DE102018008024A1 - Method for assessing a traffic situation - Google Patents
Method for assessing a traffic situation Download PDFInfo
- Publication number
- DE102018008024A1 DE102018008024A1 DE102018008024.3A DE102018008024A DE102018008024A1 DE 102018008024 A1 DE102018008024 A1 DE 102018008024A1 DE 102018008024 A DE102018008024 A DE 102018008024A DE 102018008024 A1 DE102018008024 A1 DE 102018008024A1
- Authority
- DE
- Germany
- Prior art keywords
- traffic situation
- vehicle
- predicted
- sensor system
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
- B60W2050/0014—Adaptive controllers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/05—Big data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
Die Erfindung betrifft ein Verfahren zur Bewertung einer Verkehrssituation für ein zumindest teilautonom betriebenes Fahrzeug. Erfindungsgemäß wird ein künstliches neuronales Netzwerk (2) mit während einer unkritischen Verkehrssituation (V), welche nicht zu einem Unfall des Fahrzeugs und/oder nicht zu einem manuellen Eingriff eines Fahrers während des zumindest teilautonomen Betriebs des Fahrzeugs geführt hat, mittels einer fahrzeugeigenen Umgebungssensorik (3) erfassten Daten (D) trainiert. Mittels des trainierten künstlichen neuronalen Netzwerks (2) wird eine zukünftige Verkehrssituation (V) prädiziert, wobei bei einer signifikanten Abweichung einer real auftretenden Verkehrssituation (V) von der prädizierten Verkehrssituation (V) auf eine kritische Verkehrssituation (V) geschlossen wird und bei Vorliegen einer kritischen Verkehrssituation (V) eine Intensität einer mittels der fahrzeugeigenen Umgebungssensorik (3) durchgeführten Überwachung zumindest eines Verkehrsteilnehmers, dessen Verhalten von einem prädizierten Verhalten signifikant abweicht, erhöht wird.The invention relates to a method for assessing a traffic situation for an at least partially autonomously operated vehicle. According to the invention, an artificial neural network (2) with during an uncritical traffic situation (V), which has not led to an accident of the vehicle and / or not a manual intervention of a driver during the at least partially autonomous operation of the vehicle, by means of an on-board environment sensor system ( 3) recorded data (D) trained. By means of the trained artificial neural network (2), a future traffic situation (V) is predicted, wherein in the case of a significant deviation of a traffic situation (V) occurring in reality from the predicted traffic situation (V) to a critical traffic situation (V) is concluded and if there is one Critical traffic situation (V) an intensity of a means of the vehicle's environmental sensor system (3) performed monitoring at least one road user whose behavior is significantly different from a predicted behavior, is increased.
Description
Die Erfindung betrifft ein Verfahren zur Bewertung einer Verkehrssituation gemäß dem Oberbegriff des Anspruchs 1.The invention relates to a method for evaluating a traffic situation according to the preamble of
Aus der
- - Ermitteln einer einen prädizierten Bewegungsraum des Kraftfahrzeugs beschreibenden Bewegungsrauminformation aus den Kartendaten;
- - Ermitteln einer einen prädizierten Bewegungsweg eines Verkehrsteilnehmers beschreibenden Bewegungsweginformation durch Anwenden eines Bewegungsprädiktionsmodells auf die Umgebungsdaten;
- - Ermitteln einer die Relevanz für eine Verkehrssituationsanalyse eines Teilbewegungsraums beschreibenden Bewertungsinformation in Abhängigkeit der Bewegungsrauminformation und der Bewegungsweginformation; und
- - Durchführen der Verkehrssituationsanalyse für den Teilbewegungsraum in Abhängigkeit der Bewertungsinformation.
- Determining a movement space information describing a predicted movement space of the motor vehicle from the map data;
- Determining motion path information describing a predicted motion path of a road user by applying a motion prediction model to the environment data;
- Determining a rating information describing the relevance for a traffic situation analysis of a partial movement space as a function of the movement space information and the movement path information; and
- - Carrying out the traffic situation analysis for the partial movement space as a function of the evaluation information.
