Piecewise human learning control for dynamically stable systems

The purpose of this work is to design a piecewise human learning control strategy for the autonomous control of dynamically stable systems in the following two cases. One case is in a single control process, the learning model is built up by combining some local neural networks. The other is that a desirable control target consists of some small control tasks which can be realized by human learning controllers individually. By estimating the stability region, we can guarantee the successful switch between two connected control pieces.

Authors

• Yongsheng Ou
• Yangsheng Xu

Keywords

• Humans
• Control systems
• Neural networks
• Vehicle dynamics
• Uncertainty
• Automatic control
• Switches
• Nonlinear dynamical systems
• Nonlinear control systems
• Robots
• Human Learning
• Learning Control
• Neural Network
• Control Strategy
• Control Target
• Autonomic Control
• Control System
• System Dynamics
• Support Vector Machine
• Artificial Neural Network
• Control Input
• Hidden Markov Model
• Kernel Function
• Lyapunov Function
• Error Range
• Operating Region
• Polynomial Kernel
• Range Of Degrees
• Support Vector Machine Learning
• Structural Uncertainty
• Iterative Learning Control
• System Control Input
• Neural Network Control
• Domain Of Attraction
• Neighborhood Of The Origin
• Pendulum System
• Training Data
• Repeat Steps
• Human Experts
• Off-line Training