IG-Net: Image-Goal Network for Offline Visual Navigation on A Large-Scale Game Map
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: visual navigation, offline training
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose Image-Goal Network to address the challenge of navigating vast and visually intricate gaming environments by using representation learning to encode spatial map information and enhance navigation performance.
Abstract: Navigating vast and visually intricate gaming environments poses unique challenges, especially when agents are deprived of absolute positions and orientations during testing. This paper addresses the challenge of training agents in such environments using a limited set of offline navigation data and a more substantial set of offline position data. We introduce the \textit{Image-Goal Network} (IG-Net), an innovative solution tailored for these challenges. IG-Net is designed as an image-goal-conditioned navigation agent, which is trained end-to-end, directly outputting actions based on inputs without intermediary mapping steps. Furthermore, IG-Net harnesses position prediction, path prediction and distance prediction to bolster representation learning to encode spatial map information implicitly, an aspect overlooked in prior works. Our experiments and results demonstrate IG-Net's potential in navigating large-scale gaming environments, providing both advancements in the field and tools for the broader research community.
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: 7803
Loading