DE102021209315A1 - Method for operating an infrastructure system for driving support for at least partially automated motor vehicles - Google Patents

Abstract

According to a first aspect of the invention, a method for operating an infrastructure system for driving support of motor vehicles that are at least partially automated is proposed. The method provides that initially incoming V2X messages are received, in particular by a communication unit of the infrastructure system, the V2X messages including environmental information about the environment of an infrastructure environmental sensor system of the infrastructure system. These V2X messages can be sent, for example, by one or more vehicles that are currently located or moving within the range of the infrastructure environment sensors of the infrastructure system. The environment information of the received V2X messages is now compared with data generated by the infrastructure environment sensors. Depending on the result of the comparison, suitable measures for the infrastructure environment sensors are determined and initiated.

Description

The invention relates to a method for operating an infrastructure system for driving support for at least partially automated motor vehicles. The invention also relates to an infrastructure system for driving support for at least partially automated motor vehicles. The invention also relates to a computer program.

State of the art

In the case of future services provided by an infrastructure system for driving support for fully or partially automated motor vehicles, such fully or partially automated (highly automated) vehicles can receive information from surrounding vehicles and in particular from infrastructure sensors. This can be done, for example, via object lists (e.g. in the form of a "Collective Perception Message" (CPM)) or in the form of direct control commands, which are sent via V2X, e.g. with the DSRC or C-V2X technologies. Based on the object lists, the vehicle can independently make decisions about its lateral and longitudinal control. In both cases, it is therefore essential that the information provided by the infrastructure system is correct, otherwise accidents can occur.

Particularly in scenarios in which an onboard sensor system (e.g. radar, camera) of the fully or partially automated vehicle does not work properly (e.g. at a tunnel entrance), it is important that the infrastructure data is correct, since the vehicle itself is not checked or checked Can carry out a plausibility check of the data using its own sensors.

Reasons for errors in the detection can be, for example, that a sensor has turned or was turned or, for example, a lens of a camera or an antenna of a radar sensor of the infrastructure system is dirty or has been sprayed with water. However, technical program errors can also occur, for example because a program or part of the system has crashed.

The disclosure document DE 10 2020 100 027 A1 discloses receiving a planned path from a vehicle along with status of a perception subsystem. Remedial action is initiated when it is determined that the status of the perception subsystem is healthy and the planned path deviates from a detected path by more than a threshold. The remedial action may include commanding the vehicle to stop. The sensing system may include a vehicle sensor. The instructions may further include instructions for determining the detected path based on data from an infrastructure sensor and data provided by a second vehicle.

The disclosure document DE 10 2020 105 399 A1 shows a recognition of changed driving conditions through an infrastructure. A corresponding system includes a computer, which includes a processor, and a memory. The memory stores instructions such that the processor is programmed to determine two or more sets of vehicle operating parameter values from each of a plurality of vehicles at a location over a period of time. Determining the two or more groups includes grouping data from the plurality of vehicles based on proximity to two or more corresponding medians. The processor is further programmed to determine a reportable condition when an average value for a group representing a largest number of vehicles differs from a baseline value by more than a threshold value.

Disclosure of Invention

It can be seen as one of the tasks underlying the invention, particularly in real time, to ensure that an infrastructure environment sensor system of the infrastructure system acquires correct measured values, on the basis of which information for driving support is sent to fully or partially automated motor vehicles that are moving within an infrastructure equipped with the infrastructure system , to be sent.

According to a first aspect of the invention, a method for operating an infrastructure system for driving support of motor vehicles that are at least partially automated is proposed. The method provides that initially incoming V2X messages are received, in particular by a communication unit of the infrastructure system, the V2X messages including environmental information about the environment of an infrastructure environmental sensor system of the infrastructure system. These V2X messages can be sent, for example, by one or more vehicles that are currently located or moving within the range of the infrastructure environment sensors of the infrastructure system. The environment information of the received V2X messages is now compared with data generated by the infrastructure environment sensors. Depending on the result of the comparison, suitable measures for the infrastructure environment sensors are determined and initiated.

According to a second aspect of the invention, a device for driving assistance proposed at least partially automated motor vehicles. The device includes a computing unit and a communication unit, which is designed to receive incoming V2X messages, the V2X messages including environmental information about the environment of an infrastructure environmental sensor system. The communication unit is also designed to make the environmental information available to the processing unit. The computing unit is designed to compare environmental information of the received V2X messages with data generated by the infrastructure environment sensors and depending on the comparison to determine and initiate suitable measures for the infrastructure environment sensors according to a method according to the first aspect of the invention.

According to a third aspect of the invention, an infrastructure system for driving support for at least partially automated motor vehicles is proposed. The infrastructure system includes a device according to the second aspect of the invention. The infrastructure system also includes an infrastructure environment sensor system with at least one environment sensor. The environment sensor is designed to collect information about its environment, in particular information about objects in its environment, and the infrastructure environment sensor system is designed to generate data that represent the information and to provide this data to the processing unit of the device, for example by the data be transmitted wirelessly or wired to the communication unit of the device.

