Method and device for matching event information to map for automatic driving, data platform, vehicle and method for operating vehicle
By analyzing and processing the event information in the navigation map and the autonomous driving map, the problem of mismatch between the navigation map and the autonomous driving map is solved, the event information is accurately matched, and the safety and reliability of the autonomous driving system are improved.
Patent Information
- Application Number
- CN202411019684.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-12
AI Technical Summary
In the prior art, the coordinate position between the navigation map and the map used for autonomous driving does not match, resulting in the event information reported by V2X that cannot be accurately positioned in the autonomous driving system, affecting the safety and reliability of the autonomous driving function.
By obtaining navigation maps and maps for autonomous driving, analyzing and processing event information, including standardized road information and vehicle orientation information, and using input fusion of GNSS/RTK/IMU/wheel speedometers to calculate distances along the path, combined with historical trajectory specimens Combining the road topology, achieving accurate matching and positioning of event information.
Improve the matching accuracy of event information, ensure that the autonomous driving system can correctly identify and respond to road-level events, and enhance the safety and reliability of the autonomous driving function.
Smart Images

Figure CN118936488A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving, and more particularly to a method for matching event information to a map for autonomous driving. In addition, the present invention relates to a device for matching event information to a map for autonomous driving, a corresponding backend data platform, a corresponding vehicle, a method for operating a vehicle, and a computer program product. Background Art
[0002] As autonomous driving technology continues to develop, maps used for autonomous driving play a vital role for vehicles with autonomous driving functions.
[0003] Typically, navigation maps (SD-Map) only have a positioning accuracy of a few meters or even more than 10 meters, while maps used for autonomous driving can have a positioning accuracy of less than meters or even centimeters. It is easier to achieve lane-level positioning of vehicles using maps used for autonomous driving. Therefore, in terms of technical feasibility, maps used for autonomous driving are considered to be an important safety component for vehicles with L3 and above driving automation functions.
[0004] Some countries require that when making maps, the coordinates on the map be nonlinearly and randomly offset based on the geodetic coordinate system, so that the coordinates of the buildings / facilities / roads on the map are encrypted coordinates to protect the security of geographic data. For example, the navigation geographic coordinates used in China are based on the GCJ02 standard. The position coordinates in this coordinate system are obtained by converting the target position through a coordinate conversion function so that the hardware device can offset the WGS-84 coordinates according to the offset distance and offset direction obtained. Therefore, maps used for autonomous driving are usually encrypted and deflected.
[0005] In addition, in the application of V2X (Vehicle to everything) technology, the event information reported by it may be based on the vehicle position under the navigation map. However, the positioning accuracy of the navigation map is different from that of the map used for autonomous driving, and the coordinate position of the navigation map is not the same as the coordinate position in the map used for autonomous driving due to random offsets. In addition, the encryption / deflection algorithms of electronic maps of different map manufacturers may be different, which leads to: vehicles of different manufacturers, and even different systems of different models of the same vehicle brand, use different map information as input for function implementation. These factors cause, for example, the event information reported by the V2X function to not fully match the driving assistance / autonomous driving function. The main reason may be that the information reported by V2X based on the navigation map cannot be accurately located in the map used for autonomous driving, and thus cannot be used by the autonomous driving function, and even causes adverse interference to the autonomous driving function.
[0006] Therefore, there is still a need for improvement in the prior art to address at least some of the above issues. Summary of the invention
[0007] Based on this, the present invention proposes an efficient solution, which can not only overcome the shortcomings of the existing technical solutions, but also can particularly efficiently and simply realize the matching of the navigation map with the map for autonomous driving based on the reported event information and can improve the matching accuracy.
[0008] According to a first aspect of the present invention, a method for matching event information to a map for autonomous driving is provided, wherein the method comprises the following steps:
[0009] Step S110: Acquire a navigation map and a map for autonomous driving;
[0010] Step S120: Acquire event information reported based on the vehicle wireless communication technology, wherein the event information at least includes event type, vehicle location, road information, and vehicle orientation information; and
[0011] Step S130: Analyze and process the event information so that the analyzed and processed event information matches the map for autonomous driving.
[0012] The basic concept of the present invention is to match the event information based on the navigation map to the map for autonomous driving by using the road information and the vehicle orientation information through the reported event information. This solution solves the problem of incorrect road matching between the navigation map and the map for autonomous driving. As a result, the navigation map information can be located to the road level of the map information for autonomous driving used by the autonomous driving system, thereby providing favorable technical possibilities for the path planning of the vehicle autonomous driving (such as lane change) and system functions (such as requesting the driver to take over in advance).