Der Erfindung liegt die Aufgabe zu Grunde, ein gegenüber dem Stand der Technik verbessertes Verfahren zur Bewertung einer Verkehrssituation anzugeben.The invention is based on the object to provide a comparison with the prior art improved method for assessing a traffic situation.
Die Aufgabe wird erfindungsgemäß durch ein Verfahren gelöst, welches die im Anspruch 1 angegebenen Merkmale aufweist.The object is achieved by a method having the features specified in
Vorteilhafte Ausgestaltungen der Erfindung sind Gegenstand der Unteransprüche.Advantageous embodiments of the invention are the subject of the dependent claims.
In dem Verfahren zur Bewertung einer Verkehrssituation für ein zumindest teilautonom betriebenes Fahrzeug wird erfindungsgemäß ein künstliches neuronales Netzwerk mit während einer unkritischen Verkehrssituation, welche nicht zu einem Unfall des Fahrzeugs und/oder nicht zu einem manuellen Eingriff eines Fahrers während des zumindest teilautonomen Betriebs des Fahrzeugs geführt hat, mittels einer fahrzeugeigenen Umgebungssensorik erfassten Daten trainiert. Durch das Training wird das neuronale Netzwerk in die Lage versetzt, eine zukünftige Verkehrssituation zu prädizieren.In the method for assessing a traffic situation for an at least partially autonomously operated vehicle according to the invention an artificial neural network with during an uncritical traffic situation, which does not lead to an accident of the vehicle and / or not to a manual intervention of a driver during the at least partially autonomous operation of the vehicle has trained by means of an in-vehicle environmental sensor detected data. Through training, the neural network is able to predict a future traffic situation.
Mittels des trainierten künstlichen neuronalen Netzwerks wird die zukünftige Verkehrssituation prädiziert, wobei bei einer signifikanten Abweichung einer real auftretenden Verkehrssituation von der prädizierten Verkehrssituation auf eine kritische Verkehrssituation geschlossen wird und bei Vorliegen einer kritischen Verkehrssituation eine Intensität einer mittels der fahrzeugeigenen Umgebungssensorik durchgeführten Überwachung zumindest eines Verkehrsteilnehmers, dessen Verhalten von einem prädizierten Verhalten signifikant abweicht, erhöht wird.By means of the trained artificial neural network, the future traffic situation is predicted, with a significant deviation of a real traffic situation from the predicted traffic situation to a critical traffic situation is closed and in the presence of a critical traffic situation intensity of a carried out by the vehicle's environmental sensors monitoring at least one road user, whose behavior differs significantly from a predicated behavior is increased.
Vorteilhafterweise wird das Training des neuronalen Netzwerks zunächst anhand von generischen Daten durchgeführt, die von der Umgebungssensorik vorab in unkritischen Verkehrssituationen erfasst worden sind, und erst anschließend anhand der Daten durchgeführt, die während des Betriebs des Fahrzeugs von der Umgebungssensorik erfasst werden.Advantageously, the training of the neural network is first carried out on the basis of generic data, which have been detected by the environmental sensors in advance in uncritical traffic situations, and only then carried out on the basis of the data acquired during operation of the vehicle from the environmental sensor.
Das Verfahren ermöglicht eine Verbesserung der Bewertung einer Verkehrssituation aufgrund der Erhöhung der Intensität der Überwachung. Hieraus resultiert die Möglichkeit, eine Unfallgefahr frühzeitig zu erkennen und somit eine Verkehrssicherheit zu erhöhen.The method makes it possible to improve the evaluation of a traffic situation due to the increase in the intensity of the monitoring. This results in the possibility of detecting an accident risk at an early stage and thus increasing traffic safety.
