摘要
为了解决当前机器人移动轨迹智能跟踪方法信息分析能力差,导致机器人移动轨迹跟踪结果偏差大问题,提出基于多源信息的机器人移动轨迹智能跟踪系统。选用MPC控制原理作为模型构建依据,确定机器人的移动特征,将数据控制模拟控制值应用到机器人动力学模型中,使用神经网络完成多源信息融合,将多源数据融合结果视为机器人运动特征,对机器人运动轨迹展开追踪,计算轨迹数据相似度确保降低轨迹跟踪误差。仿真实验结果表明,本方法的移动轨迹跟踪结果偏差小于对比,移动轨迹智能跟踪时间短,具有比较明显的优越性。
In order to solve the problem of the error of the tracking results of the robot, a multi-source intelligent tracking system is proposed to solve the problem of poor information analysis ability of the current robot intelligent tracking method. MPC control principle is used as the basis of model construction to determine the mobile characteristics of the robot. The simulated control value of data control is applied to the robot dynamics model. The multi-source information fusion is completed by using neural network. The results of multi-source data fusion are regarded as the motion characteristics of the robot and the trajectory of the robot is tracked, The similarity of trajectory data is calculated to reduce the tracking error.The simulation results show that the deviation of the tracking result is less than the contrast, and the intelligent tracking time of the moving trajectory is short, which has obvious advantages.
作者
杨小艳
YANG Xiao-yan(College of Electronic&Information Engineering,Ankang University,Ankang 725000 China)
出处
《自动化技术与应用》
2022年第9期13-16,共4页
Techniques of Automation and Applications
基金
安康市科技计划项目(2018AK02-12)。
关键词
多源信息
运动轨迹跟踪
神经网络
信息融合
Multi source information
Motion tracking
Neural network
Information fusion
作者简介
杨小艳(1978-),女,硕士,讲师,研究方向:计算机软件技术与应用、智能信息处理等。
