PreAfford: An Affordance-Based Pre-Grasping Framework with High Adaptability

Robotic manipulation with two-finger grippers is challenged by objects lacking distinct graspable features. Traditional pre-grasping methods, which typically involve repo- sitioning objects or utilizing external aids like table edges, are limited in their adaptability across different object categories and environments. To overcome these limitations, we intro- duce PreAfford, a novel pre-grasping planning framework incorporating a point-level affordance representation and a relay training approach. Our method significantly improves adaptability, allowing effective manipulation across a wide range of environments and object types. When evaluated on the ShapeNet-v2 dataset, PreAfford not only enhances grasping success rates by 69% but also demonstrates its practicality through successful real-world experiments. These improve- ments highlight PreAfford’s potential to redefine standards for robotic handling of complex manipulation tasks in diverse settings. : Indicates corresponding author. K. Ding, B. Chen, Z. Zhang, H. Gao, G. Zhou, and H. Zhao thank DISCOVER Robotics for providing hardware used in this research. Y. Li and Y. Zhu thank NVIDIA for providing GPUs and hardware support and are supported in part by the Beijing Nova Program. 1 Institute for AI Industry Research (AIR), Tsinghua University. 2 Xingjian College, Tsinghua University. 3 CFCS, School of Computer Science, Peking University. 4 Institute for Artificial Intelligence, Peking University. 5 College of Control Science and Engineering, Zhejiang Uni- versity. 6 School of Vehicle and Mobility, Tsinghua University.