TY - GEN
T1 - On-line recognition of driving road condition using support vector machine
AU - Watanabe, Tatsuhito
AU - Katsura, Seiichiro
PY - 2011/5/18
Y1 - 2011/5/18
N2 - A person operating a mobile robot in a remote environment receives a realistic visual feedback about the condition of the road on where the mobile robot is moving. A categorization of the road condition is necessary to evaluate the condition for safe and comfortable driving. For this purpose, the mobile robot should be capable of recognizing and classifying the condition of the road surfaces. In a previous research, author proposed a method to recognize the type of the road surfaces on the basis of the friction between the mobile robot and the road surfaces. The friction is estimated by a reaction torque observer, and a Support Vector Machine (SVM) is used to classify the surfaces. In this paper, SVM is calculated on-line, and multi-class classification is realized. Moreover, the operator is given feedback of haptic information by using mobile-hapto system As a result, the operator is given visual and force feedback about road condition. By experiments, the validity of the proposed method is confirmed.
AB - A person operating a mobile robot in a remote environment receives a realistic visual feedback about the condition of the road on where the mobile robot is moving. A categorization of the road condition is necessary to evaluate the condition for safe and comfortable driving. For this purpose, the mobile robot should be capable of recognizing and classifying the condition of the road surfaces. In a previous research, author proposed a method to recognize the type of the road surfaces on the basis of the friction between the mobile robot and the road surfaces. The friction is estimated by a reaction torque observer, and a Support Vector Machine (SVM) is used to classify the surfaces. In this paper, SVM is calculated on-line, and multi-class classification is realized. Moreover, the operator is given feedback of haptic information by using mobile-hapto system As a result, the operator is given visual and force feedback about road condition. By experiments, the validity of the proposed method is confirmed.
UR - http://www.scopus.com/inward/record.url?scp=79955940320&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79955940320&partnerID=8YFLogxK
U2 - 10.1109/ICIT.2011.5754411
DO - 10.1109/ICIT.2011.5754411
M3 - Conference contribution
AN - SCOPUS:79955940320
SN - 9781424490660
T3 - Proceedings of the IEEE International Conference on Industrial Technology
SP - 405
EP - 410
BT - Proceedings - ICIT 2011
T2 - 2011 IEEE International Conference on Industrial Technology, ICIT 2011
Y2 - 14 March 2011 through 16 March 2011
ER -