{"references": ["A. Lacaze, \"A neural network planner that prunes its own tree,\" Term\npaper, Knowledge Engineering Department, University of Meryland,\n1997.", "A. G. Barto, \"Neuronlike adaptive elements that can solve difficult\nlearning control problems,\" IEEE Transactions on System, Man and\nCybernetics, vol. 13, pp. 834-846, 1983.", "Z. Hendzel, \"Adaptive Critic Neural Networks for Motion Control of\nWheeled Mobile Robot,\" Nonlinear Dynamics, vol. 50, no. 4, pp. 849-\n855, 2007.", "K.S. Narenda, and K. Pathasarathy, \"Identification and control of\ndynamic systems using neural network,\" IEEE Transaction on Neural\nNetworks, vol. 1, no. 1, pp. 4-27, 1990.", "D. Nguyen, and B. Widrow, \"Neural Networks for Self- Learning\nControl Systems,\" IEEE Control System Magazine, vol. 10, no. 1, pp.\n18-23, Feb. 1990.", "K. Hornik, M. Stinchombe, and H. White, \"Universal Approximation of\nan Unknown mapping and its Derivatives Using Multilayer Feedforward\nNetworks,\" Neural Networks, vol. 3, 1990.", "M. Corradini, G. Ippoliti, and S. Longhi, \"Neural Networks Based\nControl of Mobile Robots: Development and Experimental Validation\",\nJournal of Robotic Systems, vol. 20, no. 10, pp. 587-600, 2003.", "Z. P. Jiang, E. Lefeber, and H. Nijmeijer, \"Saturated stabilization and\ntracking of a nonholonomic mobile robot,\" Systems & Control Letters,\nvol. 42, pp. 327-332, 2001.", "G. Ram\u251c\u00a1rez,. and S. Zeghloul, \"A New Local Path Planner for\nNonholonmic Mobile Robot Navigation in Cluttered Environments, \" in\nProc. IEEE Int. Conf. on Robotics and Automation, 2000,p. 2058-2063..\n[10] H.G. Tanner, and K.J. Kyriakopoulos, \"Backstepping for nonsmooth\nsystems, \" Automatica, vol. 39, 2003, pp. 1259-1265.\n[11] J. Velagic, B. Lacevic, and B. Perunicic, \"A 3-Level Autonomous\nMobile Robot Navigation System Designed by Using Reasoning/Search\nApproaches,\" Robotics and Autonomous Systems, vol. 54, no. 12, pp.\n989-1004, Dec. 2006.\n[12] R. Fierro, and F. L. Lewis, \"Control of a nonholonomic mobile robot\nusing neural networks\", IEEE Transactions on Neural Networks, vol. 9,\nno. 4, pp. 389-400, 1998.\n[13] S. X. Yang, and M. Meng, \"Real-time fine motion control of robot\nmanipulators with unknown dynamics,\" in: Dynamics in Continuous,\nDiscrete and Impulse Systems, Series B, 2001.\n[14] J. Velagic, and M. Hebibovic, \"Neuro-Fuzzy Architecture for\nIdentification and Tracking Control of a Robot,\" in Proc. The World\nAutomation Congress - 5th International Symposium on Soft Computing\nfor Industry ISSCI2004, June 28 - July 1, Sevilla, Spain, paper no.\nISSCI-032 (1:9), 2004.\n[15] J. Velagic, B. Lacevic, and M. Hebibovic, \"On-Line Identification of a\nRobot Manipulator Using Neural Network with an Adaptive Learning\nRate,\" in Proc. 16th IFAC World Congress, 03-08 June, Prague, Czech\nRepublic, 2005, paper no. 2684(1-6), 2005.\n[16] M. Egerstedt, X. Hu, A. Stotsky, \"Control of mobile platforms using a\nvirtual vehicle approach,\" IEEE Transactions on Automatic Control ,\nvol. 46, no. 11, pp. 1777-1882, 2001."]}

In this paper the neural network-based controller is designed for motion control of a mobile robot. This paper treats the problems of trajectory following and posture stabilization of the mobile robot with nonholonomic constraints. For this purpose the recurrent neural network with one hidden layer is used. It learns relationship between linear velocities and error positions of the mobile robot. This neural network is trained on-line using the backpropagation optimization algorithm with an adaptive learning rate. The optimization algorithm is performed at each sample time to compute the optimal control inputs. The performance of the proposed system is investigated using a kinematic model of the mobile robot.