GraspIt!: A Versatile Simulator for Grasp Analysis

Author:

Miller Andrew T.1,Allen Peter K.1

Affiliation:

1. Columbia University, New York, NY

Abstract

Abstract We have created a unique tool for grasp simulation, visualization, and analysis that allows a user to create and analyze grasps of a given 3D object model with a given articulated hand model. The grasps can be performed either automatically, where the system closes the fingers around the object at preset velocities, or manually through direct manipulation of the joints. As collisions occur between the links of the fingers and the object, the system locates the contacts and analyzes the evolving grasp on the fly. Each time the grasp changes, the system updates two numeric measures of quality and recomputes 3D projections of the grasp wrench space which are useful when visualizing a grasp’s capabilities. We provide examples of the system being used with four different articulated robotic hand models, each grasping different object models. We feel the system is very useful for hand designers who prototype different hand models in simulation and determine how design decisions affect a hand’s grasping ability. It is also useful for researchers in grasp planning or for simulation and virtual reality designers wishing to perform realistic grasping in a virtual setting.

Publisher

American Society of Mechanical Engineers

Cited by 11 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. CoGrasp: 6-DoF Grasp Generation for Human-Robot Collaboration;2023 IEEE International Conference on Robotics and Automation (ICRA);2023-05-29

2. FunctionalGrasp: Learning Functional Grasp for Robots via Semantic Hand-Object Representation;IEEE Robotics and Automation Letters;2023-05

3. Toward Human-Like Grasp: Functional Grasp by Dexterous Robotic Hand Via Object-Hand Semantic Representation;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023

4. Learning high-DOF reaching-and-grasping via dynamic representation of gripper-object interaction;ACM Transactions on Graphics;2022-07

5. Toward Human-Like Grasp: Dexterous Grasping via Semantic Representation of Object-Hand;2021 IEEE/CVF International Conference on Computer Vision (ICCV);2021-10

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3