Method for determining a trigger event for an emergency maneuver of a motor vehicle that is at least partially automated, computer program product, and support system

Abstract

The invention relates to a method for determining a trigger event (3) for data recording during an emergency maneuver of an at least partially automated motor vehicle (1) by means of a support system (2), comprising the steps of: storing vehicle-internal data over a predetermined period by means of a storage device (5) of the support system (2); determining the occurrence of the emergency maneuver by means of an electronic computing device (4) of the support system (2); providing the stored data depending on the determined emergency maneuver by means of the electronic computing device (4); analyzing the provided data for anomalies by means of the electronic computing device (4); and determining the trigger event (3) depending on the analysis by means of the electronic computing device (4). The invention further relates to a computer program product and a support system (2).

Description

[0001] The following invention relates to a method for determining a trigger event for an emergency maneuver of a motor vehicle operated at least partially automatically by means of a support system according to claim 1. The invention further relates to a corresponding computer program product and a corresponding support system.

[0002] At least partially automated vehicles, or fully automated vehicles (AVs), can encounter situations where they are unable to interpret their surroundings, leading to potential safety risks. In such cases, the vehicles are programmed to perform a minimal-risk maneuver (MRM), transitioning to a minimal-risk state (MRS) in which the vehicle can come to a safe stop. The need for a minimal-risk maneuver can arise from various factors, such as perception problems, internal errors in the electronic control units or functions, or critical scenarios the vehicle encounters.

[0003] Manufacturers of these vehicles must identify unknown, potentially critical scenarios and report them to the authorities based on the collected data in order to obtain type approval for the automated vehicles. However, it is not possible to continuously collect all vehicle data. Therefore, trigger events must be defined that initiate the collection of specific data, such as object data, CAN data, Ethernet data, lidar data, radar data, or video data.

[0004] It is known that these vehicles are only tested with a limited number of known scenarios during the development phase. Therefore, there is a difference between the actual use and testing phases and the known and unknown scenarios. The unknown scenarios can thus only be collected and analyzed by the actual fleet. To reliably detect these unknown scenarios and initiate corresponding data collection, triggers are necessary for data collection and provision. Triggers are defined events that trigger the collection of specific data. These trigger events and the collected data do not necessarily have to be the same; in other words, the trigger event and the data to be collected can differ.

[0005] There is therefore a need to find out what a trigger event is for a corresponding emergency maneuver in order to be able to carry out appropriate data collection for the emergency maneuver, especially in the case of unknown scenarios, which are only randomly occurring scenarios or were still unknown during the manufacture or testing phase of the motor vehicles.

[0006] German patent application DE 11 2020 005 125 T describes a system for recording event data from an autonomous vehicle. The document proposes an EDR (Electronic Data Record) system operating scheme suitable for the appropriate investigation of the cause of a vehicle accident. Subsystems of an autonomous driving control system can determine whether an event fulfilling a preconfigured condition has occurred and send a trigger signal to an EDR system to initiate the recording of data elements related to the event when its occurrence is detected. The EDR system can record data elements useful for reconstructing a map of the external environment of an autonomous vehicle at the time the event occurred or for reconstructing the vehicle's internal environment.

[0007] WO 2020 / 224 910 A1 addresses the detection of edge cases through the application of a neural network to predict future vehicle environment data and the identification of an edge case when the prediction error exceeds a certain threshold. This allows for the identification of edge cases resulting from unexpected vehicle environment conditions or conditions that would otherwise cause the neural network to make inaccurate predictions. These edge cases can then be used to better train machine learning systems, for example, to train autonomous vehicle control systems. Alternatively, the identification of an edge case can indicate the need for corrective action and thus trigger a warning to a vehicle control system to implement corrective measures.Other methods and systems described here improve environmental monitoring by providing a computationally efficient and accurate means of merging sensor data and using this merged data to control the sensors, as they focus on areas that would most reduce uncertainty in the monitoring system.

