The present invention relates to a nonlinear approximator (9) for use in a controller (1) for an automatic estimation of an optimal desired trajectory of an autonomous or semi-autonomous vehicle (50) for a constrained nonlinear model predictive controller (8). The approximator (9) is configured to use a learned behavioral model (2) and a learned disturbance model (3), which are encoded within layers of a deep neural network. The behavioral model (2) is responsible for estimating a behavior of a controlled system in different operating conditions and to calculate a desired trajectory. The disturbance model (3) is used for compensating disturbances.
DEEP LEARNING BASED MOTION CONTROL OF A VEHICLE
AUF TIEFENLERNEN BASIERENDE BEWEGUNGSSTEUERUNG EINES FAHRZEUGS
COMMANDE DE MOUVEMENTS D'UN VÉHICULE BASÉE SUR L APPRENTISSAGE PROFOND
2023-07-26
Patent
Elektronische Ressource
Englisch
IPC: | G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |