Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.06651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915233971306496 |
|---|---|
| author | Tordjman--Levavasseur, Valentin Caron, Stéphane |
| author_facet | Tordjman--Levavasseur, Valentin Caron, Stéphane |
| contents | Collision avoidance can be checked in explicit environment models such as elevation maps or occupancy grids, yet integrating such models with a locomotion policy requires accurate state estimation. In this work, we consider the question of collision avoidance from an implicit environment model. We use monocular RGB images as inputs and train a collisionavoidance policy from photorealistic images generated by 2D Gaussian splatting. We evaluate the resulting pipeline in realworld experiments under velocity commands that bring the robot on an intercept course with obstacles. Our results suggest that RGB images can be enough to make collision-avoidance decisions, both in the room where training data was collected and in out-of-distribution environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06651 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collision avoidance from monocular vision trained with novel view synthesis Tordjman--Levavasseur, Valentin Caron, Stéphane Robotics Collision avoidance can be checked in explicit environment models such as elevation maps or occupancy grids, yet integrating such models with a locomotion policy requires accurate state estimation. In this work, we consider the question of collision avoidance from an implicit environment model. We use monocular RGB images as inputs and train a collisionavoidance policy from photorealistic images generated by 2D Gaussian splatting. We evaluate the resulting pipeline in realworld experiments under velocity commands that bring the robot on an intercept course with obstacles. Our results suggest that RGB images can be enough to make collision-avoidance decisions, both in the room where training data was collected and in out-of-distribution environments. |
| title | Collision avoidance from monocular vision trained with novel view synthesis |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.06651 |