Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.24690 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910252282150912 |
|---|---|
| author | Kaplan, Aysu Aylin Erkent, Özgür |
| author_facet | Kaplan, Aysu Aylin Erkent, Özgür |
| contents | The motion planning problem for robotic manipulation can be addressed through classical or deep learning approaches. Existing methods face significant challenges in generalizing to diverse settings. In this study, we present a method with high generalization capability that generates collision-free trajectories using diffusion models where the denoising process is guided by the gradient of the total collision cost. We are also presenting a dynamic approach for choosing start step of the gradient guidance. Experimental results demonstrate that guiding the diffusion model dynamically with the sum of collision costs offers more robust performance by overcoming the generalization issues faced by competing methods. The proposed model demonstrates its effectiveness by achieving the highest performance on diverse test settings in M$π$nets\ dataset among the compared methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24690 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sum of Costs Diffusion with Dynamic Guidance for Motion Planning Kaplan, Aysu Aylin Erkent, Özgür Robotics Machine Learning The motion planning problem for robotic manipulation can be addressed through classical or deep learning approaches. Existing methods face significant challenges in generalizing to diverse settings. In this study, we present a method with high generalization capability that generates collision-free trajectories using diffusion models where the denoising process is guided by the gradient of the total collision cost. We are also presenting a dynamic approach for choosing start step of the gradient guidance. Experimental results demonstrate that guiding the diffusion model dynamically with the sum of collision costs offers more robust performance by overcoming the generalization issues faced by competing methods. The proposed model demonstrates its effectiveness by achieving the highest performance on diverse test settings in M$π$nets\ dataset among the compared methods. |
| title | Sum of Costs Diffusion with Dynamic Guidance for Motion Planning |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2605.24690 |