Vehicle control method and device, vehicle and storage medium
By selecting road snap points and sections in low-precision navigation maps and combining them with semantic description information to control vehicle movement, the problem of low navigation accuracy in low-precision navigation maps is solved, and accurate vehicle navigation is achieved.
Patent Information
- Application Number
- CN202411391763.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2026-01-27
- Estimated Expiration
- 2044-09-30
AI Technical Summary
Low-precision navigation maps cannot meet the real-time navigation needs of vehicles, resulting in low navigation accuracy.
By selecting multiple road snap points from the road points of the target electronic map, the target road section is determined, and the vehicle's driving is controlled according to the semantic description information of the target road section in the target electronic map to ensure that the vehicle conforms to the road attributes in the target road section.
It improves the accuracy of vehicle navigation within the target road area, avoids situations where the vehicle's driving does not conform to the road attributes due to missing semantic description information, and achieves accurate navigation.
Smart Images

Figure CN119459771B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle technology, and more specifically, to a vehicle control method, apparatus, vehicle, and computer-readable storage medium. Background Technology
[0002] With the development of lightweight map technology, autonomous driving solutions relying on low-precision navigation maps have become a mainstream research direction. However, due to the limited information described by low-precision navigation maps, they cannot meet the real-time navigation needs of vehicles, resulting in low accuracy. Summary of the Invention
[0003] This application proposes a vehicle control method, apparatus, vehicle, and computer-readable storage medium to improve the accuracy of low-precision navigation.
[0004] In a first aspect, embodiments of this application provide a vehicle control method, the method comprising:
[0005] Obtain the planned path obtained from the vehicle's path planning;
[0006] Based on the distance between the planned path and the road points in each road on the target electronic map, select multiple road snap points that the planned path snaps into.
[0007] Determine the target road interval indicated by multiple road adsorption points within the road;
[0008] The vehicle's movement is controlled based on the semantic description information of the target road section in the target electronic map and the planned route; the semantic description information of the target road section is used to indicate the road attributes of the target road section.
[0009] Secondly, embodiments of this application also provide a vehicle control device, the device comprising:
[0010] The acquisition module is used to acquire the planned path obtained by the vehicle's path planning.
[0011] The adsorption point determination module is used to select multiple road adsorption points adsorbed by the planned path from the road points based on the distance between the planned path and the road points in each road of the target electronic map.
[0012] The interval determination module is used to determine the target road interval indicated by multiple road adsorption points in the road;
[0013] The control module is used to control vehicle movement based on the semantic description information of the target road section in the target electronic map and the planned route; the semantic description information of the target road section is used to indicate the road attributes of the target road section.
[0014] Thirdly, embodiments of this application also provide a vehicle, characterized in that the vehicle includes: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to perform the above-described methods.
[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium storing processor-executable program code, which, when executed by the processor, causes the processor to perform the above-described method.
[0016] This application provides a vehicle control method, device, vehicle, and computer-readable storage medium. In this application, based on the vehicle's planned path, multiple road snap points are selected from road points on various roads in a target electronic map. Then, the target road interval indicated by the multiple road snap points is determined. Subsequently, based on the semantic description information of the target road interval in the target electronic map and the planned path, the vehicle's movement is controlled. Thus, the vehicle's movement within the target road interval conforms to the road attributes of the target road interval, improving the accuracy of the vehicle's movement within the target road interval. This effectively avoids the situation where the vehicle's movement within the target road interval lacks a basis due to missing semantic description information, leading to a situation where the vehicle's movement within the target road interval does not conform to the road attributes of the target road interval, thereby achieving accurate navigation during vehicle movement.
[0017] Other features and advantages of the embodiments of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the embodiments of this application. The objects and other advantages of the embodiments of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 A schematic diagram of a vehicle hardware environment applicable to embodiments of this application is shown.
[0020] Figure 2 A flowchart of a vehicle control method according to an embodiment of this application is shown.
[0021] Figure 3 Show Figure 2The flowchart of the steps preceding step S140 in the corresponding embodiment is shown in one embodiment.
