WO2025098781 - VERFAHREN UND MASCHINELLE LERNSYSTEM ZUM GENERIEREN VON GESCHWINDIGKEITEN VON FAHRZEUGEN
National phase entry is expected:
Publication Number
WO/2025/098781
Publication Date
15.05.2025
International Application No.
PCT/EP2024/079972
International Filing Date
23.10.2024
Title **
[German]
VERFAHREN UND MASCHINELLE LERNSYSTEM ZUM GENERIEREN VON GESCHWINDIGKEITEN VON FAHRZEUGEN
[English]
METHOD AND MACHINE LEARNING SYSTEM FOR GENERATING SPEEDS OF VEHICLES
[French]
PROCÉDÉ ET SYSTÈME D'APPRENTISSAGE AUTOMATIQUE POUR GÉNÉRER DES VITESSES DE VÉHICULES
Applicants **
ROBERT BOSCH GMBH
Inventors
ZIESCHE, Sebastian
Priority Data
102023211076.8
08.11.2023
DE
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 1880 | |
| EPO | Filing, Examination, Granting | 8113 | |
| Japan | Filing, Examination, Granting | 1998 | |
| South Korea | Filing, Examination, Granting | 1757 | |
| USA | Filing, Examination, Granting | 5340 |
Total:
19,088
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[German]
Verfahren (200) und maschinelles Lernsystem (100) zum Generieren von Geschwindigkeiten von Fahrzeugen, umfassend die Verknüpfung eines ersten generativen Modells (102) für die Sollgeschwindigkeit, wobei das generative Modell (102) keine Kenntnis über Fahrzeuginformationen hat, bzw. mit solchen Informationen trainiert wurde, und eines zweiten physikalischen Modells (104), welches die physikalischen Randbedingungen für die Sollgeschwindigkeit in Form einer Beschränkung der Beschleunigung des Fahrzeugs liefert, und unter Berücksichtigung eines zufällig aus einer Rauschverteilung gezogenen Rauschens (108).[English]
The invention relates to a method (200) and machine learning system (100) for generating speeds of vehicles, comprising the linking of a first generative model (102) for the target speed, wherein the generative model (102) has no knowledge of vehicle information or was not trained with such information, and a second physical model (104) which provides the physical boundary conditions for the target speed in the form of a restriction of the acceleration of the vehicle, and taking into account a noise (108) drawn randomly from a noise distribution.[French]
L'invention concerne un procédé (200) et un système d'apprentissage automatique (100) pour générer des vitesses de véhicules, comprenant la liaison d'un premier modèle génératif (102) pour la vitesse cible, le modèle génératif (102) n'ayant pas de connaissance d'informations de véhicule ou n'ayant pas été entraîné avec de telles informations, et un second modèle physique (104) qui fournit les conditions de limite physique pour la vitesse cible sous la forme d'une limitation de l'accélération du véhicule, et en tenant compte d'un bruit (108) extrait de manière aléatoire d'une distribution de bruit.