【摘要】 针对移动机器人避障问题,提出了一种基于支持向量机(SVM)算法的移动机器人避障方法。支持向量机建立在统计学习理论基础之上,具有理论完备、适应性强等优点,本研究基于支持向量机,选取适当的核函数及其参数,构建了支持向量机分类器,并利用基于支持向量机算法的"一对一"方法(One-against-one method)完成了对多类数据的分类。在Matlab R2007a仿真实验环境中进行了仿真实验测试,仿真结果验证了支持向量机算法在移动机器人避障中的可行性和有效性。更多还原

【Abstract】 For mobile robot obstacle avoidance problems,the approach is proposed based on the Support Vector Machine( SVM) algorithm for mobile robot obstacle avoidance. Support vector machine,built on the basis of statistical learning theory,has the advantages of theoretical completeness and adaptability. Based on support vector machine,the appropriate kernel function and its parameters were selected to construct support vector machine classifier. A multi-class classification of data was completed,using support vector machine Algorithm "one on one"approach( One-against-one method). Simulation testing was processed in Matlab R2007a simulation environment.The results verify the feasibility and effectiveness of the support vector machine algorithm for mobile robot obstacle avoidance.更多还原