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

Authors:
Boubaker Daachi;Tarek Madani;Abdelaziz Benallegue
Affiliations:
University of Paris East, Laboratoire Image, Signaux & Systèèmes Intelligents (LISSI), 122-124, rue Paul Armangot, 92400 Vitry sur Seine, France;Laboratoire d'Ingénierie des Systèmes de Versailles, 10-12, avenue de l'Europe, 78140 Vélizy, France;Laboratoire d'Ingénierie des Systèmes de Versailles, 10-12, avenue de l'Europe, 78140 Vélizy, France
Venue:
Neurocomputing
Year:
2012

Citing 13
Cited 5

Optimal redundancy control of robot manipulators

International Journal of Robotics Research
Task-priority based redundancy control of robot manipulators

International Journal of Robotics Research
Neuro-Fuzzy Control of Industrial Systems with Actuator Nonlinearities

Neuro-Fuzzy Control of Industrial Systems with Actuator Nonlinearities
A Stable Neuro-Adaptive Controller for Rigid Robot Manipulators

Journal of Intelligent and Robotic Systems
Kinematic Control and Obstacle Avoidance for Redundant Manipulators Using a Recurrent Neural Network

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Inverse Kinematic Solution based on Lyapunov Function for Redundant and non-Redundant Robots

CIRA '97 Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation
A Neural Network Adaptive Controller for End-effector Tracking of Redundant Robot Manipulators

Journal of Intelligent and Robotic Systems
Compensation of velocity and/or acceleration joint saturation applied to redundant manipulator

Robotics and Autonomous Systems
Modeling and adaptive control of redundant robots

Mathematics and Computers in Simulation
Parallel and distributed trajectory generation of redundant manipulators through cooperation and competition among subsystems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Obstacle avoidance for kinematically redundant manipulators using a dual neural network

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Multilayer neural-net robot controller with guaranteed tracking performance

IEEE Transactions on Neural Networks
Gaussian networks for direct adaptive control

IEEE Transactions on Neural Networks

Application of fuzzy inference systems to detection of faults in wireless sensor networks

Neurocomputing
A direct variational method for planning monotonically optimal paths for redundant manipulators in constrained workspaces

Robotics and Autonomous Systems
Synchronized control with neuro-agents for leader-follower based multiple robotic manipulators

Neurocomputing
Hierarchical incorporation of shape and shape dynamics for flying bird detection

Neurocomputing
Genetically evolved action selection mechanism in a behavior-based system for target tracking

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

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.