The invention is based on the idea that faults in an infrastructure environment sensor system, for example dirty or misaligned environment sensors, can be detected quickly and efficiently by comparing the environment information generated by the infrastructure environment sensor system with information that is recorded at the same time by vehicles in the environment of the infrastructure environment sensor system became. The information provided by the vehicles via V2X message includes information about the environment, which is also recorded by the infrastructure environment sensors. For example, the information includes properties of objects in the environment, such as coordinates, speeds, dimensions, direction of movement, etc.

The data generated by the infrastructure environment sensor system can be generated here in particular by a sensor data fusion of the measurement data from a number of environment sensors. Errors that can occur in such a sensor data fusion can be efficiently detected by the invention.

Device features result analogously from corresponding process features and vice versa. This therefore means that technical functionalities of the method result from corresponding technical functionalities of the devices and vice versa. The same applies to system features which result analogously from process features and/or device features and vice versa.

Technical features of the method for infrastructure-supported assistance in a motor vehicle result analogously from corresponding technical features of the method for at least partially automated driving of a motor vehicle and vice versa.

According to one embodiment, an infrastructure environment sensor system comprises one or more environment sensors, which are spatially distributed within the infrastructure.

An environment sensor is, for example, one of the following environment sensors: a radar sensor, an ultrasonic sensor, a video sensor, an infrared sensor, a lidar sensor or a magnetic field sensor.

The data generated by the infrastructure environment sensors include, for example, sensor data from individual environment sensors and/or data generated by a sensor data fusion of data from at least two environment sensors.

The data generated by the infrastructure environment sensors are generated, for example, in the form of object lists, with a position and/or a speed being determined for each detected object and transferred to the object list.

The incoming V2X messages also include object lists, for example, with a position and/or speed also being available here for each object. This achieves the technical advantage that the environmental information of the received V2X messages can be compared efficiently with data generated by the infrastructure environmental sensor system, for example by being able to compare objects in the respective object lists and their properties. In other words, a verification of the data generated by the infrastructure environment sensor system takes place.

A V2X message is to be understood within the scope of the present invention as a digital message that is transmitted to the infrastructure system, in particular wirelessly, by a road user, for example a motor vehicle. The infrastructure system can also be used in some designs Send gene of the invention V2X messages to vehicles.

The V2X messages that can be received include the so-called Cooperative Awareness Messages (CAM), for example in Europe. Here, vehicles send their own position, speed and direction of travel, among other things. This standard is already implemented by certain vehicles available on the market. Another example of a V2X message is the so-called Vulerable Road User Awareness Message (VAM). "Vulnerable Road Users" (VRUs), i.e. particularly vulnerable road users such as cyclists or pedestrians, can share information about their position, speed, direction of movement and, in particular, about their predicted trajectory.

Another example of a V2X message is the so-called Decentralized Environmental Notification Message (DENM). Here, vehicles send warnings about potential hazards, such as broken-down vehicles. This standard is also already implemented by vehicles available on the market.

Another example of a V2X message is the so-called Collective Perception Message (CPM). Here vehicles or other infrastructure systems send an object list with all objects and vehicles perceived in their environment.

Properties (position, speed, direction of movement, ...) of objects in particular are transmitted in all of these V2X messages. These properties are collected by the infrastructure system and can then be compared with object properties in object lists that were generated by the environment sensors of the infrastructure environment sensor system or by a sensor data fusion. Although these properties in the V2X messages can contain small inaccuracies, they are considered to be much more accurate than they can be determined by the infrastructure system, since automated motor vehicles, in particular highly or fully automated motor vehicles, must be able to locate themselves with great accuracy.

One or more properties of objects are preferably compared in the comparison. Depending on the result of this comparison, a systematic deviation in the sensor alignment is concluded, for example. A systematic deviation in the sensor alignment can thus be assumed if the comparison results in a similar deviation with regard to the direction or position of the object and/or the speed of the object for different objects. On the other hand, a systematic deviation in the sensor alignment can be ruled out, for example, if the comparison results in randomly distributed deviations.

A correction of the generated data can preferably be carried out depending on the comparison. For example, if a bias in sensor alignment has been detected, this information can be used to correct the generated data to include a specific offset value that can be calculated, for example, from the bias previously determined.

Alternatively or additionally, depending on the comparison, a confidence value and/or a confidence range can be assigned to the data generated by the infrastructure environment sensor system or one or more specific environment sensors of the infrastructure environment sensor system. Alternatively or additionally, this can also be done for a sensor data fusion function. This confidence value or the confidence range indicates, for example, a measure of the accuracy of the relevant surroundings sensor or the relevant sensor data fusion.

In one embodiment of the device for infrastructure-supported assistance in a motor vehicle, the processing unit and the communication unit are comprised by an RSU. This brings about the technical advantage, for example, that the method can be carried out efficiently.

The abbreviation "RSU" stands for "Road Side Unit". The term "road-side unit" can be translated into German as "roadside unit" or "roadside infrastructure unit". Instead of the term "RSU", the following terms can also be used synonymously: roadside unit, roadside infrastructure unit, communication module, roadside communication module, roadside radio unit, roadside transmitter station.

The communication unit is preferably set up to send V2X messages to motor vehicles within the infrastructure, the V2X messages sent comprising information representing the specific measures.

