Traffic lane matching method, device and server based on traffic light data
By building a global mapping relationship in the cloud, the problems of data redundancy and delay in matching traffic lights with vehicle-mounted terminals are solved, enabling efficient and real-time transmission of traffic light information and lane matching, and supporting dynamic traffic management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- VOYAH AUTOMOBILE TECH CO LTD
- Filing Date
- 2026-02-04
- Publication Date
- 2026-06-09
AI Technical Summary
In existing technologies, vehicles receive and match traffic light broadcasts from all directions at intersections in real time via onboard terminals. This results in redundant computational data, excessive load, and response delays, making it difficult to support dynamic traffic management services that are collaborative with the cloud.
A global mapping relationship is pre-built in the cloud to accurately spatially and logically associate traffic lights at intersections with roads and lanes in high-precision maps. After a vehicle reports the current road and lane markings, the cloud directly matches and sends out the relevant traffic light data, avoiding on-vehicle calculations.
It reduces the amount of communication data, lowers the vehicle-side computing load and processing latency, improves the system's real-time performance and energy efficiency, and supports flexible cloud-based traffic management services.
Smart Images
Figure CN122176914A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle technology, and in particular to a lane matching method, device, and server based on traffic light data. Background Technology
[0002] With the popularization of intelligent driving technology, vehicles need to obtain lane-level traffic information through high-precision maps and combine it with real-time traffic light status to perform route planning and decision control in order to avoid running red lights or provide optimal traffic suggestions.
[0003] In existing technologies, the matching of traffic light data with lanes relies on vehicle-side calculations. This requires the vehicle terminal to receive real-time traffic light broadcast information from all directions at the intersection and to filter the data using GPS positioning.
[0004] However, the above approach suffers from technical problems such as redundant vehicle-side computing data, excessive load, and response latency. Summary of the Invention
[0005] This application provides a lane matching method, apparatus, and server based on traffic light data to avoid the technical problems of redundant calculation data, excessive load, and response delay when matching vehicles with lanes based on traffic lights.
[0006] In a first aspect, embodiments of this application provide a lane matching method based on traffic light data, including:
[0007] Obtain the lane-level traffic light matching request sent by the vehicle, wherein the lane-level traffic light matching request carries the current road sign and the current lane sign;
[0008] Based on the current road sign and the current lane sign, the target traffic light data is determined in the global mapping relationship; the global mapping relationship is a mapping relationship of at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign, determined based on the real-time traffic light data corresponding to multiple intersections respectively.
[0009] The target traffic light data is sent to the vehicle.
[0010] In one or more embodiments, before determining the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign, the method further includes:
[0011] Obtain the real-time traffic light data corresponding to the multiple intersections;
[0012] For each intersection, the real-time traffic light data corresponding to the intersection is projected onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0013] Based on the road heading data corresponding to the intersection and the second traffic light data, determine the first traffic light data corresponding to the multiple lane markings under the intersection;
[0014] The global mapping relationship is constructed based on the first traffic light data corresponding to at least one road sign for each intersection and at least one lane sign under each road sign.
[0015] In one or more embodiments, determining the first traffic light data corresponding to the multiple lane markings at the intersection based on the road heading data corresponding to the intersection and the second traffic light data includes:
[0016] Based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data, determine the corresponding direction data between the traffic lights in the second traffic light data and the roads in the intersection;
[0017] Based on the corresponding direction data and the light type in the second traffic light data, the first traffic light data corresponding to each lane of the road in the intersection is determined.
[0018] In one or more embodiments, the real-time traffic light data corresponding to the intersection includes: traffic light location data and light group type data;
[0019] Accordingly, the step of projecting the real-time traffic light data corresponding to the intersection onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection includes:
[0020] The traffic light location data is projected onto a high-precision map, and data that is not a vehicle light in the light group type data is cleared to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0021] In one or more embodiments, prior to projecting the traffic light location data onto a high-precision map, the method further includes:
[0022] The traffic light position data is biased to obtain the processed traffic light position data.
