Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.19564 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910847426625536 |
|---|---|
| author | Ioannidis, Nicholas Reda, Daniele Cohan, Setareh van de Panne, Michiel |
| author_facet | Ioannidis, Nicholas Reda, Daniele Cohan, Setareh van de Panne, Michiel |
| contents | Diffusion models can be used as a motion planner by sampling from a distribution of possible futures. However, the samples may not satisfy hard constraints that exist only implicitly in the training data, e.g., avoiding falls or not colliding with a wall. We propose learned viability filters that efficiently predict the future success of any given plan, i.e., diffusion sample, and thereby enforce an implicit future-success constraint. Multiple viability filters can also be composed together. We demonstrate the approach on detailed footstep planning for challenging 3D human locomotion tasks, showing the effectiveness of viability filters in performing online planning and control for box-climbing, step-over walls, and obstacle avoidance. We further show that using viability filters is significantly faster than guidance-based diffusion prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19564 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-based Planning with Learned Viability Filters Ioannidis, Nicholas Reda, Daniele Cohan, Setareh van de Panne, Michiel Robotics Machine Learning Diffusion models can be used as a motion planner by sampling from a distribution of possible futures. However, the samples may not satisfy hard constraints that exist only implicitly in the training data, e.g., avoiding falls or not colliding with a wall. We propose learned viability filters that efficiently predict the future success of any given plan, i.e., diffusion sample, and thereby enforce an implicit future-success constraint. Multiple viability filters can also be composed together. We demonstrate the approach on detailed footstep planning for challenging 3D human locomotion tasks, showing the effectiveness of viability filters in performing online planning and control for box-climbing, step-over walls, and obstacle avoidance. We further show that using viability filters is significantly faster than guidance-based diffusion prediction. |
| title | Diffusion-based Planning with Learned Viability Filters |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2502.19564 |