Vehicle control method, apparatus, system, and storage medium

Abstract

Embodiments of the present application provide a vehicle control method, device, system and storage medium. A cloud obtains lane-level path planning information uploaded by a vehicle, real-time traffic signal data uploaded by an RSU, and high-definition map data. According to the lane-level path planning information, the real-time traffic signal data, and the high-definition map data, lane-level traffic signal data is determined and delivered to the vehicle. The vehicle obtains the lane-level traffic signal data delivered by the cloud. According to the lane-level traffic signal data and position information of at least one intersection ahead of the vehicle on a driving path, target speed data of the vehicle passing through each intersection under a green light condition is determined. According to the target speed data of each intersection, the vehicle is controlled to run. This scheme achieves the technical effect of efficiently passing through a red-green light intersection in actual driving.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to a vehicle control method, device, system, and storage medium. 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 for route planning and decision-making control. For example, when a vehicle approaches an intersection, it needs to quickly identify the traffic light status corresponding to the current lane to avoid running a red light or to provide the optimal passage suggestion.

[0003] Existing vehicles typically rely on onboard sensors or simple signal receiving devices to obtain traffic signal status at the intersection ahead, and use single-intersection signal prediction or fixed speed suggestions to achieve vehicle operation.

[0004] However, the above-mentioned method, which relies solely on traffic signal status, can easily lead to vehicles frequently encountering red lights and stopping during actual driving, resulting in poor traffic efficiency. Summary of the Invention

[0005] This application provides vehicle control methods, devices, systems, and storage media to achieve the technical effect of enabling vehicles to efficiently pass through traffic light intersections during actual driving.

[0006] In a first aspect, embodiments of this application provide a vehicle control method applied to a vehicle, the method comprising:

[0007] The system obtains lane-level traffic light data from the cloud, which is determined by the cloud based on lane-level route planning information uploaded by the vehicle, real-time traffic light data uploaded by the roadside unit (RSU), and high-precision map data.

[0008] Based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, determine the target speed data of the vehicle passing through each intersection under green light conditions.

[0009] The vehicle's operation is controlled based on the target speed data at each intersection.

[0010] In one or more embodiments, the lane-level traffic light data includes: countdown parameters;

[0011] Accordingly, the method further includes:

[0012] If no new lane-level traffic light data is acquired within a preset time period after the last acquisition of lane-level traffic light data, the countdown parameter in the lane-level traffic light data is updated according to the timestamp of the last acquisition of lane-level traffic light data.

[0013] In one or more embodiments, determining the target speed data of the vehicle passing through each intersection under green light conditions, based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on its travel path, includes:

[0014] Based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, at least one candidate speed data of the vehicle passing through each intersection under the green light condition is determined.

[0015] The at least one candidate speed data is filtered based on a filtering strategy to obtain target speed data for each intersection. The filtering strategy is determined based on a preset safe speed and / or the speed of other vehicles.

[0016] In one or more embodiments, the real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0017] Secondly, embodiments of this application provide a vehicle control method applied in the cloud, the method comprising:

[0018] Acquire lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data;

[0019] The lane-level traffic light data is determined based on the lane-level route planning information, the real-time traffic light data, and the high-precision map data.

[0020] The vehicle sends lane-level traffic light data, and the vehicle uses the lane-level traffic light data and the position information of at least one intersection ahead of the vehicle on its travel path to determine the target speed data of the vehicle passing through each intersection under green light conditions, and controls the operation of the vehicle.

[0021] In one or more embodiments, determining the lane-level traffic light data based on the lane-level path planning information, the real-time traffic light data, and the high-precision map data includes:

[0022] The high-precision map data and the real-time traffic light data are correlated to obtain a lane-level traffic light data dynamic layer;

[0023] The lane-level traffic light data is determined based on the lane-level path planning information and the lane-level traffic light data dynamic layer.

[0024] In one or more embodiments, the lane-level traffic light data includes: countdown parameters;

[0025] Accordingly, the countdown parameter is used to update the countdown parameter in the lane-level traffic light data based on the timestamp of the last time the lane-level traffic light data was acquired if no new lane-level traffic light data is acquired within a preset time period after the vehicle last acquired lane-level traffic light data.

[0026] In one or more embodiments, the real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0027] Thirdly, embodiments of this application provide a vehicle control device applied to a vehicle, the device comprising:

[0028] The acquisition module is used to acquire lane-level traffic light data sent from the cloud. The lane-level traffic light data is determined by the cloud based on the lane-level path planning information uploaded by the vehicle, the real-time traffic light data uploaded by the RSU, and high-precision map data.

[0029] The determination module is used to determine the target speed data of the vehicle passing through each intersection under green light conditions, based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path.

[0030] The control module is used to control the operation of the vehicle based on the target speed data at each intersection.

[0031] In one or more embodiments, the lane-level traffic light data includes: countdown parameters;

[0032] Accordingly, the determining module is also used for:

[0033] If no new lane-level traffic light data is acquired within a preset time period after the last acquisition of lane-level traffic light data, the countdown parameter in the lane-level traffic light data is updated according to the timestamp of the last acquisition of lane-level traffic light data.

