WO2021175821A1 - Procédé mis en œuvre par ordinateur pour le calcul d'itinéraires d'un véhicule à moteur à conduite autonome, procédé de conduite d'un véhicule à moteur à conduite autonome, produit programme informatique et véhicule à moteur - Google Patents
Procédé mis en œuvre par ordinateur pour le calcul d'itinéraires d'un véhicule à moteur à conduite autonome, procédé de conduite d'un véhicule à moteur à conduite autonome, produit programme informatique et véhicule à moteur Download PDFInfo
- Publication number
- WO2021175821A1 WO2021175821A1 PCT/EP2021/055126 EP2021055126W WO2021175821A1 WO 2021175821 A1 WO2021175821 A1 WO 2021175821A1 EP 2021055126 W EP2021055126 W EP 2021055126W WO 2021175821 A1 WO2021175821 A1 WO 2021175821A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- motor vehicle
- driving motor
- route
- autonomously driving
- computer
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Definitions
- COMPUTER-IMPLEMENTED METHOD FOR ROUTING CALCULATION FOR AN AUTONOMOUSLY DRIVING MOTOR VEHICLE METHOD FOR DRIVING AN AUTONOMOUSLY DRIVING MOTOR VEHICLE
- a computer-implemented method for route calculation for an autonomously driving motor vehicle a method for driving an autonomously driving motor vehicle, a computer program product and a motor vehicle are described here.
- the expected duration of a route from a starting point to a destination point can be calculated as a prognosis.
- the route itself consists of a sequence of several route segments and nodes between the route segments.
- the route segments and nodes belonging to the route are selected from a database in which a geographical area is described by a network of nodes and route segments connecting the nodes.
- the route segments can be characterized by a travel time that describes the time it takes to drive through the route segment.
- the travel time for characterizing a route segment is usually calculated from the length of the route segment and a forecast driving speed.
- the predicted driving speed can in turn depend on the road type of the respective route segment, for example Motorway or country road, depend on the current traffic situation and / or on the preset vehicle type, for example faster cars or trucks.
- the travel time from the starting point to the destination point then results from the sum of all travel times that are required to drive through the route segments belonging to the route. For many routes, the known methods for calculating the travel time give relatively exact results.
- a method for operating a navigation system for calculating the expected duration of a route from a starting point to a destination point is known, the route consisting of a sequence of route segments and nodes between the route segments, which are based on a route calculation method a database, in which a geographical area is described by a network of nodes and route segments connecting the nodes, is selected, each route segment being characterized by a travel time which describes the duration for driving through the route segment, with at least one node at least one waiting time is assigned, and wherein the expected travel time of the analyzed route is calculated by adding all the travel times of the route segments lying on the route and all waiting times of the nodes lying on the route.
- Autonomous vehicles on the other hand, have a different driving behavior than human drivers. This requires different average speeds on some routes and possibly different waiting times at intersections. As a result, conventional route calculation algorithms for autonomously driving motor vehicles are not sufficiently accurate if precise predictions about travel times and / or arrival times are to be achieved.
- the task arises of developing computer-implemented methods for route calculation for an autonomously driving motor vehicle, methods for driving an autonomously driving motor vehicle, computer program products and motor vehicles of the type mentioned in such a way that a more precise prediction of a driving time and / or better route planning for autonomous moving motor vehicles is possible.
- the object is achieved by a computer-implemented method for route calculation for an autonomously driving motor vehicle according to claim 1, a method for Driving an autonomously driving motor vehicle according to the independent claim 10, a computer program product according to the independent claim 12 and a motor vehicle according to the independent claim 13. Further developments and developments are the subject of the dependent claims.
- a computer-implemented method for calculating routes for an autonomously driving motor vehicle is described below, with the following method steps: a) providing a starting point and a destination in a real area of use for the autonomously driving motor vehicle; b) Providing a simulation environment with simulation parameters, the simulation environment having map data of the real existing area of use; c) Provision of real-time traffic data of the real existing area of application and re-enactment of a traffic situation in the simulation environment on the basis of the real-time traffic data; d) providing a driving algorithm which is set up to simulate a behavior of the autonomously driving motor vehicle in the simulation environment; e) providing an interface for data output of data obtained from the simulation environment; f) using a route calculation module to calculate a route between the starting point and the destination, the route calculation module requesting at least one parameter from the interface for at least one section of the route in the operational area, g) simulating at least one journey of the autonomously driving motor vehicle along the section of the route Simulation environment using the driving algorithm and determining the at
- the route calculation module can carry out a route calculation algorithm.
