参数化优化的仿人机器人相似性前向倒地研究  

Falling Forward of Humanoid Robot Based on Similarity with Parametric Optimum

作　　者：柯文德[1,2] 崔刚[1] 洪炳镕[1] 蔡则苏[1] 朴松昊[1] 钟秋波[1] 

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001 [2]广东石油化工学院计算机科学与技术系,茂名525000

出　　处：《自动化学报》2011年第8期1006-1013,共8页Acta Automatica Sinica

基　　金：国家自然科学基金(60905047;61075076;61075077);广东省自然科学基金(8152500002000003);广东高校优秀青年创新人才培育项目(201180)资助~~

摘　　要：提出了一种基于运动相似性的仿人机器人前向倒地动作设计方法.首先,分析了运动相似性并提出了关键姿势同步转换方法;其次,为机器人前向倒地运动四级倒立摆建立了相似性变换条件下的动力学约束方程与关联的物理条件约束;再次,引入参数化优化控制与强化技术,对机器人的触地过程进行了参数化优化.实验结果表明了该方法的有效性.The designing method of falling-forward locomotion of a humanoid robot based on the locomotion similarity is proposed. Firstly, the locomotion similarity is analyzed and the synchronous transition for key postures is proposed. Then, the kinetics constraint equations and the associated robot＇s falling-forward locomotion are constituted under the physical constraints for the 4-level headstand pendulum of condition of similarity transition. Finally, the method based on the parametric control and enhancing technique is adopted to optimize the parameters in the touching ground process of falling forward. The experiments showed the validity of this designing method.

关 键 词：仿人机器人 相似性 约束 零力矩点 参数化优化 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]