[0022] Figure 4 This diagram illustrates an actual road adsorption point in an embodiment of this application.
[0023] Figure 5 This diagram illustrates a map update process according to an embodiment of this application.
[0024] Figure 6 A structural block diagram of a vehicle control device according to an embodiment of this application is shown. Detailed Implementation
[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. The components of the embodiments of the present application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without inventive effort are within the scope of protection of the present application.
[0026] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0027] Reference Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment applicable to an embodiment of this application is shown. The vehicle 100 includes a driving system 110, which can have multiple built-in autonomous driving functions. The driving system 110 can store electronic maps. The driving system 110 can plan driving routes based on the electronic maps it stores, and can also control the vehicle to drive autonomously based on the planned driving routes.
[0028] The driving system 110 may include a data acquisition device 111, one or more (only one is shown in the figure) processors 112 and memory 113.
[0029] The data acquisition device 111 is used to detect environmental information inside and around the vehicle. The data acquisition device 111 may include sensors such as an in-vehicle camera, an in-vehicle infrared sensor, an in-vehicle monitoring radar, an external camera, an external monitoring radar, and a door monitoring radar.
[0030] The processor 112 may be a microcontroller unit (MCU) with a built-in memory 113 containing a program that can execute the contents of the following embodiments, and the processor 112 can execute the program stored in the memory 113.
[0031] The processor 112 may include one or more processors. The processor 112 uses various interfaces and circuits to connect various parts of the vehicle 100, and performs various functions of the vehicle 10 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 113, and calling data stored in the memory 113.
[0032] Memory 113 may include random access memory (RAM) or read-only memory (ROM). Memory 15 may be used to store instructions, programs, code, code sets, or instruction sets. Memory 15 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described below, etc.
[0033] Please see Figure 1 , Figure 1 A flowchart of a vehicle control method according to an embodiment of this application is shown, for a vehicle, the method comprising:
[0034] S110. Obtain the planned path obtained by performing path planning on the vehicle.
[0035] The vehicle in this embodiment can be an electric vehicle or a fuel-powered vehicle, or it can be a sedan, SUV, bus, or truck, etc.
[0036] The planned route for a vehicle can be obtained by using a target electronic map to plan the route based on the planned starting point and the planned ending point. The planned starting point and the planned ending point can be manually entered by the user, determined by the vehicle based on the user's driving habits, or determined by the vehicle based on route planning instructions sent by the user.
[0037] The target electronic map refers to the electronic map stored in the vehicle, which can be an SD map (Standard Detail Map, low-precision map). The target electronic map includes multiple roads, each with multiple road points. Each road can be indicated by these road points. For example, road A has 10 ordered road points; the road formed by connecting these 10 road points is road A.
[0038] Vehicles can construct a route from the planned starting point to the planned ending point using the target electronic map, based on the planned starting point and the planned ending point. This route is the planned route, and the route involves at least one road in the target electronic map.
[0039] In another embodiment, the vehicle can construct a path from the planned starting point to the planned ending point using a reference map based on the planned starting point and the planned ending point. This path serves as the planned path. The reference map can refer to a high-definition map (HD map).
[0040] S120. Based on the distance between the planned path and the road points in each road on the target electronic map, select multiple road points that the planned path will attract.
[0041] In one embodiment, after obtaining the planned path, the distance between the planned path and the road points in each road of the target electronic map can be determined. Then, a specified number of road points are selected in ascending order of distance as multiple road attachment points of the planned path. The specified number can be determined based on the length of the planned path; the longer the planned path, the larger the specified number.
[0042] In another embodiment, after obtaining the planned path, if the planned path includes multiple planned path points, S120 may include: determining the road point closest to each planned path point from the road points, as the road adsorption point corresponding to each planned path point.
[0043] Each planned path point corresponds to its own planned time point. When a vehicle travels along the planned path, it is positioned at the location indicated by that planned path point when the planned time point is reached. The interval between two adjacent planned time points can be fixed, for example, 0.1 seconds.