[0034] In one or more embodiments, the determining module, based on the lane-level traffic light data and the position information of the vehicle at least one intersection ahead on its travel path, determines the target speed data of the vehicle passing through each intersection under green light conditions, specifically for:

[0035] Based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, at least one candidate speed data of the vehicle passing through each intersection under the green light condition is determined.

[0036] The at least one candidate speed data is filtered based on a filtering strategy to obtain target speed data for each intersection. The filtering strategy is determined based on a preset safe speed and / or the speed of other vehicles.

[0037] In one or more embodiments, the real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0038] Fourthly, embodiments of this application provide a vehicle control device applied in the cloud, the device comprising:

[0039] The acquisition module is used to acquire lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data;

[0040] The determination module is used to determine the lane-level traffic light data based on the lane-level path planning information, the real-time traffic light data, and the high-precision map data.

[0041] The transmitting module is used to transmit lane-level traffic signal data to the vehicle. The vehicle is used to determine the target speed data of the vehicle passing through each intersection under green light conditions based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, and to control the operation of the vehicle.

[0042] In one or more embodiments, the determining module determines the lane-level traffic light data based on the lane-level path planning information, the real-time traffic light data, and the high-precision map data, specifically for:

[0043] The high-precision map data and the real-time traffic light data are correlated to obtain a lane-level traffic light data dynamic layer;

[0044] The lane-level traffic light data is determined based on the lane-level path planning information and the lane-level traffic light data dynamic layer.

[0045] In one or more embodiments, the lane-level traffic light data includes: countdown parameters;

[0046] Accordingly, the countdown parameter is used to update the countdown parameter in the lane-level traffic light data based on the timestamp of the last time the lane-level traffic light data was acquired if no new lane-level traffic light data is acquired within a preset time period after the vehicle last acquired lane-level traffic light data.

[0047] In one or more embodiments, the real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0048] Fifthly, embodiments of this application provide a vehicle, 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] Sixthly, embodiments of this application provide a cloud platform, including: a memory and a processor;

[0052] The memory stores computer-executed instructions;

[0053] The processor executes computer execution instructions stored in the memory, causing the processor to perform the second aspect and / or various possible implementations of the second aspect as described above.

[0054] In a seventh aspect, 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 and second aspects and / or various possible implementations of the first and second aspects.

[0055] Eighthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first and second aspects and / or various possible implementations of the first and second aspects.

[0056] Ninthly, embodiments of this application provide a vehicle control system, the vehicle control system comprising: a vehicle and a cloud;

[0057] The vehicle is used to implement the first aspect and / or various possible implementations of the first aspect as described above;

[0058] The cloud is used to implement the second aspect and / or various possible implementations of the second aspect as described above.

[0059] In one or more embodiments, the vehicle control system further includes: an RSU;

[0060] The RSU is used to upload real-time traffic light data to the cloud.

[0061] The vehicle control method, device, system, and storage medium provided in this application embodiment acquire lane-level path planning information uploaded by the vehicle, real-time traffic light data uploaded by the RSU, and high-precision map data from the cloud; determine lane-level traffic light data based on the lane-level path planning information, real-time traffic light data, and high-precision map data, and send it to the vehicle; the vehicle obtains the lane-level traffic light data sent from the cloud, which is jointly determined by the cloud based on the lane-level path planning information uploaded by the vehicle, the real-time traffic light data uploaded by the RSU, and the high-precision map data; determine the target speed data for the vehicle to pass through each intersection under green light conditions based on the lane-level traffic light data and the vehicle's position information at least one intersection ahead on the driving path; and control the vehicle's operation based on the target speed data at each intersection. In this solution, the cloud first integrates lane-level path planning, real-time traffic light timing, and lane-level spatial topology from a high-precision map to generate lane-level traffic light data that precisely matches the vehicle's predetermined trajectory. This data is then distributed to the vehicle, allowing it to know in advance the precise timing of traffic lights at multiple intersections in its specific lane. Based on this information and its own location, the vehicle calculates its target speed for passing through each intersection at a constant or smooth speed within the green light window. This guides the vehicle to travel at the optimal speed, ensuring consistent green light passage, effectively reducing unnecessary stops and starts, significantly improving intersection traffic efficiency and driving smoothness, while also reducing energy consumption. Attached Figure Description

[0062] 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.

[0063] Figure 1 A schematic diagram of the vehicle control system provided in the embodiments of this application. Figure 1 ;

[0064] Figure 2 Flowchart of the vehicle control method provided in the embodiments of this application Figure 1 ;

[0065] Figure 3 This is a schematic diagram of lane-level path planning information provided in an embodiment of this application;

[0066] Figure 4 This is a schematic diagram of lane-level traffic light data provided in an embodiment of this application;

[0067] Figure 5 This is a schematic diagram illustrating the calculation of the vehicle's current speed and matching it to a green light, provided in an embodiment of this application.

[0068] Figure 6 Flowchart of the vehicle control method provided in the embodiments of this application Figure 2 ;

[0069] Figure 7 This is a schematic diagram illustrating the correspondence between traffic lights and lanes on a high-precision map, provided in an embodiment of this application.

