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 (EGD) and Evaluator-based Sampling Refinement (ESR). 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. Supplementary materials are available at https://yulihn.github.io/DexDiffuser_page/

翻译：本文提出DexDiffuser，一种基于部分物体点云生成、评估与优化灵巧抓取姿态的创新方法。该系统包含基于条件扩散的抓取采样器DexSampler与灵巧抓取评估器DexEvaluator。DexSampler通过对随机采样抓取姿态进行迭代去噪，生成以物体点云为条件的高质量抓取方案。我们同时提出两种抓取优化策略：评估器引导扩散（EGD）与基于评估器的采样优化（ESR）。实验结果表明，DexDiffuser在仿真与真实机器人实验中，抓取成功率分别平均超越当前最优多指抓取生成方法FFHNet达9.12%与19.44%。补充材料详见：https://yulihn.github.io/DexDiffuser_page/