The arithmetic unit is preferably designed to generate a merged data set from data generated using the measured values from at least two surroundings sensors, which data record represents information about the surroundings of the at least two surroundings sensors, in particular information about objects in the surroundings, the arithmetic unit being designed the environment information of the emp Compare captured V2X messages to the merged data set. For this purpose, the computing unit includes, for example, one or more verifier modules.

In a preferred embodiment of the invention, the comparison of the received V2X messages with the data generated by the infrastructure environment sensor system includes determining a deviation. In particular, the deviation can be determined based on a correlation coefficient and/or a Euclidean distance of the environmental information and the data generated by the infrastructure environmental sensor system. For example, both the received V2X messages and the data generated by the infrastructure environment sensors include coordinates of objects within the infrastructure. These coordinates can be compared and a Euclidean distance and/or a correlation coefficient can be calculated. The Euclidean distance and/or the correlation coefficient can be used as a measure of a deviation.

The measures are preferably determined as a function of the deviation determined, in particular as a function of whether the deviation exceeds a predetermined limit value. In this case, it is preferably possible to wait until the deviation exceeds a predetermined limit value over a specified period of time.

It is preferably possible to compare data from the V2X messages with data generated by the infrastructure environment sensor system over a specific period of time and to form average or mean values therefrom. In this way, inaccuracies due to outliers in individual status measurements from individual vehicles or inaccuracies in individual infrastructure system measurements can be filtered out.

The measures can include, for example, deactivating the sending of V2X messages by the infrastructure system and/or sending information to the motor vehicles within the infrastructure. It can thus be efficiently avoided that the infrastructure system sends inaccurate or incorrect information to the at least partially automatically guided motor vehicles, which could otherwise endanger the motor vehicles and/or their surroundings. By sending information to the motor vehicles within the infrastructure, they can be informed about the specific deviations, so that it can be decided, for example, by a system of a respective motor vehicle whether and in what form provided by the infrastructure system environmental information to support at least partially automated driving function can be used or not.

If, after deactivation, it is determined that the system is working properly again, the infrastructure system can automatically reactivate the sending of messages or wait for a manual human check.

The phrase "at least partially automated" includes one or more of the following cases: assisted driving, partially automated driving, highly automated driving, fully automated driving of a motor vehicle.

Assisted driving means that a driver of the motor vehicle continuously carries out either the lateral or the longitudinal guidance of the motor vehicle. The respective other driving task (that is, controlling the longitudinal or lateral guidance of the motor vehicle) is carried out automatically. This means that when driving the motor vehicle with assistance, either the lateral or the longitudinal guidance is controlled automatically.

Partly automated driving means that in a specific situation (for example: driving on a motorway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings) and/or for a certain period of time, a longitudinal and a Lateral guidance of the motor vehicle are controlled automatically. A driver of the motor vehicle does not have to manually control the longitudinal and lateral guidance of the motor vehicle. However, the driver must constantly monitor the automatic control of the longitudinal and lateral guidance in order to be able to intervene manually if necessary. The driver must be ready to take full control of the vehicle at any time.

Highly automated driving means that for a certain period of time in a specific situation (for example: driving on a freeway, driving in a parking lot, overtaking an object, driving in a lane defined by lane markings), longitudinal and lateral guidance of the motor vehicle be controlled automatically. A driver of the motor vehicle does not have to manually control the longitudinal and lateral guidance of the motor vehicle. The driver does not have to constantly monitor the automatic control of the longitudinal and lateral guidance in order to be able to intervene manually if necessary. If necessary, a takeover request is automatically issued to the driver to take over control of the longitudinal and lateral guidance, in particular with a sufficient time reserve. The driver must therefore potentially be able to to take over the control of the longitudinal and lateral guidance. Limits of the automatic control of the lateral and longitudinal guidance are recognized automatically. With highly automated guidance, it is not possible to automatically bring about a risk-minimum state in every initial situation.

Fully automated driving means that in a specific situation (for example: driving on a freeway, driving within a parking lot, overtaking an object, driving within a lane that is defined by lane markings), longitudinal and lateral guidance of the motor vehicle are controlled automatically. A driver of the motor vehicle does not have to manually control the longitudinal and lateral guidance of the motor vehicle. The driver does not have to monitor the automatic control of the longitudinal and lateral guidance in order to be able to intervene manually if necessary. Before the automatic control of the lateral and longitudinal guidance is ended, the driver is automatically prompted to take over the driving task (controlling the lateral and longitudinal guidance of the motor vehicle), in particular with a sufficient time reserve. If the driver does not take over the task of driving, the system automatically returns to a risk-minimum state. Limits of the automatic control of the lateral and longitudinal guidance are recognized automatically. In all situations it is possible to automatically return to a risk-minimum system state.

Driverless control or guidance means that, regardless of a specific application (for example: driving on a freeway, driving within a parking lot, overtaking an object, driving within a lane that is defined by lane markings), longitudinal and lateral guidance of the motor vehicle be controlled automatically. A driver of the motor vehicle does not have to manually control the longitudinal and lateral guidance of the motor vehicle. The driver does not have to monitor the automatic control of the longitudinal and lateral guidance in order to be able to intervene manually if necessary. The longitudinal and lateral guidance of the vehicle is thus automatically controlled, for example, for all types of roads, speed ranges and environmental conditions. The complete driving task of the driver is thus automatically taken over. The driver is therefore no longer required. The motor vehicle can therefore drive from any desired starting position to any desired destination without a driver. Potential problems are solved automatically, i.e. without the help of the driver.

