PlaceNav: Topological Navigation through Place Recognition

TL;DR

PlaceNav introduces a topological navigation method that uses visual place recognition for subgoal selection, leveraging large-scale datasets and Bayesian filtering to significantly improve success rates and computational efficiency in indoor and outdoor navigation.

Contribution

The paper presents PlaceNav, a novel topological navigation approach that combines place recognition with Bayesian filtering, enhancing data utilization and performance over existing methods.

Findings

76% higher success rate in indoor navigation

23% higher success rate in outdoor navigation

Improved computational efficiency

Abstract

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.