- the method thus provides that a route calculation module instead of parameters that are derived from human drivers and / or autonomously driving motor vehicles from the real-time traffic data to take parameters that have been or are determined by simulations of journeys of the autonomously driving motor vehicle along the route sections checked by the route calculation module. This can be, for example, average speeds along the tested route sections, turning times, etc.
- the route calculation module uses a Dijkstra algorithm, the at least one parameter being an edge weight.
- a Dijkstra algorithm solves the problem of the shortest path from a given starting node to a given destination node.
- the Dijkstra algorithm examines a plurality of possible paths along a network of nodes. Different paths have different lengths or so-called edge weights. These edge weights can also represent a time period that is necessary to get from one node to the next.
- the adjustment of the traffic situation in the simulation environment is carried out by agents in the simulation environment.
- agents By using agents, a realistic simulation of the traffic situation can be carried out, since average speeds can structure.
- agents in the simulation environment can take the place of the real road users.
- the agents are simulated with the aid of an optimization algorithm in such a way that the real-time traffic data are simulated by the agents.
- the start location is determined by a real location of the autonomously driving motor vehicle, the destination location being determined by a user of the autonomously driving motor vehicle, a control center and / or by a computing unit in the autonomously driving motor vehicle will.
- the starting point can be determined, for example, from a current location of the motor vehicle by means of GPS or other location methods.
- the destination can either be specified by the user or by a control center (for example in the case of robot taxis, autonomous ambulances, etc.). However, the destination can also be specified by the computing unit itself, for example if the energy storage device of the motor vehicle is empty and the energy storage device needs to be refilled (e.g. by refueling or charging).
- the simulation environment is varied in the area of the requested route section and the simulation of the journey of the autonomously driving motor vehicle is carried out in step g), the parameter being a weighted parameter from the simulations carried out on the requested route section is determined.
- the route calculation module is carried out in the autonomously driving motor vehicle and / or in at least one computing unit arranged remotely from the motor vehicle.
- the corresponding data can be reused for a plurality of motor vehicles. This reduces the total computing effort and thus energy consumption.
- the motor vehicle is independent of a connection to the remote processing unit.
- the simulation is carried out in the autonomously driving motor vehicle and / or in at least one computing unit arranged remotely from the autonomously driving motor vehicle.
- the corresponding data can be reused for a plurality of motor vehicles by calculation in a computing unit arranged remotely from the motor vehicle. This reduces the total computing effort.
- the motor vehicle By calculating in the motor vehicle, the motor vehicle becomes independent of a connection to the remote processing unit.
- the route calculation module calculates a shortest, fastest or most energy-efficient route.
- the fastest route can only be slightly faster than the next faster route, but it can be considerably further or consume considerably more energy.
- a first independent subject relates to a device for calculating routes for an autonomously driving motor vehicle, the device having means for a) providing a starting point and a destination in a real-life area of use of the autonomously driving motor vehicle, b) providing a simulation environment with simulation parameters , wherein the simulation environment has map data of the real existing application area, c) providing real-time traffic data of the real existing application area and re-enacting a traffic situation in the simulation environment using the real-time traffic data, d) providing a driving algorithm that is set up to determine a behavior of the to simulate autonomously driving motor vehicles in the simulation environment; e) Providing an interface for data output of data obtained from the simulation environment are set up, wherein f) a route calculation module is provided for calculating a route between the star tort and the destination, the route calculation module being set up to request at least one parameter for at least one route section in the area of use from the interface, g) with means for performing a simulation at least one Driving the autonomously driving motor vehicle along the route section in the
- the route calculation module has a Dijkstra algorithm, the at least one parameter being an edge weight.
- means for carrying out a simulation are set up to adjust the traffic situation in the simulation environment by agents in the simulation environment.
- the means for carrying out a simulation are set up to simulate the agents with the aid of an optimization algorithm in such a way that the agents simulate the real-time traffic data.
- the start location is determined by a real location of the autonomously driving motor vehicle, the destination location being determined by a user of the autonomously driving motor vehicle, a center and / or by a computing unit in the autonomously driving motor vehicle is.
