Machine Learning in Control Systems: An Overview of the State of the Art

Control systems are in general based on the same structure, building blocks and physics-based models of the dynamic system regardless of application, and can be mathematically analyzed w.r.t. stability, robustness and so on given certain assumptions. Machine learning methods (ML), on the other hand, are highly flexible and adaptable methods but are not subject to physic-based models and therefore lack mathematical analysis. This paper presents state of the art results using ML in the control system. Furthermore, a case study is presented where a neural network is trained to mimic a feedback linearizing speed controller for an autonomous ship. The neural network outperforms the traditional controller in case of modeling errors and measurement noise.

[1]  Asgeir J. Sørensen,et al.  Relative Velocity Control and Integral LOS for Path Following of Underactuated Surface Vessels , 2012 .

[2]  Gianluca Antonelli,et al.  The null-space-based behavioral control for autonomous robotic systems , 2008, Intell. Serv. Robotics.

[3]  Fabrizio Mazzetto,et al.  Stability Analysis of an Articulated Agri-Robot Under Different Central Joint Conditions , 2015, ROBOT.

[4]  Ian Postlethwaite,et al.  Neural-network-based flush air data sensing system demonstrated on a mini air vehicle , 2010 .

[5]  Richard M. Murray,et al.  Feedback Systems: An Introduction for Scientists and Engineers , 2008 .

[6]  G. Ellis.  Observers in Control Systems: A Practical Guide , 2002 .

[7]  George Ellis.  Chapter 1 – Control Systems and the Role of Observers , 2002 .

[8]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[9]  M. Spong,et al.  Robot Modeling and Control , 2005 .

[10]  Thor I. Fossen,et al.  Handbook of Marine Craft Hydrodynamics and Motion Control , 2011 .

[11]  Sergey Levine,et al.  Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Kristin Y. Pettersen,et al.  Learning an AUV docking maneuver with a convolutional neural network , 2017, OCEANS 2017 – Anchorage.

[13]  Mikhail Skliar.  Process Dynamics and Control, 2nd Edition By Dale E. Seborg, Thomas F. Edgar, and Duncan A. Mellichamp , 2008 .

[14]  XuLei Yang,et al.  Robust Recurrent Neural Network Control of Biped Robot , 2007, J. Intell. Robotic Syst..

[15]  Asgeir J. Sørensen,et al.  Observers for Dynamic Positioning of ROVs with Experimental Results , 2012 .

[16]  Thor I. Fossen,et al.  Handbook of Marine Craft Hydrodynamics and Motion Control: Fossen/Handbook of Marine Craft Hydrodynamics and Motion Control , 2011 .

[17]  Michael Lau,et al.  Modeling and testing of hydrodynamic damping model for a complex-shaped remotely-operated vehicle for control , 2012 .

[18]  Kristin Ytterstad Pettersen,et al.  A control-oriented model of underwater snake robots exposed to currents , 2015, 2015 IEEE Conference on Control Applications (CCA).

[19]  Alaeddin Malek,et al.  Numerical solution for high order differential equations using a hybrid neural network - Optimization method , 2006, Appl. Math. Comput..

[20]  Dimitris G. Papageorgiou,et al.  Neural-network methods for boundary value problems with irregular boundaries , 2000, IEEE Trans. Neural Networks Learn. Syst..

[21]  Igor Kononenko,et al.  Machine learning for medical diagnosis: history, state of the art and perspective , 2001, Artif. Intell. Medicine.

[22]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice , 1993 .

[23]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[24]  Jürgen Schmidhuber,et al.  A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots , 2016, IEEE Robotics and Automation Letters.

[25]  Justin A. Sirignano,et al.  DGM: A deep learning algorithm for solving partial differential equations , 2017, J. Comput. Phys..

[26]  Steven L. Brunton,et al.  Machine Learning Control (MLC) , 2017 .

[27]  Sarangapani Jagannathan,et al.  Neural Network Output Feedback Control of Robot Formations , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[28]  K.Y. Pettersen,et al.  Global /spl kappa/-exponential way-point manoeuvering of ships , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[29]  Kristin Ytterstad Pettersen,et al.  Set-based Line-of-Sight (LOS) path following with collision avoidance for underactuated unmanned surface vessel , 2016, MED.

[30]  Sanjiv Singh,et al.  Obstacle detection for high speed autonomous navigation , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[31]  Lazim Abdullah,et al.  Fuzzy Multi Criteria Decision Making and its Applications: A Brief Review of Category , 2013 .

[32]  Asgeir J. Sørensen,et al.  Neural network augmented identification of underwater vehicle models , 2004 .

[33]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[34]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[35]  Kristin Ytterstad Pettersen,et al.  Line-of-sight curved path following for underactuated USVs and AUVs in the horizontal plane under the influence of ocean currents , 2016, 2016 24th Mediterranean Conference on Control and Automation (MED).

[36]  Thomas F. Edgar,et al.  Process Dynamics and Control , 1989 .

[37]  Gianluca Antonelli,et al.  Stability Analysis for Prioritized Closed-Loop Inverse Kinematic Algorithms for Redundant Robotic Systems , 2009, IEEE Trans. Robotics.