[0023] In one or more embodiments, the real-time traffic light data corresponding to the intersection further includes: traffic light orientation data, countdown data, and color data;
[0024] Accordingly, based on the corresponding direction data and the light type in the second traffic light data, the first traffic light data corresponding to each lane of the road in the intersection is determined, including:
[0025] Based on the corresponding direction data and the light type in the second traffic light data, the target traffic lights corresponding to each lane of the road in the intersection are determined.
[0026] For each lane, the first traffic light data corresponding to that lane is determined based on the orientation data, countdown data, and color data of the target traffic light.
[0027] Secondly, embodiments of this application provide a lane matching device based on traffic light data, comprising:
[0028] The acquisition module is used to acquire lane-level traffic light matching requests sent by vehicles, wherein the lane-level traffic light matching requests carry the current road sign and the current lane sign.
[0029] The determination module is used to determine the target traffic light data in a global mapping relationship based on the current road sign and the current lane sign; the global mapping relationship is determined based on the real-time traffic light data corresponding to multiple intersections and includes: a mapping relationship of at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign;
[0030] The sending module is used to send the target traffic light data to the vehicle.
[0031] In one or more embodiments, before determining the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign, the determining module is further configured to:
[0032] Obtain the real-time traffic light data corresponding to the multiple intersections;
[0033] For each intersection, the real-time traffic light data corresponding to the intersection is projected onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0034] Based on the road heading data corresponding to the intersection and the second traffic light data, determine the first traffic light data corresponding to the multiple lane markings under the intersection;
[0035] The global mapping relationship is constructed based on the first traffic light data corresponding to at least one road sign for each intersection and at least one lane sign under each road sign.
[0036] In one or more embodiments, the determining module determines the first traffic light data corresponding to the multiple lane markings at the intersection based on the road heading data corresponding to the intersection and the second traffic light data, specifically for:
[0037] Based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data, determine the corresponding direction data between the traffic lights in the second traffic light data and the roads in the intersection;
[0038] Based on the corresponding direction data and the light type in the second traffic light data, the first traffic light data corresponding to each lane of the road in the intersection is determined.
[0039] In one or more embodiments, the real-time traffic light data corresponding to the intersection includes: traffic light location data and light group type data;
[0040] Accordingly, the step of projecting the real-time traffic light data corresponding to the intersection onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection includes:
[0041] The traffic light location data is projected onto a high-precision map, and data that is not a vehicle light in the light group type data is cleared to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0042] In one or more embodiments, before projecting the traffic light location data onto a high-precision map, the determining module is further configured to:
[0043] The traffic light position data is biased to obtain the processed traffic light position data.
[0044] In one or more embodiments, the real-time traffic light data corresponding to the intersection further includes: traffic light orientation data, countdown data, and color data;
[0045] Accordingly, the determining module, based on the corresponding direction data and the light type in the second traffic light data, determines the first traffic light data corresponding to each lane of the road in the intersection, specifically for:
[0046] Based on the corresponding direction data and the light type in the second traffic light data, the target traffic lights corresponding to each lane of the road in the intersection are determined.
[0047] For each lane, the first traffic light data corresponding to that lane is determined based on the orientation data, countdown data, and color data of the target traffic light.
