We introduce the sequential multi-object robotic grasp sampling algorithm SeqGrasp that can robustly synthesize stable grasps on diverse objects using the robotic hand's partial Degrees of Freedom (DoF). We use SeqGrasp to construct the large-scale Allegro Hand sequential grasping dataset SeqDataset and use it for training the diffusion-based sequential grasp generator SeqDiffuser. We experimentally evaluate SeqGrasp and SeqDiffuser against the state-of-the-art non-sequential multi-object grasp generation method MultiGrasp in simulation and on a real robot. The experimental results demonstrate that SeqGrasp and SeqDiffuser reach an 8.71%-43.33% higher grasp success rate than MultiGrasp. Furthermore, SeqDiffuser is approximately 1000 times faster at generating grasps than SeqGrasp and MultiGrasp. Project page: https://yulihn.github.io/SeqGrasp/.

翻译：我们提出了序列化多物体机器人抓取采样算法 SeqGrasp，该算法能够利用机器人手的部分自由度（DoF）稳健地合成对不同物体的稳定抓取。我们使用 SeqGrasp 构建了大规模 Allegro Hand 序列化抓取数据集 SeqDataset，并利用其训练基于扩散模型的序列化抓取生成器 SeqDiffuser。我们在仿真环境和真实机器人上，将 SeqGrasp 和 SeqDiffuser 与最先进的非序列化多物体抓取生成方法 MultiGrasp 进行了实验评估。实验结果表明，SeqGrasp 和 SeqDiffuser 的抓取成功率比 MultiGrasp 高出 8.71% 至 43.33%。此外，SeqDiffuser 生成抓取的速度比 SeqGrasp 和 MultiGrasp 快约 1000 倍。项目页面：https://yulihn.github.io/SeqGrasp/。