This paper is concerned with the application of reinforcement learning to the dynamic ride control of an active vehicle suspension system. The study makes key extensions to earlier simulation work to enable on-line implementation of the learning automation methodology using an actual vehicle. Extensions to the methodology allow safe and continuous learning to take place on the road, using a limited instrumentation set. An important new feature is the use of a moderator to set physical limits on the vehicle states. It is shown that the addition of the moderator has little direct effect on the system's ability to learn, and allows learning to take place continuously even when the successful synthesis of a semi-active ride controller is demonstrated.
Moderated reinforcement learning of active and semi-active vehicle suspension control laws
Mäßig verstärktes Lernverfahren bei der Regelung aktiver und semiaktiver Fahrzeugaufhängungen
1996
9 Seiten, 9 Bilder, 4 Tabellen, 13 Quellen
Aufsatz (Zeitschrift)
Englisch
Europäisches Patentamt | 2023
|Microprocessor adaptive control for vehicle semi-active suspension damping
Kraftfahrwesen | 1992
|Semi-active suspension control for a full vehicle model
Kraftfahrwesen | 1991
|