[0013] Advantageous configurations of the technical solution of the present invention can be obtained from the following optional implementations.
[0014] According to an optional embodiment of the method of the present invention, the analysis and processing of the event information includes standardization of the event information, wherein the standardization of the road information includes predefined standardized road names, and the standardization of the vehicle orientation information includes unification of vehicle orientations. Such standardization of road information ensures that it can be recognized by different maps and that the reported event information is located on the correct road. In addition, since different vehicles define different zero points for vehicle orientation, the correct orientation of the reported event information relative to the vehicle orientation can be ensured by unifying the vehicle orientation information.
[0015] According to an optional implementation of the method of the present invention, the matching includes locating the event information in the map for autonomous driving. This embodiment enables accurate matching of the event information relative to the road position in the map for autonomous driving.
[0016] According to an optional embodiment of the method of the present invention, the event information also includes an offset along the path, and the value of the offset along the path is calculated based on the starting point of the road or based on the point of interest (POI) and obtained by fusion of GNSS / RTK / IMU / wheel speed meter input. This embodiment can achieve particularly accurate matching and positioning of the event information reported by the vehicle to the map for autonomous driving.
[0017] According to an optional implementation of the method of the present invention, the event information also includes a historical trajectory of the vehicle, and the normative definition and reference design of the historical trajectory are based on an in-vehicle information interaction system of LTE direct communication. This can eliminate more interference factors and further improve the matching accuracy.
[0018] According to an optional implementation of the method of the present invention, event information is reported by means of V2X technology or Car-to-X technology.
[0019] According to an optional embodiment of the method of the present invention, the reporting of event information is performed in an event-triggered manner, thereby enabling real-time, in particular continuous, matching.
[0020] In the present invention, "map for autonomous driving" refers to all types of maps by which autonomous driving vehicles can achieve autonomous driving functions.
[0021] Here, according to an optional embodiment of the method of the present invention, the map may include a high-precision map, which may be provided by a map provider and updated regularly, or provided by the vehicle OEM itself. Alternatively, the map may also be a non-high-precision map or other types of maps that are different from or deviate from the navigation map and cannot be directly used for the automatic driving of the vehicle.
[0022] According to an optional embodiment of the method of the present invention, a historical curve is fitted from the historical trajectory, wherein the historical curve is fitted by means of a high-order polynomial equation, in particular a third-order curve, so as to characterize a road topology, wherein the historical trajectory is matched to the map for autonomous driving by analyzing the road topology. This embodiment makes it possible to fit the historical curve using a high-order curve equation, thereby making it possible to achieve a particularly reliable matching of the road.
[0023] According to a second aspect of the present invention, there is provided a device for matching event information to a map for autonomous driving, wherein the device is used to perform a method for matching event information to a map for autonomous driving, wherein the device comprises:
[0024] an acquisition unit, the acquisition unit being configured to acquire map data and event information, the event information including at least event type, vehicle position, road information, and vehicle orientation information;
[0025] an analysis and processing unit configured to analyze and process the event information so that the analyzed and processed event information is suitable for the map for autonomous driving; and
[0026] A transmission unit is configured to transmit the analyzed and processed event information to the map for autonomous driving.
[0027] According to a third aspect of the present invention, there is provided a backend data platform, the backend data platform comprising the above-mentioned device for matching event information with a map for autonomous driving.
[0028] According to a fourth aspect of the present invention, there is provided a vehicle, the vehicle comprising the above-mentioned device for matching event information to a map for autonomous driving.
[0029] According to a fifth aspect of the present invention, a method for operating a vehicle, in particular a vehicle having an L3 level or higher autonomous driving function, is provided, wherein the method comprises the following steps:
[0030] Step S310: The vehicle and / or another vehicle reports the event information to the device for matching the event information with the map for autonomous driving based on the vehicle wireless communication technology, wherein the vehicle is equipped with the map for autonomous driving;
[0031] Step S320: the device executes the method for matching the event information with a map for autonomous driving;
[0032] Step S330: the device transmits the analyzed and processed event information to a map for autonomous driving of the vehicle; and
[0033] Step S340: Controlling the operation of the vehicle based on the positioning of the matched event information in the map for autonomous driving.
