移动机器人的室内定位是机器人领域中的一个热点问题，移动机器人的定位包括位置与方位两方面。为对移动机器人方位进行有效的估计，该文提出了基于支持向量机（support vector machine，SVM）的机器人方位回归模型，选定激光雷达信息作为模型的输入量、机器人的方位作为输出量；并与基于极限学习机（extreme learning machine，ELM）的机器人方位回归模型进行对比。实验结果表明：基于极限学习机回归模型的均方误差为0.320 rad，训练时间为0.936 s；基于支持向量回归模型的均方误差为0.113 rad，训练时间为9 273 s。该回归模型可为机器人方位估计提供一定的应用价值。
The positioning of mobile robots indoors is very important with the controller needed to know both the location and the orientation. This paper presents a robot orientation regression model based on a support vector machine (SVM) to estimate the robot orientation. A laser radar signal is used as the model input with the orientation as the output. Tests show that the mean square error using an extreme learning machine model is 0.320 rad with a training time of 0.936 s while the mean square error based on the current support vector regression model is 0.113 rad with a training time of 9 273 s. Thus, the regression models can provide accurate robot position estimates.
[1] HSU C C, WONG C C, TENG H C, et al. Localization of mobile robots via an enhanced particle filter incorporating tournament selection and nelder-mead simplex search[J]. International Journal of Innovative Computing, Information and Control, 2011, 7(7):3725-3737.
[2] HSU C C, WONG C C, TENG H C, et al. Dual-circle self-localization for soccer robots with omnidirectional vision[J]. Journal of the Chinese Institute of Engineers, 2012, 35(6):619-631.
[3] NELDER J A, MEAD R. A simplex method for function minimization[J]. The Computer Journal, 1965, 7(4):308-313.
[4] DELLAERT F, FOX D, BURGARD W, et al. Monte Carlo localization for mobile robots[C]//Proceedings of the International Conference on Robotics and Automation. Detroit, MI, USA:IEEE, 1999:1322-1328.
[5] ZHENG X M, LIU H P, SUN F C, et al. Sonar-based place recognition using joint sparse coding method[C]//Proceedings of the International Joint Conference on Neural Networks. Vancouver, BC, Canada:IEEE, 2016:3877-3882.
[6] ZINGARETTI P, FRONTONI E. Vision and sonar sensor fusion for mobile robot localization in aliased environments[C]//Proceedings of the International Conference on Mechatronics and Embedded Systems and Applications. Beijing, China:IEEE, 2006:1-6.
[7] ULLAH M M, PRONOBIS A, CAPUTO B, et al. Towards robust place recognition for robot localization[C]//Proceedings of the IEEE International Conference on Robotics and Automation. Pasadena, CA, USA:IEEE, 2008:530-537.
[8] JO K H, LEE J, KIM J B. Cooperative multi-robot localization using differential position data[C]//Proceedings of the International Conference on Advanced Intelligent Mechatronics. Zurich, Switzerland:IEEE, 2007:1-6.
[9] CAO J, LABROSSE F, DEE H. An evaluation of image-based robot orientation estimation[M]. NATRAJ A, CAMERON S, MELHUISH C, et al. Towards autonomous robotic systems. Berlin, Heidelberg:Springer, 2014:135-147.
[10] SILVERMAN Y, SNYDER J, BAI Y, et al. Location and orientation estimation with an electrosense robot[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura, Portugal:IEEE, 2012:4218-4223.
[11] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:Theory and applications[J]. Neurocomputing, 2006, 70(1-3):489-501.
[12] SCHÖLKOPF B, BURGES C, VAPNIK V. Extracting support data for a given task[C]//Proceedings of the 1st International Conference on Knowledge Discovery and Data Mining. Montréal, Québec, Canada:AAAI Press,1995:252-257.
[13] VAPNIK V, GOLOWICH S E, SMOLA J. Support vector method for function approximation, regression estimation, and signal processing[C]//Proceedings of the 10th Annual Conference on Neural Information Processing Systems. Denver, Colorado:MIT Press, 1996:281-287.
[14] COLLOBERT R, BENGIO S. SVMTorch:Support vector machines for large-scale regression problems[J]. Journal of Machine Learning Research, 2001, 1(2):143-160.
[15] HUANG G B, CHEN L, SIEW C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4):879-892.
[16] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:A new learning scheme of feedforward neural networks[C]//Proceedings of the International Joint Conference on Neural Networks. Budapest, Hungary:IEEE, 2004:985-990.
[17] URŠIČ P, TABERNIK D, BOBEN M, et al. Room categorization based on a hierarchical representation of space[J]. International Journal of Advanced Robotic Systems, 2013, 10(2):94.
[18] URŠIČ P, LEONARDIS A, SKOČAJ D, et al. Hierarchical spatial model for 2D range data based room categorization[C]//Proceedings of the IEEE International Conference on Robotics and Automation. Stockholm, Sweden:IEEE, 2016:4514-4521.
