# Robust Fusion for Bayesian Semantic Mapping

arXiv: https://arxiv.org/abs/2303.07836 · HTML: https://mlsanity.com/paper/2303.07836/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2023.

## Built on by (most cited first, 8 of 8)

- [Multimodal LLM Guided Exploration and Active Mapping using Fisher Information](https://mlsanity.com/paper/2410.17422/) (2024)
- [On the Overconfidence Problem in Semantic 3D Mapping](https://mlsanity.com/paper/2311.10018/) (2023)
- [Evidential Semantic Mapping in Off-road Environments with Uncertainty-aware Bayesian Kernel Inference](https://mlsanity.com/paper/2403.14138/) (2024)
- [Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environments](https://mlsanity.com/paper/2411.06632/) (2024)
- [EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images](https://mlsanity.com/paper/2503.04441/) (2025)
- [Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidence](https://mlsanity.com/paper/2405.06265/) (2024)
- [Uncertainty Estimation in Instance Segmentation of Affordances via Bayesian Visual Transformers](https://mlsanity.com/paper/2605.03614/) (2026)
- [PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memory](https://mlsanity.com/paper/2609.31716/) (2026)

## Abstract (arXiv)

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