# Goal2Pixel: A Vision-Language Navigation Method That Grounds Goals to Pixels

- Source: arXiv cs.RO
- Published: 2026-10-28T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/w4dx219ozk5xl1fa5joychfes
- Original: https://arxiv.org/abs/2606.01621

## Summary

Goal2Pixel proposes a pure pixel paradigm that reformulates vision-and-language navigation in continuous environments (VLN-CE) as navigable pixel grounding: the model predicts navigable pixels on the image plane, which are then back-projected into 3D waypoints for forward movement, while turning and stopping are encoded by auxiliary left, right, and bottom regions.