KIT | KIT-Bibliothek | Impressum | Datenschutz

Reinforcement Learning for Speed Control with Feedforward to Track Velocity Profiles in a Real Vehicle

Köpf, Florian; Puccetti, Luca; Rathgeber, Christian; Hohmann, Sören

Abstract (englisch):
Reinforcement learning (RL) for tracking arbitrary trajectories in real control applications with unobserved dynamics is a challenging subject of current research. An example of such an application is given by the speed control of a real car with unobserved longitudinal dynamics. We propose an online RL method, where the RL agent explicitly incorporates information concerning the desired velocity profile by means of a time-varying first order trajectory approximation. Furthermore, missing state information is reconstructed by learning a finite impulse response filter. We apply the presented algorithm in online training of controller parameters in a real car. Our validation results reveal that our proposed method clearly outperforms a controller that uses set points of the desired velocity by means of the resulting velocity tracking performance.

Zugehörige Institution(en) am KIT Institut für Regelungs- und Steuerungssysteme (IRS)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000122267
Erschienen in 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC), September 20 – 23, 2020
Verlag IEEE, Piscataway (NJ)
Bemerkung zur Veröffentlichung F. Köpf and L. Puccetti contributed equally to this work

Die Veranstaltung fand wegen der Corona-Pandemie als Online-Event statt
Schlagwörter Reinforcement Learning, Actor-Critic Learning, Velocity Controller
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page