[0048] Thirdly, embodiments of this application provide a server, including: a memory and a processor;
[0049] The memory stores computer-executed instructions;
[0050] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0051] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0052] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0053] The lane matching method, apparatus, and server based on traffic light data provided in this application embodiment acquire a lane-level traffic light matching request sent by a vehicle. The lane-level traffic light matching request carries the current road sign and the current lane sign. Based on the current road sign and the current lane sign, the target traffic light data is determined in a global mapping relationship. The global mapping relationship is a mapping relationship based on at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign, determined by real-time traffic light data corresponding to multiple intersections. The target traffic light data is then sent to the vehicle. This solution establishes a global mapping relationship between traffic lights at intersections and roads and lanes in a high-precision map in the cloud beforehand. When a vehicle uploads the current road sign and lane sign, the cloud can directly match and send traffic light data related only to that lane based on this mapping. This achieves precise binding of traffic light information to lanes, avoiding the need to broadcast the status of all traffic lights at the intersection to vehicles, thus significantly reducing the amount of data sent and saving communication bandwidth. At the same time, vehicles do not need to filter and match traffic light data locally, reducing the computing load and processing latency on the vehicle side and improving the real-time performance and energy efficiency of the system. Attached Figure Description
[0054] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0055] Figure 1 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 1 ;
[0056] Figure 2 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 2 ;
[0057] Figure 3 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 3 ;
[0058] Figure 4 A schematic diagram showing the correspondence between heading and orientation provided in an embodiment of this application;
[0059] Figure 5 A schematic diagram showing the lane-traffic light correspondence provided in an embodiment of this application;
[0060] Figure 6 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 4 ;
[0061] Figure 7 A schematic diagram of the structure of the lane matching device based on traffic light data provided in the embodiments of this application;
[0062] Figure 8 This is a schematic diagram of the server structure provided in an embodiment of this application.
[0063] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0064] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0065] With the popularization of intelligent driving technology, vehicles need to obtain lane-level traffic information (such as lane direction, speed limit, steering restrictions, etc.) through high-precision maps, and combine it with real-time traffic light status to carry out path planning and decision control.
[0066] In existing technologies, traffic lights utilize wireless communication modules to periodically broadcast traffic light information. Vehicles obtain their latitude and longitude information through a GPS or BeiDou module on their in-vehicle terminals. Vehicles receive the various sets of traffic light information broadcast by the traffic lights via their wireless communication modules. After receiving the traffic light information, the vehicle, combined with its latitude and longitude location, calculates the traffic light information group corresponding to its driving direction using a traffic light matching method. The vehicle then retrieves the traffic light readings from this information group and begins voice announcements or screen displays.
[0067] However, the solutions in the existing technology have the following significant drawbacks:
[0068] 1) Insufficient matching accuracy: The vehicle side needs to infer the correspondence between lanes and traffic lights based on GPS positioning and broadcast data, which is easily affected by positioning errors, resulting in lane-traffic light matching errors, especially in multi-lane or complex intersection scenarios.
[0069] 2) Data redundancy and traffic waste: Traffic light information for all directions at the intersection is broadcast to the vehicle. Even if the vehicle only needs signal data for some lanes, it still needs to receive the complete data packet, resulting in wasted communication traffic.
[0070] 3) High computing power consumption on the vehicle side: The vehicle side needs to continuously receive and parse a large amount of traffic light data and filter out information that matches its own lane through algorithms, which consumes computing resources and increases the risk of system latency.
[0071] 4) Limited functional scalability: Existing methods rely on independent processing on the vehicle side, making it difficult to support dynamic traffic management services that are collaborative with the cloud.
[0072] Accordingly, in response to the technical problems existing in the prior art, the inventors of this application have the following concept: The essential contradiction of the current solution lies in distributing the matching calculation, which could be solved once at the system level, to each vehicle for repeated execution. Therefore, if we can change our thinking and move the matching work from the vehicle to the cloud, that is, utilize the powerful computing capabilities and global data perspective of the cloud to pre-establish a precise spatial and logical association between all traffic lights at the intersection and lanes in the high-precision map, thus constructing a global mapping relationship, then when a vehicle only reports its own lane information, the cloud can query this global mapping relationship based on road and lane signs, and accurately determine and issue the corresponding traffic light status, thereby avoiding a series of technical problems caused by direct processing on the vehicle side.
[0073] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0074] It should be understood that this method is applied to servers, specifically cloud-based service devices or host computer systems.