[0034] According to a sixth aspect of the present invention, a computer program product is provided, which includes computer instructions, which, when executed by a processor, are at least used to assist in implementing the above-mentioned method for matching event information to a map for autonomous driving and / or the method for operating a vehicle.
[0035] Further features of the present invention become apparent from the claims, the drawings and the description of the drawings. The features and feature combinations mentioned in the above description and the features and feature combinations mentioned in the following description of the drawings and / or shown only in the drawings can be used not only in the corresponding specified combinations, but also in other combinations without departing from the scope of the present invention. Therefore, the following contents are also regarded as being covered and disclosed by the present invention: these contents are not explicitly shown in the drawings and are not explicitly explained, but are derived from combinations consisting of separate features from the explained contents and are generated by these combinations. The following contents and feature combinations are also regarded as being disclosed: they do not have all the features of the originally drafted independent claims. In addition, the following contents and feature combinations are regarded as being particularly disclosed by the above contents: they exceed or deviate from the feature combinations defined in the reference relationship of the claims. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The present invention will be described in more detail below with reference to the accompanying drawings, so that the principles, features and advantages of the present invention can be better understood. In the accompanying drawings:
[0037] Figure 1 A schematic flow chart showing an embodiment of a method for matching event information to a map for autonomous driving according to the present invention;
[0038] Figure 2 A schematic diagram showing an embodiment of a device for matching event information to a map for autonomous driving according to the present invention;
[0039] Figure 3a and Figure 3b A first exemplary application scenario of the method for matching event information to a map for autonomous driving according to the present invention is shown, wherein: Figure 3a FIG. 4 shows a representation of unmatched event information on a map for autonomous driving. Figure 3b The figure shows a representation of matched event information on a map for autonomous driving;
[0040] Figure 4a and Figure 4b A second exemplary application scenario of the method for matching event information to a map for autonomous driving according to the present invention is shown. Figure 4a FIG. 4 shows a representation of unmatched event information on a map for autonomous driving. Figure 4bThe figure shows a representation of matched event information on a map for autonomous driving;
[0041] Figure 5a and Figure 5b A third exemplary application scenario of the method for matching event information to a map for autonomous driving according to the present invention is shown. Figure 5a FIG. 4 shows a representation of unmatched event information on a map for autonomous driving. Figure 5b showing a representation of the matched event information on a map for autonomous driving; and
[0042] Figure 6 A schematic flow chart of an exemplary embodiment of a method according to the present invention for operating a vehicle is shown. DETAILED DESCRIPTION
[0043] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the scope of protection of the present invention.
[0044] The event information reported based on the vehicle wireless communication technology does not fully match the driving assistance / autonomous driving function. The main reason may be that the event information based on the navigation map cannot be accurately located in the map used for autonomous driving, so it cannot be used by the autonomous driving function, and even causes adverse interference to the autonomous driving function. Therefore, in order to solve the above-mentioned problems in the prior art, various aspects of the present invention are described in detail below in conjunction with the accompanying drawings. Here, the accompanying drawings can be described with reference to each other.
[0045] Figure 1 A schematic flow chart of an embodiment of a method 100 for matching event information 3 to a map for autonomous driving according to the present invention is shown. In this embodiment, the method 100 exemplarily includes steps S110 to S130.
[0046] In step S110, a navigation map and a map for autonomous driving are obtained. Here, the navigation map and the map for autonomous driving may be received by the vehicle 1 and / or a backend data platform 2 configured as a cloud server. Alternatively, the navigation map and the map for autonomous driving may be pre-stored in the vehicle 1 and / or the backend data platform 2. Here, the backend data platform 2 may be a dedicated backend data platform or a public backend data platform.
[0047] In the present invention, “obtaining a navigation map and a map for autonomous driving” may also be understood as receiving or calling a navigation map and a map for autonomous driving.
[0048] In this embodiment, the navigation map and the map for autonomous driving are obtained by random deflection and offset according to the GCJ02 standard, for example, and the map for autonomous driving has higher accuracy than the navigation map, and can assist the vehicle in achieving lane-level or centimeter-level vehicle positioning.
[0049] In step S120, the reported event information 3 is obtained, and the event information 3 includes at least the event type, the vehicle position, the road information and the vehicle direction information. The event reporting is performed based on the vehicle position under the navigation map. The reported event information 3 can be, for example, an event perceived by the vehicle 1 (the vehicle or the self-vehicle) with the help of its own sensor (such as a camera), and / or an event triggered by the self-vehicle (such as a vehicle failure, the emergency warning light is on, the passive safety function is activated, or a collision is detected, etc.) and reported.