[0070] Figure 8 This is a schematic diagram of a dynamic layer of lane-level traffic signal light data provided in an embodiment of this application;

[0071] Figure 9 Flowchart of the vehicle control method provided in the embodiments of this application Figure 3 ;

[0072] Figure 10 Schematic diagram of the vehicle control device provided in the embodiments of this application Figure 1 ;

[0073] Figure 11 Schematic diagram of the vehicle control device provided in the embodiments of this application Figure 2 ;

[0074] Figure 12 This is a schematic diagram of the vehicle structure provided in an embodiment of this application;

[0075] Figure 13 This is a schematic diagram of the cloud structure provided in an embodiment of this application;

[0076] Figure 14 A schematic diagram of the vehicle control system provided in the embodiments of this application. Figure 2 .

[0077] 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

[0078] 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.

[0079] 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.

[0080] For example, when a vehicle approaches an intersection, it needs to quickly identify the status of the traffic lights corresponding to the current lane (e.g., the remaining time of the left-turn light and the straight-ahead light) to avoid running a red light or to provide the optimal passage suggestion. However, in existing technologies, the matching of traffic light data and lanes relies on vehicle-side calculations, requiring the vehicle terminal to receive real-time traffic light broadcast information from all directions at the intersection and combine it with GPS positioning for filtering.

[0081] This leads to problems such as data redundancy, high computational load, and response latency. In addition, the traffic directions of different lanes (e.g., left turn, straight, right turn) and traffic light types (e.g., left turn light, straight light) need to be precisely matched to ensure that vehicles only receive signal information related to their own lane.

[0082] In complex intersections (such as multi-lane, multi-directional traffic lights), the accuracy of this matching process directly affects the safety and efficiency of intelligent driving systems. However, existing technologies cannot solve this problem.

[0083] To address the technical problems existing in the prior art, the inventors of this application have the following concept: Simply knowing the traffic light status is insufficient to achieve efficient traffic flow; it is necessary to combine the vehicle's driving intention with the detailed structure of the road. This leads to the integration of three key data sources: lane-level path planning reported by vehicles (reflecting the vehicle's future driving trajectory), real-time traffic light data uploaded by the RSU (providing dynamic signal timing), and high-precision maps (providing lane-level road topology). Furthermore, this information can be integrated through the cloud to pre-calculate the speed curve for each intersection within the green light window, enabling vehicles to adjust their speed in advance and achieve continuous green light wave-like passage, thereby reducing waiting time at the source and improving overall traffic efficiency.

[0084] Based on the above technical concept, Figure 1 A schematic diagram of the vehicle control system provided in the embodiments of this application. Figure 1 ,like Figure 1 As shown, the vehicle control system includes: vehicle-side (vehicle), roadside unit (RSU), and cloud-based (data service).

[0085] The RSU control box reports real-time traffic signal data to the cloud, and the vehicle reports lane-level route planning information (including lane-level route planning and location information, determined based on high-precision maps) to the cloud; then, the cloud determines the lane-level traffic signal data based on the reported information and high-precision maps.

[0086] Furthermore, the vehicle-side performs speed planning based on lane-level traffic light data and the location information of at least one intersection ahead on the driving path.

[0087] In one implementation, the RSU (Roadside Unit for Traffic Light Data) is networked to upload real-time traffic light data from each intersection to a cloud data service, including traffic light changes and update data for each intersection (intersection signage, intersection location, light orientation, light type, light color, countdown).

[0088] Cloud data service: Subscribe to real-time traffic light data for all intersections, match the real-time traffic light data (intersection location, light orientation, light type) with high-precision maps and associate it with corresponding lanes. This is equivalent to overlaying all traffic light data for all intersections onto the high-precision map to generate a dynamic layer of lane-level traffic light data.

[0089] On the vehicle side: New energy vehicles have network connectivity and intelligent driving functions. They upload lane-level path planning and location information based on high-precision maps to cloud data services, and request traffic light data of intersections covered by the lane-level path. They also receive updated traffic light data (including associated intersections and lanes, light colors, and countdowns) of the intersection lane-level traffic lights corresponding to the cloud data service (at 1-second intervals) in real time. Then, based on the traffic light data (light colors, countdowns) of the intersections associated with the path, the distance of the vehicle from the intersection, and the distance between each intersection, the vehicle calculates the current driving speed to match the green light conditions of the traffic lights associated with the path. Considering the influence of signal stability factors, the vehicle side automatically implements the countdown based on the countdown parameters in the received traffic light data of each intersection lane-level traffic light. After resuming reception, the vehicle is recalibrated to ensure that the calculated current speed (the target speed data below) meets the reliability of all intersection green light conditions.

[0090] This vehicle control system only briefly introduces the executing entity and other entities involved in this application. 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.

[0091] The following 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 be described below with reference to the accompanying drawings.

[0092] Figure 2 Flowchart of the vehicle control method provided in the embodiments of this application Figure 1 ,like Figure 2 As shown, the method includes:

[0093] Step 21: Obtain lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data from the cloud;

[0094] In this step, the cloud data service simultaneously receives three types of key data from different sources:

[0095] 1) Vehicles upload their lane-level path information based on high-precision maps via the network connectivity function. This lane-level path information describes the vehicle's expected driving lane sequence.

[0096] 2) Roadside RSUs continuously upload real-time traffic light data for the intersections they cover, including dynamic information such as intersection signage, intersection location, light orientation, light type, light color, and countdown timer.

[0097] 3) Access the high-precision map data stored in the cloud. This high-precision map data contains the fine geometry and topology of the road network, especially the lane-level connection relationships and attributes.

