EP4168999A1 - Verfahren zur unterstützung eines betriebs eines fahrzeuges mit einer sensoreinheit, computerprogrammprodukt sowie system - Google Patents
Verfahren zur unterstützung eines betriebs eines fahrzeuges mit einer sensoreinheit, computerprogrammprodukt sowie systemInfo
- Publication number
- EP4168999A1 EP4168999A1 EP22747600.9A EP22747600A EP4168999A1 EP 4168999 A1 EP4168999 A1 EP 4168999A1 EP 22747600 A EP22747600 A EP 22747600A EP 4168999 A1 EP4168999 A1 EP 4168999A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- sensor data
- evaluation
- sensor
- behavior
- vehicle
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Definitions
- the invention relates to a method for supporting the operation of a vehicle with a sensor unit for acquiring sensor data for evaluation in a trained, artificial neural network, a computer program product and a system.
- the quality of the sensor data is often not stable during operation of the vehicle due to various environmental influences. For example, disturbances such as fog, snow and/or heavy rain can lead to reduced data quality. If these disturbances are not recognized, this can lead to misinterpretations by the neural network. In particular, if the sensor data is to be interpreted for autonomous driving or for driver assistance systems, it is therefore desirable to recognize disruptions in sensor data.
- a method for supporting operation of a vehicle has a sensor unit for acquiring sensor data that is intended for evaluation in a trained, artificial neural network.
- the artificial neural network has a large number of network elements for intermediate evaluations of the sensor data, in particular within the neural network.
- the procedure also includes the following steps:
- the vehicle can advantageously be operated in an at least partially automated operating mode with a driver assistance system and/or in an autonomous operating mode.
- the sensor unit can include one or more vehicle sensors.
- the sensor unit includes a forward-looking sensor system for detecting a vehicle environment of the vehicle.
- the sensor data can be image data, radar data and/or lidar data, for example.
- the neural network can also be referred to as a neural network.
- the neural network is in particular a so-called deep neural network.
- the neural network is preferably a machine-learning-based network with a plurality, preferably three or more, layers and/or parameters for processing input data and for outputting output data.
- the neural network can preferably be implemented in the processing unit in a trained form.
- the neural network can be part of a recognition module of the processing unit.
- the neural network can of a development process must be trained using reference data from the sensor data in order to be able to recognize the event.
- the event can preferably be an event in a vehicle environment during operation of the vehicle.
- the event may include an appearance of another road user, such as a pedestrian or another vehicle.
- the event when the event is recognized, a traffic sign that the vehicle is approaching is recognized.
- object recognition can be carried out when evaluating the sensor data for recognizing the event.
- boxes can be rendered around objects in the vehicle environment.
- the sensor data can preferably be classified according to events during the evaluation.
- the sensor data when evaluating the sensor data, the sensor data can be evaluated pixel by pixel. The evaluation of the sensor data can be carried out completely until an overall evaluation is established.
- the evaluation of the sensor data to be interrupted if a sensor fault is detected when the sensor data is being evaluated.
- the network elements can be network nodes of the neural network, for example.
- the network elements can preferably include kernels, network layers, network filters and/or weights of the neural network.
- the intermediate evaluations can include scalars, for example, which are output by the network elements when evaluating the sensor data.
- the evaluation behavior of the intermediate evaluations of part or all of the network elements of the neural network can be monitored, in particular analyzed.
- the presence of the sensor fault can be checked and/or determined. For example, it can be determined whether the presence of the sensor fault is sufficiently probable based on the evaluation behavior.
- the sensor data can be classified into sensor data with and/or without interference, or into stable and/or unstable sensor data. It is therefore conceivable that when evaluating the sensor data it is determined whether the neural network has a high error rate when evaluating the sensor data due to the data quality of the sensor data.
- the sensor fault can in particular be an external fault in the sensor data.
- the sensor malfunction can be caused by weather influences in the vehicle environment.
- the sensor disturbance may include fog, heavy rain, and/or the like.
- the response action may include affecting the operation of the vehicle.
- the reaction measure includes a message to the driver of the vehicle in order to inform the driver that the sensor unit is faulty.
- the reaction measure can include a request for further sensor data in order to validate or falsify the sensor fault.
- the neural network itself can thus be analyzed in order to identify the sensor malfunction based on the behavior of the neural network.
