LVQ neural network based target differentiation method for mobile robot

This paper presents a LVQ (Learning Vector Quantization) neural network based target differentiation method for mobile robots. The typical targets can be differentiated efficiently in indoor environments with LVQ neural network by fusing the time-of-flight data and amplitude data of sonar system. The algorithm is simple and real-time and has high accuracy and robustness. The uncertainty of sonar data can be effectively dealt with the method and mobile robots can classify the targets quickly and reliably in indoor environments. In simulation experiments, a hierarchical configuration is adopted and the sonar data is preprocessed before inputted to neural network to improve the differentiation performance of LVQ network farther. The simulation experiments prove that the algorithm is effective and robust.