[0075] Figure 1 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 1 ,like Figure 1 As shown, the method includes:
[0076] Step 11: Obtain the lane-level traffic light matching request sent by the vehicle;
[0077] Among them, the lane-level traffic light matching request carries the current road sign and the current lane sign;
[0078] In this step, the cloud receives a lane-level traffic light matching request from the vehicle. This lane-level traffic light matching request means that the vehicle not only reports the road it is on, but also the lane it is in.
[0079] Therefore, the lane-level traffic light matching request includes the current road identifier (e.g., Link ID) and the current lane identifier (e.g., Lane ID).
[0080] Then, the cloud receives this lane-level traffic light matching request through the vehicle-to-everything (V2X) interface and parses out the current road signs and the current lane signs.
[0081] Step 12: Determine the target traffic light data in the global mapping relationship based on the current road signs and current lane signs;
[0082] The global mapping relationship is based on the mapping relationship between at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign, determined by the real-time traffic light data corresponding to multiple intersections.
[0083] In this step, after receiving a lane-level traffic light matching request, the cloud performs a query based on the established global mapping relationship. This global mapping relationship is a pre-built database that stores the correspondence between all road signs, lane signs and the first traffic light data.
[0084] Based on the current lane identifier in the lane-level traffic light matching request, the cloud retrieves the road identifier that matches the current road identifier in the global mapping relationship; and determines the lane identifier that matches the current lane identifier from at least one lane identifier corresponding to the road identifier; then, the first traffic light data corresponding to the lane identifier is used as the target traffic light data.
[0085] For example, target traffic light data could be the traffic light color corresponding to the current lane on the current road, countdown data, etc.
[0086] Step 13: Send the target traffic light data to the vehicle.
[0087] In this step, the cloud sends the retrieved target traffic light data to the vehicle corresponding to the lane-level traffic light matching request via the vehicle-to-everything (V2X) communication link.
[0088] Therefore, once the vehicle receives the traffic light data for the target location, it can directly perform route planning and decision-making control.
[0089] The lane matching method based on traffic light data provided in this application involves obtaining a lane-level traffic light matching request sent by a vehicle, which carries the current road sign and the current lane sign. Based on the current road sign and the current lane sign, the target traffic light data is determined in a global mapping relationship. The global mapping relationship is a mapping relationship between at least one road sign determined based on real-time traffic light data corresponding to multiple intersections, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign. The target traffic light data is then sent to the vehicle. This solution establishes a global mapping relationship between traffic lights at intersections and roads and lanes in a high-precision map in the cloud beforehand. When a vehicle uploads the current road sign and lane sign, the cloud can directly match and send traffic light data related only to that lane based on this mapping. This achieves precise binding of traffic light information to lanes, avoiding the need to broadcast the status of all traffic lights at the intersection to vehicles, thus significantly reducing the amount of data sent and saving communication bandwidth. At the same time, vehicles do not need to filter and match traffic light data locally, reducing the computing load and processing latency on the vehicle side and improving the real-time performance and energy efficiency of the system.
[0090] Figure 2 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 2 ,like Figure 2 As shown, prior to step 12, the method further includes:
[0091] Step 21: Obtain real-time traffic light data for multiple intersections;
[0092] In this step, the cloud can continuously subscribe to real-time traffic light data from multiple intersections from the vehicle network or traffic signal system. This real-time traffic light data includes the physical location of the traffic lights, light group type (vehicle lights, pedestrian lights, etc.), orientation, light group type, current color, and remaining time.
[0093] The cloud receives and caches this real-time traffic light data through a standardized interface.
[0094] Step 22: For each intersection, project the real-time traffic light data corresponding to the intersection onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0095] In this step, the real-time traffic light data corresponding to the intersection is transformed into second traffic light data containing only vehicle lights in a high-precision map coordinate system through projection and filtering.
