SyNeT: Synthetic Negatives for Traversability Learning

TL;DR

This paper presents SyNeT, a method for improving traversability estimation in autonomous robots by explicitly incorporating synthetic negatives into training, which enhances robustness and generalization without altering inference models.

Contribution

The paper introduces a novel synthetic negative data generation technique for traversability learning, compatible with existing frameworks, and proposes an object-centric FPR evaluation method.

Findings

Significant improvement in robustness across diverse environments.

Enhanced generalization in traversability estimation.

Effective integration of synthetic negatives into training pipelines.

Abstract

Reliable traversability estimation is crucial for autonomous robots to navigate complex outdoor environments safely. Existing self-supervised learning frameworks primarily rely on positive and unlabeled data; however, the lack of explicit negative data remains a critical limitation, hindering the model's ability to accurately identify diverse non-traversable regions. To address this issue, we introduce a method to explicitly construct synthetic negatives, representing plausible but non-traversable, and integrate them into vision-based traversability learning. Our approach is formulated as a training strategy that can be seamlessly integrated into both Positive-Unlabeled (PU) and Positive-Negative (PN) frameworks without modifying inference architectures. Complementing standard pixel-wise metrics, we introduce an object-centric FPR evaluation approach that analyzes predictions in regions where synthetic negatives are inserted. This evaluation provides an indirect measure of the model's ability to consistently identify non-traversable regions without additional manual labeling. Extensive experiments on both public and self-collected datasets demonstrate that our approach significantly enhances robustness and generalization across diverse environments. The source code and demonstration videos will be publicly available.