[0050] The reporting of the event information 3 is performed in an event-triggered manner. Therefore, when the occurrence of an event is recognized and confirmed, the event information 3 is automatically reported.
[0051] In the present invention, “reporting” can be understood as data transmission, that is, directly or indirectly transmitting the event information 3 to other external devices participating in the automatic driving of the vehicle 1 via wireless communication.
[0052] According to one embodiment, the reporting of event information is performed with the help of V2X technology. V2X is called vehicle-to-everything interconnection and has a corresponding V2X communication and data reporting system on the vehicle side. V2X can be understood as a standardized vehicle wireless communication technology and generally includes V2V (vehicle-to-vehicle interconnection, i.e. data communication between vehicles), V2I (vehicle-to-infrastructure interconnection, i.e. data communication between vehicles and infrastructure, such as traffic lights, road test units, etc.), V2P (vehicle-to-pedestrian interconnection, i.e. communication between vehicles and pedestrians, such as reminders to pedestrians, etc.) and V2N (vehicle-to-network interconnection, i.e. data communication between vehicles and networks, such as cloud servers, etc.).
[0053] According to another embodiment, the reporting of event information is performed by means of Car-to-X technology.
[0054] Car-to-X can be understood as a type of vehicle-to-vehicle wireless communication technology, which can, for example, enable communication between a vehicle and traffic infrastructure and / or between vehicles.
[0055] The event type may be, for example, an accident, a vehicle breakdown, a traffic sign, a road condition (eg, a pothole), etc. The vehicle position may be, for example, based on a coordinate point (x, y).
[0056] In step S130 , the event information 3 is analyzed and processed so that the analyzed event information 3 matches a map for autonomous driving.
[0057] According to this embodiment, the analysis and processing of the event information 3 includes the standardization of the event information 3, wherein the standardization of the road information includes predefined standardized road names. The standardized road names are respectively adapted to and stored in the navigation map and the map for autonomous driving. The standardized road names can be presented in Chinese, for example, "Boxing Road Auxiliary Road". Alternatively, the standardized road names can also be presented in the form of characters, such as G_R_BJ_YZ_16, etc.
[0058] In addition, the standardization of vehicle orientation information includes the unification of vehicle orientation. Since different vehicle manufacturers define different reference zero points and positive directions for vehicle orientation, it is necessary to unify the vehicle orientation information. For example, the reference zero point of the vehicle orientation is unified as facing due north, and the positive direction is clockwise. In other words, the vehicle orientations defined by different vehicles or manufacturers are converted into unified orientation information through corresponding rotation.
[0059] Therefore, the standardization of road information and the unification of vehicle orientation can beneficially achieve the correct matching of event information 3 to the map used for autonomous driving. That is, when the event information 3 based on the navigation map is used by the autonomous driving system, it is correctly located on the corresponding lane and the problem of incorrect road matching that may exist in the prior art is solved. Thus, the auxiliary vehicle 1 realizes the autonomous driving function.
[0060] According to another embodiment, the event information 3 also includes an along-path distance OFFSET, the value of which is calculated based on the starting point of the road or based on the point of interest POI and obtained by fusion of GNSS / RTK / IMU / wheel speedometer input. Since there may be offset and deflection differences between the navigation map and the map used for autonomous driving, the along-path distance OFFSET in the reported event information 3 can be used to reliably determine the distance of the vehicle 1 or traffic signs relative to the defined road starting point. In this way, the matching accuracy can be further improved.
[0061] It is understandable that the autonomous driving system should consider higher functional safety requirements, which requires more sufficient (vehicle) advance "action" time / distance along the road direction to ensure the fault tolerance time interval / fault handling time interval. The reported event information can be used to obtain distant event information in advance. Based on different system designs, especially based on the response to different events, the vehicle can respond at the corresponding "action" time / distance.
[0062] According to another embodiment, the event information 3 also includes a historical path (Path History) of the vehicle 1 , and the normative definition and reference design of the historical path are based on LTE, such as an in-vehicle information interaction system of LTE-V2X direct communication.
