Learning to Localize Reference Trajectories in Image-Space for Visual Navigation
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_ | 1866917286327091200 |
|---|---|
| author | Busch, Finn Lukas Vahs, Matti Yang, Quantao Peimbert, Jesús Gerardo Ortega Cai, Yixi Tumova, Jana Andersson, Olov |
| author_facet | Busch, Finn Lukas Vahs, Matti Yang, Quantao Peimbert, Jesús Gerardo Ortega Cai, Yixi Tumova, Jana Andersson, Olov |
| contents | We present LoTIS, a model for visual navigation that provides robot-agnostic image-space guidance by localizing a reference RGB trajectory in the robot's current view, without requiring camera calibration, poses, or robot-specific training. Instead of predicting actions tied to specific robots, we predict the image-space coordinates of the reference trajectory as they would appear in the robot's current view. This creates robot-agnostic visual guidance that easily integrates with local planning. Consequently, our model's predictions provide guidance zero-shot across diverse embodiments. By decoupling perception from action and learning to localize trajectory points rather than imitate behavioral priors, we enable a cross-trajectory training strategy for robustness to viewpoint and camera changes. We outperform state-of-the-art methods by 20-50 percentage points in success rate on conventional forward navigation, achieving 94-98% success rate across diverse sim and real environments. Furthermore, we achieve over 5x improvements on challenging tasks where baselines fail, such as backward traversal. The system is straightforward to use: we show how even a video from a phone camera directly enables different robots to navigate to any point on the trajectory. Videos, demo, and code are available at https://finnbusch.com/lotis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18803 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Localize Reference Trajectories in Image-Space for Visual Navigation Busch, Finn Lukas Vahs, Matti Yang, Quantao Peimbert, Jesús Gerardo Ortega Cai, Yixi Tumova, Jana Andersson, Olov Robotics We present LoTIS, a model for visual navigation that provides robot-agnostic image-space guidance by localizing a reference RGB trajectory in the robot's current view, without requiring camera calibration, poses, or robot-specific training. Instead of predicting actions tied to specific robots, we predict the image-space coordinates of the reference trajectory as they would appear in the robot's current view. This creates robot-agnostic visual guidance that easily integrates with local planning. Consequently, our model's predictions provide guidance zero-shot across diverse embodiments. By decoupling perception from action and learning to localize trajectory points rather than imitate behavioral priors, we enable a cross-trajectory training strategy for robustness to viewpoint and camera changes. We outperform state-of-the-art methods by 20-50 percentage points in success rate on conventional forward navigation, achieving 94-98% success rate across diverse sim and real environments. Furthermore, we achieve over 5x improvements on challenging tasks where baselines fail, such as backward traversal. The system is straightforward to use: we show how even a video from a phone camera directly enables different robots to navigate to any point on the trajectory. Videos, demo, and code are available at https://finnbusch.com/lotis. |
| title | Learning to Localize Reference Trajectories in Image-Space for Visual Navigation |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.18803 |