Ausführungsbeispiele der Erfindung werden im Folgenden anhand einer Zeichnung näher erläutert.Embodiments of the invention will be explained in more detail below with reference to a drawing.
Dabei zeigt:
-
1 schematisch ein Blockschaltbild einer Vorrichtung zur Bewertung einer Verkehrssituation.
-
1 schematically a block diagram of a device for evaluating a traffic situation.
In der einzigen
Die Vorrichtung
Für einen zuverlässigen autonomen oder teilautonomen Betrieb des Fahrzeugs ist es förderlich, Kenntnis über zukünftig auftretende Verkehrssituationen
Dies erfolgt mittels eines trainierten künstlichen neuronalen Netzwerks
Die prädizierte zukünftige Verkehrssituation
Wird in dem Vergleich eine signifikante Abweichung der real auftretenden Verkehrssituation
In diesem Fall wird eine Information über die kritische Verkehrssituation
Weiterhin wird ein optimaler Prädiktionszeitraum
BezugszeichenlisteLIST OF REFERENCE NUMBERS
- 11
- Vorrichtungcontraption
- 22
- Netzwerknetwork
- 33
- Umgebungssensorikambient sensor
- 3.1 bis 3.n3.1 to 3.n
- Sensorsensor
- 44
- Auswerteeinheitevaluation
- 55
- Steuereinheit control unit
- DD
- Datendates
- VV
- Verkehrssituationtraffic situation
- Vkrit V crit
- Verkehrssituationtraffic situation
- Vpraed V praed
- Verkehrssituationtraffic situation
ZITATE ENTHALTEN IN DER BESCHREIBUNG QUOTES INCLUDE IN THE DESCRIPTION
Diese Liste der vom Anmelder aufgeführten Dokumente wurde automatisiert erzeugt und ist ausschließlich zur besseren Information des Lesers aufgenommen. Die Liste ist nicht Bestandteil der deutschen Patent- bzw. Gebrauchsmusteranmeldung. Das DPMA übernimmt keinerlei Haftung für etwaige Fehler oder Auslassungen.This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.
Zitierte PatentliteraturCited patent literature
- DE 102016007899 A1 [0002]DE 102016007899 A1 [0002]
Claims (4)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102018008024.3A DE102018008024A1 (en) | 2018-10-10 | 2018-10-10 | Method for assessing a traffic situation |
PCT/EP2019/074070 WO2020074195A1 (en) | 2018-10-10 | 2019-09-10 | Method for assessing a traffic situation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102018008024.3A DE102018008024A1 (en) | 2018-10-10 | 2018-10-10 | Method for assessing a traffic situation |
Publications (1)
Publication Number | Publication Date |
---|---|
DE102018008024A1 true DE102018008024A1 (en) | 2019-04-11 |
Family
ID=65817387
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
DE102018008024.3A Withdrawn DE102018008024A1 (en) | 2018-10-10 | 2018-10-10 | Method for assessing a traffic situation |
Country Status (2)
Country | Link |
---|---|
DE (1) | DE102018008024A1 (en) |
WO (1) | WO2020074195A1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110231820A (en) * | 2019-05-31 | 2019-09-13 | 辽宁工业大学 | A kind of vehicle travel control method based on Internet of Things |
DE102019002790A1 (en) * | 2019-04-16 | 2020-08-06 | Daimler Ag | Method for predicting a traffic situation for a vehicle |
CN111775929A (en) * | 2020-06-11 | 2020-10-16 | 南京邮电大学 | Dynamic safety early warning method for dangerous liquid mobile vehicle-mounted device |
WO2020224910A1 (en) * | 2019-05-09 | 2020-11-12 | LGN Innovations Limited | Method and system for detecting edge cases for use in training a vehicle control system |
DE102019114737A1 (en) * | 2019-06-03 | 2020-12-03 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for predicting the behavior of a road user |
WO2021061180A1 (en) * | 2019-09-27 | 2021-04-01 | Gm Cruise Holdings Llc | Intent-based dynamic change of resolution and region of interest of vehicle perception system |
WO2021061181A1 (en) * | 2019-09-27 | 2021-04-01 | Gm Cruise Holdings Llc | Intent-based dynamic change of compute resources of vehicle perception system |