[0096] Optionally, the real-time traffic light data for the intersection includes: traffic light location data and light group type data;
[0097] Accordingly, one possible implementation of step 22 is to project the traffic light location data onto a high-precision map and clear the data that are not motor vehicle lights in the light group type data to obtain the second traffic light data corresponding to the motor vehicle lights at the intersection.
[0098] In this implementation, the cloud first projects and aligns the traffic light location data with the high-precision map through coordinate transformation to ensure that the traffic light location is consistent with the geometric location of the road and lane on the high-precision map. Then, the cloud filters out the data of non-motorized vehicle lights (such as pedestrian lights and non-motorized vehicle lights) in the light group type data, and only retains the motorized vehicle light data related to vehicle traffic to form the second traffic light data.
[0099] Optionally, before projecting the traffic light location data onto the high-precision map, another operation can be performed: skew the traffic light location data to obtain processed traffic light location data.
[0100] In this implementation, the offset processing can be used to slightly offset the real coordinates in order to meet data security or privacy protection requirements and avoid leaking precise location information.
[0101] Furthermore, the traffic light location data after offset processing can still maintain its topological relationship with the map without affecting the matching accuracy.
[0102] Step 23: Based on the road heading data and the second traffic light data corresponding to the intersection, determine the first traffic light data corresponding to the multiple lane signs below the intersection.
[0103] In this step, based on the road heading data corresponding to the intersection and the projected and filtered second traffic light data, the first traffic light data corresponding to each lane sign under the intersection is determined.
[0104] One implementation involves the cloud first matching the road heading data with the traffic light orientation information in the second traffic light data to establish corresponding direction data between the traffic lights and the road. Then, based on this corresponding direction data and the light type of the traffic lights in the second traffic light data, the cloud further accurately associates the second traffic light data corresponding to each traffic light with a specific lane that matches its control direction, and records it as the first traffic light data corresponding to that lane.
[0105] Step 24: Construct a global mapping relationship based on the data of the first traffic light corresponding to at least one road sign for each intersection and at least one lane sign under each road sign.
[0106] In this step, the cloud stores the data of the first traffic light corresponding to at least one road sign for each of the above intersections and at least one lane sign under each road sign in a structured manner, forming a global mapping table.
[0107] It should be understood that this global mapping relationship is dynamically updated and refreshed in real time as the real-time traffic light data obtained in step 21 changes.
[0108] The lane matching method based on traffic light data provided in this application involves acquiring real-time traffic light data corresponding to multiple intersections; for each intersection, projecting the real-time traffic light data onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection; determining the first traffic light data corresponding to multiple lane signs at the intersection based on the road heading data and the second traffic light data corresponding to the intersection; and constructing a global mapping relationship based on at least one road sign corresponding to each intersection and the first traffic light data corresponding to at least one lane sign under each road sign. This technical solution aggregates real-time traffic light data from multiple intersections and projects it onto a high-precision map to filter out vehicle light information. Then, combined with road heading data, it establishes a precise correspondence between traffic lights and lanes intersection by intersection and lane by lane, ultimately integrating it into a global mapping relationship. This ensures the consistency and integrity of the global data, enabling the cloud to respond to any vehicle's query request with extremely low latency, directly retrieving the corresponding traffic light status from the pre-constructed global mapping relationship based on the vehicle's lane.
[0109] Figure 3 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 3 ,like Figure 3 As shown, step 23 may include:
[0110] Step 31: Based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data, determine the corresponding direction data between the traffic lights in the second traffic light data and the roads in the intersection;
[0111] In this step, the cloud acquires the heading data (e.g., road heading) of each road at the intersection and matches it with the orientation data (e.g., orientation) of the traffic lights.
[0112] The matching process can be based on a preset angle range mapping table (as shown in Table 1 below) to map the traffic light orientation to the corresponding road heading (e.g., east, west, south, north, etc.) to obtain the corresponding direction data of the traffic lights and the roads in the intersection in the second traffic light data.
[0113] For example, the corresponding direction data could be the relationship between traffic lights and the road's direction.