[0008] The object of the present invention is to provide a method, a computer program product and a support system by means of which an improved trigger event for an emergency maneuver for data recording during an emergency maneuver of an at least partially automated motor vehicle can be realized.

[0009] This problem is solved by a method, a computer program product, and a support system according to the independent claims. Advantageous embodiments are specified in the dependent claims.

[0010] One aspect of the invention relates to a method for determining a trigger event for data recording during an emergency maneuver of an at least partially automated motor vehicle using a driver assistance system. Vehicle-internal data is stored for a predetermined period using a storage device of the driver assistance system. The occurrence of the emergency maneuver is determined by an electronic computer unit of the driver assistance system. The stored data is then made available by the electronic computer unit depending on the determined event. The provided data is analyzed for anomalies by the electronic computer unit, and the trigger event is determined based on this analysis.

[0011] This allows a reliable trigger event for data recording during an emergency maneuver.

[0012] The specific intention is that the analysis will not focus on the emergency maneuver itself, but rather on the triggering event that necessitates data recording for the emergency maneuver, particularly to comply with legal regulations. Specifically, if an emergency maneuver is triggered during at least partially automated or fully automated operation of motor vehicles, a corresponding analysis of the data that led to the maneuver is required. However, this necessitates data recording prior to the actual emergency maneuver in order to enable such analysis.

[0013] Furthermore, it is necessary to determine when data recording is to be carried out before the emergency maneuver and which data is to be evaluated accordingly. The invention provides that a trigger event for data recording is defined. In other words, it is not determined when and whether an emergency maneuver should be carried out, but rather that data recording is to be carried out because of the emergency maneuver and which corresponding trigger event is to be performed.

[0014] In other words, the invention proposes to perform an analysis of the stored data and to evaluate it as a trigger event with regard to a time and type of data recording.

[0015] The vehicle must be operating at least at SAE Level 2 or higher. In other words, the vehicle is at least partially automated. This means that the vehicle's longitudinal and / or lateral acceleration systems can be at least partially automated, for example, via a driver assistance system.

[0016] In other words, the aim of the invention is to find new trigger conditions for emergency maneuvers, which are in particular minimal-risk maneuvers, in order to identify and analyze unknown critical scenarios for at least partially automated motor vehicles.

[0017] The at least partially automated motor vehicles are in particular vehicles belonging to a fleet, in other words not test vehicles, but vehicles already in operation.

[0018] According to an advantageous embodiment, the stored data and / or the triggering event are transmitted to an external electronic computing device. This external electronic computing device can be configured as a server or a backend. In other words, the raw data can be transmitted to the external electronic computing device, and, for example, an analysis of the raw data can be performed externally. Alternatively, the triggering event determined internally by the vehicle can be transmitted to the external electronic computing device and, for example, compared with other fleet data to verify that the identified triggering event is also a significant triggering event within the fleet. Thus, a new triggering event can be determined and initiated externally and on a fleet-wide basis.

[0019] It is also advantageous if the analysis is performed internally within the vehicle. In other words, the analysis of the stored data takes place within the vehicle, and the triggering event is determined internally. This triggering event can then be transmitted, particularly via a communication device within the vehicle, to an external electronic computing unit. Thus, the triggering event can be used internally within the vehicle and still reliably transmitted to the external computing unit for fleet data analysis.

[0020] It is also advantageous if the analysis is performed externally to the vehicle. For example, the analysis can then be carried out by the vehicle's external electronic computing unit. This saves computing capacity within the vehicle's internal electronic computing unit and allows the analysis, which can sometimes be very complex, to be performed externally.

[0021] In a further advantageous embodiment, the triggering event is transmitted to at least one other vehicle for consideration. For example, the vehicle-external computing device can be configured to perform an analysis of further triggering events and, in particular upon verification of the triggering event, transmit this to the other vehicles in the fleet, so that they too are equipped with the triggering event in the future, enabling reliable data recording for the emergency maneuver.

