灵巧机械手多指协调控制技术  

Multi-fingered Coordinated Control for Dexterous Robotic Hand

作　　者：陈金宝[1] 韩冬[1] 王小涛[1] 聂宏[1] 

机构地区：[1]南京航空航天大学航天学院,南京210016

出　　处：《机械工程学报》2014年第5期42-47,共6页Journal of Mechanical Engineering

基　　金：国家自然科学基金(51105196);江苏省自然科学基金(BK2011733)资助项目

摘　　要：根据抓取力封闭约束和力平衡约束条件,将多指精细抓取的力优化问题转换为非线性规划问题。对于非线性规划问题的求解,传统算法的实现一般需要编写相对复杂的程序,因此提出一种以序列二次规划算法为核心的fmincon函数对非线性规划问题进行快速求解的方法,并将该方法用Matlab软件予以实现;针对多指抓取的任务要求,提出一种试探性抓取并采用关节阻抗控制算法控制手指各指节与物体接触力的多指强力抓取方法,该方法简单且具有一定自主性。采用ADAMS仿真软件中生成的灵巧机械手控制模块在Simulink仿真环境中建立多指协调控制仿真系统,并以此对上述提出的方法进行算例验证。分析结果表明在精细抓取和强力抓取的不同任务要求下,灵巧机械手完成了对目标物体的稳定抓取,证明了所提方法的准确性。Based on the force-closure and force-balance conditions, the grasping force optimization of precision grasp can be converted to a nonlinear programming problem. In order to solve the nonlinear programming, complex procedure is usually needed for the traditional methods. So a method implemented by the fmincon function based on sequential quadratic programming in Matlab optimization tool box is proposed. For power grasp, a simple but autonomous method is proposed. The joint impedance force control algorithm is adopted to limit the contact force to the maximum in the method. In order to validate the proposed methods, the simulation system of multi-fingered coordinated control is built in Simulink environment. The system is based on the control module generated in ADAMS software. The simulation results demonstrate that the target object can be stably grasped by the dexterous robotic hand whether the tasks are orecision ~raso or oower ~raso.

关 键 词：精细抓取 力优化 强力抓取 阻抗控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]