[0114] Table 1 shows the matching relationship between road heading and traffic light orientation.
[0115] Table 1:
[0116]
[0117] For example, Figure 4 This is a schematic diagram showing the correspondence between heading and orientation provided in the embodiments of this application, such as... Figure 4 As shown, an example of matching road heading with traffic light orientation is given.
[0118] Step 32: Based on the light type in the corresponding direction data and the second traffic light data, determine the first traffic light data corresponding to each lane of the road in the intersection.
[0119] In this step, based on the established direction data of traffic lights and road directions, the traffic lights corresponding to each lane are precisely matched according to the light type and lane travel direction, and the second traffic light data corresponding to each lane is recorded as the first traffic light data.
[0120] For example, Figure 5 This is a schematic diagram of the lane-traffic light correspondence provided in the embodiments of this application, such as... Figure 5 As shown, an example of matching two traffic lights with three lanes is given.
[0121] Optionally, the real-time traffic light data for the intersection may also include: traffic light orientation data, countdown data, and color data. Therefore, one possible implementation of step 32 could be:
[0122] Step 1: Based on the light type in the corresponding direction data and the second traffic light data, determine the target traffic light corresponding to each lane of the road in the intersection;
[0123] In this implementation, based on the corresponding direction data, the light type (e.g., left turn light, straight light, right turn light, U-turn light) is further matched with the lane travel direction to obtain the target traffic lights corresponding to each lane of the road in the intersection.
[0124] For example, left-turn lanes are matched with left-turn lights, and straight lanes are matched with straight-going lights.
[0125] Step 2: For each lane, determine the first traffic light data corresponding to the lane based on the orientation data, countdown data, and color data of the target traffic light.
[0126] In this implementation, for each successfully matched traffic light, the cloud extracts real-time data such as the current color status and remaining time (countdown) from the corresponding second traffic light data, and combines them to form the first traffic light data corresponding to that lane, for subsequent storage and distribution.
[0127] The lane matching method based on traffic light data provided in this application determines the corresponding direction data between the traffic lights and the roads in the intersection based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data. Then, based on the corresponding direction data and the light type in the second traffic light data, it determines the first traffic light data corresponding to each lane of the road in the intersection. This scheme first determines the road direction controlled by the traffic lights by matching the road heading data of the intersection with the orientation data of the traffic lights. Then, combined with the specific light type of the traffic lights, it achieves a step-by-step accurate mapping from the macroscopic road direction to the microscopic specific lane. This eliminates the need for the cloud to repeatedly calculate the matching logic for each vehicle request; it can directly and quickly retrieve the unique corresponding traffic light information based on the lane identifier. This lays a core foundation for subsequent low-latency, high-precision on-demand delivery of traffic light information.
[0128] Figure 6 A flowchart illustrating the lane matching method based on traffic light data provided in this application embodiment. Figure 4 ,like Figure 6 As shown, one possible example of this method is:
[0129] Step 61, Begin;
[0130] Step 62: Subscribe to all traffic light information at intersections from the vehicle network, including: the location, type, orientation, light group type, color, and remaining time of the signal light group's color status;
[0131] Step 63: Remove data for non-motorized vehicles, etc., and only keep traffic lights with a light group type of motorized vehicle lights;
[0132] Step 64: Match the traffic lights with the road direction to obtain the correspondence between traffic lights and roads;
[0133] Step 65: Based on the lane traffic direction (left turn, U-turn, straight, right turn) and the traffic light type (left turn light, U-turn light, straight light, right turn light), obtain the correspondence between each lane and the traffic light;
[0134] Step 66: Store in the database;
[0135] Step 67: End.
[0136] The lane matching method based on traffic light data provided in this application has the following technical effects:
[0137] Technical effect 1) Compared with the current vehicle-side matching, it reduces the vehicle-side computing power and power consumption. As a consumer, the vehicle no longer needs to calculate the matching traffic lights, and the computing load is extremely light. For intelligent driving systems that need to run for a long time, this means lower power consumption and less heat generation.