[0022] It is also advantageous to analyze data over a specified period prior to the emergency maneuver. For example, the data can be stored in a ring buffer. Data can be stored, for instance, for a period of 30 seconds before the emergency maneuver. Should an emergency maneuver occur, the data, particularly that collected 30 seconds prior, can be analyzed and evaluated to reliably determine the triggering event.

[0023] Furthermore, an advantageous embodiment of the system may provide for the consideration of the vehicle's environmental conditions during the analysis. For example, road conditions, weather conditions, lighting conditions, and the like can be included as environmental factors. This enables an improved analysis of the triggering event.

[0024] It is also advantageous to consider the vehicle's position during the analysis. For example, it is possible to determine which street the vehicle is on or in which region it is located. Based on this position, further information, such as weather data, can then be used to reliably perform the analysis and determine the triggering event.

[0025] The presented method is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means which, when the program code means are processed by the electronic computing unit, cause an electronic invoice to carry out a method according to the preceding aspect.

[0026] Furthermore, the invention also relates to a computer-readable storage medium containing the computer program product.

[0027] A further aspect of the invention relates to a support system for determining a trigger event for data recording during an emergency maneuver of an at least partially automated motor vehicle, comprising at least one storage device and an electronic computing device, wherein the support system is configured to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the support system.

[0028] Parts of the process can be carried out in the motor vehicle or by an electronic computing device external to the motor vehicle.

[0029] The invention therefore also relates, at least in part, to a motor vehicle with the support system according to the preceding aspect, if the corresponding steps are carried out internally within the motor vehicle. Furthermore, it is specifically provided that the motor vehicle is designed as an at least partially automated or as a fully automated vehicle. For this purpose, the motor vehicle 1 can have an assistance system or an electronic vehicle guidance system.

[0030] Advantageous embodiments of the process are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, the support system, and the motor vehicle. The support system and the motor vehicle, in particular, possess tangible features to enable the execution of the corresponding process steps.

[0031] An electronic vehicle control system (EVS) can be understood as an electronic system designed to control a vehicle fully automatically or autonomously, in particular without requiring any intervention from a driver. The vehicle automatically performs all necessary functions, such as steering, braking, and / or acceleration maneuvers, monitoring and recording road traffic, and reacting accordingly. Specifically, the EVS can implement a fully automatic or fully autonomous driving mode of the motor vehicle according to Level 5 of the SAE J3016 classification. An EVS can also be understood as an advanced driver assistance system (ADAS), which supports the driver during partially automated or semi-autonomous driving.In particular, the electronic vehicle guidance system can implement a partially automated or semi-autonomous driving mode according to levels 1 to 4 of the SAE J3016 classification. Here and in the following, "SAE J3016" refers to the corresponding standard in the April 2021 version.

[0032] At least partially automated vehicle control can therefore include driving the vehicle in accordance with a fully automated or fully autonomous driving mode of Level 5 according to SAE J3016. At least partially automated vehicle control can also include driving the vehicle in accordance with a partially automated or semi-autonomous driving mode according to Levels 1 to 4 of SAE J3016.

[0033] The at least one control signal can be provided, for example, to one or more actuators of the motor vehicle, including, for example, one or more brake actuators and / or one or more steering actuators and / or one or more drive motors of the motor vehicle. The one or more actuators can influence the longitudinal and / or lateral steering of the motor vehicle in order to steer the motor vehicle at least partially automatically.

[0034] The assistance information can be output via a vehicle output device, such as a display and / or an audio output system and / or a haptic output system.

[0035] In the present disclosure, a computing unit can be understood, for example, as a data processing device with processing circuits. A computing unit can therefore perform arithmetic operations to process data. These arithmetic operations can also include indexed access to a data structure, such as a lookup table (LUT).

[0036] A computing unit may, in particular, comprise one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more systems on a chip (SoCs). The computing unit may also include one or more processors, for example, one or more microprocessors, one or more central processing units (CPUs), one or more graphics processing units (GPUs), and / or one or more signal processors, in particular one or more digital signal processors (DSPs). The computing unit may also comprise a physical or virtual cluster of computers or other units of the aforementioned type.

