提出首个大规模双臂抓握数据集，提升灵巧机械手双臂协同抓取能力。
Bimanual Grasp Synthesis for Dexterous Robot Hands
- 通过优化能量函数生成稳定可行的双臂抓握姿态。
- 构建超15万条验证抓握数据，覆盖900个3D物体。
- 基于数据训练扩散模型，抓取成功率69.87%，速度显著提升。
人类在处理大型或重型物体时自然采用双手协同操作。为增强机器人对物体的操控能力，生成高效的双臂抓握姿态至关重要。然而，针对灵巧手的双臂抓握合成仍研究不足。为此，我们提出BimanGrasp算法，用于在3D物体上合成双臂抓握姿态。该算法通过优化兼顾抓握稳定性和可行性的能量函数生成抓握姿态，并使用Isaac Gym物理引擎进行验证。经验证的抓握姿态构成首个大规模合成的双臂灵巧手抓握数据集——BimanGrasp-Dataset，包含超过15万条在900个物体上的验证抓握数据，支持数据驱动的双臂抓握合成。最后，我们提出了基于该数据集训练的BimanGrasp-DDPM扩散模型，其抓取合成成功率达到69.87%，且相比原算法计算速度显著提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。