基于贝塞尔轨迹的视觉导引AGV路径跟踪研究-中国测试.PDFVIP

第43卷第8期 中国测试 Vol.43 No.8 2017年8月 CHINA MEASUREMENT TEST August，2017 doi院10.11857/j.issn.1674-5124.2017.08.023 基于贝塞尔轨迹的视觉导引AGV路径跟踪研究 刘海芹 渊聊城大学东昌学院数学与信息工程系袁山东 聊城 252000冤 摘 要院为提高视觉导引自动导引车渊automatic guided vehicle袁AGV冤路径跟踪精度袁提出一种基于贝塞尔轨迹的精 确路径跟踪算法遥该算法首先将采集的多种路径特征图像进行预处理得到形状信息袁训练SVM多层路径形状特征 分类器曰然后根据命令袁改变AGV采集到的分支路径图像的权重袁迭代计算所选择路径的若干最小内接圆曰最后袁利 用最小二乘规则袁 将最小内接圆的圆心拟合成贝塞尔轨迹袁 实现AGV的精确路径跟踪遥 将该算法应用于视觉引导 AGV 中袁并进行路径特征的在线识别和轨迹跟踪实验遥 结果表明院路径特征的识别准确率为99.7%以上袁识别时间约 为22ms袁弯道轨迹跟踪准确度为20mm和20毅曰与传统方法相比袁该方法显著提高路径特征识别和轨迹跟踪的准确 率袁更能满足工业现场需求遥 关键词院视觉导引曰自动导引车曰贝塞尔轨迹曰轨迹跟踪曰支持向量机 文献标志码院A 文章编号院1674-5124渊2017冤08-0113-06 Research on path tracking of visual navigation AGV based on Bessel trajectory LIU Haiqin 渊Department of Mathematics and Information Engineering袁Dongchang College of Liaocheng University袁 Liaocheng 252000袁China冤 Abstract: To increase path tracking accuracy of visual navigation AGV渊automatic guided vehicle冤袁 a precise path tracking algorithm based on Bessel trajectory is proposed. Firstly袁 the algorithm will pre-process the collected feature images of various paths to obtain shape information袁 and train the SVM multi-path shape feature classifier袁 and then change the weight of the branch paths of the collected images and iteratively calculate the minimum inscribed circles of the selected paths according to the order. Finally袁 based on the least squares rule袁 the centre of the minimum inscribed circle will be fitted into the Bessel trajectory to realizing the precise path tracking of AGV. The algorithm was applied in visual navigation AGV