Robust fusion for bayesian semantic mapping

Morilla-Cabello, David (Universidad de Zaragoza) ; Mur-Labadia, Lorenzo (Universidad de Zaragoza) ; Martinez-Cantin, Ruben (Universidad de Zaragoza) ; Montijano, Eduardo (Universidad de Zaragoza)

Resumen: The integration of semantic information in a map allows robots to understand better their environment and make high-level decisions. In the last few years, neural networks have shown enormous progress in their perception capabilities. However, when fusing multiple observations from a neural network in a semantic map, its inherent overconfidence with unknown data gives too much weight to the outliers and decreases the robustness. To mitigate this issue we propose a novel robust fusion method to combine multiple Bayesian semantic predictions. Our method uses the uncertainty estimation provided by a Bayesian neural network to calibrate the way in which the measurements are fused. This is done by regularizing the observations to mitigate the problem of overconfident outlier predictions and using the epistemic uncertainty to weigh their influence in the fusion, resulting in a different formulation of the probability distributions. We validate our robust fusion strategy by performing experiments on photo-realistic simulated environments and real scenes. In both cases, we use a network trained on different data to expose the model to varying data distributions. The results show that considering the model's uncertainty and regularizing the probability distribution of the observations distribution results in a better semantic segmentation performance and more robustness to outliers, compared with other methods. Video - https://youtu.be/5xVGm7z9c-0

Idioma: Inglés

DOI: 10.1109/IROS55552.2023.10342253

Año: 2023

Publicado en: Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems 2023 (2023), 76-81
ISSN: 2153-0858

Factor impacto CITESCORE: 4.4 - Software (Q2) - Computer Vision and Pattern Recognition (Q2) - Control and Systems Engineering (Q2) - Computer Science Applications (Q2)

Factor impacto SCIMAGO: 1.094 - Computer Science Applications - Software - Control and Systems Engineering - Computer Vision and Pattern Recognition

Financiación: info:eu-repo/grantAgreement/ES/MCIU/FPU20-06563
Financiación: info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2021-125209OB-I00
Financiación: info:eu-repo/grantAgreement/ES/MICINN/PID2021-125514NB-I00
Financiación: info:eu-repo/grantAgreement/EUR/MICINN/TED2021-129410B-I00
Financiación: info:eu-repo/grantAgreement/EUR/MICINN/TED2021-131150B-I00

Tipo y forma: Congress (PostPrint)

Área (Departamento): Área Ingen.Sistemas y Automát. (Dpto. Informát.Ingenie.Sistms.)