Adaptation of a non-linear controller based on Reinforcement Learning

Adaptation of a non-linear controller based on Reinforcement Learning

Khattar, Varun (TU Delft Mechanical, Maritime and Materials Engineering)

Babuska, Robert (mentor)
Shyrokau, Barys (graduation committee)
Celemin Paez, Carlos (graduation committee)

Delft University of Technology

Mechanical Engineering | Vehicle Engineering | Dynamics and Controls

2018-10-31

Closed-loop control systems, which utilize output signals for feedback to generate control inputs, can achieve high performance. However, robustness of feedback control loops can be lost if system changes and uncertainties are too large. Adaptive control combines the traditional feedback structure with providing adaptation mechanisms that adjust a controller for a system with parameter uncertainties by using performance error information on line. Reinforcement learning (RL) is one of the many methods that can be used for adaptive control. The aim of this thesis is to adapt a non-linear Anti-lock Braking System (ABS) controller of a passenger car obtained as a simplified symbolic approximation of the solution to the Bellman equation to model-plant mismatches and process variations. Results for adaptation to dry and wet asphalt have been obtained successfully and have been compared with hand tuned and adaptive proportional-integral (P-I) controllers.

Reinforcement Learning
Adaptive control
Anti-lock braking system

http://resolver.tudelft.nl/uuid:e7ee0f2c-91c4-40d7-bd90-4b5ae61dd54f

Student theses

master thesis

© 2018 Varun Khattar