Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation

TL;DR

This paper introduces ORAN, an omnidirectional audio-visual navigation system that leverages cross-task knowledge transfer and omnidirectional information gathering to improve robot navigation in unseen environments.

Contribution

The paper proposes CCPD for adaptive knowledge transfer from point-to-point wayfinding to audio-visual navigation and introduces OIG for enhanced environmental perception, achieving state-of-the-art results.

Findings

ORAN outperforms previous methods in audio-visual navigation.

Achieved 1st place in Soundspaces Challenge 2022.

Significant improvements in SPL and SR metrics.

Abstract

Audio-visual navigation is an audio-targeted wayfinding task where a robot agent is entailed to travel a never-before-seen 3D environment towards the sounding source. In this article, we present ORAN, an omnidirectional audio-visual navigator based on cross-task navigation skill transfer. In particular, ORAN sharpens its two basic abilities for a such challenging task, namely wayfinding and audio-visual information gathering. First, ORAN is trained with a confidence-aware cross-task policy distillation (CCPD) strategy. CCPD transfers the fundamental, point-to-point wayfinding skill that is well trained on the large-scale PointGoal task to ORAN, so as to help ORAN to better master audio-visual navigation with far fewer training samples. To improve the efficiency of knowledge transfer and address the domain gap, CCPD is made to be adaptive to the decision confidence of the teacher policy. Second, ORAN is equipped with an omnidirectional information gathering (OIG) mechanism, i.e., gleaning visual-acoustic observations from different directions before decision-making. As a result, ORAN yields more robust navigation behaviour. Taking CCPD and OIG together, ORAN significantly outperforms previous competitors. After the model ensemble, we got 1st in Soundspaces Challenge 2022, improving SPL and SR by 53% and 35% relatively.