- means for varying the simulation environment in the area of the requested route section are provided, the means for performing a simulation being set up to simulate the journey of the autonomously driving motor vehicle in step g), a weighted parameter being determined as the parameter from the simulations carried out on the requested route section.
- the route calculation module is arranged in the autonomously driving motor vehicle and / or in at least one computing unit arranged remotely from the motor vehicle.
- the means for performing a simulation are arranged in the autonomously driving motor vehicle and / or in at least one computing unit arranged remotely from the autonomously driving motor vehicle.
- the route calculation module is set up to calculate a shortest, fastest or most energy-efficient route.
- Another independent subject relates to a method for driving an autonomously driving motor vehicle from a starting location to a destination, a starting location of the motor vehicle and a destination of the motor vehicle being specified, a route from the starting location to the destination being calculated using the method of the type described above.
- a corresponding autonomously driving motor vehicle can arrive at the destination at a precisely determined time.
- the route is calculated in the at least one computing unit arranged remotely from the autonomously driving motor vehicle and transmitted to the autonomously driving motor vehicle.
- the corresponding data can be reused for a plurality of motor vehicles by calculation in a computing unit arranged remotely from the motor vehicle. This reduces the total computational effort. As a result of computation in the motor vehicle, the motor vehicle becomes independent of a connection to the remote processing unit.
- Another independent subject matter relates to a device for driving an autonomously driving motor vehicle from a starting point to a destination, a starting point of the motor vehicle and a destination of the motor vehicle being specified, a route from the starting point to the destination being calculated using the device of the type described above .
- the route is calculated in the at least one computing unit arranged remotely from the autonomously driving motor vehicle and transmitted to the autonomously driving motor vehicle.
- Another independent subject matter relates to a computer program product with a computer-readable storage medium on which instructions are embedded which, when executed by at least one computing unit, have the effect that the at least computing unit is set up to carry out the method of the aforementioned type.
- the method can be carried out on one or more processing units distributed so that certain method steps are carried out on one processing unit and other process steps are carried out on at least one other processing unit, with calculated data being able to be transmitted between the processing units if necessary.
- Another independent subject matter relates to a motor vehicle with a computer program product of the type described above.
- FIG. 1 shows a plan view of an autonomously driving motor vehicle
- FIG. 2 shows an illustration of a system for calculating a route for the autonomous moving motor vehicle from FIG. 1;
- 3 shows a road map of an operational area with real-time traffic information
- 4A shows a simulation environment of an area of use
- FIG. 4B shows an enlargement of a section from FIG. 4A
- FIG. 5 shows a flowchart of a method for route calculation.
- Fig. 1 shows a motor vehicle 2, which is set up for automated or autonomous driving.
- the motor vehicle 2 has a control unit 4 with a computing unit 6 and a memory 8.
- a computer program product is stored in the memory 8 and is described in more detail below in connection with FIGS.
- the control unit 4 is connected, on the one hand, to a number of environmental sensors that allow the current position of the motor vehicle 2 and the respective traffic situation to be recorded. These include environmental sensors 10, 11 at the front of the motor vehicle 2, environmental sensors 12, 13 at the rear of the motor vehicle 2, a camera 14 and a GPS module 16.
- the environmental sensors 10 to 13 can, for example, radar, lidar and / or Include ultrasonic sensors.
- sensors for detecting the state of the motor vehicle 2 are provided, including wheel speed sensors 16, acceleration sensors 18 and pedal sensors 20, which are connected to the control unit 4. With the aid of this motor vehicle sensor system, the current state of motor vehicle 2 can be reliably detected.
- the computing unit 6 has this in the memory 8
- the stored computer program product is loaded and executed.
- the computing unit 6 decides on the control of the motor vehicle 2, which the computing unit 6 would achieve by intervening in the steering 22, engine control 24 and brakes 26, which are each connected to the control unit 4.
- Data from sensors 10 to 20 are continuously temporarily stored in memory 8 and discarded after a predetermined period of time so that these environmental data can be available for further evaluation.
- FIG. 2 shows an illustration of a system for calculating a route for the autonomously driving motor vehicle 2 from FIG. 1.
- a server 28 for acquiring, providing and transmitting real-time traffic data is connected to a simulation module 32 via a network 30.
- the simulation module 32 is connected to a route calculation module 34 via an interface 33.
