2026/05/23 by Aysu Aylin Kaplan, Özgür Erkent · 1 voice
Computer Science · Engineering · #Collision #Diffusion #Diffusion process #Face (sociological concept) #Generalization #Motion (physics) #Motion planning #Process (computing) #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotic Path Planning Algorithms #cs.LG #cs.RO
paper · pdf · open access · doi:10.48550/arxiv.2605.24690
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2026/05/23 · arxiv published 2026/05/23 · arxiv updated 2026/05/23 · openalex created_date 2026/05/27 · openalex updated_date 2026/07/28
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 Mπnets dataset among the compared methods.