TY - JOUR
T1 - Neural topological SLAM for visual navigation
AU - Chaplot, Devendra Singh
AU - Salakhutdinov, Ruslan
AU - Gupta, Abhinav
AU - Gupta, Saurabh
N1 - Funding Information:
This work was supported by IARPA DIVA D17PC00340, ONR Grant N000141812861, ONR MURI, ONR Young Investigator, DARPA MCS, Apple and Nvidia.
Funding Information:
This work was supported by IARPA DIVA D17PC00340, ONR Grant N000141812861, ONR MURI, ONR Young Investigator, DARPA MCS, Apple and Nvidia. Gibson License: http://svl.stanford.edu/gibson2/ assets/GDS_agreement.pdf
Publisher Copyright:
© 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space that effectively leverage semantics and afford approximate geometric reasoning. At the heart of our representations are nodes with associated semantic features, that are interconnected using coarse geometric information. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Experimental study in visually and physically realistic simulation suggests that our method builds effective representations that capture structural regularities and efficiently solve long-horizon navigation problems. We observe a relative improvement of more than 50% over existing methods that study this task.
AB - This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space that effectively leverage semantics and afford approximate geometric reasoning. At the heart of our representations are nodes with associated semantic features, that are interconnected using coarse geometric information. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Experimental study in visually and physically realistic simulation suggests that our method builds effective representations that capture structural regularities and efficiently solve long-horizon navigation problems. We observe a relative improvement of more than 50% over existing methods that study this task.
UR - http://www.scopus.com/inward/record.url?scp=85094827966&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094827966&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.01289
DO - 10.1109/CVPR42600.2020.01289
M3 - Conference article
AN - SCOPUS:85094827966
SP - 12872
EP - 12881
JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SN - 1063-6919
M1 - 9157610
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Y2 - 14 June 2020 through 19 June 2020
ER -