Some implementations of the disclosure are directed to reducing or removing time lag in vehicle velocity prediction by training a model for vehicle velocity prediction using labeled features that provide indication of a feature associated with a vehicle acceleration or deacceleration event. In one implementation, a method includes: receiving multiple time series datasets, each of the time series datasets including sensor data, GPS data, and vehicle state data collected over time; extracting features from each of the time series datasets that are indicative of a future velocity of a vehicle; labeling the extracted features of each of the time series datasets to indicate vehicle acceleration or deacceleration events; and after labeling the extracted features of each of the time series datasets, using at least a subset of the extracted and labeled time series datasets to train a machine learning model that predicts vehicle velocity some time into the future.
A VEHICLE VELOCITY PREDICTOR USING NEURAL NETWORKS BASED ON V2X DATA AUGMENTATION TO ENABLE PREDICTIVE OPTIMAL CONTROL OF CONNECTED AND AUTOMATED VEHICLES
FAHRZEUGGESCHWINDIGKEITSPRÄDIKTOR MIT NEURONALEN NETZEN AUF DER GRUNDLAGE VON V2X-DATENVERSTÄRKUNG ZUR ERMÖGLICHUNG EINER VORAUSSCHAUENDEN OPTIMALEN STEUERUNG VON VERBUNDENEN UND AUTOMATISIERTEN FAHRZEUGEN
PRÉDICTEUR DE VITESSE DE VÉHICULE UTILISANT DES RÉSEAUX NEURONAUX REPOSANT SUR UNE AUGMENTATION DE DONNÉES V2X POUR PERMETTRE UNE COMMANDE OPTIMALE PRÉDICTIVE DE VÉHICULES CONNECTÉS ET AUTOMATISÉS
2022-07-13
Patent
Electronic Resource
English
European Patent Office | 2020
|European Patent Office | 2020
|European Patent Office | 2020
|