Name
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. |
Year | Venue | Field |
|---|---|---|
2018 | ICLR | Graph,Topology,Navigation system,Parametric statistics,Semiparametric model,Topological map,Landmark,Memory architecture,Mathematics |
DocType | Volume | Citations |
Journal | abs/1803.00653 | 14 |
PageRank | References | Authors |
0.55 | 15 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nikolay Savinov | 1 | 126 | 7.03 |
| Alexey Dosovitskiy | 2 | 1797 | 80.48 |
| Vladlen Koltun | 3 | 4064 | 162.63 |