DexDiffuser: Generating Dexterous Grasps with Diffusion Models

Zehang Weng*, Haofei Lu*, Danica Kragic, Jens Lundell
Division of Robotics, Perception and Learning (RPL), KTH
(* equal contribution)
Paper Code(Coming Soon)

Our method can generate high-quality grasp poses for unknown objects based on 3D partial point clouds. We conducted our study in both simulation and real world.

Abstract

We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterative denoising of randomly sampled grasps. We also introduce two grasp refinement strategies: Evaluator-Guided Diffusion and Evaluator-based Sampling Refinement. The experiment results demonstrate that DexDiffuser consistently outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 9.12% and 19.44% higher grasp success rate in simulation and real robot experiments, respectively

Real Robot Grasping

Grasps for the toy plane

BibTeX

@misc{weng2024dexdiffusergeneratingdexterousgrasps,
      title={DexDiffuser: Generating Dexterous Grasps with Diffusion Models}, 
      author={Zehang Weng and Haofei Lu and Danica Kragic and Jens Lundell},
      year={2024},
      eprint={2402.02989},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2402.02989}, }