Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidence

TL;DR

This paper introduces an evidential semantic mapping framework using Dempster-Shafer Theory and Evidential Deep Learning to improve uncertainty estimation in off-road environments, outperforming existing methods in challenging scenes.

Contribution

The novel integration of Dempster-Shafer Theory with deep learning for semantic mapping enhances uncertainty reliability in complex environments.

Findings

Improved uncertainty map reliability in challenging scenes

Semantic accuracy comparable to state-of-the-art methods

Outperforms existing methods in high uncertainty environments

Abstract

Semantic mapping with Bayesian Kernel Inference (BKI) has shown promise in providing a richer understanding of environments by effectively leveraging local spatial information. However, existing methods face challenges in constructing accurate semantic maps or reliable uncertainty maps in perceptually challenging environments due to unreliable semantic predictions. To address this issue, we propose an evidential semantic mapping framework, which integrates the evidential reasoning of Dempster-Shafer Theory of Evidence (DST) into the entire mapping pipeline by adopting Evidential Deep Learning (EDL) and Dempster's rule of combination. Additionally, the extended belief is devised to incorporate local spatial information based on their uncertainty during the mapping process. Comprehensive experiments across various off-road datasets demonstrate that our framework enhances the reliability of uncertainty maps, consistently outperforming existing methods in scenes with high perceptual uncertainties while showing semantic accuracy comparable to the best-performing semantic mapping techniques.