Remote control of the motor vehicle means that lateral and longitudinal guidance of the motor vehicle are controlled remotely. This means, for example, that remote control signals for remote control of the lateral and longitudinal guidance are sent to the motor vehicle. The remote control is performed, for example, by means of a remote control device.

Advantages of the invention are that errors in the infrastructure environment sensor system and/or the sensor data fusion can be detected quickly. The V2X messages used for this are sent anyway by the appropriately equipped vehicles and can be received by the infrastructure system. No additional hardware is therefore necessary to implement the invention.

In conventional methods, the different environment sensors are often compared with one another. However, it is generally not known which of the surroundings sensors supplies the most accurate values and which supplies incorrect sensor data. In addition, this often requires several redundant sensor sets. However, this approach can also be combined with the approach of this invention, resulting in an improvement in the safety layer, ie the overall security of the infrastructure system with regard to avoiding damage to road users.

Furthermore, approaches are already known for including incoming V2X messages in the sensor data fusion and thereby improving the accuracy of the properties (position, etc.) of the objects. Since the equipment rate of all vehicles with V2X communication will remain below 100% for many years, only a small percentage of the objects can be improved. With the approach proposed here, however, despite the low equipment rate, a verification of the surroundings sensors and the sensor data fusion can be carried out and faults can be reliably detected.

Furthermore, approaches are already known for checking incoming V2X messages for the trustworthiness of the sender, for example by reading the attached digital signature. It can thereby be ensured that the method according to the invention cannot be overridden by corrupted messages.

character list

• 1 zeigt ein Infrastruktursystem gemäß einem möglichen Ausführungsbeispiel der Erfindung.
• 2 a) zeigt schematisch eine Vorrichtung zur Fahrunterstützung von zumindest teilautomatisiert geführten Kraftfahrzeugen gemäß dem Stand der Technik.
• 2 b) zeigt schematisch eine Vorrichtung zur Fahrunterstützung von zumindest teilautomatisiert geführten Kraftfahrzeugen gemäß einem ersten Ausführungsbeispiel der Erfindung.
• 2 c) zeigt schematisch eine Vorrichtung zur Fahrunterstützung von zumindest teilautomatisiert geführten Kraftfahrzeugen gemäß einem zweiten Ausführungsbeispiel der Erfindung.
• 3 a) und 3 b) zeigen beispielhaft jeweils einen Vergleich von Umgebungsinformationen der empfangenen V2X-Nachrichten mit durch die Infrastrukturumfeldsensorik erzeugten Daten gemäß einem Ausführungsbeispiel der Erfindung.
• 4 a) und 4 b) zeigen beispielhaft jeweils einen Vergleich von Umgebungsinformationen der empfangenen V2X-Nachrichten mit durch die Infrastrukturumfeldsensorik erzeugten Daten gemäß einem weiteren Ausführungsbeispiel der Erfindung wobei abhängig von dem jeweiligen Vergleich ein jeweiliger Konfidenzbereich eines Umfeldsensors bestimmt wird.
• 5 zeigt ein Ablaufdiagramm eines Verfahrens nach einem Ausführungsbeispiel der Erfindung.

Embodiments of the invention are described in detail with reference to the attached figures.

• 1 shows an infrastructure system according to a possible embodiment of the invention.
• 2 a) shows schematically a device for driving assistance of at least partially automated guided motor vehicles according to the prior art.
• 2 B) shows schematically a device for driving assistance of at least partially automated guided motor vehicles according to a first embodiment of the invention.
• 2c) shows schematically a device for driving assistance of at least partially automated guided motor vehicles according to a second embodiment of the invention.
• 3 a) and 3 b) each show an example of a comparison of environmental information of the received V2X messages with data generated by the infrastructure environmental sensor system according to an embodiment of the invention.
• 4 a) and 4 b) show an example of a comparison of environmental information of the received V2X messages with data generated by the infrastructure environmental sensor system according to a further exemplary embodiment of the invention, a respective confidence range of an environmental sensor being determined depending on the respective comparison.
• 5 shows a flow chart of a method according to an embodiment of the invention.

Preferred Embodiments of the Invention

In the following description of the exemplary embodiments of the invention, the same elements are denoted by the same reference symbols, with a repeated description of these elements being dispensed with if necessary. The figures represent the subject matter of the invention only schematically.

1 shows a schematic top view of an infrastructure system 100, a road 30 and several road users 12, 14, 16, 18 that are on the road in the area of the infrastructure system 100. This means in particular that road users 12 , 16 , 18 equipped with appropriate communication means can send V2X messages to the infrastructure system 100 and possibly also receive V2X messages from the infrastructure system 100 . In the exemplary situation shown, a road user 12 is in the form of a truck. Another road user 16 is designed as a car. The road users 12 and 16 are technically equipped to send V2X messages, eg Cooperative Awareness Messages (CAM) to the infrastructure system 100 using a wireless communication link 15 . Another road user 18 is designed as a bicycle. The road user 18 is technically equipped to send V2X messages, eg Vulnerable Road User Awareness Messages (VAM) to the infrastructure system 100 using a wireless communication link 15 . Another road user 14, in this example a bus, is not equipped to send V2X messages.

