A Behavioral Approach to Visual Navigation with Graph Localization Networks
This work addresses robot navigation in dynamic environments, but it is incremental as it builds on existing methods like graph neural networks and behavioral decomposition.
The paper tackles visual navigation for robots by introducing a behavioral approach using topological maps and graph neural networks for localization, achieving superior performance over baselines in both seen and unseen environments in the Gibson simulator.
Inspired by research in psychology, we introduce a behavioral approach for visual navigation using topological maps. Our goal is to enable a robot to navigate from one location to another, relying only on its visual input and the topological map of the environment. We propose using graph neural networks for localizing the agent in the map, and decompose the action space into primitive behaviors implemented as convolutional or recurrent neural networks. Using the Gibson simulator, we verify that our approach outperforms relevant baselines and is able to navigate in both seen and unseen environments.