用于灵巧机器人手的双手抓取合成
Bimanual Grasp Synthesis for Dexterous Robot Hands
- School of Information Science and Technology at ShanghaiTech University（上海科技大学信息科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出BimanGrasp算法与BimanGrasp-Dataset数据集，并训练扩散模型BimanGrasp-DDPM，实现灵巧手双手抓取合成，成功率达69.87%且计算速度显著提升。
AI中文摘要：
人类自然地执行双手技能来处理大型和重型物体。为了增强机器人的物体操作能力，生成有效的双手抓取姿态至关重要。然而，针对灵巧手操作器的双手抓取合成仍未得到充分探索。为弥补这一空白，我们提出了BimanGrasp算法，用于在3D物体上合成双手抓取。BimanGrasp算法通过优化一个考虑抓取稳定性和可行性的能量函数来生成抓取姿态。此外，合成的抓取使用Isaac Gym物理仿真引擎进行验证。这些经过验证的抓取姿态构成了BimanGrasp-Dataset，据我们所知，这是第一个大规模合成的双手灵巧手抓取姿态数据集。该数据集包含900个物体上的超过150k个经过验证的抓取，有助于通过数据驱动的方法合成双手抓取。最后，我们提出了BimanGrasp-DDPM，这是一个在BimanGrasp-Dataset上训练的扩散模型。该模型实现了69.87%的抓取合成成功率，并且与BimanGrasp算法相比，计算速度显著加快。
英文摘要：
Humans naturally perform bimanual skills to handle large and heavy objects. To enhance robots' object manipulation capabilities, generating effective bimanual grasp poses is essential. Nevertheless, bimanual grasp synthesis for dexterous hand manipulators remains underexplored. To bridge this gap, we propose the BimanGrasp algorithm for synthesizing bimanual grasps on 3D objects. The BimanGrasp algorithm generates grasp poses by optimizing an energy function that considers grasp stability and feasibility. Furthermore, the synthesized grasps are verified using the Isaac Gym physics simulation engine. These verified grasp poses form the BimanGrasp-Dataset, the first large-scale synthesized bimanual dexterous hand grasp pose dataset to our knowledge. The dataset comprises over 150k verified grasps on 900 objects, facilitating the synthesis of bimanual grasps through a data-driven approach. Last, we propose BimanGrasp-DDPM, a diffusion model trained on the BimanGrasp-Dataset. This model achieved a grasp synthesis success rate of 69.87\% and significant acceleration in computational speed compared to BimanGrasp algorithm.
