Enregistré dans:
Détails bibliographiques
Auteurs principaux: Johnson, Faith, Cao, Bryan Bo, Ashok, Ashwin, Jain, Shubham, Dana, Kristin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2411.09893
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912153957564416
author Johnson, Faith
Cao, Bryan Bo
Ashok, Ashwin
Jain, Shubham
Dana, Kristin
author_facet Johnson, Faith
Cao, Bryan Bo
Ashok, Ashwin
Jain, Shubham
Dana, Kristin
contents Visual navigation takes inspiration from humans, who navigate in previously unseen environments using vision without detailed environment maps. Inspired by this, we introduce a novel no-RL, no-graph, no-odometry approach to visual navigation using feudal learning to build a three tiered agent. Key to our approach is a memory proxy map (MPM), an intermediate representation of the environment learned in a self-supervised manner by the high-level manager agent that serves as a simplified memory, approximating what the agent has seen. We demonstrate that recording observations in this learned latent space is an effective and efficient memory proxy that can remove the need for graphs and odometry in visual navigation tasks. For the mid-level manager agent, we develop a waypoint network (WayNet) that outputs intermediate subgoals, or waypoints, imitating human waypoint selection during local navigation. For the low-level worker agent, we learn a classifier over a discrete action space that avoids local obstacles and moves the agent towards the WayNet waypoint. The resulting feudal navigation network offers a novel approach with no RL, no graph, no odometry, and no metric map; all while achieving SOTA results on the image goal navigation task.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09893
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Memory Proxy Maps for Visual Navigation
Johnson, Faith
Cao, Bryan Bo
Ashok, Ashwin
Jain, Shubham
Dana, Kristin
Computer Vision and Pattern Recognition
Visual navigation takes inspiration from humans, who navigate in previously unseen environments using vision without detailed environment maps. Inspired by this, we introduce a novel no-RL, no-graph, no-odometry approach to visual navigation using feudal learning to build a three tiered agent. Key to our approach is a memory proxy map (MPM), an intermediate representation of the environment learned in a self-supervised manner by the high-level manager agent that serves as a simplified memory, approximating what the agent has seen. We demonstrate that recording observations in this learned latent space is an effective and efficient memory proxy that can remove the need for graphs and odometry in visual navigation tasks. For the mid-level manager agent, we develop a waypoint network (WayNet) that outputs intermediate subgoals, or waypoints, imitating human waypoint selection during local navigation. For the low-level worker agent, we learn a classifier over a discrete action space that avoids local obstacles and moves the agent towards the WayNet waypoint. The resulting feudal navigation network offers a novel approach with no RL, no graph, no odometry, and no metric map; all while achieving SOTA results on the image goal navigation task.
title Memory Proxy Maps for Visual Navigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.09893