The infrastructure system 100 includes a communication unit 50 which is designed to receive the incoming V2X messages. These V2X messages received from road users 12, 16 and 18 include information about the surroundings, in particular information about objects and their properties such as position, speed, etc.

The infrastructure system 100 also includes a computing unit 40 which is connected to the communication unit via a data line 55 in terms of communication technology, it being possible for the connection to be wireless or wired. The communication unit 50 can make the received V2X messages and/or the environmental information contained therein available to the processing unit 40 via the data line 55 . The communication unit 50 is also designed to send information, e.g.

The infrastructure system 100 also includes an infrastructure environment sensor system 20, which in this example has an environment sensor 22 designed as a radar sensor. In this example, the environment sensor 22 is fixed in a stationary manner to a mounting device 28 (e.g. a gantry sign or the like) spanning the road 30 . The environment sensor has a field of vision 24 . Objects that are within the field of view 24 can be detected by the environment sensor 22 and data, in particular object lists with properties such as position, speed, of the detected objects can be generated. In the situation shown, environment sensor 22 can, for example, detect road users 14, 16 and 18 as objects.

The infrastructure environment sensor system 20 is connected to the computing unit 40 in terms of communication via a data line 25, it being possible for the connection to be wireless or wired. About the data line 25, the infrastructure Surrounding area sensors 20 to provide the data generated to the computing unit 40.

The processing unit 40 is designed to compare the received V2X messages with the data generated by the infrastructure environment sensors 20 . Depending on the comparison, suitable measures for the infrastructure environment sensor system 20 can be determined and initiated. If the comparison shows, for example, a large discrepancy between the object properties determined by the infrastructure environment sensors 20 and those in the received V2X messages, the environment sensor 22 in question, which generated the data, can be shut down or the infrastructure environment sensors 20 can correct the generated data based on the V2X messages.

In 2 a) a stationary device 101` for driving support of at least partially automated motor vehicles is shown, as is known from the prior art. The device 101' comprises a computing unit 40' and a communication unit 50'. The computing unit 40' is set up to receive measurement data 24' from two surroundings sensors 21', 22' of an infrastructure surroundings sensor system 20'. The measurement data 24' include, for example, object lists with object properties associated with specific detected objects. These object lists are fed to a fusion module 140', which generates a fused data set; the fusion module can be designed as a hardware module or as a software module. The merged data set now includes a more complete object list. This is fed to a communication module 50' via a data connection 55'. The communication module 50' is designed to send V2X messages to road users using a wireless communication link 15' and/or to receive V2X messages from road users using the wireless communication link 15'. In particular, the communication module 50' can transmit the merged measurement data or the merged data set to an at least partially automated motor vehicle, which can be operated at least partially automatically on the basis of this data. In this embodiment, there is no verification, which means that the data sent by the communication module 50' can be faulty.

in the in 2 B) Schematically illustrated embodiment of a stationary device 101 for driving support of at least partially automated motor vehicles, the invention is used to compare the data at several points with a verifier with the incoming V2X messages and thereby check them. The device 101 includes a computing unit 40 and a communication unit 150. The computing unit 40 is set up to receive measurement data 123, 124 from two environment sensors 121, 122 of an infrastructure environment sensor system 120. The measurement data 124 include, for example, object lists with object properties associated with specific detected objects.

By means of a communication unit 150, which is designed as a transmitter/receiver unit, to receive V2X messages from road users in the vicinity of the infrastructure sensor system 120 by means of a wireless communication link 115, V2X messages (e.g. CAM, DENM or VAM) are received and sent via a Data line 155 is transmitted to a read-in unit 180 of the arithmetic unit 40 . The reading unit 180 extracts object lists contained therein from the V2X messages, i.e. objects and their associated object properties. The different transmission latencies of the infrastructure environment sensor system 120 and the V2X information can also be compensated for in the reading unit 180, for example by comparing the time stamps contained and then carrying out a prediction of one of the two data sets. The communication unit 150 is also designed to send information, e.g.

The measurement data 123 of the first surroundings sensor 121 are initially supplied to a first verifier module 165 . Furthermore, the read-in module 180 makes the object lists extracted from the received V2X messages available to the first verifier module 165 . The verifier module 165 is designed to compare the object lists contained in the measurement data 124 with the object lists extracted from the received V2X messages and thus to verify them. For example, if the object lists include coordinates of the respective objects, the verifier module 165 may be configured to convert the coordinates into a common coordinate system and to determine a Euclidean distance between the objects. Alternatively, the conversion can also take place in the read-in module 180 , with only the comparison being carried out by the verifier module 165 .