[0098] For example, Figure 3 This is a schematic diagram of lane-level path planning information provided in an embodiment of this application, such as... Figure 3 As shown in the diagram, yellow circles represent vehicles; and crosses within circles represent intersections.

[0099] Lane-level path planning information includes: the vehicle's current position; the distance d0 from the first intersection; the intersection and the distance between intersections (d3 is shown as the 4th intersection in the attached diagram).

[0100] Step 22: The cloud determines the lane-level traffic light data based on lane-level route planning information, real-time traffic light data, and high-precision map data;

[0101] In this step, the cloud performs association and matching calculations based on the lane-level path planning information, real-time traffic light data, and high-precision map data obtained in the previous steps, and finally extracts and generates lane-level traffic light data that precisely corresponds to the vehicle's planned path.

[0102] In other words, lane-level traffic signal data actually involves mapping discrete intersection signal states onto specific lanes on a high-precision map, and only filtering out the signal information of those intersections and corresponding lanes that the vehicle's path passes through.

[0103] For example, Figure 4 This is a schematic diagram of lane-level traffic signal data provided in an embodiment of this application, such as... Figure 4 As shown in the diagram, Figure 3 Based on this, lane-level traffic light data is given as an example: at the second intersection, the light color is c2, and the countdown is t2.

[0104] Step 23: The cloud sends lane-level traffic light data to the vehicles;

[0105] The vehicle is used to determine the target speed data for passing through each intersection under green light conditions based on lane-level traffic signal data and the vehicle's position information at least one intersection ahead on its driving path, and to control the vehicle's operation.

[0106] In this step, the cloud continuously and in real time transmits the lane-level traffic light data related to the vehicle path determined in step 22 above to the vehicle at a preset frequency (e.g., at 1-second intervals).

[0107] Correspondingly, vehicles obtain lane-level traffic light data from the cloud.

[0108] For example, lane-level traffic light data includes a countdown parameter. In this case, if the vehicle does not acquire new lane-level traffic light data within a preset time period after the last acquisition of lane-level traffic light data, the countdown parameter in the lane-level traffic light data is updated based on the timestamp of the last acquired lane-level traffic light data.

[0109] In this implementation, considering the potential for temporary instability in communication between the vehicle and the cloud, the vehicle has a local countdown maintenance function, namely:

[0110] If a new lane-level traffic light data is not received from the cloud within a preset time period (e.g., a period greater than 1 second) after successfully receiving lane-level traffic light data, the vehicle will not wait passively. Instead, it will automatically calculate and update the countdown locally based on the timestamp and countdown parameters from the most recently successfully received lane-level traffic light data to maintain signal continuity.

[0111] Furthermore, once communication is restored, the vehicle receives new lane-level traffic light data and immediately uses the new lane-level traffic light data to calibrate the locally maintained countdown, ensuring the reliability of subsequent speed calculations.

[0112] Step 24: Based on lane-level traffic signal data and the vehicle's position information at least one intersection ahead on its driving path, the vehicle determines the target speed data for passing through each intersection under green light conditions.

[0113] In this step, after receiving lane-level traffic light data from the cloud, the vehicle analyzes the location information of at least one intersection ahead on the driving path to determine one (or more) appropriate driving speeds, enabling the vehicle to arrive and pass safely when the traffic lights of the associated lanes at each intersection are green. This appropriate driving speed is then determined as the target speed data for passing each intersection.

[0114] The location information of at least one intersection ahead can be: distance information between it and other intersections on the path ahead.

[0115] In one possible implementation, for each intersection, the target speed data for that intersection is the speed data from the current vehicle position (or, when passing through the previous intersection) until passing through that intersection, which can be a speed curve arranged along a time series.

[0116] In another possible implementation, the target speed data for each intersection can be a determined current speed v0.

[0117] For example, Figure 5 This is a schematic diagram illustrating the calculation of the vehicle's current speed and matching it to a green light, provided in an embodiment of this application. Figure 5 As shown in the attached diagram, the distance d, light color c, and countdown parameter t of each intersection (taking 4 intersections as an example) are as follows:

[0118] Intersection 1: d0, c1, t1; Intersection 2: d1, c2, t2; Intersection 3: d2, c3, t3; Intersection 4: d3, c4, t4.

[0119] Therefore, the vehicle's current speed v0 = f((d0, c1, t1), (d1, c2, t2), (d2, c3, t3), (d3, c4, t4)). If there are more intersections, continue to add them.

[0120] Optionally, one possible implementation of step 24 is:

[0121] Step 1: Based on lane-level traffic signal data and the vehicle's position information at least one intersection ahead on its travel path, determine at least one candidate speed data for the vehicle to pass through each intersection under green light conditions.

[0122] In this implementation, the vehicle first calculates one or more theoretical speed values ​​based on the distance information from the vehicle's current position to the intersection to be calculated, the current color of the traffic light at the intersection, and the remaining green light time (or the start time of the next green light cycle), so that the vehicle arrives at the intersection just within the green light window, and these are recorded as at least one candidate speed data.

[0123] For example, the distance d between the vehicle's current position and the intersection, the current traffic light color (green or red) and the remaining green light time t1, and the remaining red light time (or the start time of the next green light cycle) t0.

