Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm

In this paper, an adaptive single neuron Proportional–Integral–Derivative (PID) controller based on the extended Kalman filter (EKF) training algorithm is proposed. The use of EKF training allows online training with faster learning and convergence speeds than backpropagation training method. Moreover, the propose adaptive PID approach includes a back-calculation anti-windup scheme to deal with windup effects, which is a common problem in PID controllers. The performance of the proposed approach is shown by presenting both simulation and experimental tests, giving results that are comparable to similar and more complex implementations. Tests are performed for a four wheeled omnidirectional mobile robot. Tests show the superiority of the proposed adaptive PID controller over the conventional PID and other adaptive neural PID approaches. Experimental tests are performed on a KUKA® Youbot® omnidirectional platform.

[1]  Mikhail Budko,et al.  Hybrid parallel neuro-controller for multirotor unmanned aerial vehicle , 2016, 2016 8th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT).

[2]  Sen Wang,et al.  Adaptive low-level control of autonomous underwater vehicles using deep reinforcement learning , 2018, Robotics Auton. Syst..

[3]  Maolin Jin,et al.  A New Adaptive Sliding-Mode Control Scheme for Application to Robot Manipulators , 2016, IEEE Transactions on Industrial Electronics.

[4]  Željko Ivandić,et al.  SOLUTIONS TO THE CHARACTERISTIC EQUATION FOR INDUSTRIAL ROBOT ’ S ELLIPTIC TRAJECTORIES , 2016 .

[5]  Danil V. Prokhorov,et al.  Conditioned adaptive behavior from Kalman filter trained recurrent networks , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[6]  Mir Mohammad Ettefagh,et al.  Robust adaptive control of a bio-inspired robot manipulator using bat algorithm , 2016, Expert Syst. Appl..

[7]  陈彦民,et al.  Decentralized PID neural network control for a quadrotor helicopter subjected to wind disturbance , 2015 .

[8]  M. R. Katebi,et al.  Predictive PID control: a new algorithm , 2001, IECON'01. 27th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.37243).

[9]  Alma Y. Alanis,et al.  Visual Servoing for an Autonomous Hexarotor Using a Neural Network Based PID Controller , 2017, Sensors.

[10]  Wen-Hui Li,et al.  Single Neuron PID Model Reference Adaptive Control Based on RBF Neural Network , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[11]  Yuttana Kitjaidure,et al.  Neural network controller based on PID using an extended Kalman filter algorithm for multi-variable non-linear control system , 2016, 2016 Eighth International Conference on Advanced Computational Intelligence (ICACI).

[12]  Xiucai Guo,et al.  PID neural networks in multivariable systems , 2002, Proceedings of the IEEE Internatinal Symposium on Intelligent Control.

[13]  Oishee Mazumder,et al.  Scanning Camera and Augmented Reality Based Localization of Omnidirectional Robot for Indoor Application , 2017 .

[14]  Jose Rivera-Mejia,et al.  PID Based on a Single Artificial Neural Network Algorithm for Intelligent Sensors , 2012 .

[15]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[16]  Payam Kheirkhahan,et al.  Robust anti-windup control design for PID controllers , 2017, 2017 17th International Conference on Control, Automation and Systems (ICCAS).

[17]  Guoqiang Hu,et al.  Adaptive Vision-Based Leader–Follower Formation Control of Mobile Robots , 2017, IEEE Transactions on Industrial Electronics.

[18]  Francesco Piazza,et al.  On the complex backpropagation algorithm , 1992, IEEE Trans. Signal Process..

[19]  Jian Weng,et al.  Adaptive population extremal optimization-based PID neural network for multivariable nonlinear control systems , 2019, Swarm Evol. Comput..

[20]  Christopher G. Pretty,et al.  Mechatronic design and development of a non-holonomic omnidirectional mobile robot for automation of primary production , 2016 .

[21]  Shantha Gamini Jayasinghe,et al.  Experimental Study of Command Governor Adaptive Control for Unmanned Underwater Vehicles , 2019, IEEE Transactions on Control Systems Technology.

