D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation

arXiv:2403.12861v1 Announce Type: cross
Abstract: Mastering dexterous robotic manipulation of deformable objects is vital for overcoming the limitations of parallel grippers in real-world applications. Current trajectory optimisation approaches often struggle to solve such tasks due to the large search space and the limited task information available from a cost function. In this work, we propose D-Cubed, a novel trajectory optimisation method using a latent diffusion model (LDM) trained from a task-agnostic play dataset to solve dexterous deformable object manipulation tasks. …

abstract applications arxiv cost cs.lg cs.ro current diffusion function information limitations manipulation objects optimisation robotic robotic manipulation search solve space struggle tasks trajectory type vital world