Learning control of nonhonolomic robot based on support vector machine

Abstract

A learning controller of nonhonolomic robot in real-time based on support vector machine (SVM) is presented. The controller includes two parts: one is kinematic controller based on nonlinear law, and the other is dynamic controller based on SVM. The kinematic controller is aimed to provide desired velocity which can make the steering system stable. The dynamic controller is aimed to transform the desired velocity to control torque. The parameters of the dynamic system of the robot are estimated through SVM learning algorithm according to the training data of sliding windows in real time. The proposed controller can adapt to the changes in the robot model and uncertainties in the environment. Compared with artificial neural network (ANN) controller, SVM controller can converge to the reference trajectory more quickly and the tracking error is smaller. The simulation results verify the effectiveness of the method proposed.

Keywords

nonhonolomic robot / learning control / support vector machine / nonlinear control law / dynamic control

References

[1] BrockettR. W.Asymptotic stability and feedback stabilization in differential geometric control theory [M], 1983Boston, MABirkhauiser181-191

[2] KANAYAMA Y, KIMURA Y, MIYAZAKI F, NOGUCHI T. A stable tracking control method for an autonomous mobile robot[C]// Proc IEEE Int Conf Robot Automat, Cincinnati, OH, 1990: 384–389.

[3] BlochA. M., ReyhanogluM., McClamrochN. H.. Control and stabilization of nonholonomic dynamic systems [J]. IEEE Trans Automat Control, 1992, 37(11): 1746-1757

[4] FelipeN. M., WanderleyC. C., RicardoC., MarioS. F., TeoianoF. B. F.. An adaptive dynamic controller for autonomous mobile robot trajectory tracking [J]. Control Engineering Practice, 2008, 16(11): 1354-1363

[5] FierroR., LewisF. L.. Control of nonholonomic mobile robot: Backstepping kinematics into dynamics [J]. Journal of Robotics Systems [J], 1997, 14(3): 149-163

[6] DasT., KarI. N.. Design and implementation of an adaptive fuzzy logic-based controller for wheeled mobile robots [J]. IEEE Transactions on Control Systems Technology, 2006, 14(3): 501-510

[7] ParkB. S., YooS. J., ParkJ. B., ChoiY. H.. Adaptive neural sliding mode control of nonholonomic wheeled mobile robots with model uncertainty [J]. IEEE Transactions on Control Systems Technology, 2009, 17(1): 207-214

[8] YeJun.. Adaptive control of nonlinear PID-based analog neural networks for a nonholonomic mobile robot [J]. Neurocomputing, 2008, 71(7/8/9): 1561-1565

[9] KlancarG., SkrjancI.. Tracking-error model-based predictive control for mobile robots in real time [J]. Robotics and Autonomous Systems, 2007, 55(6): 460-469

[10] SatoM., KandaA., IshiiK.. A controller design method based on a neural network for an outdoor mobile robot [J]. Journal of Bionic Engineering, 2008, 5(Suppl): 130-137

[11] FierroR., LewisF. L.. Control of a nonholonomic mobile robot using neural networks [J]. IEEE Transactions on Neural Networks, 1998, 9(4): 589-600

[12] AntoniniP., IppolitiG., LonghiS.. Learning control of mobile robots using a multiprocessor system [J]. Control Engineering Practice, 2006, 14(11): 1279-1295

[13] LinW.-s., YangP.-chieh.. Adaptive critic motion control design of autonomous wheeled mobile robot by dual heuristic programming [J]. Automatica, 2008, 44(11): 2716-2723

[14] TopalovA. V., KimJ. H., ProychevT. P.. Fuzzy-net control of non-holonomic mobile robot using evolutionary feedback-error-learning [J]. Robotics and Autonomous Systems, 1998, 23(3): 187-200

[15] SchaalS., AtkesonC. G., VijayakumarS.. Scalable techniques from nonparametric statistics for real time robot learning [J]. Applied Intelligence, 2002, 17(1): 49-60

[16] JiangL., DengM., InoueA.. Support vector machine-based two-wheeled mobile robot motion control in a noisy environment [J]. Journal of Systems and Control Engineering, 2008, 222(7): 733-743

[17] LV G F, J. SONG J Y, LIANG H, SUN C Y. Inverse system control of nonlinear systems using LS-SVM [C]// Proceedings of the 26th Chinese Control Conference, Zhangjiajie, 2007: 233–236.

[18] HuangL.. Speed control of differentially driven wheeled mobile robots-model-based adaptive approach [J]. Journal of Robotic Systems, 2005, 22(6): 323-332

[19] VapnikV., GolowichS., SmolaA.. Support vector method for function approximation, regression estimation, and signal processing [M]. Advances in Neural Information Processing Systems, 1997CambridgeMIT Press281-287

[20] SuykensJ. A. K., VandewalleJ., MoorB.. Optimal control by least squares support vector machines [J]. Neural Networks, 2001, 14(1): 23-35

[21] LiZ.-j., ZhangY.-n., YangY.-peng.. Support vector machine optimal control for mobile wheeled inverted pendulums with unmodelled dynamics [J]. Neurocomputing, 2010, 73(13/14/15): 2773-2782