[0124] If the current light is green, and t1 is greater than the shortest time d / vmax required for a vehicle to reach the intersection at its maximum legal speed vmax, then there exists a passable speed range. The theoretical lower speed limit can be obtained by calculating the minimum speed v1 = d / (t1 + δ) at which the vehicle just reaches the intersection when the green light ends (where δ is the reserved safety buffer time), and ensuring that v1 is not lower than the lower speed limit vmin. If v1 ≤ vmax, then any speed within the range [v1, vmax] will guarantee that the vehicle passes through the green light window.

[0125] If the current light is red, the speed of the vehicle arriving at the intersection after the start of the next green light cycle needs to be calculated: Let the start time of the next green light be t0, then the arrival time of the vehicle t2 should be greater than or equal to t0 + δ. Combining the travel distance d, the theoretical speed v = d / (t0 + δ - t3) can be obtained, where t3 is the current time, and it is necessary to check whether v is within the range of [v1, vmax].

[0126] Step 2: Filter at least one candidate speed data based on the filtering strategy to obtain the target speed data for each intersection. The filtering strategy is determined based on the preset safe speed and / or the speed of other vehicles.

[0127] In this implementation, at least one candidate speed data obtained in the previous step may contain unrealistic or potentially dangerous values ​​(e.g., excessively high or low speeds). Therefore, the vehicle will apply a preset filtering strategy to screen these candidate speeds.

[0128] The filtering strategy may include:

[0129] 1) Preset safe speed constraints: Limit candidate speed data to the legal speed limit of the road, the safe speed under the current weather and road conditions, and a reasonable range allowed by the vehicle's performance;

[0130] For example, in a scenario where the speed limit at an intersection is 60 km / h, if the candidate speed data is 75 km / h, it can be compared with a preset safe speed threshold (e.g., 110% of the speed limit, i.e., 66 km / h). Since the candidate speed data exceeds the preset safe speed, it can be directly filtered out and not included in the final target speed dataset, thus ensuring that vehicle speeds always comply with road regulations and safety limits, avoiding the risk of speeding.

[0131] 2) Consideration of the speed of other vehicles: Combine vehicle network information or sensor data to consider the average speed of the surrounding traffic flow, and avoid conflicts or dangers caused by excessive differences between one's own speed and the traffic flow.

[0132] For example, at a congested intersection, the average speed of surrounding vehicles is collected in real time as 30 km / h. If a candidate speed is 50 km / h, it can be compared with the average speed of surrounding vehicles. If the filtering strategy requires that the speed not exceed 120% of the average speed (i.e., 36 km / h), then the candidate speed of 50 km / h will be filtered out because it is significantly higher than the overall traffic flow speed. This encourages vehicles to coordinate their speed with the traffic flow, reducing safety hazards caused by sudden acceleration or braking.

[0133] Step 25: The vehicle controls its operation based on the target speed data at each intersection.

[0134] In this step, the vehicle's control system (such as adaptive cruise control or advanced driver assistance system) takes the target speed data obtained above as input and generates specific throttle and brake control commands to control the vehicle to smoothly accelerate / decelerate at or around the target speed data.

[0135] Furthermore, by tracking the vehicle's position in real time and comparing it with updated traffic light data and target speed, the control system can dynamically adjust the vehicle's speed to ensure that it conforms as closely as possible to the preset green wave speed curve during actual driving.

[0136] In the vehicle control method provided in this application embodiment, the cloud acquires lane-level path planning information uploaded by the vehicle, real-time traffic light data uploaded by the RSU, and high-precision map data; based on the lane-level path planning information, real-time traffic light data, and high-precision map data, it determines lane-level traffic light data and sends it to the vehicle. The vehicle acquires the lane-level traffic light data sent from the cloud, which is jointly determined by the cloud based on the lane-level path planning information uploaded by the vehicle, the real-time traffic light data uploaded by the RSU, and the high-precision map data; based on the lane-level traffic light data and the vehicle's position information at least one intersection ahead on the driving path, it determines the target speed data for the vehicle to pass through each intersection under green light conditions; and based on the target speed data for each intersection, it controls the vehicle's operation. In this solution, the cloud first integrates lane-level path planning, real-time traffic light timing, and lane-level spatial topology from a high-precision map to generate lane-level traffic light data that precisely matches the vehicle's predetermined trajectory. This data is then distributed to the vehicle, allowing it to know in advance the precise timing of traffic lights at multiple intersections in its specific lane. Based on this information and its own location, the vehicle calculates its target speed for passing through each intersection at a constant or smooth speed within the green light window. This guides the vehicle to travel at the optimal speed, ensuring consistent green light passage, effectively reducing unnecessary stops and starts, significantly improving intersection traffic efficiency and driving smoothness, while also reducing energy consumption.

[0137] Based on the above embodiments, Figure 6Flowchart of the vehicle control method provided in the embodiments of this application Figure 2 ,like Figure 6 As shown, the execution entity is the cloud, and step 22 may include:

[0138] Step 61: Perform correlation processing on the high-precision map data and real-time traffic light data to obtain a dynamic layer of lane-level traffic light data;

[0139] In this step, the cloud uses lane geometry, topology, and intersection structure information from high-precision map data to perform spatial and logical correlation processing with real-time traffic light data uploaded by the RSU.

