Sum of Costs Guided Diffusion for Motion Planning Hareket Planlama için Maliyetlerin Toplami Kilavuzlu Difüzyon
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Turkey, 7 - 10 July 2026, (Full Text)
- Publication Type: Conference Paper / Full Text
- Doi Number: 10.1109/siu71813.2026.11636458
- City: İstanbul
- Country: Turkey
- Keywords: Diffusion, Motion Planning, Robotic Manipulation
- Hacettepe University Affiliated: Yes
Abstract
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 test environments. In this study, we present a method with high generalization capability that generates collision-free trajectories using diffusion models. Each denoising step of the diffusion model is guided by the gradient of the total collision cost. Experimental results demonstrate that guiding the diffusion model with the sum of 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 Mπnets dataset among the compared methods.