Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance
This addresses the challenge of reducing human labeling costs and errors for off-road robot navigation, though it is incremental by building on existing self-supervised and metric learning approaches.
The paper tackles the problem of self-supervised traversability estimation for mobile robots in off-road environments by introducing a deep metric learning method that incorporates unlabeled data with prototypes to mitigate epistemic uncertainty from scarce negative data, achieving competitive performance on new datasets like Dtrail and SemanticKITTI.
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.