Learning Risk-aware Costmaps for Traversability in Challenging Environments

TL;DR

This paper introduces a neural network-based method to learn risk-aware traversability costmaps that improve safety and efficiency for robots navigating uncertain, unstructured environments by focusing on tail-risk estimation.

Contribution

The authors propose a novel neural network architecture that learns the distribution of traversability costs emphasizing tail risks, enhancing robustness and computational efficiency over traditional geometric methods.

Findings

The method reliably learns tail risk distributions for traversability.

It produces more robust and accurate costmaps compared to baselines.

Validated on data from a legged robot in challenging environments.

Abstract

One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move. A significant source of difficulty in this determination arises from stochasticity and uncertainty, coming from localization error, sensor sparsity and noise, difficult-to-model robot-ground interactions, and disturbances to the motion of the vehicle. Classical approaches to this problem rely on geometric analysis of the surrounding terrain, which can be prone to modeling errors and can be computationally expensive. Moreover, modeling the distribution of uncertain traversability costs is a difficult task, compounded by the various error sources mentioned above. In this work, we take a principled learning approach to this problem. We introduce a neural network architecture for robustly learning the distribution of traversability costs. Because we are motivated by preserving the life of the robot, we tackle this learning problem from the perspective of learning tail-risks, i.e. the Conditional Value-at-Risk (CVaR). We show that this approach reliably learns the expected tail risk given a desired probability risk threshold between 0 and 1, producing a traversability costmap which is more robust to outliers, more accurately captures tail risks, and is more computationally efficient, when compared against baselines. We validate our method on data collected a legged robot navigating challenging, unstructured environments including an abandoned subway, limestone caves, and lava tube caves.