Reinforcement Learning for Semi-Active Vertical Dynamics Control with Real-World Tests
Open Access
- 12 August 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (16) , 7066
Abstract
In vertical vehicle dynamics control, semi-active dampers are used to enhance ride comfort and road-holding with only minor additional energy expenses. However, a complex control problem arises from the combined effects of (1) the constrained semi-active damper characteristic, (2) the opposing control objectives of improving ride comfort and road-holding, and (3) the additionally coupled vertical dynamic system. This work presents the application of Reinforcement Learning to the vertical dynamics control problem of a real street vehicle to address these issues. We discuss the entire Reinforcement Learning-based controller design process, which started with deriving a sufficiently accurate training model representing the vehicle behavior. The obtained model was then used to train a Reinforcement Learning agent, which offered improved vehicle ride qualities. After that, we verified the trained agent in a full-vehicle simulation setup before the agent was deployed in the real vehicle. Quantitative and qualitative real-world tests highlight the increased performance of the trained agent in comparison to a benchmark controller. Tests on a real-world four-post test rig showed that the trained RL-based controller was able to outperform an offline-optimized benchmark controller on road-like excitations, improving the comfort criterion by about 2.5% and the road-holding criterion by about 2.0% on average.Keywords
Funding Information
- Bundesministerium für Forschung, Technologie und Raumfahrt (01IS20010A)
- DLR basic funding (01IS20010A)
This publication has 30 references indexed in Scilit:
- Modelling and Validation of the TMeasy Tyre Model for Extreme Parking Manoeuvres2022
- Enhancing skyhook for semi-active suspension control via machine learningIFAC Journal of Systems and Control, 2021
- Semi-Active Suspension Control Based on Deep Reinforcement LearningIEEE Access, 2020
- Objectification methods for ride comfortForschung im Ingenieurwesen, 2019
- Explicit model predictive control of semi-active suspension systems using Artificial Neural Networks (ANN)2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Survey and performance evaluation on some automotive semi-active suspension control methods: A comparative study on a single-corner modelAnnual Reviews in Control, 2012
- Batch Reinforcement Learning for semi-active suspension control2009
- Extended Ground-Hook - New Concept of Semi-Active Control of Truck's SuspensionVehicle System Dynamics, 1997
- Continuous action reinforcement learning applied to vehicle suspension controlMechatronics, 1997