# Language Sensor Model: Estimating 3D Scene Spatial Beliefs from Natural Language and Fusing with Perception

- Source: arXiv cs.RO
- Published: 2026-10-26T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/gp882lyp4xeh5kbo7u8iau5ox
- Original: https://arxiv.org/abs/2606.08666

## Summary

The authors propose the Language Sensor Model (LSM), which maps each natural language description and its scene-graph context to a multimodal distribution, using mixture weights to represent referential ambiguity and component covariances to represent spatial uncertainty.