[22]  Moses O. Tadé,et al.  A nonlinear PID controller with applications , 1999 .

[23]  Jun Jiao,et al.  Single Neuron PID Control of Agricultural Robot Steering System Based on Online Identification , 2018, 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService).

[24]  Rastislav Pirník,et al.  Integration of Inertial Sensor Data into Control of the Mobile Platform , 2015 .

[25]  Bing He,et al.  Varying gain MPC for consensus tracking with application to formation control of omnidirectional mobile robots , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[26]  Alma Y. Alanis,et al.  KAdam: Using the Kalman Filter to Improve Adam algorithm , 2019, CIARP.

[27]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[28]  Y. Kosaka,et al.  Position rectification control for Mecanum wheeled omni-directional vehicles , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[29]  L. Angel,et al.  Evaluation of the windup effect in a practical PID controller for the speed control of a DC-motor system , 2019, 2019 IEEE 4th Colombian Conference on Automatic Control (CCAC).

[30]  Richard M. Murray,et al.  Feedback Systems An Introduction for Scientists and Engineers , 2007 .

[31]  Mark E. Oxley,et al.  Comparative Analysis of Backpropagation and the Extended Kalman Filter for Training Multilayer Perceptrons , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Bing Qiao,et al.  Kinematic Model of a Four Mecanum Wheeled Mobile Robot , 2015 .

[33]  Richa Negi,et al.  A comparative study of PID tuning methods using anti-windup controller , 2012, 2012 2nd International Conference on Power, Control and Embedded Systems.

[34]  Mariano De Paula,et al.  Incremental Q-learning strategy for adaptive PID control of mobile robots , 2017, Expert Syst. Appl..

[35]  Julio E. Normey-Rico,et al.  Mobile robot path tracking using a robust PID controller , 2001 .

[36]  Zhijun Li,et al.  Trajectory-Tracking for a Mobile Robot Using Robust Predictive Control and Adaptive Control , 2018, 2018 3rd International Conference on Advanced Robotics and Mechatronics (ICARM).

[37]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[38]  Pavol Božek,et al.  Trends in Simulation and Planning of Manufacturing Companies , 2016 .

[39]  Ching-Chih Tsai,et al.  Motion controller design and embedded realization for Mecanum wheeled omnidirectional robots , 2011, 2011 9th World Congress on Intelligent Control and Automation.

[40]  Yi Sun,et al.  Passivity-based control of an omnidirectional mobile robot , 2016, Robotics and biomimetics.

[41]  Laxmidhar Behera,et al.  A passivity based system design for non-holonomic mobile robot in presence of delay and traffic disturbances , 2017, 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[42]  Saeid Nahavandi,et al.  Robust Adaptive Control Scheme for Teleoperation Systems With Delay and Uncertainties , 2020, IEEE Transactions on Cybernetics.

[43]  Youguo Pi,et al.  PID neural networks for time-delay systems , 2000 .

[44]  Chun-Yi Su,et al.  Vision-Based Model Predictive Control for Steering of a Nonholonomic Mobile Robot , 2016, IEEE Transactions on Control Systems Technology.

[45]  Luis Govinda García-Valdovinos,et al.  Neural Network-Based Self-Tuning PID Control for Underwater Vehicles , 2016, Sensors.

[46]  Lijun Zhao,et al.  Design and implementation of an omnidirectional mobile robot platform with unified I/O interfaces , 2017, 2017 IEEE International Conference on Mechatronics and Automation (ICMA).

[47]  Jih-Gau Juang,et al.  A single neuron PID control for twin rotor MIMO system , 2009, 2009 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[48]  Igi Ardiyanto.  Task Oriented Behavior-Based State-Adaptive PID (Proportional Integral Derivative) Control for Low-Cost Mobile Robot , 2010, 2010 Second International Conference on Computer Engineering and Applications.

[49]  D. P. Atherton,et al.  An analysis package comparing PID anti-windup strategies , 1995 .

[50]  Yun Zhang,et al.  An adaptive neural PID controller for torque control of hybrid electric vehicle , 2011, 2011 6th International Conference on Computer Science & Education (ICCSE).