| 基于能效优化的仿人机器人跑步步态优化与控制 |
| |
| 引用本文： | 杨亮,傅瑜,付根平,邓春健.基于能效优化的仿人机器人跑步步态优化与控制[J].计算机科学,2016,43(6):270-275. |
| |
| 作者姓名： | 杨亮 傅瑜 付根平 邓春健 |
| |
| 作者单位： | 电子科技大学中山学院计算机学院 中山528402;广东工业大学自动化学院 广州510006,电子科技大学中山学院计算机学院 中山528402,仲恺农业工程学院自动化学院 广州510225,电子科技大学中山学院计算机学院 中山528402 |
| |
| 基金项目： | 本文受国家自然科学基金(61302115,5),广东高校优秀青年创新人才培养计划项目(2013LYM0104,2013LYM0103),广东省自然科学基金项目(S2013010015764,S2012040011123,S2013010012307),广东省高等学校优秀青年教师培养计划项目(Yq2013204,Yq2013206,YQ2015242),中山市科技计划项目(2015B2308),广东大学生科技创新培育专项(pdhj2016b0912)资助 |
| |
| 摘 要： | 针对高能耗导致的仿人机器人难以大规模实用化的问题,提出了一种新的仿人机器人参数化跑步步态优化方法。分析了不同跑步步态参数对仿人机器人水平、垂直方向的稳定性及能耗的影响,将机器人步态优化问题转化为对步态参数的多目标寻优问题,根据连杆模型得到机器人跑步过程中水平、垂直方向的稳定裕度及能耗表达式,并构造目标函数,采用基于对位学习的遗传算法对机器人参数化跑步步态进行多目标寻优,在保证机器人俯仰、翻滚和偏摆各方向力矩平衡的前提下降低整体能量消耗；针对传统遗传算法早熟及收敛速度慢的问题,提出基于领域知识的精细化初始成员策略,采取生成种群成员对位点的方式更新种群,以加快收敛速度；为提高轨迹跟踪性能,设计了自适应控制器,并给出了稳定性证明。仿真实验表明:该方法能有效降低能耗并保证其稳定性。
|
| 关 键 词： | 仿人机器人 步态规划 对位学习 遗传算法 多目标优化 |
| 收稿时间： | 2015/3/24 0:00:00 |
| 修稿时间： | 2015/7/14 0:00:00 |
Running Gait Planning and Control for Humanoid Robot Based on Energy Efficiency Optimization |
| |
| YANG Liang,FU Yu,FU Gen-ping and DENG Chun-jian.Running Gait Planning and Control for Humanoid Robot Based on Energy Efficiency Optimization[J].Computer Science,2016,43(6):270-275. |
| |
| Authors: | YANG Liang FU Yu FU Gen-ping and DENG Chun-jian |
| |
| Affiliation: | School of Computer Engineering,University of Electronic Science and Technology of China,Zhongshan Inistitute,Zhongshan 528402,China;School of Automation,Guangdong University of Technology,Guangzhou 510006,China,School of Computer Engineering,University of Electronic Science and Technology of China,Zhongshan Inistitute,Zhongshan 528402,China,College of Automation,Zhongkai University of Agriculture and Engineering,Guangzhou 510225,China and School of Computer Engineering,University of Electronic Science and Technology of China,Zhongshan Inistitute,Zhongshan 528402,China |
| |
| Abstract: | A novel parametric running gait optimization algorithm was proposed for solving the fatal problem of high energy consumption for humanoid robot,limiting the practical application of humanoid robot.After analyzing the impact of different gait parameters on horizontal and vertical stability,the gait planning problem is transformed to the multi-objective optimization problem,and the expressions of stability and energy consumption are obtained according to connective link model.In order to achieve the ideal running gait,a method based on opposite learning generic algorithm was proposed,which helps to reduce energy consumption and obtain good stability margin in pitching,rolling and yawing axis.In view of the problems of early maturing and slow convergence of traditional GA algorithm,an effective policy of initiating population based on domain knowledge was developed and the population was updated by generating opposite entity.To improve the trajectory tracking performance,an adaptive controller was designed and the stability proof was provided.The simulation results prove the validity of the method. |
| |
| Keywords: | Humanoid robot Gait planning Opposition based learning Generic algorithm Multi-objective optimization |
|
|
点击此处可从《计算机科学》下载全文 |
|
