Intelligent nonlinear observer design for a class of nonlinear discrete-time flexible joint robot

In this paper, a nonlinear intelligent observer design is applied for a class of nonlinear discrete-time flexible joint robot (DFJR) dynamic system based on artificial neural network (ANN). The DFJR system has a relatively complex nonlinear dynamic and internal states’ estimation of it poses a challenging robotic problem. Multilayer perceptron (MLP) is an important class of feed-forward ANNs that maps set of inputs onto a set of suitable outputs. The ANN under online learning is one of the artificial intelligence methods. Therefore, the MLP neural nonlinear observer is trained online and it is robust in the presence of external and internal uncertainties. The learning method of the intelligent observer is a simple back propagation (BP) algorithm and, furthermore, the learning method of estimation of the link positions and the velocities is BP-developed algorithm. Simulation results show promising performance of the proposed observer in the presence of measurement noise and parameters uncertainties.

[1]  A. Tornambè,et al.  An approximate observer for a class of nonlinear systems , 1989 .

[2]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[3]  Frank Allgöwer,et al.  Observers with impulsive dynamical behavior for linear and nonlinear continuous-time systems , 2007, 2007 46th IEEE Conference on Decision and Control.

[4]  Malek Ghanes,et al.  Observer Design for Nonlinear Systems Under Unknown Time-Varying Delays , 2013, IEEE Transactions on Automatic Control.

[5]  Mrdjan Jankovic,et al.  Observer based control for elastic joint robots , 1995, IEEE Trans. Robotics Autom..

[6]  Heidar Ali Talebi,et al.  Neural Network-Based State Estimation of Nonlinear Systems , 2010 .

[7]  Hassan K. Khalil,et al.  A Nonlinear High-Gain Observer for Systems With Measurement Noise in a Feedback Control Framework , 2013, IEEE Transactions on Automatic Control.

[8]  Heidar Ali Talebi,et al.  Neural Network-Based State Estimation of Nonlinear Systems: Application to Fault Detection and Isolation , 2009 .

[9]  Wei Chen,et al.  Position control of a 2DOF underactuated planar flexible manipulator , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[10]  Yau-Zen Chang,et al.  On the adaptive control of flexible joint robots , 1992, Autom..

[11]  Guang-Hong Yang,et al.  Robust fault detection and isolation for a class of uncertain single output non-linear systems , 2014 .

[12]  Jianbo Su,et al.  Design of a Disturbance Observer for a Two-Link Manipulator With Flexible Joints , 2014, IEEE Transactions on Control Systems Technology.

[13]  M. Spong.  Modeling and Control of Elastic Joint Robots , 1987 .

[14]  Wan Kyun Chung,et al.  Unified external torque-sensing algorithm for flexible-joint robot based on Kalman filter , 2013, 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[15]  R. Ghasemi,et al.  Designing Observer Based Variable Structure Controller for Large Scale Nonlinear Systems , 2013 .

[16]  Antonio Tornambè,et al.  A nonlinear observer for elastic robots , 1988, IEEE J. Robotics Autom..

[17]  Adrian Moise,et al.  Automatic expert system for fuzzy control of robot trajectory in joint space , 2013, 2013 IEEE International Conference on Mechatronics and Automation.

[18]  Katsunari Shibata,et al.  Emergence of flexible prediction-based discrete decision making and continuous motion generation through actor-Q-learning , 2013, 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[19]  Leonid M. Fridman,et al.  Two-Stage Neural Observer for Mechanical Systems , 2008, IEEE Transactions on Circuits and Systems II: Express Briefs.

[20]  Xu Wenfu,et al.  Modeling and simulation study of flexible space robot for capturing large flexible spacecraft , 2013, Proceedings of the 32nd Chinese Control Conference.

[21]  Guang-Zhong Yang,et al.  Design of a multitasking robotic platform with flexible arms and articulated head for Minimally Invasive Surgery , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Hiroshi Kaminaga,et al.  Development of backdrivable hydraulic joint mechanism for knee joint of humanoid robots , 2009, 2009 IEEE International Conference on Robotics and Automation.

[23]  D. Luenberger.  Observing the State of a Linear System , 1964, IEEE Transactions on Military Electronics.

[24]  L. J. Ricalde,et al.  Trajectory tracking via adaptive recurrent control with input saturation , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[25]  Wan Kyun Chung,et al.  External torque-sensing algorithm for flexible-joint robot based on Kalman filter , 2013 .

[26]  Jian Huang,et al.  Nonlinear Disturbance Observer-Based Dynamic Surface Control for Trajectory Tracking of Pneumatic Muscle System , 2014, IEEE Transactions on Control Systems Technology.

[27]  Alin Albu-Schäffer,et al.  State feedback controller for flexible joint robots: a globally stable approach implemented on DLR's light-weight robots , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[28]  P. Tomei.  An observer for flexible joint robots , 1990 .

[29]  Shuzhi Sam Ge,et al.  Adaptive neural network control of flexible joint manipulators in constrained motion , 1998 .

[30]  K. Machida,et al.  PRECISE TELEROBOTIC SYSTEM FOR SPACE EXPERIMENT ON ETS-VII , 1998 .

[31]  Taro Nakamura,et al.  Development of a soft manipulator using a smart flexible joint for safe contact with humans , 2003, Proceedings 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2003).

[32]  Mohammed M'Saad,et al.  Continuous-Discrete Time Observer for a class of MIMO Nonlinear Systems , 2013 .

[33]  J. A. R. Vargas,et al.  Adaptive observer design based on scaling and neural networks , 2013, IEEE Latin America Transactions.

[34]  Lih-Chang Lin,et al.  Control of flexible joint robots via external linearization approach , 1990, J. Field Robotics.

[35]  Petar V. Kokotovic,et al.  An integral manifold approach to the feedback control of flexible joint robots , 1987, IEEE J. Robotics Autom..

[36]  Spyros G. Tzafestas,et al.  High-Level Feedback Control with Neural Networks, Y.H. Kim, F.L. Lewis, World Scientific, Singapore, 1998, ISBN 9810233760, pp. X+216. , 2000 .

[37]  Alexander G. Loukianov,et al.  Real-Time Recurrent Neural State Estimation , 2011, IEEE Transactions on Neural Networks.

[38]  G. Monsees,et al.  Discrete-time sliding mode control , 2002 .

[39]  C. Kravaris,et al.  Time-discretization of nonlinear control systems via Taylor methods , 1999 .

[40]  Mark W. Spong,et al.  On the force control problem for flexible joint manipulators , 1989 .

[41]  Qiang Chen,et al.  Discrete-time sliding mode control coupled with asynchronous sensor fusion for rigid-link flexible-joint manipulators , 2013, 2013 10th IEEE International Conference on Control and Automation (ICCA).