Method for verifying map real-time performance

Abstract

A method for verifying the real-time status of at least one digital map, in particular by a control unit, is disclosed, wherein the at least one digital map is received or called up, measurement data about the vehicle's surroundings are received, a vehicle position is determined within the at least one digital map based on landmarks, data of a driver assistance function are received, and a comparison between the vehicle position within the at least one digital map and the data of the driver assistance function is performed to verify the real-time status of the at least one digital map. In addition, a handover arrangement, a control unit, a computer program, and a machine-readable storage medium are disclosed.

Description

Technical Field

[0001] The invention relates to a method for verifying the real-time status of at least one digital map, in particular by means of a control unit, a control unit, a computer program, and a machine-readable storage medium. Background Art

[0002] Methods for crowd-based mapping of roads that can be traveled by vehicles are already known. Here, measurement data from vehicle sensors are transmitted via a communication connection to a server. The transmitted measurement data of the vehicle sensors are collected on the server and a map of the relevant road section is generated from the data from a plurality of vehicles.

[0003] For example, such a map can be used for automated driving in the following manner: an automatically operated vehicle can determine its position within the map and use it for automated navigation. Such vehicle positioning can be performed based on landmarks of the map.

[0004] In order to ensure a high degree of accuracy and reliability of positioning, possible changes in the vehicle's surroundings that can be driven through must be detected early and robustly in the map. Methods used to detect such changes so far are based on the evaluation of satellite images, which is associated with increased complexity. Summary of the invention

[0005] The object on which the present invention is based can be seen as providing a method which makes it possible to detect changes in the surroundings of a vehicle that can be driven through in a technically simple manner relative to a map.

[0006] This object is achieved by means of the respective subject matter of the independent claims. Advantageous embodiments of the invention are the subject matter of the respective dependent claims.

[0007] According to one aspect of the present invention, a method for verifying the real-time status of at least one digital map is provided. The method can preferably be implemented by a vehicle-side and / or vehicle-external controller.

[0008] In one step, at least one digital map is received or called up. Measurement data about the vehicle's surroundings are received. The measurement data can be received in particular from a vehicle sensor system, which can have a radar sensor, a lidar sensor, a GNSS sensor, a camera sensor, or the like.

[0009] The vehicle position is determined based on landmarks within at least one digital map. To this end, the landmarks can be extracted from measurement data of vehicle sensors and detected within the at least one digital map.

[0010] In a further step, data of the driver assistance function are received. For example, the drivability of the lane, the distance to lane markings, the distance to adjacent road users, etc. can be received by the controller. The data of the driver assistance function can in particular be the result of the driver assistance function.

[0011] In order to verify the timeliness of the at least one digital map, a comparison is performed between the vehicle position within the at least one digital map and the data of the driver assistance function.

[0012] According to another aspect of the invention, a controller is provided, wherein the controller is configured to implement the method. The controller may be, for example, a vehicle-external controller or a vehicle-external server unit, such as a cloud system. The controller is preferably capable of receiving measurement data of a vehicle sensor device of at least one vehicle. Alternatively or additionally, the controller may be a vehicle-internal controller capable of receiving and analyzing measurement data of a vehicle sensor.

[0013] In addition, according to one aspect of the present invention, there is provided a computer program comprising instructions, wherein when the computer program is implemented by a computer or a controller, the instructions cause the computer or the controller to implement the method according to the present invention. According to another aspect of the present invention, there is provided a machine-readable storage medium on which the computer program according to the present invention is stored.

[0014] The controller can be installed in the vehicle or can communicate with the vehicle via a communication connection. In this case, the vehicle can be operated assisted, partially automated, highly automated and / or fully automated or without a driver according to the BASt (Bundesanstalt für Straβenwese, German Federal Institute for Traffic Research) standard.

[0015] In this case, the driver assistance function can access the measurement data of the vehicle sensors or has its own sensors for collecting measurement data. For example, lane keeping assistance, emergency brake assistance, distance keeping assistance, etc. can be used as driver assistance functions.