- an incorrect behavior of the neural network can be detected and/or predicted.
- misinterpretations of the sensor data can be avoided, which improves safety when operating the vehicle.
- the method comprises the following step:
- Identifying key elements of the multiplicity of network elements in particular by the computing unit, a server and/or the vehicle.
- the interim evaluations of the key elements are preferably monitored.
- the key elements can be understood to mean, in particular, sensitive network elements whose intermediate evaluations behave in a characteristic manner when there is a sensor fault. In particular, only the interim evaluations of the key elements can be monitored when monitoring the evaluation behavior. A required computing capacity can thereby be reduced. It is conceivable that the identification of the key elements takes place in a separate process. However, it is also conceivable that a collection, in particular in the form of a list and/or a catalogue, of the key elements is obtained from the vehicle in order to identify the key elements. For example, the collection of the key elements can be provided by a server. A behavior of the interim evaluations of the key elements can thus represent a characteristic for detecting the sensor fault. Furthermore, by identifying the key elements, the required computing power when monitoring the evaluation behavior and/or when evaluating the sensor data can be reduced.
- a calibration process is carried out to identify the key elements and/or to evaluate the sensor data, in which reference data affected by interference and reference data free of interference are evaluated by the neural network, preferably with the Calibration process behavioral deviations of the interim evaluations are recorded when evaluating the noisy and no-noise reference data.
- the calibration process can be performed iteratively.
- the reference data affected by interference can be understood to mean exemplary sensor data that have a sensor fault, as a result of which the evaluation of the sensor data is incorrect or error-prone.
- the error-free reference data can be understood to mean exemplary sensor data which, when the sensor data is evaluated, lead to an error-free overall result or an overall result within a tolerance range.
- a further artificial neural network can be trained during the calibration process in that the further neural network receives the intermediate evaluations and the reference data as input data in order to output output data in the form of an evaluation for detecting the sensor fault and/or the key elements.
- the calibration process can thus improve accuracy when detecting the sensor malfunction.
- the calibration process is carried out by a server, with the evaluation of the sensor data, the monitoring of the evaluation behavior and the evaluation of the sensor data being carried out by the vehicle.
- the identified key elements, the neural network and/or an architecture of the neural network can be transmitted from the server to the vehicle. This allows the results of the calibration process to be made available to multiple vehicles. Furthermore, a computing load in the vehicle can be reduced as a result. Because the vehicle is responsible for evaluating the sensor data, monitoring the evaluation behavior and evaluating the sensor data, the sensor data can be evaluated in real time in the vehicle at the same time, in order to be able to react quickly in a particularly critical driving situation.
- the key elements can be weighted when identifying the key elements, with the weighting being taken into account when evaluating the sensor data.
- the weighting can, for example, include weighting factors when evaluating the sensor data for detecting the sensor fault.
- the weights can be set during the calibration process. For example, it can be recognized during the calibration process that the behavior of the interim evaluations of certain key elements has a stronger influence on the evaluation of the sensor data with regard to the sensor disturbance than the behavior of the interim evaluations of other key elements. This can be done by weighting are taken into account, which means that the sensor fault can be detected with greater accuracy.
- an averaging for several intermediate evaluations takes place.
- the interim evaluations can be averaged for several network elements.
- an averaging takes place. This can reduce the influence of measurement errors, for example.
- the evaluation behavior is compared with a reference behavior of the intermediate evaluations, with at least one limit value for a deviation of the evaluation behavior from the reference behavior for detecting the sensor fault, i.e. in particular for Recognizing the presence of the sensor malfunction is specified.
- the reference behavior can be determined during the calibration process using the interference-free reference data.
- the limit value can be determined during the calibration process on the basis of the noisy reference data, in particular by comparing the evaluation behavior when evaluating the noisy and no-noise reference data. For example, provision can be made for the sensor fault to be detected when the limit value is reached or exceeded. In particular, several limit values can be specified for the interim evaluations. An advantageous detection of the sensor fault can thus be implemented.
- the sensor data can be classified with regard to a fault classification when the sensor data are evaluated, with the reaction measure taking place as a function of the fault classification.
- the fault classification can include the type of sensor fault. So it is conceivable that sensor data with fog receive a different fault classification than sensor data with heavy rain.
