Machine learning control

Types of problems and tasks

• Control parameter identification: MLC translates to a parameter identification if the structure of the control law is given but the parameters are unknown. One example is the genetic algorithm for optimizing coefficients of a PID controller or discrete-time optimal control.
• Control design as regression problem of the first kind: MLC approximates a general nonlinear mapping from sensor signals to actuation commands, if the sensor signals and the optimal actuation command are known for every state. One example is the computation of sensor feedback from a known full state feedback. A neural network is commonly used technique for this task.
• Control design as regression problem of the second kind: MLC may also identify arbitrary nonlinear control laws which minimize the cost function of the plant. In this case, neither a model, nor the control law structure, nor the optimizing actuation command needs to be known. The optimization is only based on the control performance as measured in the plant. Genetic programming is a powerful regression technique for this purpose.
• Reinforcement learning control: The control law may be continually updated over measured performance changes using reinforcement learning.

Applications

• Altitude control of satellites.
• Building thermal control.
• Feedback turbulence control.
• Remotely operated under water vehicle.
• Many more engineering MLC application are summarized in the review article of PJ Fleming & RC Purshouse.