[0037] A processing unit can also include one or more hardware and / or software interfaces and / or one or more memory units. A memory unit can be implemented as volatile data storage, for example as dynamic random access memory (DRAM) or static random access memory (SRAM), or as non-volatile data storage, for example as read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or flash EEPROM, or ferromagnetic random access memory (FRAM).a magnetoresistive random access memory, MRAM (magnetoresistive random access memory), or a phase-change random access memory, PCRAM (phase-change random access memory).

[0038] The invention also includes the combination of the features of the described embodiments.

[0039] The following describes exemplary embodiments of the invention. This is illustrated by: Fig. 1 a schematic side view of an embodiment of a motor vehicle with an embodiment of a support system; Fig. 2 a schematic flowchart according to one embodiment of the method.

[0040] The embodiments described below are preferred embodiments of the invention. In these embodiments, the described components each represent individual features of the invention that can be considered independently of one another. Each of these features further develops the invention independently and can therefore be considered part of the invention individually or in a combination other than that shown. Furthermore, the described embodiments can also be supplemented by other features of the invention already described.

[0041] In the figures, functionally identical elements are each provided with the same reference symbols.

[0042] Fig. Figure 1 shows a schematic side view of an embodiment of a motor vehicle 1 with an embodiment of a support system 2. The motor vehicle 1 is designed as a motor vehicle that is at least partially automated or fully automated. The support system 2 can at least partially perform a method for determining a trigger event 3 for data recording during an emergency maneuver of the at least partially automated motor vehicle 1.

[0043] The support system 2 comprises at least one electronic computing device 4, which is preferably integrated within the vehicle. Furthermore, a storage device 5 is provided. In addition, at least one component 6 is provided, which records data relating to the emergency maneuver and / or components involved in the emergency maneuver. Furthermore, the vehicle 1 or the support system 2 comprises at least one communication device 7. The communication device 7 can, in particular, communicate with an electronic computing device 8 located outside the vehicle. It is also possible that, in one embodiment, the electronic computing device 8 located outside the vehicle is considered part of the support system 2.

[0044] Furthermore, in the Fig. 1 another fleet 9 was shown, which is made up of a large number of other motor vehicles.

[0045] In particular, the Fig. 1. Thus, a method for determining the triggering event 3. In this process, vehicle-internal data, for example from component 6, is stored for a predetermined period using the storage device 5. The occurrence of the emergency maneuver is then determined using the electronic computing device 4. The stored data is then made available, depending on the determined emergency maneuver, using the electronic computing device 4 and / or the vehicle-external electronic computing device 8. The provided data is then analyzed for anomalies using the electronic computing device 4 and / or the vehicle-external electronic computing device 8. The triggering event 3 is then determined based on the analysis using the electronic computing device 4 and / or the vehicle-external electronic computing device 8.

[0046] In particular, it may be provided that the stored data and / or the trigger event 3 are transmitted to the vehicle-external electronic computing device 8. As already mentioned, the analysis can be carried out either within the vehicle or externally.

[0047] Furthermore, it may be provided that the trigger event 3 is transmitted to at least one other motor vehicle, in particular to fleet 9, for consideration.

[0048] Furthermore, the data will be analyzed over the specified period before the emergency maneuver begins.

[0049] It may also be stipulated that environmental conditions 10 of the vehicle 1 are taken into account in the analysis. Furthermore, the position of the vehicle 1 may also be taken into account in the analysis.

[0050] Fig.Figure 2 shows a schematic flowchart according to one embodiment of the method. In a first step S1, data collection takes place. This data can be stored, for example, in a ring buffer, and at least the last 30 seconds can be made available as data. CAN signals or Ethernet signals can be stored in this way. Furthermore, diagnostic data from electronic computing devices of the vehicle 1 can be stored. Operating states and event information, such as excessively high battery temperature, can also be stored. Environmental information, such as object data, temperature, and weather information, can also be stored. Additional data from the vehicle 1, such as position P, speed, driving status, and time, can also be stored.

