仿人机器人相似性阶梯行走约束与优化控制.PDFVIP

第36 卷第2 期 机器人 ROBOT Vol.36, No.2 2014 年3 月 Mar., 2014 DOI ：10.3724/SP.J.1218.2014.00233 仿人机器人相似性阶梯行走约束与优化控制 1 1 2 1 柯文德 ，彭志平 ，蔡则苏 ，陈 珂 （1. 广东石油化工学院计算机科学与技术系，广东 茂名 525000 ； 2. 哈尔滨工业大学计算机科学与技术学院，黑龙江 哈尔滨 150001） 摘 要：针对基于运动相似性的仿人机器人动作规划中固定运动捕获轨迹难以适应可变目标环境的问题，以 仿人机器人上阶梯为例，提出了一种基于运动相似性的行走约束与优化控制方法．首先，为相似性阶梯运动轨迹 划分子相关键姿势，施加运动学约束；其次，对运动的稳定性、方向、落脚缓冲等施加动力学约束；再次，结合 粒子群优化与分层强化学习方法，提出粒子群分层强化矢量位置择优算法，用于对机器人阶梯运动轨迹进行优化． 实验证明了方法的有效性． 关键词：仿人机器人；相似性；约束；优化 中图分类号：TP242.6 文献标识码：A 文章编号：1002-0446(2014)-02-0233-08 Constraint and Optimization Control on Similar Stepping Upstairs for Humanoid Robot KE Wende1 ，PENG Zhiping1 ，CAI Zesu2 ，CHEN Ke1 (1. Department of Computer Science and Technology, Guangdong University of Petrochemical Technology, Maoming 525000, China; 2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China) Abstract: A method of constraint and optimization control on the similar stepping-upstairs process for humanoid robots is proposed to solve the problem that the fixed tracks captured from the human locomotion can’t be used in the changeable target environment in the similar motion planning of humanoid robots. Firstly, the similar stepping-upstairs processes are divided into the sub phases and key poses, and the corresponding kinematics constraints are set as well. Secondly, the dynamics constraints are also set for the locomotion stability, walking direction and landing-buffer process. Thirdly, the HRPSO (particle swarm optimization with hierarchical reinforcement learning) algorithm is propos