Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Semi-parametric topological memory for navigation
Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
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 SPTM-based agent outperforms existing agents with LSTM memory by a large margin.
TL;DR:We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals.
Keywords:deep learning, navigation, memory
Enter your feedback below and we'll get back to you as soon as possible.