[0044] In one embodiment, the multiple planned path points are ordered, and the distance between two adjacent planned path points is fixed, for example, the distance between two adjacent planned path points is 5m. The order of the multiple planned path points refers to the sequence in which the vehicle passes through each planned path point as it travels along the planned route from the planned starting point to the planned ending point.
[0045] For each planned path point, determine the nearest road point as the road adsorption point of that planned path point. Traverse all planned path points to obtain the road adsorption points of all planned path points, which are then used as multiple road adsorption points of the planned path.
[0046] S130. Determine the target road interval indicated by multiple road adsorption points in the road.
[0047] After obtaining multiple road snap points, the road interval indicated by the multiple road snap points in the road on the target electronic map can be determined based on the location of the multiple road snap points in the road, and this interval can be used as the target road interval.
[0048] In this context, a road interval refers to a section of a road located between any two road points. For example, if road B has 13 ordered road points, the section of road B between the 3rd and 4th road points can be considered a road interval, and the section of road B between the 10th and 14th road points can also be considered a road interval.
[0049] In some implementations, as described above, the multiple planned path points included in the planned path are ordered. In this case, S130 may include: determining the order of multiple road adsorption points according to the order of the multiple planned path points in the planned path; for any two adjacent road adsorption points, taking the road interval between the two adjacent road adsorption points as a target road interval indicated by the two adjacent road adsorption points.
[0050] Specifically, for each planned path point, the sequence number of the planned path point in the planned path can be used as the sequence number of the road adsorption point corresponding to that planned path point. In this way, by traversing each planned path point, the sequence number of each road adsorption point is obtained, and multiple road adsorption points are arranged according to their respective sequence numbers, thereby determining the order of multiple road adsorption points.
[0051] Then, for a set of ordered road adsorption points, the road interval between two adjacent road adsorption points is taken as a target road interval indicated by the two adjacent road adsorption points. In this way, all road adsorption points are traversed to obtain each target road interval.
[0052] S140. Control vehicle movement based on semantic description information of the target road section in the target electronic map and the planned route.
[0053] The semantic description information of the target road section is used to indicate the road attributes of the target road section.
[0054] For each road segment indicated by each road point in the target electronic map, semantic description information can be configured for each road segment based on requirements and actual road conditions.
[0055] The semantic description information of a road section refers to the information describing the road attributes of the road section. The road attributes of a road section may include speed limit information, lane change information (whether lane changes are allowed in the road section), and temporary shielding areas (temporarily shielded areas in the road section). The reasons for temporary shielding may be road construction or road work.
[0056] Semantic description information can be assigned to each road segment based on user needs, or it can be determined based on driving data uploaded by different vehicles. Driving data can include vehicle speed, acceleration, surrounding environment information (such as the speed, acceleration, and position of surrounding obstacles), steering wheel angle, and lighting information.
[0057] For example, for a certain road section, the speed limit information of that road section can be updated based on the actual driving speed in the driving data of different vehicles (increasing the minimum speed limit or decreasing the maximum speed limit, etc.), and the updated speed limit information can be used as the semantic description information of that road section.
[0058] For example, for a certain road section, the lane change information (whether lane changing is allowed or not) can be updated based on the actual lane change situation in the driving data of different vehicles, and the updated lane change information can be used as the semantic description information of the road section.
[0059] For example, for a certain road section, obstacle information in the driving data of different vehicles can be used to determine that there is a temporary construction area in the road section, and the temporary construction area can be determined as a temporary shielding area of the road section, and the temporary shielding area can be used as the semantic description information of the road section.
[0060] Of course, the technical personnel responsible for managing the target electronic map can also manually configure the semantic description information for each road section. The technical personnel can determine the semantic description information for each road section based on the driving data uploaded by different vehicles, or they can determine the semantic description information for each road section based on actual needs. This will not be elaborated here.
[0061] The semantic description information of each road segment indicated by each road point in the target electronic map can be stored in the target electronic map. The semantic description information of the target road segment can be directly obtained from the target electronic map. Then, by combining the semantic description information of the target road segment with the planned route, the vehicle can be controlled to drive, so that the vehicle travels with reference to the semantic description information of the target road segment.