Alternatively or additionally, the verifier module 165 can be designed to calculate correlation coefficients in each case. If the comparison results in a deviation that is in particular greater than a predetermined limit value or limit range, then it is concluded that surroundings sensor 121 has a defect, for example, or is, for example, defective is dirty, twisted, or otherwise restricted in its function. Depending on the size of the deviation, for example, the verifier module 165 can determine and initiate a measure for the first environment sensor 121 and/or the entire infrastructure environment sensor system 120 . A catalog of measures can be specified for this purpose, for example. In the event of a deviation that exceeds a predetermined limit value, for example, first surroundings sensor 121 can be deactivated or measurement data 123 from the first surroundings sensor can no longer be used. Alternatively or additionally, a V2X message can be generated and sent to road users in the vicinity of the infrastructure sensor system 120 by means of the communication unit 150 using the wireless communication link 115, which message contains the information that the first environment sensor 121 and/or the infrastructure sensor system 120 is currently not reliable can provide data. In the case of a smaller deviation, a correction of the measurement data 123 can be carried out as a measure, for example.

In parallel, the measurement data 124 of the second surroundings sensor 122 are supplied to a second verifier module 160 . Furthermore, the read-in module 180 makes the object lists extracted from the received V2X messages available to the second verifier module 160 . Like the first verifier module 165, the second verifier module 160 is designed to compare the object lists contained in the measurement data 124 with the object lists extracted from the received V2X messages and thus to verify them. For example, if the object lists include coordinates of the respective objects, the verifier module 160 may be configured to convert the coordinates into a common coordinate system and to determine a Euclidean distance between the objects. Alternatively or additionally, the verifier module 160 can be designed to calculate correlation coefficients in each case. If the comparison shows a deviation that is greater than a predetermined limit value or limit range, it is concluded that second surroundings sensor 122 has a defect, for example, or is dirty or twisted, for example, or is otherwise restricted in its function. Depending on the size of the deviation, for example, the verifier module 160 can determine and initiate a measure for the second environment sensor 122 and/or the entire infrastructure environment sensor system 120 . A catalog of measures can be specified for this purpose, for example. For example, if there is a deviation that exceeds a predetermined limit value, second surroundings sensor 122 can be deactivated or measurement data 124 from second surroundings sensor 122 can no longer be used. Alternatively or additionally, a V2X message can be generated and sent to road users in the vicinity of the infrastructure sensor system 120 by means of the communication unit 150 using the wireless communication link 115, which message contains the information that the second environment sensor 122 and/or the infrastructure sensor system 120 is currently not reliable can provide data. In the case of a smaller deviation, a correction of the measurement data 124 can be carried out as a measure, for example.

If the verifier modules 160 , 165 do not detect any major deviations in the measurement data 123 , 124 , the measurement data 123 , 124 are fed to a sensor data fusion module 140 . The sensor data fusion module 140 calculates a fused data set 145 comprising a fused object list from the measurement data 123, 124 or from the object lists comprised by the measurement data 123, 124 in a known manner. The merged data set 145 is fed to a third verifier module 167 .

The read-in module 180 makes the object lists extracted from the received V2X messages available to the third verifier module 167 . The third verifier module 167 is designed similarly to the first and second verifier module 160, 165 to compare the object lists contained in the merged data record 145 with the object lists extracted from the received V2X messages and thus to verify them. If the object lists include coordinates of the respective objects, for example, the verifier module 167 can be designed to convert the coordinates into a common coordinate system and to determine a Euclidean distance between the objects. Alternatively or additionally, the verifier module 167 can be designed to calculate correlation coefficients in each case. If the comparison results in a deviation that is in particular greater than a predetermined limit value or limit range, then it is concluded that the fusion module has carried out an incorrect calculation or is otherwise restricted in its function. Depending on the size of the deviation, for example, the verifier module 160 can determine and initiate an action. A catalog of measures can be specified for this purpose, for example. In the event of a deviation that exceeds a predetermined limit value, for example, the sensor data fusion can be deactivated or the fused data set 145 can no longer be used or sent to motor vehicles. Alternatively or additionally, a V2X message can be generated and sent by the communication unit 150 via the wireless communication link 115 to road users in the vicinity of the infrastructure sensor system 120, which contains the information that the sensor data fusion cannot currently provide reliable data. At a If the deviation is smaller, a correction of the merged data record 145 can be carried out as a measure, for example. If only minor deviations or no significant deviations are found, the merged data set can be transmitted to the communication device 150 wirelessly or by wire via the data line 156 . The communication unit 150 can send V2X messages comprising the information (object lists) of the merged data set 145 by means of the wireless communication link 115 to at least partially automated guided motor vehicles in the vicinity of the infrastructure sensor system 120, which they can use to support the at least partially automated driving function.

2c) shows an alternative embodiment of a stationary device 102 for driving support of at least partially automated motor vehicles. The components and mode of operation of the device 102 essentially correspond to those in 2 B) device 101 shown. The arithmetic unit 40 of the device 102 additionally comprises a decision-making module 190. The results of the verifier modules 160, 165 and 167 are fed to the decision-making module 190. The decision-maker module 190 is designed to compare the results generated by the verifier modules 160, 165 and 167 with one another. Depending on the comparison, conclusions can be drawn by the decision-maker module 190 as to which point in the infrastructure system an error has occurred, and can optionally determine and initiate additional measures accordingly. For example, sensor data fusion may be restarted by the sensor data fusion module 140 if only the verifier module 176 detects an anomaly. The decision-making module 190 can, for example, improve itself using machine learning methods and learn at which point in the system which error occurs under which conditions. If, for example, all environment sensors that are mounted on a specific mast of the infrastructure fail, the decision-maker module 190 can conclude that there is a problem with the power supply of this mast.