[0016] This method enables the detection of deviations or inconsistencies between a digital map and the real vehicle surroundings. This detection of deviations, which is carried out solely by means of a positioning map and / or a planning map, can be expensive, since it is usually based on unreliable positioning estimates. In contrast, the method according to the invention utilizes the vehicle-side positioning estimate and information from driver assistance functions and fuses the parallel data with one another in order to detect changes in the positioning map and / or the planning map. Alternatively or additionally, the map can be based on measurement data from a lidar sensor, a radar sensor, a camera sensor, etc.

[0017] Thus, a verification of the real-time nature of the so-called HAD map at the time of the vehicle localization can be performed when using the driver assistance function. Thus, at the time of the localization, it can be decided locally in the vehicle under consideration whether a map update is required.

[0018] Depending on whether the result of the verification is positive or negative, the vehicle can continue its travel or should no longer trust the used map. In the case of a negative result in the verification of the real-timeness of at least one map, for example, the automated driving mode can be terminated and vehicle control can be handed over to the driver.

[0019] Depending on the result of the verification, further actions can be carried out or initiated within the scope of the method. Such actions can include, for example, noting inconsistencies between the map and the actual vehicle surroundings, sending a report about a failed verification, starting a remapping on the vehicle side, starting a remapping outside the vehicle, performing a map update, etc. In particular, the real-time nature of the digital map can be confirmed or the lack of real-time nature of the digital map can be determined by the method.

[0020] The method can improve the quality of digital maps, in particular for automated driving. By controlling the transmission of measurement data from vehicle sensors, the updating of digital maps can be reduced to the necessary extent. This can accelerate map creation in a targeted manner and reduce the time required to provide current maps. In addition, the transmission of information relevant to cartography can be controlled in a situation-dependent manner. This can reduce the amount of data to be transmitted.

[0021] Furthermore, the reliability of the HAD map and thus also the confidence level of the positioning can be improved by the method according to the present invention.

[0022] According to one embodiment, if the vehicle position obtained within the digital map is consistent with the data of the driver assistance function, the real-time nature of the digital map is confirmed. This makes it possible to determine the agreement between the digital map and the real vehicle surroundings. If, for example, not only the position in the positioning map but also the result of the driver assistance function can consistently obtain a drivable position of the vehicle, the at least one digital map is successfully verified. In this case, the planning map parallel to the positioning map can also be confirmed. Now, this information can be used not only locally or inside the vehicle but also outside the vehicle. A positive verification result of the digital map can especially evoke the use of the digital map on the vehicle inside the vehicle and / or data upload.

[0023] Furthermore, the amount of data transmitted by the control unit to the external server unit can be reduced, since the measured data of the vehicle sensors are transmitted to the external server unit only when necessary or only if the result of the verification of at least one digital map is negative. This also makes it possible to reduce the scope and frequency of such sensor data transmission. Thus, if the digital map is still correct and therefore no map update is required, data transmission between the control unit and the external server unit can be avoided.

[0024] According to another embodiment, the real-time verification of the digital map yields a negative result if a deviation is detected between the vehicle position determined within the digital map and the data of the driver assistance function. Dissatisfaction between at least one digital map and the vehicle surroundings can thus be determined. This situation occurs, for example, when the driver assistance function implemented as lane keeping assistance is able to achieve continuous lane guidance, but the positioning service detects a lane deviation or cannot determine a valid position. This situation can occur in particular in the case of construction sites, for example when changing lanes to the opposite road or to the emergency lane.

[0025] If such dissatisfaction is detected by the controller, the vehicle should no longer trust the digital map, and the reliability of the vehicle's automated driving mode can no longer be guaranteed.

[0026] If a change in a digital map in the form of a positioning map is detected, it can be concluded with high probability that the planning map has also changed for the same location and needs to be recreated for the relevant area.

[0027] According to another specific embodiment, after a deviation between the vehicle position ascertained within the digital map and the data of the driver assistance function is determined, an external server unit is notified. This allows an external server unit, which receives measurement data from a plurality of vehicles and creates a digital map from the measurement data, to be notified or warned.