[0062] For example, if the semantic description information of the target road section indicates that the maximum speed limit of the target road section is 60 km / h, then when a vehicle travels along the planned route in the target road section, its speed shall not exceed 60 km / h; or if the semantic description information of the target road section indicates that lane changing is not allowed in the target road section, then when a vehicle travels along the planned route in the target road section, lane changing is prohibited.
[0063] In this embodiment, based on the vehicle's planned path, multiple road snap points are selected from the road points on each road in the target electronic map. Then, the target road interval indicated by the multiple road snap points is determined. Subsequently, based on the semantic description information of the target road interval in the target electronic map and the planned path, the vehicle's driving is controlled. As a result, the vehicle's driving process in the target road interval can conform to the road attributes of the target road interval, improving the accuracy of the vehicle's driving process in the target road interval. This effectively avoids the situation where the vehicle's driving process in the target road interval lacks a basis due to the lack of semantic description information of the target road interval, resulting in the vehicle's driving process not conforming to the road attributes of the target road interval. This achieves accurate navigation of the vehicle's driving process.
[0064] Secondly, the target road interval is indicated by at least two road snap points. The corresponding target road interval is determined by the road snap points, without the need to calculate the similarity of road intervals. Thus, the road snap points can be quickly determined from the target electronic map stored in the vehicle based on the distance between the road points in the target electronic map and the planned path, thereby quickly determining the target road interval. This improves the efficiency of determining the target road interval and, in turn, enhances the real-time performance of vehicle control based on the semantic description information of the target road interval in the target electronic map and the planned path.
[0065] In one embodiment, such as Figure 3 As shown, before S140, the method further includes:
[0066] S210: Receives multiple actual road adsorption points sent from the cloud, as well as configuration semantic description information configured for the road sections to be processed.
[0067] The road section to be processed refers to the road section indicated by multiple actual road adsorption points in the road; the multiple actual road adsorption points are determined from the road points.
[0068] The cloud refers to the server that communicates with the vehicle. This server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.
[0069] In this application, the actual driving path of the vehicle can be collected during the driving process; based on the distance between the actual driving path and the road points in each road, multiple actual road points can be selected from the road points and attached to the actual driving path; and the multiple actual road points can be sent to the cloud.
[0070] In this application, the actual driving path may include multiple actual path points. During the vehicle's journey, the vehicle's location is collected at each collection time point to obtain an actual path point. The collection time points can be set according to requirements, such as an interval of 0.1 seconds between two adjacent collection time points. Alternatively, during the vehicle's journey, the vehicle's location can also be collected at collection distance intervals to obtain an actual path point; for example, the collection distance interval can be 5 meters.
[0071] The actual driving path includes multiple actual path points that can be ordered. The order of these actual path points is the order in which they are collected by the vehicle during its journey. In this case, the road point closest to each actual path point can be determined from the road points and used as the actual road adsorption point for each actual path point. This process is repeated for each actual path point to obtain multiple actual road adsorption points adsorbed by the actual driving path. Then, these multiple actual road adsorption points are sent to the cloud.
[0072] In one embodiment, during vehicle operation, in response to a triggered target event, the vehicle's driving path within a target time period corresponding to the target event can be collected as the actual driving path. Specifically, to ensure that the actual driving path within the target time period accurately reflects the target event, the start time of the target time period is earlier than the start time of the target event, and the end time of the target time period is later than the end time of the target event.
[0073] The target event can refer to lane change abnormality event, deceleration abnormality event, acceleration abnormality event, construction obstacle detection event, and user trigger operation detection. Among them, the vehicle can be set with a trigger button, and the vehicle responds to the user's operation on the trigger button (such as long press, double press, etc.) to determine that the user's trigger operation has been detected.
[0074] Lane change anomaly events refer to discrepancies between the lane change information displayed by the vehicle and the lane change information shown on the target electronic map. For example, the vehicle changes lanes, but the target electronic map indicates that lane changing is not allowed. Deceleration anomaly events occur when the vehicle's speed decreases below the minimum speed limit for the road on the target electronic map. Acceleration anomaly events occur when the vehicle's speed increases above the maximum speed limit for the road on the target electronic map.