- the server 28 can also be connected to the route calculation module 34 for the purpose of detecting, providing and transmitting real-time traffic data.
- simulations of a virtual representation of the autonomously driving motor vehicle 2 are carried out on the basis of map data of a real application area.
- the simulations are used to map the driving behavior of the autonomously driving motor vehicle 2 as realistically as possible under current traffic conditions and thereby to generate parameters that can be used by the route calculation module 34 to calculate the best route according to the criteria set.
- the route calculation module 34 checks various routes within the deployment area for the relevant parameters, for example time, energy consumption and / or distance.
- edge geometry weights are required that represent virtual lengths between two nodes.
- the simulation module 32 and / or the route calculation module 34 can be arranged in the autonomously driving motor vehicle 2 or remotely, for example on computers in one or more data centers.
- the server 28 for recording and transmitting real-time traffic data can transmit the corresponding data in various forms, for example as average speeds along certain route sections, waiting times at traffic nodes and / or as movement profiles of individual road users, for example drivers of motor vehicles, motorcycles or Pedestrians.
- the server 28 can be connected to the simulation module 32 and to the route calculation module 34 (shown in dashed lines) for the acquisition and transmission of real-time traffic data.
- the simulation module 32 can be set up to continue to use corresponding edge weights for various simulations of different autonomously driving motor vehicles that are to drive on a corresponding route section under similar conditions.
- FIG. 3 shows a road map 36 of a real existing operational area 37.
- the road map 36 of the operational area 37 has traffic flow information relating to the traffic flow on different roads.
- This traffic flow information is real-time information that can be provided via various services. Such real-time information can be determined, for example, from cell phone location data, vehicle navigation data, camera recordings from traffic monitoring cameras and the like.
- individual roads are marked on the road map 36 of the operational area 37 with slow-moving traffic 38 (shown in dashed lines) or heavily slow-moving traffic 40 (shown in solid lines).
- Slow traffic can be defined as traffic that flows at an average speed of less than 20 km / h
- very slow traffic can be defined as traffic that flows at an average speed of less than 5 km / h.
- FIGS. 4A, B show a simulation environment 42 of the road map 36 of the operational area 37, FIG. 4B showing an enlarged section from FIG. 4A.
- the road network of the road map 36 in the operational area 37 is mapped over a large area between a starting point S and a destination Z, so that several possible routes between starting point S and destination Z are possible.
- Real-time traffic data are integrated for the roads shown in the simulation environment 42, that is to say congested traffic 38 and heavily congested traffic 40.
- the present mission is selected parallel to the driving task of the autonomously driving motor vehicle 2, namely to drive the simulated motor vehicle 2 along a specific route from a starting point S to a destination Z.
- FIG. 4B shows an enlargement of an area surrounding a road intersection 44 within the simulation environment 42.
- agents 46.1 to 46.8 are used, which are moved in an optimized manner by means of an optimization method in such a way that the real-time traffic data are realistically simulated.
- the autonomously driving motor vehicle 2 is among the agents 46.1 to 46.8 and is controlled according to the driving algorithm it uses in such a way that it determines the edge weights requested by the route calculation module 34 for a specific section by driving the route.
- a time t for traveling the section is measured and returned to the route calculation algorithm of the route calculation module 34 as an edge weight parameter.
- the corresponding edge weights can be calculated accordingly for all requested sections, so that the route calculation module 34 can calculate the best possible route for the autonomously driving motor vehicle 2.
- 5 shows a flow chart of the method.
- real-time traffic data a simulation environment based on map data of an area of use of the autonomously driving motor vehicle 2 and a requested destination based on the current starting point of the motor vehicle 2 are initially provided.
- the route calculation module 34 queries the edge weights for different route sections in the simulation environment.
- a simulation is then carried out on the requested route sections for a predetermined number of repetitions n in the simulation environment 42, the traffic data being varied between the repetitions so that the driving algorithm of the autonomously driving motor vehicle 2 is always exposed to different traffic situations.
- the corresponding edge weights can be averaged or weighted. Edge weights from simulations that are very close to the real-time traffic data for the corresponding route section can be weighted more heavily than edge weights that are further away from the real-time traffic data.
- the correspondingly weighted edge weight is transferred to the route calculation module and the route calculation module can calculate the route.
