-based reinforcement learning approach that learns in a single simulation and transfers directly to real-world scenarios without additional training.

Findings

Zero-shot transfer to multiple environments including real-world.

Efficient learning using domain knowledge and graph neural networks.

Scalable real-time decision-making policy.

Abstract

This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single simulation environment, and transferring it to other environments, which may be physical or virtual. Recent work in transfer learning achieves encouraging performance by domain adaptation and domain randomization to expose an agent to scenarios that fill the inherent gaps in sim2sim and sim2real approaches. However, it is inefficient to train an agent in environments with randomized conditions to learn the important features of its current state. An agent can use domain knowledge provided by human experts to learn efficiently. We propose a novel approach that uses graph neural networks in conjunction with deep reinforcement learning, enabling decision-making over graphs containing relevant exploration information provided by human experts to predict a robot's optimal sensing action in belief space. The policy, which is trained only in a single simulation environment, offers a real-time, scalable, and transferable decision-making strategy, resulting in zero-shot transfer to other simulation environments and even real-world environments.