Reinforcement Learning-based Path Following Control for a Vehicle with Variable Delay in the Drivetrain
Autor: | Jonathan Brembeck, Ricardo de Castro, Jonas Mirwald, Johannes Ultsch |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
Computer science
Payload 010401 analytical chemistry Drivetrain 020206 networking & telecommunications 02 engineering and technology 01 natural sciences Reinforcement Learning 0104 chemical sciences law.invention Control theory Robustness (computer science) law Path (graph theory) 0202 electrical engineering electronic engineering information engineering Hydraulic brake Reinforcement learning Fahrzeug-Systemdynamik Hydraulic machinery Pfadfolgeregelung |
Popis: | In this contribution we propose a reinforcement learning-based controller able to solve the path following problem for vehicles with significant delay in the drivetrain. To efficiently train the controller, a control-oriented simulation model for a vehicle with combustion engine, automatic gear box and hydraulic brake system has been developed. In addition, to enhance the reinforcement learning-based controller, we have incorporated preview information in the feedback state to better deal with the delays. We present our approach of designing a reward function which enables the reinforcement learning-based controller to solve the problem. The controller is trained using the Soft Actor-Critic algorithm by incorporating the developed simulation model. Finally, the performance and robustness is evaluated in simulation. Our controller is able to follow an unseen path and is robust against variations in the vehicle parameters, in our case an additional payload. |
Databáze: | OpenAIRE |
Externí odkaz: |