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.

The Neural Topological SLAM model consists of 3 components, a Graph Construction module which updates the topological map as it receives observations, a Global Policy which samples subgoals, and a Local Policy which takes navigational actions to reach the subgoal.

@inproceedings{chaplot2020neural,
  title={Neural Topological SLAM for Visual Navigation},
  author={Chaplot, Devendra Singh and Salakhutdinov, Ruslan and 
          Gupta, Abhinav and Gupta, Saurabh},
  booktitle={CVPR},
  year={2020}}