PlaceNav: Topological Navigation through Place Recognition
This work addresses navigation performance and data scarcity for robots in indoor and outdoor environments, representing an incremental improvement over existing methods.
The paper tackled the problem of limited training data and poor computational scaling in topological navigation by subdividing the robot-independent part into navigation-specific and generic computer vision components, using visual place recognition for subgoal selection, resulting in a 76% higher success rate indoors and 23% higher outdoors with improved efficiency.
Recent results suggest that splitting topological navigation into robot-independent and robot-specific components improves navigation performance by enabling the robot-independent part to be trained with data collected by robots of different types. However, the navigation methods' performance is still limited by the scarcity of suitable training data and they suffer from poor computational scaling. In this work, we present PlaceNav, subdividing the robot-independent part into navigation-specific and generic computer vision components. We utilize visual place recognition for the subgoal selection of the topological navigation pipeline. This makes subgoal selection more efficient and enables leveraging large-scale datasets from non-robotics sources, increasing training data availability. Bayesian filtering, enabled by place recognition, further improves navigation performance by increasing the temporal consistency of subgoals. Our experimental results verify the design and the new method obtains a 76% higher success rate in indoor and 23% higher in outdoor navigation tasks with higher computational efficiency.