[0075] If there is no construction obstacle information at a certain location on the target electronic map, but a construction obstacle is detected when a vehicle is driving near that location (nearby can mean that the distance between the vehicle and the vehicle does not exceed a specified distance, such as 10m or 20m), then the construction obstacle detection event is determined.
[0076] After determining that the target event has occurred, the actual driving path of the vehicle during the target time period is obtained, and then multiple actual road snap points are determined in the target electronic map stored in the vehicle based on the actual driving path.
[0077] In some implementations, the cloud selects multiple actual road attachment points from the road points based on the distance between the simulated driving path and the road points in each road; the cloud simulates the driving process of the vehicle to obtain the simulated driving path.
[0078] In other words, the cloud can simulate the driving process of a vehicle based on its driving data over a certain period of time (which can be specified based on demand), obtain a simulated driving path, and then determine multiple actual road attachment points from the target electronic map stored in the cloud based on the simulated driving path.
[0079] The simulated driving path can include multiple simulated waypoints. The road point closest to each simulated waypoint (i.e., the closest road point to the simulated waypoint) can be determined from the target electronic map stored in the vehicle's memory. This road point serves as the actual road attachment point for each simulated waypoint. During the simulated vehicle driving process, the vehicle's location is collected at each simulated time point to obtain a simulated waypoint. The simulated time points can be set according to requirements, such as an interval of 0.1 seconds between two adjacent simulated time points. Alternatively, the vehicle's location can be collected at simulated distance intervals during the simulated vehicle driving process; for example, the simulated distance interval could be 5 meters.
[0080] After obtaining multiple actual road snap points, the cloud can determine the road intervals indicated by these snap points within the target electronic map as the road intervals to be processed. Note that the roads and road points in the target electronic map stored in the cloud and the target electronic map stored in the vehicle are consistent, but the semantic description information corresponding to the road intervals may differ.
[0081] Specifically, when the actual road adsorption points are determined based on the actual driving path of the vehicle, the arrangement order of multiple actual road adsorption points can be determined according to the arrangement order of multiple actual path points in the actual driving path; for any two adjacent actual road adsorption points, the road section between the two adjacent actual road adsorption points is taken as a road section to be processed indicated by the two adjacent actual road adsorption points.
[0082] Specifically, for each actual path point, the sequence number of the actual path point in the actual driving path can be used as the sequence number of the actual road adsorption point corresponding to that actual path point. In this way, by traversing each actual path point, the sequence number of each actual road adsorption point is obtained. Multiple actual road adsorption points are arranged according to their respective sequence numbers to determine the order of multiple actual road adsorption points.
[0083] Then, for a plurality of ordered actual road adsorption points, the road interval between two adjacent actual road adsorption points is taken as a road interval to be processed indicated by the two adjacent actual road adsorption points. In this way, all actual road adsorption points are traversed to obtain at least one road interval to be processed.
[0084] like Figure 4 As shown, 401 and 402 are roads on the target electronic map. The actual driving path of the vehicle within the target time period is 403. Based on the actual driving path 403, the actual driving path includes the actual path points 4031, 4032, 4033, and 4034. The actual road snapping points determined from 401 and 402 are 4041, which is closest to 4031; 4042, which is closest to 4032; 4043, which is closest to 4033; and 4044, which is closest to 4034. Therefore, the road interval to be processed determined based on these four actual road snapping points can be 4051, 4052, and 4053.
[0085] Similarly, when the actual road adsorption points are determined based on the simulated driving path of the vehicle, the arrangement order of multiple actual road adsorption points can be determined according to the arrangement order of multiple simulated path points in the simulated driving path; for any two adjacent actual road adsorption points, the road section between the two adjacent actual road adsorption points is taken as a road section to be processed indicated by the two adjacent actual road adsorption points.
[0086] Specifically, for each simulated path point, the sequence number of the simulated path point in the simulated driving path can be used as the sequence number of the actual road adsorption point corresponding to that simulated path point. In this way, by traversing each simulated path point, the sequence number of each actual road adsorption point is obtained. The multiple actual road adsorption points are arranged according to their respective sequence numbers, thereby determining the order of the multiple actual road adsorption points.