[0028] Therefore can trigger the re-mapping of the relevant area of ​​vehicle surroundings.In addition, vehicle surroundings that are no longer correctly stored in the digital map can be marked as invalid and / or no longer real-time for all vehicles.

[0029] According to another embodiment, after a deviation between the vehicle position determined within the digital map and the data of the driver assistance function is determined, a map update and / or remapping is started. Information about the determined deviation can thus be transmitted to an external server unit via a wireless communication connection. The external server unit can, based on the transmitted information, specifically acquire measurement data from vehicles in the area and can thus correct the digital map in places that are no longer current. This allows a map update to be carried out in a situation-dependent manner, which can be started when necessary.

[0030] According to another embodiment, the deviation between the vehicle position obtained within the digital map and the data of the driver assistance function is evaluated and / or classified. The severity of the deviation can be obtained. The severity or degree of the deviation can be determined, for example, by the controller according to the influence on the vehicle and the automated operating mode. In particular, deviations such as on the contour mark or on the edge of the driving road can be classified as minor. Other deviations (such as changed driving road guidance, blocked lanes, etc.) can be classified as severe. This classification of the deviations obtained can further reduce the amount of data transmitted, because only severe deviations are reported to the external server unit.

[0031] According to another specific embodiment, the determined deviations are stored in a memory that can be connected to the control unit. In this way, in particular, deviations that are classified as minor can be noted first within the vehicle, since they have no direct impact on traffic or only a minor impact. In the event of a further passage through vehicle surroundings with a deviation between the digital map and the vehicle surroundings that is classified as minor, a message can be transmitted by the control unit to an external server unit if the deviation still exists. In this way, minor deviations can be continuously monitored, so that changes in the impact of the deviation on the vehicle can be recognized early and taken into account when updating the map. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] A preferred embodiment of the present invention is explained in more detail below based on a highly simplified schematic diagram. It is shown here:

[0033] Figure 1 : a schematic diagram of a vehicle arrangement for illustrating a method according to one embodiment, and

[0034] Figure 2 : A schematic flow chart illustrating the method. DETAILED DESCRIPTION

[0035] exist Figure 12 shows a schematic diagram of a vehicle arrangement 1 for illustrating a method 2 according to one specific embodiment. The vehicle arrangement 1 has at least one vehicle 4 which is driven along a vehicle surroundings U in an automated driving mode.

[0036] The vehicle 4 has a vehicle-internal control unit 6 which is configured to execute the method 2. For this purpose, the control unit 6 can access a machine-readable storage medium 8 on which at least one computer program is stored. The control unit 6 can preferably execute the computer program stored on the machine-readable storage medium 8.

[0037] Furthermore, the vehicle 4 has a vehicle sensor system 10. The vehicle sensor system 10 may be composed of, for example, one or more lidar sensors, radar sensors, camera sensors, GNSS sensors, etc. The vehicle sensor system 10 may in particular collect measurement data about the vehicle surroundings U. The acquired measurement data may be transmitted to the control unit 6 and evaluated by the control unit 6.

[0038] The measurement data of the vehicle sensor system 10 can be accessed by a driver assistance function 11 or a driver assistance system of the vehicle 4. The driver assistance function 11 can be, for example, a lane keeping assistant, which checks whether the vehicle 4 is in a drivable lane. The driver assistance function 11 can, for example, detect road markings and / or lane markings and / or the road surface in order to determine the drivability of the vehicle surroundings U.

[0039] Via the communication connection 12 , the controller 6 can send data to or receive data from an external server unit 14 .

[0040] The controller 6 can, for example, receive digital maps and / or map updates from the external server unit 14 . Furthermore, the controller 6 can send received measurement data of the vehicle sensor system 10 to the external server unit 14 .

[0041] Figure 2 A schematic flow chart for illustrating method 2 is shown.

[0042] In one step of method 2, measurement data of vehicle sensor system 10 are first detected by a mapping vehicle or a mapping fleet and transmitted to a mapping service 15. Vehicle 4 can also be designed as a mapping vehicle or used as a mapping vehicle.

