Kinematic enveloping grasp planning method for robotic dexterous hands and three-dimensional objects

Authors:
Shahram Salimi;Gary m. Bone
Affiliations:
Department of mechanical engineering, mcmaster university, hamilton, ontario l8s 4l7, canada;Department of mechanical engineering, mcmaster university, hamilton, ontario l8s 4l7, canada
Venue:
Robotica
Year:
2008

Citing 4
Cited 2

Robot grasp synthesis algorithms: a survey

International Journal of Robotics Research
Multifingered dextrous robotics hand design and control: a review

Robotica
Design and tests of a three finger hand with 1-DOF articulated fingers

Robotica
Overall design of Ca.U.M.Ha. robotic hand for harvesting horticulture products

Robotica

Kinematic feasibility analysis of 3-D multifingered grasp

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
A neural network based hierarchical motor schema of a multi-finger hand and its motion diversity

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Three-dimensional (3D) enveloping grasps for dexterous robotic hands possess several advantages over other types of grasps. This paper describes a new method for kinematic 3D enveloping grasp planning. A new idea for grading the 3D grasp search domain for a given object is proposed. The grading method analyzes the curvature pattern and effective diameter of the object, and grades object regions according to their suitability for grasping. A new approach is also proposed for modeling the fingers of the dexterous hand. The grasp planning method is demonstrated for a three-fingered, six degrees-of-freedom, dexterous hand and several 3D objects containing both convex and concave surface patches. Human-like high-quality grasps are generated in less than 20 s per object.