[0087] Then, for a plurality of ordered actual road adsorption points, the road interval between two adjacent actual road adsorption points is taken as a road interval to be processed indicated by the two adjacent actual road adsorption points. In this way, all actual road adsorption points are traversed to obtain at least one road interval to be processed.
[0088] In some embodiments, different road points in the road network of the target electronic map correspond to their respective point identifiers. When multiple actual road snap points are determined from the roads of the target electronic map, the point identifiers of the actual road snap points can be recorded, and the actual road snap points can be indicated by their point identifiers. Then, the vehicle can send the point identifiers of the actual road snap points to the cloud to achieve the purpose of sending the actual road snap points to the cloud. The point identifier used to indicate different road points in the roads of the target electronic map can be a point ID, which can be a combination of numbers, letters, and symbols.
[0089] After receiving the actual road adsorption points, the cloud can determine the semantic description information of each road section to be processed in the same way as the semantic description information of the road section determined in S140 above, and use it as the configuration semantic description information of the road section to be processed.
[0090] Afterwards, the cloud can send multiple actual road adsorption points and configuration semantic description information configured for the road section to be processed to the vehicle.
[0091] It is worth mentioning that if the vehicle sends a point identifier to the cloud that is the actual road adsorption point, the cloud can also return a point identifier that is the actual road adsorption point, so as to achieve the purpose of returning the actual road adsorption point.
[0092] S220. Determine the road sections to be processed indicated by multiple actual road snap-in points from the road in the target electronic map stored in the vehicle, and replace the semantic description information of the road sections to be processed in the target electronic map according to the configured semantic description information, so as to update the semantic description information of the road sections to be processed.
[0093] The vehicle can determine the road interval to be processed indicated by multiple actual road snap points from the road in the target electronic map stored in its own memory. Then, it can directly replace the semantic description information of the road interval to be processed in the target electronic map according to the configured semantic description information of the road interval to be processed, so as to update the semantic description information of the road interval to be processed and realize the update of the target electronic map stored in its own memory.
[0094] The process by which a vehicle can determine the road section to be processed indicated by multiple actual road adsorption points from the road in the target electronic map stored in its own memory is described in the aforementioned S210 and will not be repeated here.
[0095] For example, the actual road adsorption points indicating the road interval q to be processed are q1 and q2. q1 and q2 are determined in the road of the target electronic map of the vehicle. Then, the section of road between q1 and q2 is taken as the road interval to be processed.
[0096] For example, the map update process is as follows: Figure 5 As shown, the vehicle (i.e., the vehicle itself) determines the actual road snap-in point and then uploads it to the cloud. The cloud determines the road section to be processed and obtains the configuration semantic description information of the road section to be processed. The cloud can store the road section to be processed and the corresponding configuration semantic description information as vehicle control data in JSON format and send the vehicle control data to the vehicle. After that, the vehicle determines the road section to be processed based on the vehicle control data and replaces the semantic description information: the semantic description information of the road section to be processed in the target electronic map is replaced with the configuration semantic description information of the road section to be processed in the vehicle control data, thereby realizing the map update.
[0097] In this embodiment, the cloud determines the road sections to be processed based on multiple actual road snap points identified in the target electronic map, and obtains the configuration semantic description information allocated to each road section to be processed. Then, the road sections to be processed and the configuration semantic description information allocated to each road section to be processed are sent to the vehicle. The vehicle determines the road sections to be processed from the road network of the target electronic map stored in the vehicle, and then replaces the semantic description information of the road sections to be processed in the target electronic map stored in the vehicle according to the configuration semantic description information corresponding to each road section to be processed. This realizes the update of the semantic description information of the road sections to be processed in the target electronic map stored in the vehicle, thereby realizing the update of the target electronic map stored in the vehicle, so that the updated target electronic map can meet the real-time navigation needs of the vehicle.
