tailieunhanh - An Introduction to Intelligent and Autonomous Control-Chapter 13: Intelligent Robot Prehension

Tham khảo tài liệu 'an introduction to intelligent and autonomous control-chapter 13: intelligent robot prehension', công nghệ thông tin, quản trị web phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 13 INTELLIGENT ROBOT PREHENSION Thang N. Nguyen IBM United States Systems Management Consulting Washington Systems Center Gaithersburg Maryland 20879 Harry E. Stephanou Center for Advanced Technology in Automation and Robotics Rensselaer Polytechnic Institute Troy New York 12180 Abstract The intriguing ease with which humans perform grasping and manipulation activities has triggered new investigations to provide robots with prehensile capability for complex tasks in unstructured environment. These investigations resulted in a number of schemes ranging from high-level Al-oriented distributed symbolic schemes to low-lev el contact-based numeric schemes. Current numeric schemes however are limited to tip prehension . intentional grasping by the fingertips while symbolic schemes have been investigated rather separately from the former and the results of the linking between symbolic and numeric schemes are rather modest. This chapter deals with an intelligent integrated symbolic-numeric scheme for dextrous manipulation using a topological approach. In this chapter we introduce i a grasp-based topological model of multifingered robot hands with its associated reasoning scheme called topological reasoning and ii discuss its application to dextrous 320 INTELLIGENT AND AUTONOMOUS CONTROL grasps in the framework of an intelligent robot prehension system. Our topological model for multifingered robot hands is capable of describing an arbitrary multifingered hand posture with associated topological algorithms for grasp selection and regrasping. We show that using topological reasoning both the hand posture and the hand functionality can be derived from symbolic high level task requirements and object attributes and can be transformed into numeric low level joint space variables. A discussion on simulation results is given. 1. INTRODUCTION Grippers and special-purpose end-effectors are adequate for simple operations in structured environments in which task object identity .