[0051] In a second step, S2, the trigger event 3 is located, particularly based on an anomaly search, once the emergency maneuver has occurred. Specifically, in the second step, S2, a corresponding anomaly search is performed whenever vehicle 1 executes an emergency maneuver. The data from the ring buffer, for example, the last 30 seconds, is then made available. This data is analyzed and filtered, for example, within vehicle 1. All data that deviate from the expected behavior, as well as data that correlate with it, can be used. Furthermore, anomalies can be detected, such as signals that usually correlate but no longer do.

[0052] This data can be stored locally or sent to the vehicle's external electronic computing unit 8 and tagged with the corresponding reason for the emergency maneuver, the time and location, the software version, the temperature and weather conditions, as well as environmental information such as an object list and / or the dynamics of the environment. The relevant data are then determined and a new trigger event 3 is provided.

[0053] In the third step, S3, an evaluation of the new trigger event 3 takes place. This can be carried out internally within the vehicle or externally, in particular by comparing it with other vehicles in fleet 9, specifically to determine whether they have, for example, identified the same trigger event 3. Specifically, the evaluation assesses whether trigger event 3 was identified multiple times, whether the same trigger event 3 was identified in the same geographical area, whether trigger event 3 was identified in several vehicles in fleet 9, and whether trigger event 3 was assigned the same labels.

[0054] In the fourth step, S4, trigger event 3 is classified as relevant and accordingly established in fleet 9. In this process, trigger event 3, or rather trigger events 3, are used for the other vehicles. Potential geographical dependencies and vehicle versions 1 can also be taken into account.

[0055] In particular, in the fourth step S4, a usage and correction phase can still be taken into account, in which the newly determined trigger event 3 is further verified accordingly. Reference symbol list 1 motor vehicle 2 Support system 3. Triggering event 4 electronic computing equipment 5 Storage setup 6 components 7 Communication device 8 vehicle-external electronic computing device 9 Fleet 10 Environmental conditions P Position S1 - S4 Steps of the procedure QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] DE 11 2020 005 125 T

[0006] WO 2020 / 224 910 A1

[0007]

Claims

[1] Method for determining a trigger event (3) for data recording during an emergency maneuver of a motor vehicle (1) that is at least partially automated using a support system (2), comprising the steps: - Storing vehicle-internal data over a specified period of time using a storage device (5) of the support system (2); - Determining the occurrence of the emergency maneuver by means of an electronic computing device (4) of the support system (2); - Providing the stored data depending on the specific emergency maneuver using the electronic computing device (4); - Analyzing the provided data for anomalies using the electronic computing device (4); and - Determining the triggering event (3) depending on the analysis using the electronic computing device (4). [2] Method according to claim 1, characterized by, that the stored data and / or the triggering event (4) are transmitted to an electronic computing device (8) external to the motor vehicle. [3] Method according to claim 1 or 2, characterized by that the analysis is carried out internally within the vehicle. [4] Method according to claim 1 or 2, characterized by that the analysis is carried out externally to the motor vehicle. [5] Method according to any one of the preceding claims, characterized by , that the triggering event (3) is transmitted to at least one other motor vehicle for consideration. [6] Method according to any one of the preceding claims, characterized by that data over the specified period before the emergency maneuver is carried out will be analyzed. [7] Method according to any one of the preceding claims, characterized by , that environmental conditions (10) of the motor vehicle (1) are taken into account in the analysis. [8] Method according to any one of the preceding claims, characterized by , that a position (P) of the motor vehicle (1) is taken into account in the analysis. [9] Computer program product comprising program code means which cause an electronic computing device (4) to perform a method according to any one of claims 1 to 8 when the program code means are executed by the electronic computing device (4). [10] Support system (2) for determining a trigger event (3) for data recording during an emergency maneuver of a motor vehicle (1) that is at least partially automated, comprising at least one storage device (5) and an electronic computing device (4), wherein the support system (2) is configured to carry out a method according to any one of claims 1 to 8.

Images