NOLO: Navigate Only Look Once

The in-context learning ability of Transformer models has brought new possibilities to visual navigation. In this paper, we focus on the video navigation setting, where an in-context navigation policy needs to be learned purely from videos in an offline manner, without access to the actual environme...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Bohan Zhou, Zhang, Zhongbin, Wang, Jiangxing, Lu, Zongqing
Format: Article
Language:English
Subjects:
Algorithms
Context
Labels
Machine learning
Navigation
Optical flow (image analysis)
Video
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The in-context learning ability of Transformer models has brought new possibilities to visual navigation. In this paper, we focus on the video navigation setting, where an in-context navigation policy needs to be learned purely from videos in an offline manner, without access to the actual environment. For this setting, we propose Navigate Only Look Once (NOLO), a method for learning a navigation policy that possesses the in-context ability and adapts to new scenes by taking corresponding context videos as input without finetuning or re-training. To enable learning from videos, we first propose a pseudo action labeling procedure using optical flow to recover the action label from egocentric videos. Then, offline reinforcement learning is applied to learn the navigation policy. Through extensive experiments on different scenes both in simulation and the real world, we show that our algorithm outperforms baselines by a large margin, which demonstrates the in-context learning ability of the learned policy. For videos and more information, visit https://sites.google.com/view/nol0.
ISSN:2331-8422