Abstract
L'invention concerne un procédé mis en œuvre par ordinateur pour un véhicule à conduite autonome qui comprend les étapes suivantes : Fournir un lieu de départ et un lieu d'arrivée dans un domaine d'application existant réellement du véhicule, fournir un environnement de simulation ayant des paramètres de simulation, fournir des données de circulation en temps réel et ajuster une position de circulation dans l'environnement de simulation au moyen des données de circulation en temps réel, fournir un algorithme de conduite qui simule un comportement du véhicule à moteur à conduite autonome, disposer d'une interface destinée à fournir des données provenant de l'environnement de simulation, utiliser un module de calcul d'itinéraires pour calculer un itinéraire entre le lieu de départ et le lieu d'arrivée, le module de calcul d'itinéraires demandant à l'interface au moins un paramètre concernant au moins une section de trajet dans le domaine d'application, simuler au moins un trajet du véhicule à moteur à conduite autonome le long de la section de trajet dans l'environnement de simulation et déterminer ledit au moins un paramètre demandé et transmettre ledit au moins un paramètre au module de calcul d'itinéraires par l'intermédiaire de l'interface, calculer un itinéraire entre un lieu de départ et un lieu d'arrivée au moyen dudit au moins un paramètre, par l'algorithme de calcul d'itinéraires.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102020202650.5A DE102020202650A1 (de) | 2020-03-02 | 2020-03-02 | Computerimplementiertes Verfahren zur Routenberechnung für ein autonom fahrendes Kraftfahrzeug, Verfahren zum Fahren eines autonom fahrenden Kraftfahrzeugs, Computerprogrammprodukt sowie Kraftfahrzeug |
DE102020202650.5 | 2020-03-02 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021175821A1 true WO2021175821A1 (fr) | 2021-09-10 |
Family
ID=74856847
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2021/055126 WO2021175821A1 (fr) | 2020-03-02 | 2021-03-02 | Procédé mis en œuvre par ordinateur pour le calcul d'itinéraires d'un véhicule à moteur à conduite autonome, procédé de conduite d'un véhicule à moteur à conduite autonome, produit programme informatique et véhicule à moteur |
Country Status (2)
Country | Link |
---|---|
DE (1) | DE102020202650A1 (fr) |
WO (1) | WO2021175821A1 (fr) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230159033A1 (en) * | 2021-11-19 | 2023-05-25 | Motional Ad Llc | High fidelity data-driven multi-modal simulation |
DE102022118631A1 (de) | 2022-07-26 | 2024-02-01 | Dr. Ing. H.C. F. Porsche Aktiengesellschaft | Verfahren, System und Computerprogrammprodukt zur Validierung eines Fahrerassistenzsystems (ADAS) und/oder eines automatisierten Fahrsystems (ADS) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19856704A1 (de) * | 1998-12-09 | 2000-06-21 | Daimler Chrysler Ag | Verfahren und Vorrichtung zur Fahrzeugzielführung und/oder Reisezeitschätzung |
DE102007053215A1 (de) | 2007-11-06 | 2009-05-07 | Navigon Ag | Verfahren zum Betrieb eines Navigationssystems |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11092446B2 (en) | 2016-06-14 | 2021-08-17 | Motional Ad Llc | Route planning for an autonomous vehicle |
DE102018217004A1 (de) | 2017-10-12 | 2019-04-18 | Honda Motor Co., Ltd. | Autonome Fahrzeugstrategiegenerierung |
DE102017124954B3 (de) | 2017-10-25 | 2019-04-18 | Dr. Ing. H.C. F. Porsche Aktiengesellschaft | Verfahren zum Betrieb eines selbstfahrenden Kraftfahrzeugs |
-
2020
- 2020-03-02 DE DE102020202650.5A patent/DE102020202650A1/de active Pending
-
2021
- 2021-03-02 WO PCT/EP2021/055126 patent/WO2021175821A1/fr active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19856704A1 (de) * | 1998-12-09 | 2000-06-21 | Daimler Chrysler Ag | Verfahren und Vorrichtung zur Fahrzeugzielführung und/oder Reisezeitschätzung |
DE102007053215A1 (de) | 2007-11-06 | 2009-05-07 | Navigon Ag | Verfahren zum Betrieb eines Navigationssystems |
