Adaptive neural controller for redundant robot manipulators and collision avoidance with mobile obstacles

The paper presents a new controller approach applied to redundant robot manipulators constrained by mobile obstacles. The proposed controller is constructed in task space by using optimization strategy, in order to achieve a good trajectory tracking of the end effector even if the obstacles are fixed or mobile. The criterion to be optimized is chosen as the sum of the joint displacements energy and the internal penalty functions that take into account the obstacle positions. Any knowledge on the dynamic model is needed, only its structure. All unknown functions in the robot dynamical model, written in extended Cartesian space, are carried out using multilayer perceptron (MLP) neural networks. The adaptation laws of the neural parameters are obtained via closed loop stability analysis of the system (Lyapunov approach). In order to evaluate the proposed controller performance a 3 DOF robot manipulator evolving in a vertical space constrained by a mobile obstacle is used. The obtained results show its effectiveness.

[1]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[2]  John Baillieul,et al.  Avoiding obstacles and resolving kinematic redundancy , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[3]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[4]  Jun Wang,et al.  A recurrent neural network for minimum infinity-norm kinematic control of redundant manipulators with an improved problem formulation and reduced architecture complexity , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Haizhou Li,et al.  Adaptive learning tracking control of robotic manipulators with uncertainties , 2010 .

[6]  Marek Balazinski,et al.  A hierarchical neuro-fuzzy system to near optimal-time trajectory planning of redundant manipulators , 2008, Eng. Appl. Artif. Intell..

[7]  Boubaker Daachi,et al.  A Neural Network Adaptive Controller for End-effector Tracking of Redundant Robot Manipulators , 2006, J. Intell. Robotic Syst..

[8]  Charles A. Klein,et al.  Review of pseudoinverse control for use with kinematically redundant manipulators , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[9]  O. Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[10]  Nagarajan Sukavanam,et al.  Neural network-based nonlinear tracking control of kinematically redundant robot manipulators , 2011, Math. Comput. Model..

[11]  Shugen Ma,et al.  A Dynamic Approach to Real-Time Obstacle Avoidance Control of Redundant Manipulators , 1996 .

[12]  Toshio Tsuji,et al.  Parallel and distributed trajectory generation of redundant manipulators through cooperation and competition among subsystems , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[13]  A. Ramdane-Cherif,et al.  Inverse kinematic solution based on Lyapunov function for redundant and non-redundant robots , 1997, Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA'97. 'Towards New Computational Principles for Robotics and Automation'.

[14]  Abdelaziz Benallegue,et al.  A Stable Neuro-Adaptive Controller for Rigid Robot Manipulators , 1997, J. Intell. Robotic Syst..

[15]  Sung-Woo Kim,et al.  Redundancy resolution of robot manipulators using optimal kinematic control , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[16]  Giuseppe Oriolo,et al.  Control of redundant robots on cyclic trajectories , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[17]  Yoshihiko Nakamura,et al.  Optimal Redundancy Control of Robot Manipulators , 1987 .

[18]  Frank L. Lewis,et al.  Neuro-Fuzzy Control of Industrial Systems with Actuator Nonlinearities , 1987 .

[19]  Jun Wang,et al.  A dual neural network for bi-criteria kinematic control of redundant manipulators , 2002, IEEE Trans. Robotics Autom..

[20]  Yunong Zhang,et al.  Obstacle avoidance for kinematically redundant manipulators using a dual neural network , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  T. Shamir,et al.  Repeatability of redundant manipulators: mathematical solution of the problem , 1988 .

[22]  S. Sastry,et al.  Dynamic control of redundant manipulators , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[23]  Amar Ramdane-Cherif.  Invesion des modeles geometrique et cinematique d'un robot redondant : une solution neuronale adaptative , 1998 .

[24]  Frank L. Lewis,et al.  Robot Manipulator Control: Theory and Practice , 2003 .

[25]  Maarouf Saad,et al.  Modeling and adaptive control of redundant robots , 2006, Math. Comput. Simul..

[26]  Maria da Graça Marcos,et al.  Trajectory planning of redundant manipulators using genetic algorithms , 2009 .

[27]  Bojan Nemec,et al.  Compensation of velocity and/or acceleration joint saturation applied to redundant manipulator , 2007, Robotics Auton. Syst..

[28]  T. Yoshikawa,et al.  Task-Priority Based Redundancy Control of Robot Manipulators , 1987 .

[29]  Jun Wang,et al.  Kinematic Control and Obstacle Avoidance for Redundant Manipulators Using a Recurrent Neural Network , 2001, ICANN.