基于模式识别的机器人运行轨迹数据分类存储系统设计  

Design of robot moving trajectory data classification and storage system based on pattern recognition

作　　者：刘帅[1] 王敏珍[1] 刘超[1] LIU Shuai;WANG Minzhen;LIU Chao(Changchun Institute of Technology,Changchun 130012,China)

机构地区：[1]长春工程学院

出　　处：《现代电子技术》2020年第4期145-148,共4页Modern Electronics Technique

基　　金：吉林省科技厅省级项目(120190003)

摘　　要：目前传统数据分类存储系统多数基于遗传算法,这类系统存在系统吞吐量较差、效率低的问题。为此,设计一种基于模式识别的机器人运行轨迹数据分类系统。首先设计系统整体框架,包括数据采集、处理以及存储模块;其次在硬件设计上,选择XC2VP30芯片作为FPGA核心芯片,设计数据采集模块接口电路,利用合适的FLASH芯片进行数据存储完成系统硬件设计;最后根据模式识别方法,建立标准数据样本集,确定特征向量,计算隶属度函数完成数据分类,再利用FPGA将已分类数据存储至FLASH模块中完成软件设计。测试结果表明,与传统的数据分类存储系统相比,基于模式识别的机器人运行轨迹数据分类存储系统的系统吞吐量提高了15.9%,效率得到了提高。A robot moving trajectory data classification system based on pattern recognition is designed to improve the poor system throughput and low efficiency in the most traditional data classification and storage systems based on genetic algorithm.The overall framework of the system is designed,which includes the data acquisition,data processing and data storage modules.In the hardware design,XC2VP30 chip is selected as the core chip of FPGA to design the interface circuit of data acquisition module,and the appropriate Flash chip is used for the data storage,so as to complete the hardware design of the system.The standard data sample set is established by means of the pattern recognition method,the feature vector is determined,the membership function is calculated to complete the data classification,and the classified data is stored in the Flash module by FPGA to complete the software design.Therefore,the overall design of the system has been completed.The testing results show that in comparison with the traditional data classification and storage system,the system throughput of the robot moving trajectory data classification and storage system based on pattern recognition is increased by 15.9%,and the efficiency is improved.

关 键 词：运行轨迹 数据分类存储 模式识别 系统吞吐量 系统设计 系统测试 

分 类 号：TN919-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]