Transferring Grasp Configurations using Active Learning and Local Replanning

2018/07/22 by Hao Tian, Tian, Hao, Changbo Wang +5
Computer Science · Engineering · #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Robot Manipulation and Learning #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1807.08341

openalex publication_date 2018/07/22 · openalex created_date 2018/08/03 · openalex updated_date 2026/07/28

Abstract

We present a new approach to transfer grasp configurations from prior example objects to novel objects. We assume the novel and example objects have the same topology and similar shapes. We perform 3D segmentation on these objects using geometric and semantic shape characteristics. We compute a grasp space for each part of the example object using active learning. We build bijective contact mapping between these model parts and compute the corresponding grasps for novel objects. Finally, we assemble the individual parts and use local replanning to adjust grasp configurations while maintaining its stability and physical constraints. Our approach is general, can handle all kind of objects represented using mesh or point cloud and a variety of robotic hands.

Related

• Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
• NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Hands
• Robotic Grasping through Combined Image-Based Grasp Proposal and 3D Reconstruction
• TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance
• Planning High-Quality Grasps using Mean Curvature Object Skeletons