基于支持向量机的移动机器人环境识别

Environment Identification Based on Support Vector Machine for Mobile Robot

针对未知环境下移动机器人的环境理解与识别问题,提出了一种支持向量机(SVM)的环境识别算法。在对移动机器人室内外特征环境分析和建模的基础上,通过机器人配置的多超声波传感器获取环境的距离信息,直接作为环境的特征,按照从左到右的顺序组成表征环境轮廓的六维特征向量,送入支持向量机训练并用于特征环境的识别。克服了多超声波传感器测量数据的不确定性对分类结果准确度的影响,实现了移动机器人对室内外特征环境的正确识别。仿真和实验验证了方法的可行性,与传统的分类算法相比,算法对环境具有更高的识别正确率,在训练样本较少的情况下,能够在不同的位置和角度准确测量识别多类特征环境,具有一定的实用价值。

Aimed at environment understanding and identification for mobile robot in uncertain environments,a kind of environment identification arithmetic based on support vector machine （SVM） is proposed. Based on the analyzing and modeling indoor and outdoor environment with special features for mobile robot,the distance information of environment is measured by multi-ultrasonic sensors in mobile robot and used as the feature of environment directly. Afterward,these features are combined into a six-dimensional eigenvector for environment profile from left to right,which is sent to support vector machine for training and recognition. The method overcomes the effects of data uncertainties from multi-ultrasonic sensors on accuracy of classification results and implements the accurate recognition of the indoor and outdoor environment with special features for mobile robot. The simulation and experimental results show its feasibility. Compared with the traditional classification methods,this method shows higher recognition ratio. In the case of small samples,the method can measure and identify multiclass environment accurately at different ranges and angles. So it is valuable.