US20220227379A1 (en) * | 2019-05-09 | 2022-07-21 | LGN Innovations Limited | Network for detecting edge cases for use in training autonomous vehicle control systems |
WO2022184363A1 (en) * | 2021-03-04 | 2022-09-09 | Psa Automobiles Sa | Computer-implemented method for training at least one algorithm for a control unit of a motor vehicle, computer program product, control unit, and motor vehicle |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016007899A1 (en) | 2016-06-28 | 2017-12-28 | Audi Ag | Method for operating a device for traffic situation analysis, motor vehicle and data processing device |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10065562B2 (en) * | 2013-12-31 | 2018-09-04 | International Business Mahcines Corporation | Vehicle collision avoidance |
US9764736B2 (en) * | 2015-08-14 | 2017-09-19 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle operation relative to unexpected dynamic objects |
US9889859B2 (en) * | 2015-12-21 | 2018-02-13 | Intel Corporation | Dynamic sensor range in advanced driver assistance systems |
-
2018
- 2018-10-10 DE DE102018008024.3A patent/DE102018008024A1/en not_active Withdrawn
-
2019
- 2019-09-10 WO PCT/EP2019/074070 patent/WO2020074195A1/en active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016007899A1 (en) | 2016-06-28 | 2017-12-28 | Audi Ag | Method for operating a device for traffic situation analysis, motor vehicle and data processing device |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102019002790A1 (en) * | 2019-04-16 | 2020-08-06 | Daimler Ag | Method for predicting a traffic situation for a vehicle |
US11945450B2 (en) | 2019-04-16 | 2024-04-02 | Mercedes-Benz Group AG | Method for predicting a traffic situation for a vehicle |
WO2020212061A1 (en) * | 2019-04-16 | 2020-10-22 | Daimler Ag | Method for predicting a traffic situation for a vehicle |
DE102019002790B4 (en) | 2019-04-16 | 2023-05-04 | Mercedes-Benz Group AG | Method for predicting a traffic situation for a vehicle |
US20220227379A1 (en) * | 2019-05-09 | 2022-07-21 | LGN Innovations Limited | Network for detecting edge cases for use in training autonomous vehicle control systems |
WO2020224910A1 (en) * | 2019-05-09 | 2020-11-12 | LGN Innovations Limited | Method and system for detecting edge cases for use in training a vehicle control system |
CN110231820B (en) * | 2019-05-31 | 2022-08-05 | 江苏亿科达科技发展有限公司 | Vehicle running control method based on Internet of things |
CN110231820A (en) * | 2019-05-31 | 2019-09-13 | 辽宁工业大学 | A kind of vehicle travel control method based on Internet of Things |
DE102019114737A1 (en) * | 2019-06-03 | 2020-12-03 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for predicting the behavior of a road user |
WO2021061181A1 (en) * | 2019-09-27 | 2021-04-01 | Gm Cruise Holdings Llc | Intent-based dynamic change of compute resources of vehicle perception system |
US11037000B2 (en) | 2019-09-27 | 2021-06-15 | Gm Cruise Holdings Llc | Intent-based dynamic change of resolution and region of interest of vehicle perception system |
US11037001B2 (en) | 2019-09-27 | 2021-06-15 | Gm Cruise Holdings Llc | Intent-based dynamic change of region of interest of vehicle perception system |
US11070721B2 (en) | 2019-09-27 | 2021-07-20 | Gm Cruise Holdings Llc | Intent-based dynamic change of compute resources of vehicle perception system |
WO2021061180A1 (en) * | 2019-09-27 | 2021-04-01 | Gm Cruise Holdings Llc | Intent-based dynamic change of resolution and region of interest of vehicle perception system |
US11594039B2 (en) | 2019-09-27 | 2023-02-28 | Gm Cruise Holdings Llc | Intent-based dynamic change of region of interest of vehicle perception system |
CN111775929B (en) * | 2020-06-11 | 2024-03-19 | 南京邮电大学 | Dynamic safety early warning method for dangerous liquid mobile vehicle-mounted device |
