TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance
This addresses the challenge of reducing annotation effort in robotics for object grasping, though it is incremental as it builds on shape correspondence and refinement techniques.
The paper tackles the problem of grasp pose estimation for robots by proposing TransGrasp, a method that predicts grasp poses for a category of objects using only one labeled instance, achieving high-quality grasps as demonstrated in experiments.
Grasp pose estimation is an important issue for robots to interact with the real world. However, most of existing methods require exact 3D object models available beforehand or a large amount of grasp annotations for training. To avoid these problems, we propose TransGrasp, a category-level grasp pose estimation method that predicts grasp poses of a category of objects by labeling only one object instance. Specifically, we perform grasp pose transfer across a category of objects based on their shape correspondences and propose a grasp pose refinement module to further fine-tune grasp pose of grippers so as to ensure successful grasps. Experiments demonstrate the effectiveness of our method on achieving high-quality grasps with the transferred grasp poses. Our code is available at https://github.com/yanjh97/TransGrasp.