|
|
|
Gait planning for humanoid robot based on hybrid
evolutionary algorithm |
| ZHONG Qiu-bo1,2 , PIAO Song-hao2, GAO Chao2, HONG Bing-rong2 |
1. College of Electronic and Information Engineering, Ningbo University of Technology, Ningbo 315016, China;
2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China |
|
|
|
Abstract According to the structural features of humanoid robot, a gait planner of going upstairs for humanoid robot is designed. A model with seven links for humanoid robot was presented for the process of going upstairs. Because of neural network in the superiority of nonlinear systems, off-line was trained for the motions during the single and double supporting periods by two BP neural networks respectively. To speed up training time and avoid falling into local minimum, the weights of networks were optimized by a hybrid particle swarm optimization algorithm and the optimal stable gait was generated. The environmental information was gathered by an embedded single vision system, and which was to be as the input of the network and the trajectories of joints required for moving were outputting online. Validity of the proposed method is proved by the simulations in Matlab and experiments on real robot．
|
|
Published: 01 May 2012
|
|
|
基于混合进化算法的仿人机器人步态规划
针对仿人机器人的结构特点,设计一种仿人机器人上楼梯的在线步态规划系统.使用7连杆模型对仿人机器人的上楼梯运动过程进行建模,根据神经网络在拟合非线性系统上的优越性,使用2个BP神经网络对仿人机器人上楼梯过程中的双腿支撑周期和单腿支撑周期分别进行离线训练.为了加速训练时间和避免陷入局部最小值,采用基于混合粒子群的神经网络控制方式对网络的权值进行优化.在加速训练过程的同时,生成稳定性最优的步态,通过嵌入式单目视觉采集现场环境信息作为神经网络的输入,实时控制输出步态所需的关节轨迹进行运动.实验结果表明通过Matlab仿真和实物机器人上所提方法有效.
|
|
| ［1］ VUKOBRATOVIC M. Zero moment point, thirty five years of its life ［J］. International Journal of Humanoid Robotics, 2004,1(1):157-173．
［2］ HUANG Qiang. Planning walking patterns for a biped robot ［J］. IEEE Transaction on Robot and Automation, 2001,17(3):155-162．
［3］ PEIMAN N M,AHMAD B. Mathematical simulation of a seven link biped robot on various surfaces and ZMP considerations ［J］. Applied Mathematical Modeling, 2007,31(1):18-37．
［4］ JOAO P F, MANUEL C, PAULO A C. ZMP trajectory reference for the sagittal plane control of a biped robot based on a human CoP and gait ［C］∥ Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. St. Louis, USA: IEEE, 2009:1588-1593．
［5］ TOMOMICHI S. Standing stabilizability and stepping maneuver in planar bipedalism based on the best COMZMP regulator ［C］∥ Proceedings of the IEEE International Conference on Robotics and Automation, Kobe International Conference Center Kobe. Tokyo, JAPAN: IEEE, 2009:1966-1971．
［6］ CUPEC R, SCHMIDT G, LORCH O. Visionguided walking in a structured indoor scenario ［J］. Automatika, 2005, 46(1):49-57.
［7］ JIMMY Or. A hybrid CPGZMP control system for stable walking of a simulated flexible spine humanoid robot ［J］. Neural Networks, 2010, 23(1):452-460．
［8］ REZA G, QIONG WU, GARY W G. Nearly optimal neural network stabilization of bipedal standing using genetic algorithm ［J］. Engineering Applications of Artificial Intelligence, 2007,20(1):473-480．
［9］ CHINGLONG S. Ascending and descending stairs for a biped robot ［J］. IEEE Transactions on Systems, MAN, and CyberneticsPART A: Systems and Humans, 1999, 29(3):255-268．
［10］ GUAN Y, YOKOI K, TANIE K. Feasibility: can humanoid robots overcome given obstacles？ ［C］ ∥ Proceedings of the IEEE International Conference on Robotics and Automation. Barcelona, Spain: IEEE, 2005: 1054-1059．
［11］ 潘云忠. 类人猿机器人双足步行及步行方式动态转换运动控制研究［D］.哈尔滨:哈尔滨工业大学,2006．
PAN Yunzhong. Research on biped walking and dynamic walking modes shifting control for a gorilla robot ［D］. Harbin: Harbin Institute of Technology,2006．
［12］ CHAU K W. Application of a PSObased neural network in analysis of outcomes of construction claims ［J］. Automation in Construction, 2007(16):642-646．
［13］ HONJO T, LUO Zhiwei， NAGANO A. Parametric excitation of a biped robot as an inverted pendulum ［C］ ∥ Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Acropolis Convention Center Nice, France: IEEE, 2008: 3408-3413．
［14］REN H E, ZHONG Qiubo, KANG Junfeng. Object recognition algorithm research based on variable illumination ［C］ ∥ Proceedings of the IEEE International Conference on Automation and Logistics. Shenyang, IEEE, 2009:1609-1613.
［15］ LEUNG H F, LAM H K, LING S H, et al. Tuning of the structure and parameters of a neural network using an improved genetic algorithm ［J］. IEEE Transaction on Neural Networks, 2003, 14(3):79-88． |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