- the reaction measure can thus be carried out individually for the fault classification. It can e.g. B. be provided that the reaction measure includes a control of driver assistance systems depending on the fault classification. In particular, a predetermined driver assistance system can be activated for a specific fault classification.
- the reaction measure comprises a validation process for validating the assessment and/or the evaluation of the sensor data. Through the validation process, an intervention in the driving behavior of the vehicle can be avoided or postponed. In this way, in particular, additional security can be gained when detecting the sensor fault.
- the validation process includes feeding the sensor data into a further, artificial neural network, which is trained to evaluate sensor data of the fault classification in order to recognize the event.
- the further neural network can be specialized in the evaluation of sensor data that is disturbed by fog.
- sensor data that exhibit a sensor fault can also be evaluated with regard to the event.
- the further neural network can be implemented in the vehicle or in the server.
- the validation process includes feeding the sensor data into several, further, trained artificial neural networks, with a consolidation process being carried out in order to obtain an overall evaluation of the sensor data with regard to the event and/or with regard to the sensor malfunction.
- the evaluation behavior of intermediate evaluations of the further neural networks can be monitored and the sensor data can be evaluated for detecting the sensor fault as a function of the evaluation behavior of all further neural networks.
- the evaluation can take into account whether a majority of the other neural networks classify the sensor data as being subject to interference or free of interference.
- the additional neural networks can be trained using different training data.
- the evaluation behavior of the intermediate evaluations of the other neural networks can differ.
- errors in detecting the sensor malfunction can be detected and/or the accuracy in detecting the sensor malfunction can be improved.
- the reaction measure includes an automatic triggering of a driving maneuver of the vehicle.
- a driver assistance system of the vehicle can be activated.
- the speed of the vehicle can be reduced and/or a driving maneuver can be carried out, in particular to carry out an emergency stop of the vehicle.
- safe operation of the vehicle take place by intervening in normal operation of the vehicle when the sensor fault is detected, in order to avoid incorrect behavior of the vehicle due to an incorrect evaluation by the neural network caused by the sensor fault.
- a computer program product includes instructions which, when executed by a processing unit, cause the processing unit to carry out a method according to the invention.
- a computer program product thus entails the same advantages as have already been described in detail with reference to a method according to the invention.
- the method can in particular be a computer-implemented method.
- the computer program product may be implemented as computer-readable instruction code in any suitable programming language, such as JAVA, C++, C# and/or Python.
- the computer program product can be stored on a computer-readable storage medium such as a data disk, a removable drive, a volatile or non-volatile memory, or a built-in memory/processor.
- the instruction code can influence and/or control a computer or other programmable device such as a controller in such a way that the desired functions are carried out.
- the computer program product can be made available or made available on a network such as the Internet, from which it can be downloaded by a user when required.
- the computer program product can be implemented both by means of software and by means of one or more special electronic circuits, i. H. in hardware or in any hybrid form, i. H. by means of software components and hardware components.
- a system has a vehicle with a sensor unit for acquiring sensor data. Furthermore, the system includes a computing unit for executing a method according to the invention.
- the computing unit can advantageously have a processor and/or microprocessor. Furthermore, the computing unit can be integrated into the vehicle and/or a server. In particular, the arithmetic unit can have a number of arithmetic modules which are distributed in a decentralized manner. For example, a computing module of the computing unit in the vehicle and another computing module Arithmetic unit to be integrated into the server.
- the vehicle preferably has a driver assistance system for automatically carrying out a driving maneuver.
- FIG. 1 shows an artificial neural network
- FIG. 2 shows a method according to the invention for supporting operation of a vehicle
- FIG. 3 a validation process of the method
- FIG. 4 a system with the vehicle
- FIGS. 5, 6 reference data for a calibration process of the method.
- FIG. 1 shows a trained, artificial neural network 10 for evaluating 103 sensor data 200 from a sensor unit 4 of a vehicle 2.
- a system 1 according to the invention with the vehicle 2 and the sensor unit 4 is shown in FIG.
- the neural network 10 can be implemented in a computing unit 3 .
- the processing unit 3 is preferably integrated into the vehicle 2 and/or a server 5 .
- the neural network 10 has a large number of network elements 11 for intermediate evaluations 210 for evaluating the sensor data 200 .
- the network elements 11 can include network layers, network filters and/or weightings of the neural network 10, for example.