[0063] When using V2X technology, the historical trajectory function module (hereinafter referred to as PH) in the V2X communication system uses the past positioning information of the vehicle and calculates a series of adaptive, concise, and representative moving trajectories of the current vehicle within a certain distance. PH can provide other vehicles with information on the predicted road geometry. Through the reference position of the target vehicle to the road geometry, it provides the basis for the classification of the position of the target vehicle relative to the vehicle.
[0064] Therefore, additionally considering the historical trajectory of the vehicle 1 in the event information for matching can eliminate more interference factors and further improve the matching accuracy.
[0065] In an optional embodiment, a history curve is fitted through the history trajectory, wherein the history curve is fitted by means of a high-order polynomial equation, especially a third-order curve.
[0066] For example, define a third-order curve as: Y = A + BX + CX 2 +DX 3 , where there are four unknown parameters A, B, C and D, so four sets of known values are used to obtain the curve Y. For example, given the starting state (x0, y0), (x0, y0'), (x0, y0") and the end state (x1, y1), four sets of equations are obtained:
[0067] A=y0-(Dx0 3 +Cx0 3 +Bx0);
[0068] B=y0′-(3Dx0 2 +2Cx0);
[0069] C = (y0"-6Dx0) / 2;
[0070] D=(y1–A-Bx1-Cx1 2 );
[0071] Therefore, four unknown parameters can be obtained when x0=0, and thus the historical curve can be fitted using a third-order curve.
[0072] If the third-order curve is not sufficient to fit the historical curve or to characterize the historical trajectory, or the standard deviation is greater than a predetermined threshold or a predetermined time threshold, then multiple, for example, twenty historical values of vehicle orientations can be processed, thereby fitting a corresponding historical curve to characterize the road topology, and matching the historical trajectory with the map used for autonomous driving can be achieved through analysis of the road topology.
[0073] Figure 2 A schematic diagram showing an embodiment of an apparatus 200 for matching event information to a map for autonomous driving according to the present invention.
[0074] The device 200 is capable of performing Figure 1 A method 100 for matching event information to a map for autonomous driving is provided in the embodiment. According to this embodiment, the device 200 includes an acquisition unit 210, which is configured to be suitable for acquiring map data and event information 3. The event information 3 includes at least an event type, a vehicle position, road information, and a vehicle orientation information and can be reported based on V2X technology or Car-to-X technology. The acquisition unit 210 can be configured as a communication module, which can receive event information and other data information reported from the vehicle 1 and / or another vehicle 4 based on corresponding communication technologies, such as cellular communication technologies (LTE and 5G).
[0075] In addition, the device 200 includes an analysis processing unit 220, which is configured to analyze and process the event information 3 so that the analyzed event information 3 is suitable for a map used for autonomous driving. Figure 1 As described, the evaluation of the event information 3 includes the normalization of the event information 3 .
[0076] The device 200 further includes a transmission unit 230 , which is configured to be suitable for transmitting the analyzed event information 3 to a map for autonomous driving.
[0077] According to one embodiment, the device 200 may be arranged in the backend data platform 2, and the event information 3 reported via V2X is analyzed and processed in the backend data platform 2 and matched with the map for autonomous driving. Therefore, the backend data platform 2 stores the map for autonomous driving and the navigation map accordingly.
[0078] According to another alternative embodiment, the device 200 may also be arranged in a vehicle 1, which has L3 level and above autonomous driving functions. Therefore, the vehicle 1 can obtain corresponding event information 3 from another vehicle 4 via V2X and perform corresponding analysis and processing on the event information 3 inside the vehicle 1 and match it with a map for autonomous driving.
[0079] The technical solution of the present invention is further described below in combination with different application scenarios.
[0080] Figure 3a and Figure 3b A first exemplary application scenario of the method 100 for matching event information to a map for autonomous driving according to the present invention is shown, wherein: Figure 3a FIG. 3 shows the representation of unmatched event information 3 on a map for autonomous driving. Figure 3b The figure shows a representation of the matched event information 3 on a map for autonomous driving.
[0081] like Figure 3a As shown in the example, vehicle 1 (the vehicle itself or the vehicle itself) is a vehicle with L3 or higher level autonomous driving function and is located on a road with two lanes. Vehicle 1 is currently located in lane L2 (right lane). Vehicle 1 is traveling forward along driving direction F and detects the surrounding environment of vehicle 1 with the help of its own sensors, such as lidar and camera.
