Learning Exploration Policies for Navigation

TL;DR

This paper presents a learning-based exploration policy for autonomous navigation in complex 3D environments, outperforming classical methods and aiding downstream tasks.

Contribution

It introduces a novel approach using spatial memory, imitation learning, and coverage rewards for effective task-agnostic exploration.

Findings

Learned policies outperform classical geometry-based exploration.

Spatial memory and imitation learning improve exploration efficiency.

Exploration policies benefit downstream navigation tasks.

Abstract

Numerous past works have tackled the problem of task-driven navigation. But, how to effectively explore a new environment to enable a variety of down-stream tasks has received much less attention. In this work, we study how agents can autonomously explore realistic and complex 3D environments without the context of task-rewards. We propose a learning-based approach and investigate different policy architectures, reward functions, and training paradigms. We find that the use of policies with spatial memory that are bootstrapped with imitation learning and finally finetuned with coverage rewards derived purely from on-board sensors can be effective at exploring novel environments. We show that our learned exploration policies can explore better than classical approaches based on geometry alone and generic learning-based exploration techniques. Finally, we also show how such task-agnostic exploration can be used for down-stream tasks. Code and Videos are available at: https://sites.google.com/view/exploration-for-nav.