ForestTrav: Accurate, Efficient and Deployable Forest Traversability Estimation for Autonomous Ground Vehicles

TL;DR

This paper introduces ForestTrav, a novel, efficient method for assessing ground vehicle traversability in vegetated environments using a 3D voxel representation and sparse convolutional networks, outperforming existing methods.

Contribution

The paper presents a new high-fidelity 3D voxel-based traversability estimation method that is accurate, efficient, and capable of generalizing to unseen environments with minimal training data.

Findings

Outperforms state-of-the-art MCC score of 0.39 with 0.59

Generalizes well to unseen environments

Requires only minutes of training on a desktop

Abstract

Autonomous navigation in unstructured vegetated environments remains an open challenge. To successfully operate in these settings, ground vehicles must assess the traversability of the environment and determine which vegetation is pliable enough to push through. In this work, we propose a novel method that combines a high-fidelity and feature-rich 3D voxel representation while leveraging the structural context and sparseness of SCNN's to assess Traversability Estimation (TE) in densely vegetated environments. The proposed method is thoroughly evaluated on an accurately-labeled real-world data set that we provide to the community. It is shown to outperform state-of-the-art methods by a significant margin (0.59 vs. 0.39 MCC score at 0.1m voxel resolution) in challenging scenes and to generalize to unseen environments. In addition, the method is economical in the amount of training data and training time required: a model is trained in minutes on a desktop computer. We show that by exploiting the context of the environment, our method can use different feature combinations with only limited performance variations. For example, our approach can be used with lidar-only features, whilst still assessing complex vegetated environments accurately, which was not demonstrated previously in the literature in such environments. In addition, we propose an approach to assess a traversability estimator's sensitivity to information quality and show our method's sensitivity is low.