[0082] In addition, the vehicle 1 can also communicate with the backend data platform 2 by means of V2X and can report the detected event information 3 in an event-triggered manner, wherein Figure 2 In the embodiment, the device 200 of the present invention is arranged in the backend data platform 2.
[0083] At present, vehicle 1 detects an event ahead in lane L2 (own lane), which event exemplarily represents a traffic accident, such as in Figure 3a and Figure 3b In the case where the driver is driving the vehicle 1, the event detected by the sensor can be correctly located and displayed in the navigation map, and the driver can perform corresponding operations based on the event identified in the navigation map, such as changing the vehicle 1 to the lane L1.
[0084] During the autonomous driving process, the event information 3 reported by V2X should be correctly located in the map used for autonomous driving, so that the vehicle 1 can automatically or assistedly perform corresponding operations of the vehicle 1 based on the correct event information 3, especially based on the correct position of the event information 3 in the map used for autonomous driving.
[0085] However, there is a problem of position matching in the event information 3 based on the navigation map. Therefore, the event information 3 that should have been correctly located in the lane L2 is incorrectly located in the lane L1 in the map for autonomous driving due to the random offset and deflection of the map for autonomous driving relative to the navigation map (see Figure 3a ).
[0086] Therefore, the vehicle 1 cannot correctly know the event that is actually located in front of the lane (lane L2) based on the map for autonomous driving when the autonomous driving function is activated, and cannot correctly make correct and timely vehicle operations based on the map for autonomous driving. This makes the functional safety of the autonomous driving function of the vehicle 1 not guaranteed.
[0087] Therefore, vehicle 1 reports (transmits) event information 3 of the detected event to backend data platform 2 by means of V2X, and device 200 arranged in backend data platform 2 analyzes and processes event information 3, and matches the analyzed event information 3 with the map for autonomous driving. Here, the analysis and processing of event information 3 or the matching of event information 3 with the map for autonomous driving is performed in Figure 1 As described in . Thus, the analyzed event information 3 is sent to the vehicle 1. Therefore, the event information 3 matched to the map for autonomous driving can be correctly located in the map for autonomous driving (see Figure 3b solid box in the figure).
[0088] Thus, the vehicle 1 can make a decision in advance on the next operation of the vehicle 1 based on the event information 3 correctly located in the map for automatic driving, such as changing lanes in advance or reducing the speed, etc. In this embodiment, the vehicle 1 is not equipped with the device 200 of the present invention.
[0089] However, according to another embodiment, the vehicle 1 is equipped with the device 200 of the invention. Figure 3a and Figure 3b Unlike the embodiment in the embodiment, the vehicle 1 does not need the backend data platform 2 and can analyze and process the event information 3 detected by itself in the vehicle 1 with the aid of the device 200, thereby matching the event information 3 with the map for autonomous driving in the vehicle 1. Thus, the matching efficiency is improved, the data transmission is reduced, and the occupied bandwidth is saved.
[0090] Figure 4a and Figure 4b A second exemplary application scenario of the method 100 for matching event information to a map for autonomous driving according to the present invention is shown, wherein: Figure 4a FIG. 3 shows the representation of unmatched event information 3 on a map for autonomous driving. Figure 4b The figure shows a representation of the matched event information 3 on a map for autonomous driving.
[0091] Figure 4a and Figure 4b The scene and Figure 3a and Figure 3bThe difference between the scenario is that there is another vehicle 4 in lane L2, and the other vehicle 4 can detect its surrounding environment with the help of its sensors and report the detected event information to the backend data platform 2.
[0092] In the present invention, the other vehicle 4 should be understood as one or more other vehicles 4, and in this embodiment, the other vehicle 4 is a vehicle that does not have L3 level and above autonomous driving functions.
[0093] In the second exemplary application scenario, the vehicle 1 and the other vehicle 4 have the same vehicle attributes, such as belonging to the same vehicle manufacturer or the same model, and they are both equipped with the same Car-to-X communication technology. Therefore, the backend data platform 2 can be a cloud server supporting Car-to-X communication.
[0094] exist Figure 4a In the example, another vehicle 4 detects an event (such as a traffic accident) ahead in lane L2 and reports event information 3 to the backend data platform 2. Figure 3a Similarly, the event information 3 based on the navigation map has a problem of position matching with the map for autonomous driving. Therefore, the event information 3 that should have been correctly located in the lane L2 is incorrectly located in the lane L1 in the map for autonomous driving due to the random offset and deflection of the map for autonomous driving relative to the navigation map (see Figure 4a ).
