摘要
触觉感知信息的模式识别可以有效提高人机交互的效率,为此设计了一种触觉传感单元功能模块,可以在2D平面内识别人机接触的方向信息。采用PCA算法来提取触觉感知数据特征,从而去除数据的噪音并且降低维度;采用BP神经网络对人机接触方式进行识别分类,提高鲁棒性。对于不同实验对象的训练样本和测试样本进行数据采集,结果表明该方法可以实现93.1%的模式识别正确率。
To imprnve the efficiency of communication in human- robot cooperation through tactile information, this paper proposes a method to recognize human intended direction in 2 - D using an equipment with taetile arrays. The PCA method is em- ployed in this study to extract essential information thus reduce computation complex and increase robustness. BP neural network is hnplcmented for classifying the intended direction of human operators. Three members of the project team were involved in the study, The efficiency of proposed algnrithm is investigated. Experimental results shows that the proposed method couht achieve 93. 1% recognition accuracy if both the training data and validation data contain tactile images fi'om all the users.
出处
《武汉理工大学学报(信息与管理工程版)》
CAS
2016年第1期128-130,共3页
Journal of Wuhan University of Technology:Information & Management Engineering
基金
国家自然科学基金资助项目(61403289)
关键词
触觉
PCA算法
BP神经网络
模式识别
tactile sensing
PCA method
BP neural network
pattern recognition