paper-with-me

Papers

A Hybrid Optimization Framework for Grasp Synthesis under Partial Observations

2026-06-16 · Wenzheng Zhang, Fahira Afzal Maken, Tin Lai, Fabio Ramos arxiv

We propose a hybrid grasp synthesis framework that combines a learning-based Energy-Based Model (EBM) with an analytical Iterative Closest Point (ICP) method to generate robust grasps from partially observed point clouds. The learned energy function acts as a prior within a Stein Variational Gradient Descent (SVGD) framework, guiding iterative refinement of grasp configurations. Evaluated on 67 objects with 5,360 grasp attempts, our method achieves an average success rate of 60.9\%, outperforming AnyGrasp (31.1\%) and Grasp Pose Detection (48.4\%) and AS-ICP (56.6\%). These results highlight the strong generalization ability of our approach and demonstrate how combining data-driven learning with geometric optimization addresses the limitations of either strategy in isolation.

📄 PDF Abstract BibTeX arXiv:2606.18053

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors

2026-07-06 · Mingrui Yu, Yongpeng Jiang, Yongyi Jia, Kangchen Lv 외 arxiv

Dexterous grasping across diverse object scales requires contact modes ranging from two-finger pinches to bimanual grasps. Existing dexterous grasp synthesis methods reduce the high-dimensional optimization space with ma…

GraspADMM: Improving Dexterous Grasp Synthesis via ADMM Optimization

2026-03-14 · Liangwang Ruan, Jiayi Chen, He Wang, Baoquan Chen arxiv

Synthesizing high-quality dexterous grasps is a fundamental challenge in robot manipulation, requiring adherence to diversity, kinematic feasibility (valid hand-object contact without penetration), and dynamic stability …

Robot Manipulation

ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact

2019-04-07 · Samarth Brahmbhatt, Ankur Handa, James Hays, Dieter Fox

Grasping and manipulating objects is an important human skill. Since most objects are designed to be manipulated by human hands, anthropomorphic hands can enable richer human-robot interaction. Desirable grasps are not o…

Object

BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes

2026-04-08 · Mu Lin, Yi-Lin Wei, Jiaxuan Chen, Yuhao Lin 외 arxiv

Bimanual dexterous grasping is a fundamental and promising area in robotics, yet its progress is constrained by the lack of comprehensive datasets and powerful generation models. In this work, we propose BiDexGrasp, cons…

Variational Shape Inference for Grasp Diffusion on SE(3)

2025-08-24 · S. Talha Bukhari, Kaivalya Agrawal, Zachary Kingston, Aniket Bera arxiv

Grasp synthesis is a fundamental task in robotic manipulation which usually has multiple feasible solutions. Multimodal grasp synthesis seeks to generate diverse sets of stable grasps conditioned on object geometry, maki…