3 a) shows a coordinate system 210, which in this and the following examples as a UTM coordinate system (also referred to as global coordinate system), with the direction east (also easting or east value) to the right and the direction north (also northing or north value) being applied to the top. First object coordinates 212, 214, 216 and 218 are entered in coordinate system 210, which represent measured values for positions of objects that are measured by an environment sensor of an infrastructure environment sensor system (for example as in 1 shown) were recorded. Furthermore, second object coordinates 312, 316 and 318 are entered in the coordinate system 210, which correspond to object positions that were received from V2X messages from road users in the detection range of the environment sensor of the infrastructure environment sensor system. The object coordinates 212 and 312 belong to the same real object, for example the vehicle 12 in 1 . The object coordinate 212 was measured using the surroundings sensor 22 of the infrastructure surroundings sensor system 20 . The object coordinate 312 was, for example, transmitted by the vehicle 12 as its own position at the time of measurement using a V2X message. Similarly, object coordinates 216 and 316 represent the position of another object, such as vehicle 16; the object coordinates 218 and 318 also represent the bicycle 18 in this example. The vehicle 14 does not send any position information via V2X message, so only the object coordinates 214 measured by the environment sensor 22 of the infrastructure environment sensor system 20 are known for this.

Alternatively or in addition to the object coordinates, speeds, directions of movement, accelerations, or other object properties of road users 12, 16 and 18 can also be compared.

If, in this example, the respective Euclidean distance is determined as a measure for the deviation between the object coordinates 212 and 312, or 216 and 316, or 218 and 318 that belong together, it can be seen that the respective distances are below a predetermined limit value. It can also be seen that the deviations in the object coordinates detected by means of the surroundings sensor are statistically independent and are therefore very likely to be attributed to measurement inaccuracies. The initiation of measures is not necessary in this example. It can be assumed that the object coordinate 314 also has sufficient accuracy.

In 3 b) the results of a further measurement of the object coordinates in a coordinate system 220 are shown. In this example it can be seen that the object coordinates 212, 216 and 218 determined by the infrastructure environment sensor system 20 are systematically shifted by a similar distance in a similar direction (indicated by the vector 225) compared to the object coordinates 312, 316 and 318 transmitted by V2X messages . This can indicate, for example, that the environment sensor in question has been moved or rotated to its original installation position and alignment, so that a recalibration is required as a measure of the environment sensor may be necessary. As an alternative or in addition, the measured values 212, 214, 216 and 218 can be corrected by means of the determined vector 225 as a measure.

Another possible degradation measure according to the invention is that the detected object properties can be observed together with their confidences/inaccuracies and, in the event of a deviation, these confidences can be improved or corrected. This can also happen when there is no error, for example when the surroundings sensor has not been rotated and only the accuracy of the detection is not sufficient. This is in the 4 a) and b) shown. In the 4 a) and b) in turn, UTM coordinate systems 410 and 420 are shown with object coordinates 212, 214, 216, 218 measured by an infrastructure environment sensor system, and with object coordinates 312, 316, 318 received by V2X messages. As in 4 a) shown, each object coordinate 212, 214, 216, 218 measured by the infrastructure environment sensor system is assigned a confidence range 512, 514, 516, 518, which represents an expected measurement uncertainty and which depends, for example, on the distance and measurement angle to the environment sensor in question, or in the case of a sensor data fusion of the algorithm used and/or the parameters used. As can be seen, of the object coordinates 312, 316, 318 received by V2X messages, only the object coordinate 316 is within the confidence range 516 of the associated object coordinate 216 measured by the infrastructure environment sensor system.

According to one possible embodiment of the invention, a respective adaptation of the affected confidence regions 512 and 518 can now be determined and initiated as a measure for the infrastructure environment sensor system. this is in 4 b) shown. New confidence ranges 612 and 618 are determined which are large enough that the object coordinates 312, 318 received by V2X messages are within the new confidence ranges 612 and 618.

The confidence ranges 516, 514 and the new confidence ranges 612 and 618 can now be provided together with the associated object coordinates 212, 214, 216 and 218 detected by the infrastructure environment sensor system for at least partially automated motor vehicles for driving support.

5 shows a flow chart of a method according to the invention for operating an infrastructure system for driving support of motor vehicles that are at least partially automated. In a first step 1010, incoming V2X messages are received, in particular by a communication unit of the infrastructure system, the V2X messages including environmental information about the environment of an infrastructure environmental sensor system of the infrastructure system. In a second step 1030, the infrastructure environment sensor system of the infrastructure system generates data that includes information about the environment of the infrastructure environment sensor system, for example by receiving and/or evaluating measurement data from one or more environment sensors of the infrastructure environment sensor system. Steps 1010 and 1030 can be performed either sequentially or in parallel in time. In a third step 1050, the environment information of the received V2X messages is compared with the data generated by the infrastructure environment sensors and a discrepancy is determined. In step 1070, depending on the result of the comparison, suitable measures for the infrastructure environment sensor system are determined and initiated.