[0138] Technical effect 2) Improved communication efficiency: The network transmits refined data in this solution, only sending the traffic light status and the remaining passage time of the corresponding light color associated with the lane where the vehicle is located or the recommended lane. The amount of data sent is small. Compared with the current solution of broadcasting the traffic lights of the entire intersection, the amount of data is greatly reduced, the bandwidth usage is minimal, the latency is lower, and the communication efficiency is greatly improved.
[0139] Technical effect 3) This solution supports more flexible services and business models. Based on this solution, services such as green wave traffic, priority traffic, and dynamic lane management can be easily realized in the cloud. The cloud can plan the optimal traffic light signal sequence for specific vehicles or fleets according to the overall traffic situation.
[0140] Figure 7 This is a schematic diagram of the lane matching device based on traffic light data provided in an embodiment of this application, as shown below. Figure 7 As shown, the lane matching device based on traffic light data includes:
[0141] The acquisition module 71 is used to acquire the lane-level traffic light matching request sent by the vehicle. The lane-level traffic light matching request carries the current road sign and the current lane sign.
[0142] The determination module 72 is used to determine the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign. The global mapping relationship is determined based on the real-time traffic light data corresponding to multiple intersections and includes: a mapping relationship of at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign.
[0143] The sending module 73 is used to send the target traffic light data to the vehicle.
[0144] In one or more embodiments, before determining the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign, the determining module 72 is further configured to:
[0145] Obtain real-time traffic light data for multiple intersections;
[0146] For each intersection, the real-time traffic light data corresponding to the intersection is projected onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
[0147] Based on the road heading data and the second traffic light data corresponding to the intersection, determine the first traffic light data corresponding to the multiple lane signs under the intersection;
[0148] A global mapping relationship is constructed based on the data of the first traffic light corresponding to at least one road sign at each intersection and at least one lane sign under each road sign.
[0149] In one or more embodiments, the determining module 72 determines the first traffic light data corresponding to multiple lane markings at the intersection based on the road heading data and the second traffic light data corresponding to the intersection, specifically for:
[0150] Based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data, determine the corresponding direction data between the traffic lights in the second traffic light data and the roads in the intersection;
[0151] Based on the light type in the corresponding direction data and the second traffic light data, determine the first traffic light data corresponding to each lane of the road in the intersection.
[0152] In one or more embodiments, the real-time traffic light data corresponding to the intersection includes: traffic light location data and light group type data;
[0153] Accordingly, the real-time traffic light data corresponding to the intersection is projected onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection, including:
[0154] The traffic light location data is projected onto a high-precision map, and data that is not for motor vehicles is cleared from the light group type data to obtain the second traffic light data corresponding to the motor vehicle lights at the intersection.
[0155] In one or more embodiments, before projecting the traffic light location data onto a high-precision map, the determination module 72 is further configured to:
[0156] The traffic light position data is biased to obtain the processed traffic light position data.
[0157] In one or more embodiments, the real-time traffic light data corresponding to the intersection further includes: traffic light orientation data, countdown data, and color data;
[0158] Accordingly, module 72 determines the first traffic light data corresponding to each lane of the road at the intersection based on the corresponding direction data and the light type in the second traffic light data. Specifically, this is used for:
[0159] Based on the corresponding direction data and the light type in the second traffic light data, determine the target traffic light corresponding to each lane of the road in the intersection;
[0160] For each lane, the first traffic light data corresponding to the lane is determined based on the orientation data, countdown data, and color data of the target traffic light.
[0161] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical element, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls, or entirely in hardware. Alternatively, some modules can be implemented through processing element calls in software, while others can be implemented in hardware. Moreover, these modules can be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.
