Neural network adaptive robust trajectory tracking method and controller
An adaptive robust, trajectory tracking technology, applied in the direction of adaptive control, general control system, control/adjustment system, etc., can solve the problems of poor control effect and poor stability
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2015-07-29
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of robot trajectory tracking control, and relates to a neural network self-adaptive robust trajectory tracking method and a controller. Background technique
[0002] When the structure of the robot is determined and the parameters are known, the complete dynamic characteristics of the system can be described by the dynamic model, so that various automatic control theories can be applied to design a model-based controller to realize the trajectory tracking control of the robot, so that the robot's position, Variables such as velocity and acceleration have ideal tracking conditions. However, robot dynamics are actually highly nonlinear and uncertain systems. Therefore, dealing with the nonlinear uncertainty of the system is a very critical research content in the trajectory tracking control of the robot.
[0003] There are two basic solutions for robots with uncertainties such as modeling errors, external di...
Examples
Embodiment Construction
[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.
[0074] The example of the present invention combines neural network with robust adaptive control, and proposes an adaptive robust trajectory tracking control strategy based on neural network for uncertain robots. Firstly, the nominal part of the trajectory tracking system is obtained through the PD controller, and then the uncertain items of the trajectory tracking system are obtained through the neural network, and then the adaptive robust controller is used to reduce the approximation error of the neural network, in which the adaptive law is used for Tuning of Uncertain Parameters for Robust Controllers.
[0075] Uncertain robots are those that have unmodeled dynam...