PSYCH OpenIR  > 中国科学院行为科学重点实验室
Topometric imitation learning for route following under appearance change
Cai, Shaojun1; Wan, Yingjia2
2020-06
Correspondent Emailshaojun.cai@uisee.com ; wanyj@psych.ac.cn
Conference Name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
Source PublicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
Pages4354-4362
Conference Date2020, June 14, 2020 - June 19, 2020
Conference Place不详
Contribution Rank2
Abstract

Traditional navigation models in autonomous driving rely heavily on metric maps, which severely limits their application in large scale environments. In this paper, we introduce a two-level navigation architecture that contains a topological-metric memory structure and a deep image-based controller. The hybrid memory extracts visual features at each location point with a deep convolutional neural network, and stores information about local driving commands at each location point based on metric information estimated from egomotion information. The topological-metric memory is seamlessly integrated with a conditional imitation learning controller through the navigational commands that drives the vehicle between different vertices without collision. We test the whole system in teach-and-repeat experiments in an urban driving simulator. Results show that after being trained in a separate environment, the system could quickly adapt to novel environments with a single teach trial and follow route successively under various illumination and weather conditions.

DOI10.1109/CVPRW50498.2020.00513
Indexed ByEI
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.psych.ac.cn/handle/311026/32462
Collection中国科学院行为科学重点实验室
Affiliation1.UISEE Technology Inc., 85 Hongan Road, Fangshan District, Beijing, China
2.Chinese Academy of Sciences, Key Laboratory of Behavioral Sciences, Institute of Psychology, 16 Lincui Road, Chaoyang District, Beijing, China
Recommended Citation
GB/T 7714
Cai, Shaojun,Wan, Yingjia. Topometric imitation learning for route following under appearance change[C],2020:4354-4362.
Files in This Item:
File Name/Size DocType Version Access License
Topometric imitation(913KB)会议论文 限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cai, Shaojun]'s Articles
[Wan, Yingjia]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cai, Shaojun]'s Articles
[Wan, Yingjia]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cai, Shaojun]'s Articles
[Wan, Yingjia]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.