[0162] As can be seen from the above, the lane matching device based on traffic light data provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0163] Figure 8 This is a schematic diagram of the server structure provided in an embodiment of this application. Figure 8 As shown, the server provided in this embodiment includes at least one processor 81 and a memory 82.
[0164] Optionally, the server also includes a communication component 83.
[0165] The processor 81, memory 82, and communication component 83 are connected via bus 84.
[0166] In a specific implementation, at least one processor 81 executes computer execution instructions stored in memory 82, causing at least one processor 81 to perform the above-described method.
[0167] The specific implementation process of processor 81 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0168] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0169] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0170] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0171] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0172] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0173] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0174] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0175] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0176] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0177] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0178] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0179] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0180] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A lane matching method based on traffic light data, characterized in that, include: Obtain the lane-level traffic light matching request sent by the vehicle, wherein the lane-level traffic light matching request carries the current road sign and the current lane sign; Based on the current road sign and the current lane sign, the target traffic light data is determined in the global mapping relationship; The global mapping relationship is based on the mapping relationship of at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign, determined by real-time traffic light data corresponding to multiple intersections respectively. The target traffic light data is sent to the vehicle.
2. The method according to claim 1, characterized in that, Before determining the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign, the method further includes: Obtain the real-time traffic light data corresponding to the multiple intersections; For each intersection, the real-time traffic light data corresponding to the intersection is projected onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection. Based on the road heading data corresponding to the intersection and the second traffic light data, determine the first traffic light data corresponding to the multiple lane markings under the intersection; The global mapping relationship is constructed based on the first traffic light data corresponding to at least one road sign for each intersection and at least one lane sign under each road sign.
3. The method according to claim 2, characterized in that, The step of determining the first traffic light data corresponding to the multiple lane markings at the intersection based on the road heading data and the second traffic light data includes: Based on the road heading data corresponding to the intersection and the orientation data in the second traffic light data, determine the corresponding direction data between the traffic lights in the second traffic light data and the roads in the intersection; Based on the corresponding direction data and the light type in the second traffic light data, the first traffic light data corresponding to each lane of the road in the intersection is determined.
4. The method according to claim 2 or 3, characterized in that, The real-time traffic light data corresponding to the intersection includes: traffic light location data and light group type data; Accordingly, the step of projecting the real-time traffic light data corresponding to the intersection onto a high-precision map to obtain the second traffic light data corresponding to the vehicle lights at the intersection includes: The traffic light location data is projected onto a high-precision map, and data that is not a vehicle light in the light group type data is cleared to obtain the second traffic light data corresponding to the vehicle lights at the intersection.
5. The method according to claim 4, characterized in that, Before projecting the traffic light location data onto the high-precision map, the method further includes: The traffic light position data is biased to obtain the processed traffic light position data.
6. The method according to claim 4, characterized in that, The real-time traffic light data corresponding to the intersection also includes: traffic light orientation data, countdown data, and color data; Accordingly, based on the corresponding direction data and the light type in the second traffic light data, the first traffic light data corresponding to each lane of the road in the intersection is determined, including: Based on the corresponding direction data and the light type in the second traffic light data, the target traffic lights corresponding to each lane of the road in the intersection are determined. For each lane, the first traffic light data corresponding to that lane is determined based on the orientation data, countdown data, and color data of the target traffic light.
7. A lane matching device based on traffic light data, characterized in that, include: The acquisition module is used to acquire lane-level traffic light matching requests sent by vehicles, wherein the lane-level traffic light matching requests carry the current road sign and the current lane sign. The determination module is used to determine the target traffic light data in the global mapping relationship based on the current road sign and the current lane sign; The global mapping relationship is determined based on the real-time traffic light data corresponding to multiple intersections and includes: a mapping relationship of at least one road sign, at least one lane sign corresponding to each road sign, and the first traffic light data corresponding to each lane sign; The sending module is used to send the target traffic light data to the vehicle.
8. A server, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, is used to implement the method as described in any one of claims 1-6.