Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance

TL;DR

This paper presents a self-supervised method for 3D traversability estimation in off-road environments, combining semantic segmentation and metric learning to leverage unlabeled data and reduce labeling costs.

Contribution

It introduces a novel deep metric learning approach with a new evaluation metric and a comprehensive off-road dataset, enhancing traversability estimation accuracy.

Findings

Effective in leveraging unlabeled data for traversability estimation

Improves performance on off-road and urban datasets

Reduces reliance on extensive manual labeling

Abstract

Traversability estimation for mobile robots in off-road environments requires more than conventional semantic segmentation used in constrained environments like on-road conditions. Recently, approaches to learning a traversability estimation from past driving experiences in a self-supervised manner are arising as they can significantly reduce human labeling costs and labeling errors. However, the self-supervised data only provide supervision for the actually traversed regions, inducing epistemic uncertainty according to the scarcity of negative information. Negative data are rarely harvested as the system can be severely damaged while logging the data. To mitigate the uncertainty, we introduce a deep metric learning-based method to incorporate unlabeled data with a few positive and negative prototypes in order to leverage the uncertainty, which jointly learns using semantic segmentation and traversability regression. To firmly evaluate the proposed framework, we introduce a new evaluation metric that comprehensively evaluates the segmentation and regression. Additionally, we construct a driving dataset `Dtrail' in off-road environments with a mobile robot platform, which is composed of a wide variety of negative data. We examine our method on Dtrail as well as the publicly available SemanticKITTI dataset.