[0095] Therefore, if the vehicle 1 in lane L2 receives unprocessed event information 3 reported by another vehicle 4 from the backend data platform 2 via Car-to-X, the event information 3 will also be incorrectly located in the map for autonomous driving of the vehicle 1. Therefore, the vehicle 1 now believes that the reported event information 3 does not exist in front of the vehicle in lane L2. Therefore, the vehicle 1 may continue to drive straight at a high speed, which requires the vehicle 1 to make a correct response in a very short time to avoid an accident when facing the event.
[0096] Therefore, similarly, the device 200 arranged in the backend data platform 2 analyzes and processes the event information 3, and matches the analyzed and processed event information 3 to the map for autonomous driving. Then, the analyzed and processed event information 3 is transmitted to the vehicle 1. The event information 3 is therefore correctly located in the map for autonomous driving in the vehicle 1. As a result, the vehicle 1 can perform the autonomous driving function with a greater safety margin based on the correctly located event information 3. In this embodiment, the vehicle 1 is not equipped with the device 200 of the present invention.
[0097] According to another embodiment, the vehicle 1 is equipped with a device 200. Here, the other vehicles 4 and the vehicle 1 can also serve as the reporting party of the event information 3. The backend data platform 2 only serves as the receiver and broadcaster of the data or event information 3, but does not have the device 200.
[0098] Here, the backend data platform 2 receives event information 3 reported from different traffic participants (in this embodiment, from vehicle 1 and another vehicle 4) and transmits the event information 3 to vehicle 1 in a predetermined frequency, format and size. Vehicle 1 receives event information 3 reported from different traffic participants (such as another vehicle 4) from the backend data platform 2 and analyzes and processes the event information 3 in the device 200 of vehicle 1 itself, thereby matching the event information 3 with the map for autonomous driving in vehicle 1.
[0099] Figure 5a and Figure 5b A third exemplary application scenario of the method for matching event information to a map for autonomous driving according to the present invention is shown, wherein: Figure 5a FIG. 3 shows the representation of unmatched event information 3 on a map for autonomous driving. Figure 5b The figure shows a representation of the matched event information 3 on a map for autonomous driving.
[0100] Figure 5a and Figure 5b The vehicle 1 shown is equipped with the device 200 of the present invention. Furthermore, the vehicle 1 can communicate with another vehicle 4 by way of example via V2X (V2V).
[0101] like Figure 5a As shown, another vehicle 4 in lane L2 is located in front of the right side of vehicle 1 in adjacent lane L1. Now, since another vehicle 4 is located in front of vehicle 1 and detects the event in front of vehicle 1 in lane L2 earlier than vehicle 1, another vehicle 4 can transmit the event information 3 to vehicle 1 via V2X without being processed. Here, there is a problem of position matching for the map used for autonomous driving based on the navigation map and the unprocessed event information 3. Therefore, the event information 3 that should have been correctly located in lane L2 is incorrectly located in lane L1 in the map used for autonomous driving due to the random offset and deflection of the map used for autonomous driving relative to the navigation map (see Figure 5a ).
[0102] After receiving the event information 3 from the other vehicle 4, the vehicle 1 analyzes the event information 3 in its own device 200 to match the event information 3 with the map for autonomous driving. Then, the analyzed event information 3 matched with the map for autonomous driving is transmitted to its own map for autonomous driving. Therefore, the event information 3 is correctly located in the lane L2 in the map for autonomous driving (see Figure 5b Therefore, based on the event information 3, the automatic driving system of the vehicle 1 does not respond to the event information 3 and maintains the current driving state of the vehicle 1.
[0103] According to another embodiment not shown, the vehicle 1 may not be equipped with the device 200 of the present invention, while the other vehicle 4 is equipped with the device 200 of the present invention. The vehicle 1 receives the event information 3 matched to the map for autonomous driving after analysis and processing by the other vehicle 4 for controlling its own operation. This can save the computing power of the vehicle 1 and reduce power consumption. In this case, the vehicle 1 and the other vehicle 4 should be equipped with the same map for autonomous driving.
[0104] Figure 6 A schematic flow chart of an exemplary embodiment of a method 300 according to the present invention for operating a vehicle 1 is shown. The method 300 exemplarily includes steps S310 to S340.