- FIG. 2 shows a method 100 according to the invention for supporting the operation of the vehicle 2 with the sensor unit 4 in a schematic representation of method steps.
- Method 100 is preferably executed by computing unit 3 .
- a computer program product is advantageously provided for this purpose, which comprises instructions which, when executed by the processing unit 3, cause the processing unit 3 to carry out the method 100.
- the method 100 comprises providing 102 the sensor data 200 for the neural network 10 and evaluating 103 the sensor data 200 for detecting the event by the neural network 10.
- the event may be an occurrence of an object, such as B. another road user, act in a vehicle environment.
- an identification 101 of key elements 11.1 of the multiplicity of network elements 11 is provided.
- a calibration process 101.1 is carried out, in which reference data 201 subject to interference and reference data 202 free of interference are evaluated by the neural network 10.
- the reference data 201, 202 can include image data.
- An example of undisturbed reference data 202 is shown in FIG. 5, while an example of noisy reference data 201 with a sensor disturbance in the form of rain is shown in FIG.
- the interference-free reference data 202 can correspond to the training data of the neural network 10, for example. Provision can be made for further reference parameters 203 to be fed into the neural network 10 during the calibration process 101.1.
- the sensor malfunction can therefore be an external malfunction, e.g. B. an environmental impact act.
- deviations in behavior of the intermediate evaluations 210 are recorded during the evaluation 103 of the reference data 201, 202 with and without interference.
- a characteristic behavior of the neural network 10 in the form of characteristic interim evaluations 210 or a characteristic change in the interim evaluations 210 can be identified in order to identify the sensor malfunction.
- the key elements 11.1 can preferably also be weighted, with key elements 11.1, for example, whose intermediate evaluations 210 behave more characteristically compared to other key elements 11.1, being given greater weight for detecting the sensor fault. In this way, in particular, a number of the key elements 11.1 can be reduced.
- the method 100 also monitors 104 an evaluation behavior of the intermediate evaluations 210 during the evaluation 103 of the sensor data 200.
- the intermediate evaluations 210 of the key elements 11.1 which have the characteristic behavior in the event of the sensor fault are monitored.
- an evaluation 105 of the sensor data 200 for detecting the sensor fault as a function of the evaluation behavior, in particular taking into account the weighting of the key elements 11.1.
- an averaging in particular over time and/or across elements, can be carried out for a plurality of intermediate evaluations 210 .
- the sensor fault is detected during the evaluation 105 of the sensor data 200 in particular by comparing the evaluation behavior with a reference behavior of the intermediate evaluations 210 .
- the reference behavior can be derived from the reference data 201, 202, which are in particular free of interference.
- the sensor fault is detected in particular when the limit value 212 is reached or exceeded.
- a plurality of limit values 212 are provided, through which a tolerance corridor is formed, in which the sensor data 200 is considered to be error-free. Provision can be made for the sensor data 200 to be classified with regard to a fault classification 213 .
- the calibration process 101.1 is preferably carried out by the server 5 and the evaluation 103 of the sensor data 200, the monitoring 104 of the evaluation behavior and the evaluation 105 of the sensor data 200 by the vehicle 2 executed.
- the server 5 and the vehicle 2 can each include computing modules of the computing unit 3 .
- a reaction measure 106 is carried out, such as B. an automatic triggering of a driving maneuver of the vehicle 2 by a driver assistance system 6.
- the vehicle 2 can be braked if the sensor malfunction is present in order to avoid impairment of the vehicle 2 by a misinterpretation of the sensor data 200.
- the reaction measure 106 includes a validation process 106.1 for validating the evaluation and/or the evaluation of the sensor data 200.
- the validation process 106.1 can include feeding the sensor data 200 into a further, artificial neural network 10.1.
- the additional artificial neural network 10.1 can be specially trained to recognize the event when evaluating 103 sensor data 200 of the fault classification 213.
- the validation process 106.1 can include feeding the sensor data 200 into a plurality of further trained artificial neural networks 10.2.
- a consolidation process is carried out by the additional, trained artificial neural networks 10.2 in order to obtain an overall evaluation of the sensor data 200 with regard to the event and/or with regard to the sensor malfunction.
