arrow
返回

Active Perception for Visual-Language Navigation

delete2022-12-03
delete5
PRE
AI
王
王汉卿 (Hanqing Wang)
王文冠 封面图
王文冠 (Wenguan Wang)
W
Wei Liang
S
Steven C. H. Hoi
沈
沈建冰 (Jianbing Shen) *
L
Luc Van Gool
DOI:10.1007/s11263-022-01721-6delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Visual-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. Agents trained by current approaches typically suffer from this and would consequently struggle to take navigation actions at every step. In contrast, when humans face such a challenge, we can still maintain robust navigation by actively exploring the surroundings to gather more information and thus make a more confident navigation decision. This work draws inspiration from human navigation behavior and endows an agent with an active perception ability for more intelligent navigation. To achieve this, we propose an end-to-end framework for learning an exploration policy that decides (i) when and where to explore, (ii) what information is worth gathering during exploration, and (iii) how to adjust the navigation decision after the exploration. In this way, the agent is able to turn its past experiences as well as new explored knowledge to contexts for more confident navigation decision making. In addition, an external memory is used to explicitly store the visited visual environments and thus allows the agent to adopt a late action-taking strategy to avoid duplicate exploration and navigation movements. Our experimental results on two standard benchmark datasets show promising exploration strategies emerged from training, which leads to significant boost in navigation performance.
Keyword:
Visual-language navigation
Active perception
Curriculum reinforcement learning

期刊

International Journal of Computer Vision 封面图
International Journal of Computer Vision
IF:
9.3
论文数:
3.9K
被引数:
2.8W

机构

S
salesforce
学者数:
65
论文数: 71
被引数: 0
B
beijing institute of technology
学者数:
5.5W
论文数: 4.0W
被引数: 63
S
swiss federal institutes of technology domain
学者数:
9.0W
论文数: 8.0W
被引数: 163
U
university of technology sydney
学者数:
1.6W
论文数: 2.0W
被引数: 25
U
University of Macau
学者数:
1.1W
论文数: 1.3W
被引数: 2.0W
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
Impact of antibiotic treatment on immunotherapy response in women with recurrent gynecologic cancer
err2021-04-01
err0
PREAI
errLaura M. Chambers; Chad M. Michener; Peter G. Rose; Ofer Reizes; Meng Yao; Roberto Vargas
err分享
err收藏
Impact of Coastal Hazards on Residents’ Spatial Accessibility to Health Services
err2019-12-01
err0
errOAAI
errGeorgios P. Balomenos; Yujie Hu; Jamie E. Padgett; Kyle Shelton
err分享
err收藏
Hyperuniform flow fields resulting from hyperuniform configurations of circular disks
err2018-12-05
err0
PREAI
errZhenya Ding; Yu Zheng; Yaopengxiao Xu; Yang Jiao; Wei Li
err分享
err收藏
ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
err分享
err收藏
学者 查看更多内容