[0140] One possible implementation is to find the corresponding physical intersection on a high-precision map based on parameters such as intersection location, light orientation, and light type in real-time traffic signal data, and further determine one or more specific lanes controlled by the signal light (e.g., left-turn lane, straight-ahead lane).

[0141] For example, Figure 7 This is a schematic diagram illustrating the correspondence between traffic lights and lanes on a high-precision map, as provided in an embodiment of this application. Figure 7 As shown (described from left to right), the first green light corresponds to lanes 1 and 2; the second green light corresponds to lane 3; the third green light corresponds to lanes 4, 5, 6, and 7; and the fourth green light corresponds to lane 8.

[0142] Through this association, traffic light data that was originally based on intersections is transformed into lane-signal correspondences that are bound to specific lanes in the map. All these associated data then form a dynamic layer of lane-level traffic light data in the cloud that covers the entire road network and can be updated in real time.

[0143] For example, Figure 8 This is a schematic diagram of a dynamic layer of lane-level traffic signal data provided in an embodiment of this application, such as... Figure 8 As shown, the pink curve represents the road network, and the green dots indicate the location of traffic lights.

[0144] Step 62: Determine the lane-level traffic light data based on the lane-level path planning information and the dynamic layer of lane-level traffic light data.

[0145] In this step, the cloud compares and performs spatial queries on the lane-level route planning information uploaded by the vehicle (i.e., the specific lane sequence that the vehicle plans to drive in) with the lane-level traffic light data dynamic layer generated in step 61 to determine the lane-level traffic light data.

[0146] One possible implementation is to traverse the planned path in the lane-level path planning information, and extract and filter all lane-level traffic light data of intersections that intersect or are related to the path from the dynamic layer of lane-level traffic light data.

[0147] Furthermore, the lane-level traffic light data that is ultimately determined and prepared to be issued to vehicles is strictly limited to all intersections that the vehicle will actually encounter on its driving path ahead, and is accurate to the real-time status of the traffic lights (including light color and countdown parameters, etc.) of the specific lane that the vehicle is currently in or about to enter.

[0148] In the vehicle control method provided in this application embodiment, the cloud-based vehicle system correlates high-precision map data and real-time traffic light data to obtain a dynamic layer of lane-level traffic light data. Based on lane-level path planning information and the dynamic layer of lane-level traffic light data, lane-level traffic light data is determined. This solution generates a dynamically updated lane-level traffic light data layer by correlating and fusing the lane-level static topology of the high-precision map with the real-time traffic light time-series data provided by the RSU, achieving precise spatial and temporal mapping of traffic light states. Furthermore, the cloud-based system matches this dynamic layer with the specific lane-level driving path uploaded by the vehicle, extracting and distributing time-series traffic light data precisely corresponding to the planned lane for each vehicle, providing core support for improving traffic efficiency.

[0149] Based on the above embodiments, Figure 9 Flowchart of the vehicle control method provided in the embodiments of this application Figure 3 ,like Figure 9 As shown, one possible implementation of the vehicle-road-cloud interaction timing sequence is presented:

[0150] The implementing entities are: RSU, cloud-based data services, and vehicle-side (vehicles).

[0151] Step 91: The cloud subscribes to all intersection traffic light data from the RSU;

[0152] Step 92: The RSU sends and updates the intersection traffic light data to the cloud;

[0153] Step 93: Match the cloud with the high-precision map and associate it with the corresponding lanes to generate a dynamic layer of traffic light data;

[0154] Step 94: The vehicle uploads lane-level route planning and location information based on high-precision maps to the cloud;

[0155] Step 95: Match the traffic light data of the intersections covered by the lane-level path in the cloud;

[0156] Step 96: The cloud sends and updates traffic signal light data at the intersection lane level at 1-second intervals;

[0157] Step 97: The vehicle calculates its current speed based on the traffic light data of the intersection lanes associated with its path, the distance between the vehicle and the intersection, and the distance between each intersection. It also performs countdown verification of the traffic light data of each intersection lane to match the green light of the traffic light associated with the path for passage.

[0158] The vehicle control method provided in this application embodiment involves uploading lane-level path planning and location information based on a high-precision map from the vehicle to the cloud. The cloud then uses the vehicle's lane-level path planning and location information, combined with the high-precision map, to match and cover traffic light data at all intersections along the path. Based on changes in the vehicle's location, the cloud sends and updates traffic light data (including light color and countdown) at 1-second intervals for all intersections along the path. The vehicle calculates its current speed based on the traffic light data associated with its path to determine the appropriate green light for passage. This technical solution can achieve the following technical effects:

[0159] Technical benefits: 1. Existing solutions can only obtain traffic light data for the current intersection. This technical solution can obtain lane-level traffic light data for all intersections along the vehicle's travel path through cloud data services and high-precision maps. Therefore, it can predict the lane-level traffic light data for the second, third, fourth, ... Nth intersection in advance, thereby controlling the driving speed in advance to match the green light passage of multiple intersections, further improving the efficiency of intelligent traffic flow, and reducing energy consumption by reducing parking.

[0160] Technical benefit 2: Existing solutions can only obtain traffic light data when vehicles are within a certain range of the RSU at the intersection, which has limitations. In contrast, this technical solution connects all RSUs at all intersections, and traffic light data is distributed by cloud data services, allowing vehicles to obtain traffic light data from any location.

