从单视角点云通过多物体场景数据集实现端到端的灵巧抓取学习
End-to-End Dexterous Grasp Learning from Single-View Point Clouds via a Multi-Object Scene Dataset
- Harbin Institute of Technology（哈尔滨工业大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出DGS-Net，通过多物体场景的单视角点云学习密集抓取配置，改进了现有抓取数据集的局限性，实验显示其在仿真和真实机器人平台上的抓取成功率较高，且具有较低的穿透深度。
中文摘要 AI 辅助
多物体场景中的灵巧抓取构成了机器人操作中的基本挑战。当前主流抓取数据集主要集中在单物体场景和预定义抓取配置，往往忽视环境干扰和灵巧预抓取姿态的建模，从而限制了其在现实应用中的泛化能力。为了解决这一问题，我们提出了DGS-Net，一个端到端的抓取预测网络，能够从多物体场景的单视角点云中学习密集抓取配置。此外，我们提出了一种两阶段的抓取数据生成策略，从密集的单物体抓取合成逐步过渡到密集的场景级抓取生成。我们的数据集包含307个物体、240个多物体场景和超过350,000个验证的抓取。通过显式建模抓取偏移和预抓取配置，该数据集为灵巧抓取学习提供了更加稳健和准确的监督。实验结果表明，DGS-Net在仿真中实现了88.63%的抓取成功率，在真实机器人平台上实现了78.98%的抓取成功率，同时表现出较低的穿透深度，平均穿透深度为0.375毫米，穿透体积为559.45立方毫米，优于现有方法，显示出强大的有效性和泛化能力。我们的数据集可在https://github.com/4taotao8/DGS-Net上获得。
英文摘要
Dexterous grasping in multi-object scene constitutes a fundamental challenge in robotic manipulation. Current mainstream grasping datasets predominantly focus on single-object scenarios and predefined grasp configurations, often neglecting environmental interference and the modeling of dexterous pre-grasp gesture, thereby limiting their generalizability in real-world applications. To address this, we propose DGS-Net, an end-to-end grasp prediction network capable of learning dense grasp configurations from single-view point clouds in multi-object scene. Furthermore, we propose a two-stage grasp data generation strategy that progresses from dense single-object grasp synthesis to dense scene-level grasp generation. Our dataset comprises 307 objects, 240 multi-object scenes, and over 350k validated grasps. By explicitly modeling grasp offsets and pre-grasp configurations, the dataset provides more robust and accurate supervision for dexterous grasp learning. Experimental results show that DGS-Net achieves grasp success rates of 88.63\% in simulation and 78.98\% on a real robotic platform, while exhibiting lower penetration with a mean penetration depth of 0.375 mm and penetration volume of 559.45 mm^3, outperforming existing methods and demonstrating strong effectiveness and generalization capability. Our dataset is available at https://github.com/4taotao8/DGS-Net.