Non-Patent Citations (2)
Title |
---|
BEST ANDREW ET AL: "AutonoVi-Sim: Autonomous Vehicle Simulation Platform with Weather, Sensing, and Traffic Control", 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), IEEE, 18 June 2018 (2018-06-18), pages 1161 - 11618, XP033475447, DOI: 10.1109/CVPRW.2018.00152 * |
BROGLE CRAIG ET AL: "Hardware-in-the-Loop Autonomous Driving Simulation Without Real-Time Constraints", IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, IEEE, vol. 4, no. 3, 1 September 2019 (2019-09-01), pages 375 - 384, XP011742974, ISSN: 2379-8858, [retrieved on 20190826], DOI: 10.1109/TIV.2019.2919457 * |
Also Published As
Publication number | Publication date |
---|---|
DE102020202650A1 (de) | 2021-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102016122402A1 (de) | Verfahren und vorrichtung zur vorhersage eines kraftstoffverbrauchs und zur kostenschätzung über schwarmabtastung in einem fahrzeugnavigationssystem | |
DE102011083677A1 (de) | Prognose einer Verkehrssituation für ein Fahrzeug | |
EP3005338B1 (fr) | Système d'aide à la conduite contenant des informations additionnelles complétant une carte routière | |
AT510101B1 (de) | Verfahren zur computerbasierten Erzeugung eines Fahrzyklus-Datensatzes und eines Längsprofil-Datensatzes sowie Verfahren zum Testen eines Kraftfahrzeuges | |
EP3970077A1 (fr) | Procédé pour l'entraînement d'au moins un algorithme pour un appareil de commande d'un véhicule automobile, produit de programme informatique, véhicule automobile ainsi que système | |
DE102016012465B4 (de) | Verfahren zur Bestimmung einer Änderung im auf ein Kraftfahrzeug wirkenden Luftwiderstand | |
DE102018128398B3 (de) | Verfahren zum Vorhersagen des Verhaltens eines Umgebungsobjektes und Fahrerassistenzsystem | |
DE102011104838A1 (de) | Erzeugen von Fahrtroutenverfolgungen in einem Navigationssystem unter Verwendung eines Wahrscheinlichkeitsmodells | |
WO2021175821A1 (fr) | Procédé mis en œuvre par ordinateur pour le calcul d'itinéraires d'un véhicule à moteur à conduite autonome, procédé de conduite d'un véhicule à moteur à conduite autonome, produit programme informatique et véhicule à moteur | |
DE102015223656A1 (de) | Fahrerassistenzsystem und -Verfahren zur Fahrspurempfehlung | |
DE102016207276A1 (de) | Verfahren zur Freigabe einer Fahrfunktion in einem Fahrzeug | |
Stojčić | Application of ANFIS model in road traffic and transportation: a literature review from 1993 to 2018 | |
DE102022101233A1 (de) | Verkehrssimulation und strassennetzmodellierung für autonome fahrzeuge | |
DE102021105159A1 (de) | Erfassung von fahrzeugen und reaktion darauf | |
DE102020210962A1 (de) | Computerimplementiertes Verfahren und Rechnersystem zum Erzeugen von Eingangsparametern für eine Simulation | |
DE102017218383A1 (de) | Verfahren und Vorrichtung zum Ermitteln eines Reibwertes einer Fahrbahn | |
WO2020020621A1 (fr) | Procédé et dispositif d'estimation de l'autonomie pour un véhicule | |
Prokudin et al. | Development of vehicle speed forecasting method for intelligent highway transport system | |
DE102021129166A1 (de) | Verbesserte dimensionierung von komponenten | |
Haberl et al. | Simulation assisted impact analyses of automated driving on motorways for different levels of automation and penetration | |
EP3665057B1 (fr) | Procédé et dispositif pour déterminer un coefficient de frottement d'une chaussée | |
DE102017214094A1 (de) | Verfahren und Vorrichtung zum Ermitteln eines Reibwertes einer Fahrbahn | |
DE102017007468A1 (de) | Verfahren zum Betrieb eines Fahrzeugs | |
EP3665059B1 (fr) | Procédé et dispositif pour déterminer le coefficient de frottement d'une chaussée | |
DE112022000970T5 (de) | Verarbeitungsvorrichtung, verarbeitungsverfahren, verarbeitungsprogramm und verarbeitungssystem |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21709652 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21709652 Country of ref document: EP Kind code of ref document: A1 |