[0161] Technical Effect 3: Existing solutions match traffic light information within a preset vehicle travel distance based on route planning information, location information, and heading information. This is road-level matching and has a large matching error. This technical solution matches traffic light data at intersections (intersection location, light orientation, and light type) with high-precision maps and associates them with corresponding lanes to generate a dynamic layer of lane-level traffic light data. Then, it matches the traffic light data of the covered intersections with the lane-level route planning and location information based on the high-precision map on the vehicle side. This is lane-level matching and effectively reduces matching errors.

[0162] Technical Effect 4: Existing solutions dynamically select the optimal data source to ensure that the vehicle can obtain the correct traffic light information. However, this method is singular and does not form a verification closed loop. In this technical solution, the vehicle automatically performs a countdown based on the countdown parameters in the received lane-level traffic light data of each intersection. After resuming reception, it is recalibrated to ensure that the calculated current speed meets the reliability of the green light conditions for all intersections.

[0163] Figure 10 Schematic diagram of the vehicle control device provided in the embodiments of this application Figure 1 ,like Figure 10 As shown, the vehicle control device is applied to a vehicle and includes:

[0164] The acquisition module 101 is used to acquire lane-level traffic light data sent from the cloud. The lane-level traffic light data is determined by the cloud based on the lane-level path planning information uploaded by the vehicle, the real-time traffic light data uploaded by the RSU, and the high-precision map data.

[0165] The determination module 102 is used to determine the target speed data of the vehicle passing through each intersection under green light conditions, based on lane-level traffic signal light data and the position information of the vehicle at least one intersection ahead on the driving path.

[0166] The control module 103 is used to control vehicle operation based on the target speed data at each intersection.

[0167] In one or more embodiments, lane-level traffic light data includes: countdown parameters;

[0168] Accordingly, the determining module 102 is also used for:

[0169] If no new lane-level traffic light data is acquired within a preset time period after the last acquisition of lane-level traffic light data, the countdown parameter in the lane-level traffic light data is updated based on the timestamp of the last acquisition of lane-level traffic light data.

[0170] In one or more embodiments, the determining module determines the target speed data of the vehicle passing through each intersection under green light conditions, based on lane-level traffic light data and the position information of the vehicle at least one intersection ahead on its travel path; specifically, it is used for:

[0171] Based on lane-level traffic signal data and the vehicle's position information at least one intersection ahead on its travel path, determine at least one candidate speed data for the vehicle to pass through each intersection under green light conditions.

[0172] The filtering strategy is used to filter at least one candidate speed data to obtain the target speed data for each intersection. The filtering strategy is determined based on a preset safe speed and / or the speed of other vehicles.

[0173] In one or more embodiments, real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0174] Figure 11 Schematic diagram of the vehicle control device provided in the embodiments of this application Figure 2 ,like Figure 11 As shown, this vehicle control device is cloud-based and includes:

[0175] The acquisition module 111 is used to acquire lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data;

[0176] The determination module 112 is used to determine lane-level traffic light data based on lane-level path planning information, real-time traffic light data, and high-precision map data.

[0177] The sending module 113 is used to send lane-level traffic signal data to the vehicle. The vehicle uses the lane-level traffic signal data and the position information of at least one intersection ahead on the driving path to determine the target speed data of the vehicle passing through each intersection under green light conditions and control the vehicle operation.

[0178] In one or more embodiments, the determining module 112 determines lane-level traffic light data based on lane-level path planning information, real-time traffic light data, and high-precision map data, specifically for:

[0179] By correlating high-precision map data and real-time traffic light data, a dynamic layer of lane-level traffic light data is obtained.

[0180] Based on lane-level route planning information and dynamic layers of lane-level traffic signal data, determine the lane-level traffic signal data.

[0181] In one or more embodiments, lane-level traffic light data includes: countdown parameters;

[0182] Correspondingly, the countdown parameter is used to update the countdown parameter in the lane-level traffic light data based on the timestamp of the last time the lane-level traffic light data was acquired if no new lane-level traffic light data is acquired within a preset time period after the vehicle last acquired lane-level traffic light data.

[0183] In one or more embodiments, real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

[0184] 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.

[0185] As can be seen from the above, the vehicle control device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0186] Figure 12 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Figure 12 As shown, this embodiment provides a vehicle (e.g., a controller in the vehicle).

[0187] The vehicle includes at least one processor 121 and a memory 122.

[0188] Optionally, the vehicle also includes: communication components 123.

[0189] The processor 121, memory 122 and communication component 123 are connected via bus 124.

[0190] In a specific implementation, at least one processor 121 executes computer execution instructions stored in memory 122, causing at least one processor 121 to perform the above-described method.

[0191] The specific implementation process of processor 121 can be found in the above-described method embodiment for the application vehicle. Its implementation principle and technical effect are similar, and will not be repeated here.

[0192] Figure 13 This is a schematic diagram of the cloud structure provided in an embodiment of this application. Figure 13 As shown, this embodiment provides a cloud platform (e.g., a cloud-based server).

[0193] The cloud includes at least one processor 131 and memory 132.

[0194] Optionally, the cloud also includes: communication component 133.

[0195] The processor 131, memory 132 and communication component 133 are connected via bus 134.

