End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon

Published: 16 Jan 2024, Last Modified: 11 Feb 2024ICLR 2024 posterEveryoneRevisionsBibTeX
Primary Area: applications to robotics, autonomy, planning
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.
Keywords: Navigation, Embodied AI, Perception
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: In an ImageGoal navigation context, we propose two pre-text tasks which let correspondence emerge as a solution and train a dual visual encoder based on a binocular transforme
Abstract: Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations generalizable to unseen environments and in learning high-capacity perception modules capable of reasoning on high-dimensional input. The latter is particularly difficult when the goal is not given as a category ("ObjectNav") but as an exemplar image ("ImageNav"), as the perception module needs to learn a comparison strategy requiring to solve an underlying visual correspondence problem. This has been shown to be difficult from reward alone or with standard auxiliary tasks. We address this problem through a sequence of two pretext tasks, which serve as a prior for what we argue is one of the main bottleneck in perception, extremely wide-baseline relative pose estimation and visibility prediction in complex scenes. The first pretext task, cross-view completion is a proxy for the underlying visual correspondence problem, while the second task addresses goal detection and finding directly. We propose a new dual encoder with a large-capacity binocular ViT model and show that correspondence solutions naturally emerge from the training signals. Experiments show significant improvements and SOTA performance on the two benchmarks, ImageNav and the Instance-ImageNav variant, where camera intrinsics and height differ between observation and goal.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: zip
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 326