CN111775929A (en) * | 2020-06-11 | 2020-10-16 | 南京邮电大学 | Dynamic safety early warning method for dangerous liquid mobile vehicle-mounted device |
WO2022184363A1 (en) * | 2021-03-04 | 2022-09-09 | Psa Automobiles Sa | Computer-implemented method for training at least one algorithm for a control unit of a motor vehicle, computer program product, control unit, and motor vehicle |
Also Published As
Publication number | Publication date |
---|---|
WO2020074195A1 (en) | 2020-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102018008024A1 (en) | Method for assessing a traffic situation | |
DE102013019424B4 (en) | Method for operating a vehicle system for monitoring a driver and motor vehicle | |
DE102017205093A1 (en) | Method and system for predicting sensor signals of a vehicle | |
DE102009006336A1 (en) | Method of monitoring a parking operation | |
DE102009046913A1 (en) | Method for detecting fatigue of driver of e.g. lorry during driving, involves evaluating information about steering movement and surrounding information for determining whether information about steering movement indicates fatigue of driver | |
EP3616180B1 (en) | Method for data collection | |
WO2014194898A1 (en) | Method and driver assistance system for assessing and/or maintaining the alertness of a driver of a vehicle | |
DE102017205508A1 (en) | Method for automatic movement control of a vehicle | |
DE102020113611A1 (en) | Method and safety system for securing an automated vehicle function and motor vehicle | |
DE102016007899A1 (en) | Method for operating a device for traffic situation analysis, motor vehicle and data processing device | |
EP3505414B1 (en) | Motor vehicle control device and method for operating the control device for autonomous driving of a motor vehicle | |
DE102018126830A1 (en) | Device and control unit for automating a change in state of a window pane of a vehicle | |
DE102018213600A1 (en) | - gesture recognition device for a vehicle - | |
DE102021201539A1 (en) | Generation of training data for a machine learning algorithm | |
DE102018213378B4 (en) | Driver assistance system for a vehicle, vehicle with the same and driver assistance method for a vehicle | |
DE102017217986A1 (en) | METHOD AND DEVICE FOR PREDICTING POTENTIAL COLLISIONS, DRIVER ASSISTANCE SYSTEM AND VEHICLE | |
DE102019217723A1 (en) | DRIVING SAFETY CONTROL SYSTEM USING AMBIENT NOISE AND CONTROL METHOD THEREFOR | |
DE102018212266A1 (en) | Adaptation of an evaluable scanning range of sensors and adapted evaluation of sensor data | |
WO2019120709A1 (en) | Method and control unit for controlling a function of a vehicle driven at least partially in an automated manner | |
DE102018204883A1 (en) | Method for operating a control device, motor vehicle and computer program | |
EP3727981B1 (en) | Method for carrying out a self-diagnosis in an automated vehicle | |
DE102018119834A1 (en) | Method for operating an autonomously driving vehicle | |
DE102020114609B4 (en) | Method for providing an introspective error prediction model, assistance system and motor vehicle | |
DE102017004114A1 (en) | Method and device for operating a fully autonomously or at least partially autonomously driving vehicle | |
DE102019130298B3 (en) | Method for the detection of specific driving behavior and a system and a motor vehicle for this purpose |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
R230 | Request for early publication | ||
R012 | Request for examination validly filed | ||
R081 | Change of applicant/patentee |
Owner name: DAIMLER AG, DE Free format text: FORMER OWNER: DAIMLER AG, 70327 STUTTGART, DE |
|
R119 | Application deemed withdrawn, or ip right lapsed, due to non-payment of renewal fee |