Learning-based Traversability Costmap for Autonomous Off-road Navigation

TL;DR

This paper introduces a learning-based method that combines visual and geometric data to generate accurate traversability costmaps for off-road navigation, improving safety and efficiency.

Contribution

It presents a novel risk-aware labeling approach using proprioceptive data and demonstrates superior performance in costmap accuracy and navigation success over previous methods.

Findings

Costmap prediction achieves high accuracy and low MSE.

Navigation using learned costmaps results in safer, smoother driving.

Outperforms previous methods in success rate and efficiency.

Abstract

Traversability estimation in off-road terrains is an essential procedure for autonomous navigation. However, creating reliable labels for complex interactions between the robot and the surface is still a challenging problem in learning-based costmap generation. To address this, we propose a method that predicts traversability costmaps by leveraging both visual and geometric information of the environment. To quantify the surface properties like roughness and bumpiness, we introduce a novel way of risk-aware labelling with proprioceptive information for network training. We validate our method in costmap prediction and navigation tasks for complex off-road scenarios. Our results demonstrate that our costmap prediction method excels in terms of average accuracy and MSE. The navigation results indicate that using our learned costmaps leads to safer and smoother driving, outperforming previous methods in terms of the highest success rate, lowest normalized trajectory length, lowest time cost, and highest mean stability across two scenarios.