Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied NavigationDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: Audio-Visual Navigation, Scene Priors, Object Relations, Embodied AI
TL;DR: We introduce knowledge-driven scene priors in audio-visual navigation, combining semantics from a knowledge graph, spatial knowledge from dual Graph Encoder Networks, and background knowledge from pre-training tasks—all within an RL framework.
Abstract: Generalisation to unseen contexts remains a challenge for embodied navigation agents. In the context of semantic audio-visual navigation (SAVi) tasks, generalisation includes both generalising to unseen indoor visual scenes as well as generalising to unheard sounding objects. Previous SAVi task definitions do not include evaluation conditions on truly novel sounding objects, resorting instead to evaluating agents on unheard sound clips of known objects; meanwhile, previous SAVi methods do not include explicit mechanisms for incorporating domain knowledge about object and region semantics. These weaknesses limit the development and assessment of models' abilities to generalise their learned experience. In this work, we introduce the use of knowledge-driven scene priors in the semantic audio-visual embodied navigation task: we combine semantic information from our novel knowledge graph that encodes object-region relations, spatial knowledge from dual Graph Encoder Networks, and background knowledge from a series of pre-training tasks---all within a reinforcement learning framework for audio-visual navigation. We define a new audio-visual navigation sub-task, where agents are evaluated on novel sounding objects, as opposed to unheard clips of known objects. We show improvements over strong baselines in generalisation to unseen regions and novel sounding objects, within the Habitat-Matterport3D simulation environment, under the SoundSpaces task. We release code, knowledge graphs, and dataset generation details in the supplementary material.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)
10 Replies

Loading