[0098] Secondly, the road segment to be processed is indicated by at least two actual road snap points. Therefore, determining the corresponding road segment by using actual road snap points eliminates the need for similarity calculations. This allows for rapid determination of actual road snap points from the target electronic map stored in the vehicle, based on the distance between road points in the target electronic map and the driving path (actual or simulated), thus quickly identifying the road segment to be processed. This improves the efficiency of determining the road segment and consequently, the update efficiency of the target electronic map. Furthermore, indicating the road segment by at least two actual road snap points, rather than by a segment of road, reduces the amount of data used to indicate the road segment, thereby reducing the amount of data transmitted from the cloud to the vehicle, improving data transmission efficiency, and reducing network bandwidth pressure.
[0099] In addition, based on the actual driving path of the vehicle, multiple actual road snap points are determined, and the target electronic map is updated based on the semantic description information of the road sections determined by the multiple actual road snap points. This realizes real-time updating of the target electronic map according to the vehicle's driving situation and improves the real-time accuracy of the target electronic map.
[0100] Furthermore, it can simulate vehicle driving to obtain simulated driving paths, and determine multiple actual road adsorption points from the target electronic map stored in the cloud based on the simulated driving paths. Thus, multiple actual road adsorption points can be determined without the vehicle driving in real time, reducing the difficulty and cost of obtaining actual road adsorption points and improving the efficiency of obtaining actual road adsorption points.
[0101] See appendix Figure 6 , Figure 6 This illustration shows a structural block diagram of a vehicle control device according to one embodiment of this application. For use in a vehicle, the device 800 includes:
[0102] The acquisition module 810 is used to acquire the planned path obtained by the path planning of the vehicle.
[0103] The adsorption point determination module 820 is used to select multiple road adsorption points adsorbed by the planned path from the road points based on the distance between the planned path and the road points in each road of the target electronic map.
[0104] The interval determination module 830 is used to determine the target road interval indicated by multiple road adsorption points in the road;
[0105] The control module 840 is used to control vehicle movement based on the semantic description information of the target road section in the target electronic map and the planned route; the semantic description information of the target road section is used to indicate the road attributes of the target road section.
[0106] Optionally, the planned path includes multiple planned path points; the adsorption point determination module 820 is also used to determine the road point closest to each planned path point from the road points, as the road adsorption point corresponding to each planned path point.
[0107] Optionally, the interval determination module 830 is also used to determine the arrangement order of multiple road adsorption points according to the arrangement order of multiple planned path points in the planned path; for any two adjacent road adsorption points, the road interval located between the two adjacent road adsorption points is taken as a target road interval indicated by the two adjacent road adsorption points.
[0108] Optionally, the device further includes an update module for receiving multiple actual road snap points sent from the cloud and configuration semantic description information configured for the road section to be processed; the road section to be processed refers to the road section indicated by multiple actual road snap points in the road; the multiple actual road snap points are determined from road points; the road section to be processed indicated by multiple actual road snap points is determined from the roads in the target electronic map stored in the vehicle, and the semantic description information of the road section to be processed in the target electronic map is replaced according to the configuration semantic description information to update the semantic description information of the road section to be processed.
[0109] Optionally, the update module is also used to collect the actual driving path of the vehicle during the vehicle's journey; select multiple actual road adsorption points from the road points based on the distance between the actual driving path and the road points in each road; and send the multiple actual road adsorption points to the cloud.
[0110] Optionally, the update module is also used to collect the vehicle's driving path within the target time period corresponding to the target event during the vehicle's driving process in response to the triggering of the target event, as the actual driving path; the start time of the target time period is earlier than the start time of the target event, and the end time of the target time period is later than the end time of the target event.
[0111] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0112] Furthermore, the functions in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module.
[0113] On the other hand, this application also provides a computer-readable storage medium storing program code that can be called by a processor to execute the methods described in the above method embodiments.
[0114] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or a cluster of ROMs. Optionally, computer-readable storage media include non-volatile computer-readable storage media. The computer-readable storage media has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.
