Semi-Parametric Topological Memory for Navigation

Abstract

We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with nodes corresponding to locations in the environment and a (parametric) deep network capable of retrieving nodes from the graph based on observations. The graph stores no metric information, only connectivity of locations corresponding to the nodes. We use SPTM as a planning module in a navigation system. Given only 5 minutes of footage of a previously unseen maze, an SPTM-based navigation agent can build a topological map of the environment and use it to confidently navigate towards goals. The average success rate of the SPTM agent in goal-directed navigation across test environments is higher than the best-performing baseline by a factor of three.

Cite

Text

Savinov et al. "Semi-Parametric Topological Memory for Navigation." International Conference on Learning Representations, 2018.

Markdown

[Savinov et al. "Semi-Parametric Topological Memory for Navigation." International Conference on Learning Representations, 2018.](https://mlanthology.org/iclr/2018/savinov2018iclr-semiparametric/)

BibTeX

@inproceedings{savinov2018iclr-semiparametric,
  title     = {{Semi-Parametric Topological Memory for Navigation}},
  author    = {Savinov, Nikolay and Dosovitskiy, Alexey and Koltun, Vladlen},
  booktitle = {International Conference on Learning Representations},
  year      = {2018},
  url       = {https://mlanthology.org/iclr/2018/savinov2018iclr-semiparametric/}
}