ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912986847772672 |
|---|---|
| author | Le, Chi Cuong Zhi, Weiming |
| author_facet | Le, Chi Cuong Zhi, Weiming |
| contents | Reliable robot perception requires not only predicting scene structure, but also identifying where predictions should be treated as unreliable due to sparse or missing observations. We present ContraMap, a contrastive continuous mapping method that augments kernel-based discriminative maps with an explicit uncertainty class trained using synthetic noise samples. This formulation treats unobserved regions as a contrastive class, enabling joint environment prediction and spatial uncertainty estimation in real time without Bayesian inference. Under a simple mixture-model view, we show that the probability assigned to the uncertainty class is a monotonic function of a distance-aware uncertainty surrogate. Experiments in 2D occupancy mapping, 3D semantic mapping, and tabletop scene reconstruction show that ContraMap preserves mapping quality, produces spatially coherent uncertainty estimates, and is substantially more efficient than Bayesian kernelmap baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27632 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation Le, Chi Cuong Zhi, Weiming Robotics Artificial Intelligence Computer Vision and Pattern Recognition Reliable robot perception requires not only predicting scene structure, but also identifying where predictions should be treated as unreliable due to sparse or missing observations. We present ContraMap, a contrastive continuous mapping method that augments kernel-based discriminative maps with an explicit uncertainty class trained using synthetic noise samples. This formulation treats unobserved regions as a contrastive class, enabling joint environment prediction and spatial uncertainty estimation in real time without Bayesian inference. Under a simple mixture-model view, we show that the probability assigned to the uncertainty class is a monotonic function of a distance-aware uncertainty surrogate. Experiments in 2D occupancy mapping, 3D semantic mapping, and tabletop scene reconstruction show that ContraMap preserves mapping quality, produces spatially coherent uncertainty estimates, and is substantially more efficient than Bayesian kernelmap baselines. |
| title | ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27632 |