[0043] The external server unit 14 can, for example, create 16 a positioning map from the received measurement data. The positioning map can preferably be embodied as a digital map and can be made available to the vehicle for positioning.

[0044] During driving, a digital map configured as a positioning map is received 17 by a positioning service. The position 18 of the vehicle 4 is continuously determined in the positioning map by the positioning service. For this purpose, in addition to the positioning map, measurement data of the vehicle sensor system 10 can also be received 13 and used. In parallel with the determination 18 of the vehicle position, a situation analysis is performed based on existing driver assistance functions of the vehicle 4. For example, lane keeping assistance, emergency brake assistance, distance keeping assistance, sign recognition assistance, etc. can be used as such driver assistance functions. Based on the results of the driver assistance functions, the vehicle 4 can be guided 19 in the lane.

[0045] The two processes 18, 19 are then compared 20. If both the vehicle position in the localization map and the result of the driver assistance function can be consistently determined to a drivable position, it can be determined that the map real-time is satisfactory or positively verified. In this case, the projected map is confirmed 21.

[0046] If the lane keeping assistant enables continuous lane guidance and the positioning service detects a lane departure or cannot determine a valid position, an unacceptable or negative verification can be determined, for example, by the control unit 6. This situation can occur in particular in construction sites, for example when changing lanes to the opposite road. Changes or deviations in the digital map can be detected 22. This information can now also be transmitted locally by the control unit 6 and / or to a so-called mapping service 15, for example an external server unit 14.

[0047] After a continuous comparison of the results of the situation analysis of the driver assistance function or of the driver assistance system with the localization map, the detection of a match can be used to terminate the updating phase 23 .

Claims

1. A method (2) for verifying the real-time nature of at least one digital map by means of a controller (6), wherein: - receiving or calling (17) the at least one digital map, - receiving (13) measurement data about the vehicle's surroundings (U) from the vehicle's sensor system, - extracting landmarks from the measurement data and detecting the landmarks within the at least one digital map, - based on detected landmarks within the vehicle surroundings (U), determining (18) the vehicle position within the at least one digital map, - receiving (19) data of a driving assistance function (11), wherein the data of the driving assistance function (11) are a result of the driving assistance function (11), wherein lane keeping assistance is used as the driving assistance function (11), - in order to verify the real-time nature of the at least one digital map, carrying out (20) a comparison between the vehicle position ascertained within the digital map and the result of the driver assistance function (11), A positive verification of the map's timeliness is determined if both the vehicle position in the digital map designed as a position map and the result of the driver assistance function consistently determine a drivable position, If a deviation between the vehicle position ascertained within the digital map and the result of the driver assistance function (11) is determined, the deviation between the vehicle position ascertained within the digital map and the result of the driver assistance function is evaluated and classified, wherein the severity of the deviation is ascertained, wherein only severe deviations are notified to an external server unit (14) via a communication connection (12).

2. The method according to claim 1, wherein: If the vehicle position ascertained within the digital map matches the data of the driver assistance function (11), the real-time nature of the digital map is confirmed (21).

3. The method according to claim 1 or 2, wherein: If a deviation is detected between the vehicle position ascertained within the digital map and the data of the driver assistance function (11), a negative result is obtained in the verification of the real-time status of the digital map (22).

4. The method according to claim 1 or 3, wherein: After a deviation is determined between the vehicle position ascertained within the digital map and the data of the driver assistance function (11), a map update and / or remapping is initiated.

5. The method according to claim 1 or 3, wherein: The determined deviation is stored in a memory (8) which can be connected to the controller (6).

6. A controller (6), wherein: The controller (6) is configured to implement the method (2) according to any one of claims 1 to 5.

7. A computer program product comprising instructions which, when executed by a computer or a controller (6), cause the computer or controller to carry out the method according to any one of claims 1 to 5.

8. A machine-readable storage medium (8) having instructions stored thereon, which, when executed by a computer or a controller (6), cause the computer or controller to implement the method according to any one of claims 1 to 5.

Images