[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A vehicle control method, characterized in that, The method includes: Obtain the planned path obtained from the vehicle's path planning; Based on the distance between the planned path and the road points in each road of the target electronic map, select multiple road adsorption points that the planned path adsorbs from the road points; Determine the target road interval indicated by the plurality of road adsorption points in the road; The vehicle's movement is controlled based on the semantic description information of the target road section in the target electronic map and the planned route; the semantic description information of the target road section is used to indicate the road attributes of the target road section. Before controlling the vehicle's movement based on the semantic description information of the target road section in the target electronic map and the planned path, the method further includes: The system receives multiple actual road adsorption points sent from the cloud, along with configuration semantic description information for the road section to be processed. The road section to be processed refers to the road section indicated by the multiple actual road adsorption points in the road, which are determined from the road points. The cloud selects multiple actual road adsorption points adsorbed by the simulated driving path from the road points based on the distance between the simulated driving path and the road points in each road. The cloud simulates the driving process of the vehicle to obtain the simulated driving path. The system determines the road intervals to be processed indicated by the plurality of actual road snap points from the roads in the target electronic map stored in the vehicle, and replaces the semantic description information of the road intervals to be processed in the target electronic map according to the configured semantic description information, so as to update the semantic description information of the road intervals to be processed.
2. The method according to claim 1, characterized in that, The planned path includes multiple planned path points; The step of selecting multiple road-attached points attracted by the planned path from the road points based on the distance between the planned path and the road points in each road of the target electronic map includes: The road point closest to each of the planned path points is determined from the road points and used as the road adsorption point corresponding to each of the planned path points.
3. The method according to claim 2, characterized in that, Determining the target road interval indicated by the plurality of road adsorption points in the road includes: The arrangement order of the multiple road adsorption points is determined based on the arrangement order of the multiple planned path points in the planned path; For any two adjacent road adsorption points, the road interval between the two adjacent road adsorption points is taken as a target road interval indicated by the two adjacent road adsorption points.
4. The method according to claim 1, characterized in that, Before receiving the multiple actual road adsorption points sent from the cloud and the configuration semantic description information configured for the road section to be processed, the method further includes: During the vehicle's journey, the actual driving path of the vehicle is collected; Based on the distance between the actual driving path and the road points in each of the roads, select multiple actual road adsorption points that are adsorbed by the actual driving path from the road points; The multiple actual road adsorption points are sent to the cloud.
5. The method according to claim 4, characterized in that, The process of collecting the vehicle's actual driving path during vehicle operation includes: During vehicle operation, in response to a triggered target event, the vehicle's driving path within a target time period corresponding to the target event is collected as the actual driving path; the start time of the target time period is earlier than the start time of the target event, and the end time of the target time period is later than the end time of the target event.
6. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire the planned path obtained from the path planning of the vehicle. The adsorption point determination module is used to select multiple road adsorption points adsorbed by the planned path from the road points based on the distance between the planned path and the road points in each road of the target electronic map. An interval determination module is used to determine the target road interval indicated by the plurality of road adsorption points in the road; The control module is used to control the vehicle's movement based on the semantic description information of the target road section in the target electronic map and the planned path; the semantic description information of the target road section is used to indicate the road attributes of the target road section. The control module is further configured to perform the following steps before controlling the vehicle to drive based on the semantic description information of the target road section in the target electronic map and the planned path: The system receives multiple actual road adsorption points sent from the cloud, along with configuration semantic description information for the road section to be processed. The road section to be processed refers to the road section indicated by the multiple actual road adsorption points in the road, which are determined from the road points. The cloud selects multiple actual road adsorption points adsorbed by the simulated driving path from the road points based on the distance between the simulated driving path and the road points in each road. The cloud simulates the driving process of the vehicle to obtain the simulated driving path. The system determines the road intervals to be processed indicated by the plurality of actual road snap points from the roads in the target electronic map stored in the vehicle, and replaces the semantic description information of the road intervals to be processed in the target electronic map according to the configured semantic description information, so as to update the semantic description information of the road intervals to be processed.
7. A vehicle, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-5.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores processor-executable program code, which, when executed by the processor, causes the processor to perform the method according to any one of claims 1-5.
Citation Information
Patent Citations
Path planning method and system, electronic equipment and vehicle
CN115265574A
Vehicle control information determination method and device and vehicle
CN116767225A