- the neural network 10 By monitoring 104 the evaluation behavior, the neural network 10 itself can thus be analyzed to identify the sensor fault. As a result, an incorrect behavior of the neural network 10 can be detected and/or predicted in order to avoid misinterpretation of the sensor data 200 . As a result, the safety of the vehicle 2, in particular in an at least partially automated or autonomous driving mode, can be improved, in particular without a high computing capacity being required in the vehicle 2.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (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)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102021207493.6A DE102021207493A1 (de) | 2021-07-14 | 2021-07-14 | Verfahren zur Unterstützung eines Betriebs eines Fahrzeuges mit einer Sensoreinheit, Computerprogrammprodukt sowie System |
| PCT/EP2022/068386 WO2023285179A1 (de) | 2021-07-14 | 2022-07-04 | Verfahren zur unterstützung eines betriebs eines fahrzeuges mit einer sensoreinheit, computerprogrammprodukt sowie system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4168999A1 true EP4168999A1 (de) | 2023-04-26 |
Family
ID=82703128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP22747600.9A Pending EP4168999A1 (de) | 2021-07-14 | 2022-07-04 | Verfahren zur unterstützung eines betriebs eines fahrzeuges mit einer sensoreinheit, computerprogrammprodukt sowie system |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20240403607A1 (de) |
| EP (1) | EP4168999A1 (de) |
| CN (1) | CN117693777A (de) |
| DE (1) | DE102021207493A1 (de) |
| WO (1) | WO2023285179A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102023204261A1 (de) | 2023-05-09 | 2024-11-14 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren und Steuergerät zum Überwachen eines Fahrzeugs |
| DE102024133950A1 (de) * | 2024-11-19 | 2026-05-21 | Cariad Se | Verfahren zum Berechtigungsmanagement für zumindest eine erste Fahrzeugfunktion, Computerprogrammprodukt sowie Fahrzeug |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020249755A1 (de) * | 2019-06-14 | 2020-12-17 | Volkswagen Aktiengesellschaft | Verfahren zum betreiben eines fahrassistenzsystems eines fahrzeugs und fahrerassistenzsystem für ein fahrzeug |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9633306B2 (en) | 2015-05-07 | 2017-04-25 | Siemens Healthcare Gmbh | Method and system for approximating deep neural networks for anatomical object detection |
| US10521677B2 (en) * | 2016-07-14 | 2019-12-31 | Ford Global Technologies, Llc | Virtual sensor-data-generation system and method supporting development of vision-based rain-detection algorithms |
| US10836379B2 (en) * | 2018-03-23 | 2020-11-17 | Sf Motors, Inc. | Multi-network-based path generation for vehicle parking |
| DE202018104373U1 (de) | 2018-07-30 | 2018-08-30 | Robert Bosch Gmbh | Vorrichtung, die zum Betreiben eines maschinellen Lernsystems eingerichtet ist |
| CN109760635B (zh) * | 2019-01-08 | 2020-11-27 | 同济大学 | 一种基于gan网络的线控雨刷控制系统 |
| DE102019201990A1 (de) * | 2019-02-14 | 2020-08-20 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Erkennung einer Störung in einem Bild |
| JP7281923B2 (ja) * | 2019-03-01 | 2023-05-26 | キヤノン株式会社 | 制御装置、画像処理システム、制御方法及びプログラム |
| CN210822158U (zh) * | 2019-09-27 | 2020-06-23 | 深圳市豪恩汽车电子装备股份有限公司 | 机动车雨刷自动控制系统 |
| CN110689021A (zh) * | 2019-10-17 | 2020-01-14 | 哈尔滨理工大学 | 一种基于深度学习的低可见度环境下实时目标检测方法 |
| DE102019218613B4 (de) | 2019-11-29 | 2021-11-11 | Volkswagen Aktiengesellschaft | Objektklassifizierungsverfahren, Objektklassifizierungsschaltung, Kraftfahrzeug |
| CN112801195A (zh) * | 2021-02-04 | 2021-05-14 | 四川望村网络科技有限公司 | 一种基于深度学习的雾天能见度预测方法,存储装置及服务器 |
-
2021
- 2021-07-14 DE DE102021207493.6A patent/DE102021207493A1/de active Pending
-
2022
