文章摘要
张劲波*,左韬* **,胡新宇*,伍一维*.基于支持向量机和改进蚁群算法的移动机器人路径规划[J].高技术通讯(中文),2021,31(3):288~297
基于支持向量机和改进蚁群算法的移动机器人路径规划
Path planning of mobile robot based on support vector machine and improved ant colony algorithm
  
DOI:10.3772/j.issn.1002-0470.2021.03.009
中文关键词: 蚁群算法(ACO); 支持向量机(SVM); 路径规划; 移动机器人
英文关键词: ant colony algorithm (ACO), support vector machine (SVM), path planning, mobile robot
基金项目:
作者单位
张劲波*  
左韬* **  
胡新宇*  
伍一维*  
摘要点击次数: 979
全文下载次数: 649
中文摘要:
      针对传统蚁群算法(ACO)收敛速度慢、全局搜索能力不佳、易陷入局部最优、路径不光滑及不安全等缺点,本文提出一种将改进的蚁群算法和非线性支持向量机(SVM)结合的移动机器人路径规划算法。对传统蚁群算法引入两个角度信息,增加算法的朝向性,克服局部最优问题;信息素挥发因子随迭代次数自适应调整,加快全局搜索能力和收敛速度。在此基础上结合高斯径向基核最小二乘支持向量机,采用提出的改进蚁群算法获得支持向量机的惩罚系数和核函数宽度,利用径向基核函数和决策函数在改进蚁群算法的路径转向位置处训练优化,得到平滑及安全的路径。仿真结果表明,提出的算法不但可以有效提高收敛速度和精度,而且使得路径光滑且安全。
英文摘要:
      Aiming at the shortcomings of traditional ant colony algorithm(ACO), such as slow convergence speed, poor global search ability, easy to fall into local optimum, unsmooth and unsafe path, a path planning algorithm for mobile robot is proposed, which combines the improved ant colony algorithm and nonlinear support vector machine (SVM). Two angle information is introduced to the traditional ant colony algorithm to increase the direction of the algorithm and overcome the local optimization problem. The pheromone volatility factor is adjusted adaptively with the number of iterations to improve the global search ability and convergence speed. Basis on this, combined with the Gaussian radial basis kernel least squares support vector machine, the improved ant colony algorithm is used to obtain the penalty coefficient and kernel function width of the support vector machine, the radial basis kernel function and decision function are used to train and optimize the improved ant colony algorithm path turning position to obtain a smooth and safe path. Simulation results show that the proposed algorithm can improve the convergence speed and accuracy, and make the path smooth and safe.
查看全文   查看/发表评论  下载PDF阅读器
关闭

分享按钮