GOAG：用于灵巧机器人操作的生成式与物体无关的抓取规划器
GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
浏览论文内容
中文总结 AI 辅助
本研究提出GOAG模型，通过学习夹爪接触表面分布的紧凑潜在表示，无需物体特定训练数据即可高效生成有效抓取配置，在MultiDex数据集上平均成功率达86.93%，实现了出色的泛化性能。
中文摘要 AI 辅助
多指抓取是机器人的关键技能，但当前深度学习抓取规划器常因在有限的物体特定数据集上训练，难以泛化到新物体。我们基于“夹爪与物体在相互接触点处具有相同表面几何结构”的观察，提出一种根本不同的方法：GOAG（Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation），这是一种新型深度生成模型，可学习特定夹爪接触表面分布的紧凑潜在表示，无需依赖物体特定训练数据即可高效采样有效抓取配置。我们通过仅在推理时引入物体特征，使模型能有效检索与夹爪能力兼容的可允许接触区域。我们在模拟和真实场景的既定抓取协议上开展大量实验验证该方法，证明其对文献中不同夹爪的有效性。我们的方法在MultiDex数据集物体上达到了最先进的结果，平均成功率为86.93%；在生成大量抓取时处理速度显著更快，同时与在该数据集上专门训练的领先方法性能相当。与这些方法不同，我们的方法不依赖物体特定训练数据，凸显了物体无关学习的优势，有效解决了传统数据驱动抓取规划器面临的泛化挑战。代码和视频可在我们的项目网站this https URL获取。
英文摘要
Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets. We introduce a fundamentally different approach, grounded in the observation that the gripper and the object share identical surface geometry at their mutual contact points. We propose GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation, a novel deep generative model that learns a compact latent representation of a specific gripper's contact surface distribution, enabling the efficient sampling of valid grasp configurations without relying on object-specific training data. We show that by introducing object features only at inference time, our model can effectively retrieve admissible contact areas that are compatible with the gripper's capabilities. We validate our approach through extensive experiments on established grasp protocols in both simulated and real-world scenarios, demonstrating its effectiveness with different grippers from the literature. Our method delivers state-of-the-art results on the objects from the MultiDex dataset, achieving an average success rate of 86.93%. It offers significantly faster processing when generating numerous grasps, while matching the performance of leading approaches specifically trained on this dataset. Unlike these methods, our approach does not rely on object-specific training data, highlighting the advantages of object-agnostic learning. It effectively addresses the generalization challenges faced by traditional data-driven grasp planners. Code and videos are available on our project website https://cea-list.github.io/goagweb/ .
发表机构
- Université Paris-Saclay（巴黎萨克雷大学）
- CEA（法国原子能和替代能源委员会）
- Ecole Centrale de Lyon（里昂中央理工学院）
- CNRS（法国国家科学研究中心）
- Institut Universitaire de France (IUF)（法国大学研究院）
机构由 AI 辅助整理，请以论文原文为准。