[0105] In step S310, event information is reported by vehicle 1 and / or another vehicle 4, wherein vehicle 1 is equipped with a map for autonomous driving. In step S320, the method 100 for matching event information to a map for autonomous driving is executed by the device 200 of the present invention. In step S330, the device 200 of the present invention transmits the analyzed event information 3 to the map for autonomous driving of vehicle 1. In step S340, the operation of vehicle 1 is controlled based on the location of the matched event information 3 in the map for autonomous driving.
[0106] The present invention also protects a computer program product.
[0107] In addition, it should be noted that the step numbers described herein do not necessarily represent a chronological order, but are merely a reference numeral. The order may be changed according to specific circumstances as long as the technical purpose of the present invention can be achieved.
[0108] Other advantages and alternative embodiments of the present invention are obvious to those skilled in the art. Therefore, the present invention in its broader sense is not limited to the specific details, representative structures and exemplary embodiments shown and described. On the contrary, those skilled in the art can make various modifications and substitutions without departing from the basic spirit and scope of the present invention.
Claims
1. A method (100) for matching event information (3) to a map for autonomous driving, wherein: The method (100) comprises the following steps: Step S110: Acquire a navigation map and a map for autonomous driving; Step S120: Acquire event information (3) reported based on the vehicle wireless communication technology, wherein the event information (3) at least includes event type, vehicle location, road information, and vehicle orientation information; and Step S130: Analyze and process the event information (3) so that the analyzed and processed event information (3) matches the map for autonomous driving.
2. The method (100) according to claim 1, wherein: The analysis and processing of the event information (3) includes standardization of the event information (3), wherein the standardization of the road information includes predefined standardized road names, and the standardization of the vehicle orientation information includes standardization of vehicle orientations; and / or The matching includes locating the event information (3) in the map for autonomous driving.
3. The method (100) according to claim 1 or 2, wherein: The event information (3) also includes the distance along the path, where the value of the distance along the path is calculated based on the starting point of the road or based on the point of interest and is obtained by integrating the input of GNSS / RTK / IMU / wheel speed meter.
4. The method (100) according to claim 3, wherein: The event information (3) also includes the historical trajectory of the vehicle, and the normative definition and reference design of the historical trajectory are based on the vehicle information interaction system of LTE direct communication.
5. The method (100) according to any one of claims 1 to 4, wherein: Reporting event information using V2X technology or Car-to-X technology(3); and / or The reporting of the event information (3) is carried out in an event-triggered manner; and / or The map used for autonomous driving includes a high-precision map.
6. The method (100) according to claim 4, wherein: A historical curve is fitted through the historical trajectory, wherein the historical curve is fitted with the aid of a high-order polynomial equation, especially a third-order curve, so as to characterize the road topology, wherein the historical trajectory is matched to the map for autonomous driving by analyzing the characterized road topology.
7. A device (200) for matching event information (3) to a map for autonomous driving, wherein: The device (200) is used to perform the method (100) according to any one of claims 1 to 6, wherein the device (200) comprises: An acquisition unit (210), the acquisition unit (210) being configured to acquire map data and event information (3), the event information (3) comprising at least event type, vehicle position, road information and vehicle orientation information; an analysis and processing unit (220), the analysis and processing unit (220) being configured to analyze and process the event information (3) so that the analyzed and processed event information (3) is suitable for the map for autonomous driving; and A transmission unit (230) is configured to transmit the analyzed and processed event information (3) to the map for autonomous driving.
8. A backend data platform (2), comprising the device (200) according to claim 7.
9. A vehicle (1) comprising a device (200) according to claim 7.
10. A method (300) for operating a vehicle (1), in particular a vehicle (1) having an L3 level or higher autonomous driving function, wherein: The method (300) comprises the following steps: Step S310: The vehicle (1) and / or another vehicle (4) reports the event information (3) to the device (200) according to claim 7 based on vehicle wireless communication technology, wherein the vehicle (1) is equipped with a map for autonomous driving; Step S320: The device (200) executes the method (100) for matching event information (3) to a map for autonomous driving according to any one of claims 1 to 6; Step S330: the device (200) transmits the analyzed and processed event information (3) to a map for autonomous driving of the vehicle (1); and Step S340: Controlling the operation of the vehicle (1) based on the positioning of the matched event information (3) in the map for autonomous driving.
Citation Information
Cited By
Communication safety control method and system applied to automobile navigation
CN121283608A
A method and system for controlling communication safety of car navigation
CN121283608B