[0196] In a specific implementation, at least one processor 131 executes computer execution instructions stored in memory 132, causing at least one processor 131 to perform the above-described method.

[0197] The specific implementation process of processor 131 can be found in the above-mentioned application cloud method embodiment, which has a similar implementation principle and technical effect, and will not be repeated here.

[0198] 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.

[0199] The memory may include high-speed memory (Random Access Memory, RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0200] 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.

[0201] Figure 14 A schematic diagram of the vehicle control system provided in the embodiments of this application. Figure 2 ,like Figure 14 As shown, the vehicle control system includes: vehicle 141 and cloud 142;

[0202] Vehicle 141 is used to execute the vehicle control method applied to vehicle 141 in the above embodiments;

[0203] Cloud 142 is used to execute the vehicle control method applied to cloud 142 in the above embodiments.

[0204] Optionally, the vehicle control system also includes: RSU 143; RSU 143 is used to upload real-time traffic light data to the cloud 142.

[0205] As can be seen from the above, the vehicle control system provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0206] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0207] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0208] 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.

[0209] 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 application-specific integrated circuits (ASICs). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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 vehicle control method, characterized in that, Applied to vehicles, the method includes: The system obtains lane-level traffic light data from the cloud, which is determined by the cloud based on lane-level path planning information uploaded by the vehicle, real-time traffic light data uploaded by the roadside unit (RSU), and high-precision map data. Based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, determine the target speed data of the vehicle passing through each intersection under green light conditions. The vehicle's operation is controlled based on the target speed data at each intersection.

2. The method according to claim 1, characterized in that, The lane-level traffic signal data includes: countdown parameters; Accordingly, the method further includes: If no new lane-level traffic light data is acquired within a preset time period after the last acquisition of lane-level traffic light data, the countdown parameter in the lane-level traffic light data is updated according to the timestamp of the last acquisition of lane-level traffic light data.

3. The method according to claim 1 or 2, characterized in that, The step of determining the target speed data of the vehicle passing through each intersection under green light conditions, based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on its travel path, includes: Based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, at least one candidate speed data of the vehicle passing through each intersection under the green light condition is determined. The at least one candidate speed data is filtered based on a filtering strategy to obtain target speed data for each intersection. The filtering strategy is determined based on a preset safe speed and / or the speed of other vehicles.

4. The method according to claim 1 or 2, characterized in that, The real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

5. A vehicle control method, characterized in that, Applied to the cloud, the method includes: Acquire lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data; The lane-level traffic light data is determined based on the lane-level route planning information, the real-time traffic light data, and the high-precision map data. The vehicle sends lane-level traffic light data, and the vehicle uses the lane-level traffic light data and the position information of at least one intersection ahead of the vehicle on its travel path to determine the target speed data of the vehicle passing through each intersection under green light conditions, and controls the operation of the vehicle.

6. The method according to claim 5, characterized in that, The step of determining the lane-level traffic light data based on the lane-level path planning information, the real-time traffic light data, and the high-precision map data includes: The high-precision map data and the real-time traffic light data are correlated to obtain a lane-level traffic light data dynamic layer; The lane-level traffic light data is determined based on the lane-level path planning information and the lane-level traffic light data dynamic layer.

7. The method according to claim 5 or 6, characterized in that, The lane-level traffic signal data includes: countdown parameters; Accordingly, the countdown parameter is used to update the countdown parameter in the lane-level traffic light data based on the timestamp of the last time the lane-level traffic light data was acquired if no new lane-level traffic light data is acquired within a preset time period after the vehicle last acquired lane-level traffic light data.

8. The method according to claim 5 or 6, characterized in that, The real-time traffic signal data includes: intersection signage, intersection location, light orientation, light type, light color, and countdown.

9. A vehicle control device, characterized in that, Applied to vehicles, the device includes: The acquisition module is used to acquire lane-level traffic light data sent from the cloud. The lane-level traffic light data is determined by the cloud based on the lane-level path planning information uploaded by the vehicle, the real-time traffic light data uploaded by the RSU, and high-precision map data. The determination module is used to determine the target speed data of the vehicle passing through each intersection under green light conditions, based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path. The control module is used to control the operation of the vehicle based on the target speed data at each intersection.

10. A vehicle control device, characterized in that, The device, applied in the cloud, includes: The acquisition module is used to acquire lane-level route planning information uploaded by vehicles, real-time traffic light data uploaded by RSUs, and high-precision map data; The determination module is used to determine the lane-level traffic light data based on the lane-level path planning information, the real-time traffic light data, and the high-precision map data. The transmitting module is used to transmit lane-level traffic signal data to the vehicle. The vehicle is used to determine the target speed data of the vehicle passing through each intersection under green light conditions based on the lane-level traffic signal data and the position information of the vehicle at least one intersection ahead on the driving path, and to control the operation of the vehicle.

11. A vehicle, 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 1-4.

12. A cloud computing platform, 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 5-8.

13. A vehicle control system, characterized in that, The vehicle control system includes: a vehicle and a cloud platform; The vehicle is used to perform the method according to any one of claims 1-4; The cloud is used to perform the method described in any one of claims 5-8.

14. The system according to claim 13, characterized in that, The vehicle control system also includes: RSU; The RSU is used to upload real-time traffic light data to the cloud.

15. 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 1-8.

Images