- 2022-07-04 EP EP22747600.9A patent/EP4168999A1/de active Pending
- 2022-07-04 WO PCT/EP2022/068386 patent/WO2023285179A1/de not_active Ceased
- 2022-07-04 CN CN202280049169.9A patent/CN117693777A/zh active Pending
- 2022-07-04 US US18/578,179 patent/US20240403607A1/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020249755A1 (de) * | 2019-06-14 | 2020-12-17 | Volkswagen Aktiengesellschaft | Verfahren zum betreiben eines fahrassistenzsystems eines fahrzeugs und fahrerassistenzsystem für ein fahrzeug |
Also Published As
| Publication number | Publication date |
|---|---|
| DE102021207493A1 (de) | 2023-01-19 |
| CN117693777A (zh) | 2024-03-12 |
| WO2023285179A1 (de) | 2023-01-19 |
| US20240403607A1 (en) | 2024-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102018222720B4 (de) | Überwachung von auf neuronalen Netzwerken basierten Fahrfunktionen | |
| EP3792150B1 (de) | Erkennung von hands-off-situationen auf basis von schwarmdaten | |
| DE102017009471A1 (de) | Humankollaboratives robotersystem mit verbesserter genauigkeit der erfassung einer äusseren kraft durch maschinelles lernen | |
| DE102022205084B3 (de) | Verfahren, Computerprogramm und Vorrichtung zur Umfeldwahrnehmung im Fahrzeug sowie entsprechendes Fahrzeug | |
| DE102019209462A1 (de) | Verfahren zur Bestimmung eines Vertrauens-Wertes eines detektierten Objektes | |
| EP3945338B1 (de) | Vorrichtung zur umfelderkennung eines automatisiert betreibbaren fahrsystems | |
| DE102020113611A1 (de) | Verfahren und Sicherheitssystem zum Absichern einer automatisierten Fahrzeugfunktion und Kraftfahrzeug | |
| DE102021202813A1 (de) | Verfahren, Vorrichtung und Computerprogramm für eine Unsicherheitsbewertung einer Bildklassifikation | |
| DE102017214531A1 (de) | Verfahren und Vorrichtung zum Betreiben eines Kraftfahrzeugs in einem automatisierten Fahrbetrieb sowie Kraftfahrzeug | |
| WO2023285179A1 (de) | Verfahren zur unterstützung eines betriebs eines fahrzeuges mit einer sensoreinheit, computerprogrammprodukt sowie system | |
| DE102017218438A1 (de) | Verfahren und System zum Betreiben eines Fahrzeugs | |
| DE102017204745A1 (de) | Architektur und Vorrichtung für eine fortschrittliche Arbitration in integrierten Steuerungen | |
| DE102018129563A1 (de) | Verfahren zum Bestimmen des Steuermodus eines Lenkrads | |
| DE102015224696A1 (de) | Risikobasierte Steuerung eines Kraftfahrzeugs | |
| DE112019007286T5 (de) | Fahrzeuginterne steuerungsvorrichtung und fahrzeuginternes steuerungssystem | |
| DE102022200729A1 (de) | Verfahren zum Ermitteln eines aktuellen Steuermodus eines Lenkrades | |
| WO2024002777A1 (de) | Verfahren zur handdetektion, computerprogramm, und vorrichtung | |
| DE102018216423A1 (de) | Bestimmung eines Ansteuerungssignals für ein teilautonomes Fahrzeug | |
| DE102017113478A1 (de) | Verfahren zum Betreiben einer Steuerungseinrichtung für den Betrieb mit einer redundanten Sensorvorrichtung in einem Kraftfahrzeug | |
| DE112023000537T5 (de) | Bilderkennungssystem | |
| EP3947100B1 (de) | Verfahren und einrichtung zum erzeugen eines statussignals | |
| DE102020203819B4 (de) | Verfahren zum Betreiben eines zumindest teilautomatisiert fahrenden Fahrzeugs und Fahrzeug | |
| DE102020204388A1 (de) | Verfahren und Vorrichtung zum Ansteuern eines Agenten | |
| DE102016208076A1 (de) | Verfahren und vorrichtung zur auswertung eines eingabewerts in einem fahrerassistenzsystem, fahrerassistenzsystem und testsystem für ein fahrerassistenzsystem | |
| DE102023204318A1 (de) | Verfahren für eine Servereinheit zur Plausibilisierung eines Fahrverhaltens eines wenigstens teilweise automatisiert fahrenden Ego-Fahrzeugs und Verfahren zur Steuerung des Ego-Fahrzeugs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230719 |
|
| RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20251117 |