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). Our simulation and real-world experiments on the Allegro Hand consistently demonstrate that DexDiffuser outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 21.71--22.20\% higher grasp success rate.

翻译：我们提出了DexDiffuser，一种新颖的灵巧抓取方法，能够在部分物体点云上生成、评估并优化抓取姿态。DexDiffuser包含基于条件扩散的抓取采样器DexSampler和灵巧抓取评估器DexEvaluator。DexSampler通过对随机采样的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。我们还引入了两种抓取优化策略：评估器引导扩散（EGD）和基于评估器的采样优化（ESR）。在Allegro Hand上进行的仿真与真实世界实验一致表明，DexDiffuser的性能优于当前最先进的多指抓取生成方法FFHNet，平均抓取成功率高出21.71%至22.20%。