Matrix analysis
On the adaptive control of robot manipulators
International Journal of Robotics Research
Theory of Robot Control
Adaptive Neural Network Control of Robotic Manipulators
Adaptive Neural Network Control of Robotic Manipulators
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Sliding Mode Adaptive Neural-Network Control for Nonholonomic Mobile Modular Manipulators
Journal of Intelligent and Robotic Systems
IEEE Transactions on Robotics
Window-shaped obstacle avoidance for a redundant manipulator
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Multilayer neural-net robot controller with guaranteed tracking performance
IEEE Transactions on Neural Networks
Control of a nonholonomic mobile robot using neural networks
IEEE Transactions on Neural Networks
Neural-network control of mobile manipulators
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
This paper investigates self-motion control of redundant nonholonomic mobile manipulators, to execute multiple secondary tasks including tip-over prevention, singularity removal, obstacle avoidance and physical limits escape. An extended gradient projection method (EGPM) is proposed to determine self-motion directions, and a real-time fuzzy logic self-motion planner (FLSMP) is devised to generate the corresponding self-motion magnitudes. Unlike the task-priority allocation method and the extended Jacobian method, the proposed scheme is simple to implement and is free from algorithm singularities. The proposed dynamic model is established with consideration of nonholonomic constraints of the mobile platform, interactive motions between the mobile platform and the onboard manipulator, as well as self-motions allowed by redundancy of the entire robot. Furthermore, a robust adaptive neural-network controller (RANNC) is developed to accomplish multiple secondary tasks without affecting the primary one in the workspace. The RANNC does not rely on precise prior knowledge of dynamic parameters and can suppress bounded external disturbance effectively. In addition, the RANNC does not require any off-line training and can ensure the control performance by online adjusting the neural-network parameters through adaptation laws. The effectiveness of the proposed algorithm is verified via simulations on a three-wheeled redundant nonholonomic mobile manipulator.