| 引用本文: | 龙亿,杜志江,王伟东.GA优化的RBF神经网络外骨骼灵敏度放大控制[J].哈尔滨工业大学学报,2015,47(7):26.DOI:10.11918/j.issn.0367-6234.2015.07.003 |
| LONG Yi,DU Zhijiang,WANG Weidong.RBF neural network with genetic algorithm optimization based sensitivity amplification control for exoskeleton[J].Journal of Harbin Institute of Technology,2015,47(7):26.DOI:10.11918/j.issn.0367-6234.2015.07.003 |
|
| 摘要: |
| 为改善外骨骼机器人灵敏度放大控制(SAC)性能,结合遗传算法(GA)与径向基函数(RBF)神经网络建立在线计算外骨骼机器人的精确动力学模型．用GA优化RBF神经网络的中心矢量与基宽度,并对RBF网络的权值实时更新,在线学习外骨骼机器人动力学模型中的参数矩阵,进一步推导出SAC控制律．仿真结果表明:GA优化后的RBF网络,可以在线学习外骨骼的动力学模型,基于该模型的SAC能够实现精确的人体轨迹跟踪,相比于优化前,人体轨迹跟踪误差以及人机交互信息会快速减小并收敛到0的微小邻域内,可实现人机协调运动． |
| 关键词: 遗传算法 RBF神经网络 灵敏度放大控制 外骨骼机器人 轨迹跟踪 |
| DOI：10.11918/j.issn.0367-6234.2015.07.003 |
| 分类号:TH133; TP183 |
| 基金项目:国家自然科学基金(61105088). |
|
| RBF neural network with genetic algorithm optimization based sensitivity amplification control for exoskeleton |
|
LONG Yi, DU Zhijiang, WANG Weidong
|
|
(State Key Laboratory of Robotics and System(Harbin Institute of Technology), 150001 Harbin, China)
|
| Abstract: |
| To improve performance of sensitivity amplification control(SAC) for exoskeleton robot, genetic algorithm(GA) and RBF neural network was combined to obtain accurate dynamic model of exoskeleton robot online. Parameters of center vector and base width of RBF neural network were obtained by GA optimization, and online RBF weights learning process was constructed to obtain estimation matrix parameters of dynamics system, finally, SAC control law was deduced. Simulation results showed that the RBF network optimized by GA could learn exoskeleton dynamics model parameters online. Based on the learned model, the SAC could achieve more precise human trajectory tracking where tracking error and human-robot interaction force converged to the small neighborhood of zero simultaneously compared with those without optimization. The proposed RBF neural network with GA optimization which learned dynamics model parameters online for exoskeleton robot dynamics model could achieve highly accurate trajectory following for SAC, ultimately realize cooperative movement between human and exoskeleton. |
| Key words: genetic algorithm RBF neural network sensitivity amplification control exoskeleton robot trajectory tracking |