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was 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.

Patent Literature Cited

• DE 102020100027 A1 [0005]
• DE 102020105399 A1 [0006]

Claims (16)

Method for operating an infrastructure system (100) for driving support of motor vehicles that are at least partially automated, wherein - Incoming V2X messages are received, in particular by a communication unit (50, 150) of the infrastructure system (100), the V2X messages including environmental information about the environment of an infrastructure environmental sensor system (20, 120) of the infrastructure system (100), - the environment information of the received V2X messages is compared with data generated by the infrastructure environment sensors, - Wherein depending on the result of the comparison, suitable measures for the infrastructure environment sensors (20, 120) are determined and initiated. procedure after claim 1 , characterized in that the comparison comprises determining a deviation, the deviation being determined in particular on the basis of a correlation coefficient and/or a Euclidean distance of the environmental information and the data generated by the infrastructure environmental sensor system (20, 120). procedure after claim 2 , characterized in that the measures are determined depending on the specific deviation, in particular depending on whether the deviation exceeds a predetermined limit value for a short time or over a certain period of time. Method according to one of the preceding claims, characterized in that the measures include deactivating the sending of V2X messages by the infrastructure system (100) and/or sending information representing the result of the comparison to the motor vehicles within the infrastructure. Method according to one of the preceding claims, characterized in that data generated by the infrastructure environment sensor system (20, 120) is sensor data (123, 124) from individual environment sensors (22, 121, 122) and/or by a sensor data fusion of data from at least two environment sensors (121, 122) generated data (145). Method according to one of the preceding claims, characterized in that the data (123, 124, 145) generated by the infrastructure environment sensors (20, 120) are generated in the form of object lists, with at least one position and/or speed and/or Direction of movement is determined and transferred to the object list. Method according to one of the preceding claims, characterized in that the incoming V2X messages include object lists, with each object having a position and/or speed and/or direction of movement. Procedure according to one of Claims 4 or 5 , characterized in that the comparison compares properties of objects and, depending on the result of the comparison, a systematic deviation (225) in the sensor alignment of at least one environment sensor (22, 121 122) of the infrastructure environment sensor system (20, 120) is concluded. Method according to one of the preceding claims, characterized in that the generated data (123, 124, 145) is corrected as a measure dependent on the comparison. Method according to one of the preceding claims, characterized in that as a measure depending on the comparison to the infrastructure environment sensors (20, 120) and/or to one or more specific environment sensors (22, 121, 122) the infrastructure environment sensors (20, 120) and / or to a sensor data fusion module (140) or to the infrastructure environment sensor system (20, 120) and/or one or more specific environment sensors (22, 121, 122) of the infrastructure environment sensor system (20, 120) and/or to a sensor data fusion module (140). data, a respective confidence value and/or a confidence range (512, 514, 516, 518, 612, 618) is adapted and the infrastructure environment sensor system (20, 120) and/or the specific environment sensor(s) (22, 121, 122) of the infrastructure environment sensor system (20 , 120) and/or the sensor data fusion module (140). Method according to one of the preceding claims, characterized in that the environmental information of the V2X messages is generated by a respective environmental sensor system of the road user (12, 16, 18) sending the V2X message. Device (101, 102) for driving support for at least partially automated motor vehicles, comprising a computing unit (40) and a communication unit (50, 150), which is designed to receive incoming V2X messages, the V2X messages containing environmental information about the environment of an infrastructure environmental sensor system ( 20, 120) include, wherein the communication unit (50, 150) is designed to provide the environmental information of the processing unit (40), and wherein the Arithmetic unit (40) is formed, according to a method according to any one of the preceding Claims 1 until 11 to compare the environment information of the received V2X messages with the data generated by the infrastructure environment sensor system (20, 120) and, depending on the comparison, to determine and initiate suitable measures for the infrastructure environment sensor system (20, 120). Device (101, 102) according to claim 12 , characterized in that the communication unit (50, 150) is set up to send V2X messages to motor vehicles (12, 16, 18) within the infrastructure, the sent V2X messages comprising information representing the specific measures. Device (101, 102) according to one of Claims 12 or 13 , characterized in that the computing unit (40) is designed to generate a merged data set (145) from data generated by means of the measured values (123, 124) from at least two surroundings sensors (121, 122), which contains information on the surroundings of the at least two environment sensors (121, 122), in particular information on objects (12, 14, 16, 18) in the environment, with the processing unit (40) being designed to combine the environment information of the received V2X messages with the merged data set (145). compare. Infrastructure system (100) for driving support of at least partially automated guided motor vehicles comprising - a device (101) according to one of Claims 12 until 14 - an infrastructure environment sensor system (20, 120) with at least one environment sensor (22, 121, 122), the environment sensor (22, 121, 122) being designed to store information about its environment, in particular information about objects (12, 14, 16, 18). its environment, and the infrastructure environment sensor system (20, 120) is designed to generate data (123, 124) that represent the information and to make this data available to the processing unit (40). Computer program, comprising program code for carrying out the method according to one of Claims 1 until 11 , if the computer program runs on a computer.

Images