基于声信号的履带机器人地面分类试验研究

为了拓展地面识别方式及提升识别率，提出利用履带机器人行驶噪声进行地面类型识别.使用声压传感器采集履带机器人在行驶过程中与地面相互作用辐射的声音信号，对声音信号提取修正的梅尔频率倒谱系数（MFCC）及其一阶差分（△MFCC）使用优化后的支持向量机（SVM）进行分类，并测试了该方法在多种背景噪声环境下的效果.结果表明，行驶噪声包含能够表征地面特点的信息.相比于幅域、频域和时频域特征，修正的MFCC+△MFCC特征具有明显优势.在校园环境中分类准确率达到了89.5%，当信噪比高于20 dB时，在多种背景噪声环境中分类准确率均达到80%左右. 

Experimental Study on Terrain Classification Based on Acoustic Signal for Tracked Robot

In order to extend terrain classification methods and improve accuracy,a terrain classification method based on acoustic signal was proposed.An acoustic pressure sensor was installed to acquire acoustic signal resulted from tracked robot-terrain interaction.The modified MFCC+△MFCC feature vector was extracted.Finally,a tuned support vector machine(SVM)was adopted to perform classification.The results indicate that the information carried by the acoustic signal is able to characterize terrain type.The modified MFCC+△MFCC feature vector is obviously superior to features extracted from amplitude domain,frequency domain and time-frequency domain.The highest accuracy of 89.5% is achieved in campus environment.When the SNR is higher than 20 dB,accuracies around 80% can be achieved in various background environments.Acoustic-based method is proved to be effective in terrain classification application.