Topological mapping for traversability-aware long-range navigation in off-road terrain

TL;DR

This paper introduces a topological mapping approach for long-range, traversability-aware navigation in unknown off-road terrains, utilizing vision and GPS, with novel traversability analysis and exploration strategies demonstrated in forest environments.

Contribution

It presents a new method combining topological mapping, traversability prediction, and goal-conditioned behavior cloning for autonomous off-trail navigation in complex terrains.

Findings

Successfully explored 400m² forest sites unseen during training

Achieved reliable long-range navigation in challenging off-road conditions

Demonstrated effective exploration with frontier-based planning

Abstract

Autonomous robots navigating in off-road terrain like forests open new opportunities for automation. While off-road navigation has been studied, existing work often relies on clearly delineated pathways. We present a method allowing for long-range planning, exploration and low-level control in unknown off-trail forest terrain, using vision and GPS only. We represent outdoor terrain with a topological map, which is a set of panoramic snapshots connected with edges containing traversability information. A novel traversability analysis method is demonstrated, predicting the existence of a safe path towards a target in an image. Navigating between nodes is done using goal-conditioned behavior cloning, leveraging the power of a pretrained vision transformer. An exploration planner is presented, efficiently covering an unknown off-road area with unknown traversability using a frontiers-based approach. The approach is successfully deployed to autonomously explore two 400 meters squared forest sites unseen during training, in difficult conditions for navigation.