Vehicle passing control method, device and equipment and storage medium
By using lane information and navigation information to generate virtual traffic signals, the problem that smart cars are difficult to judge the traffic status in complex intersection environments is solved, and the smoothness and safety of smart cars passing through intersections is achieved.
Patent Information
- Application Number
- CN202510199466.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-21
- Publication Date
- 2025-05-13
AI Technical Summary
In complex intersection environments, it is difficult for smart cars to effectively judge whether they can pass through the intersection ahead normally, especially when traffic flow and pedestrians meet in multiple directions.
Through lane information on the road and navigation information of the current vehicle, passable information on each lane is judged, and virtual traffic signals are generated based on physical traffic lights, so that intelligent cars can quickly and smoothly pass through the intersection according to the virtual traffic signals of each lane.
It realizes that smart cars can quickly and accurately judge the traffic status of each lane in complex intersection environments, and improve the smoothness and safety of passing through intersections.
Smart Images
Figure CN119992848A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent driving technology, and in particular to a vehicle traffic control method, device, equipment and storage medium. Background Art
[0002] With the rapid development of science and technology, the application of intelligent driving technology is becoming more and more widespread. Intelligent cars can perceive the road environment through the on-board sensor system and quickly identify road traffic lights, so as to automatically plan the driving route and control the vehicle to pass the corresponding intersection. In a complex intersection environment, there are usually traffic and pedestrians from multiple directions. At this time, when passing through the intersection, the intelligent car needs to make a decision on whether to continue driving based on the real-time traffic signals. Therefore, how to more effectively determine whether the vehicle can pass the intersection ahead normally is a problem to be solved in this field. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide a vehicle traffic control method, device, equipment and storage medium, which can determine the trafficable information on each lane through the lane information on the road and the navigation information of the current vehicle, and generate virtual traffic signals based on physical traffic lights, so that smart cars can pass through the intersection quickly and smoothly according to the virtual traffic signals of each lane. The specific scheme is as follows:
[0004] In a first aspect, the present application provides a vehicle traffic control method, comprising:
[0005] Determine lane information of each lane on the road where the target vehicle is currently located; the lane information includes ground signs of the lane driving direction and first signal light information of the physical traffic light corresponding to the front of the lane;
[0006] Determine the passable information corresponding to the target vehicle on each lane based on the current navigation information of the target vehicle and the ground sign of the lane driving direction;
[0007] Generating second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information;
[0008] The target vehicle is controlled to pass through the current road based on the second signal light information.
[0009] Optionally, generating second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information includes:
[0010] Inputting the first traffic light information and the passable information into a preset machine learning model;
[0011] Classifying each lane according to the first signal light information and the passable information through the decision tree of the preset machine learning model to obtain a corresponding classification result;
[0012] Based on the classification result, the second traffic light information of the virtual traffic light corresponding to the target vehicle on each lane is generated.
[0013] Optionally, after generating the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane, the method further includes:
[0014] Determining an information error of the target vehicle on a current road based on a comparison result between the first signal light information and the second signal light information;
[0015] The preset machine learning model is optimized using a target training set generated based on the information error, so as to continue to use the optimized preset machine learning model to generate the second signal light information of the target vehicle.
[0016] Optionally, the determining, based on the current navigation information of the target vehicle and the ground sign of the lane driving direction, the corresponding passable information of the target vehicle on each lane includes:
[0017] Determine the current navigation direction of the target vehicle based on the navigation information of the current target vehicle, and determine the lane travel direction of each lane based on the lane travel direction ground sign;
[0018] The corresponding passable information of the target vehicle on each lane is determined according to the navigation direction and the lane passing direction.
[0019] Optionally, before determining the passable information corresponding to the target vehicle on each lane based on the current navigation information of the target vehicle and the ground mark of the lane driving direction, the method further includes:
[0020] Determine a target distance between the current target vehicle and the stop line of the first intersection to be passed on the current road based on the lane information; the first intersection to be passed is an intersection where the lane travel direction ground sign and / or the physical traffic light first appear in front of the target vehicle;
[0021] The target distance is compared with a preset distance threshold, so as to determine the passable information of the target vehicle on each lane when the target distance is not greater than the preset distance threshold.
[0022] Optionally, determining the passable information corresponding to the target vehicle on each lane according to the navigation direction and the lane passing direction includes:
[0023] If the lane traffic direction of the lane is unidirectional, determining whether the navigation direction is consistent with the traffic directions of each lane on the road where the target vehicle is currently located;
[0024] Determine a first lane as impassable; the first lane is a lane where the navigation direction and the lane passing direction are inconsistent;
[0025] The second lane is determined to be passable; the second lane is a lane where the navigation direction and the lane passing direction are consistent.
[0026] Optionally, determining the passable information corresponding to the target vehicle on each lane according to the navigation direction and the lane passing direction includes:
[0027] If the lane has a multi-directional traffic direction, determining whether there is a lane on the road where the target vehicle is currently located whose lane traffic direction is consistent with the navigation direction;
[0028] Determine the third lane as impassable; the third lane is a lane whose passing direction is inconsistent with the navigation direction;
[0029] The fourth lane is determined to be passable, and the driving direction of the target vehicle on the fourth lane is determined based on the navigation direction; the fourth lane is a lane whose lane driving direction is consistent with the navigation direction.
[0030] Optionally, the process of controlling the target vehicle to pass the current road based on the second signal light information includes:
[0031] If the lane currently in which the target vehicle is located is not passable, the target vehicle is controlled to travel to a currently passable lane, so that based on the second signal light information, the target vehicle is controlled to pass the current road in the currently passable lane.
[0032] In a second aspect, the present application provides a vehicle traffic control device, comprising:
[0033] A lane information determination module is used to determine the lane information of each lane on the road where the target vehicle is currently located; the lane information includes the ground sign of the lane driving direction and the first signal light information of the physical traffic light corresponding to the front of the lane;
[0034] A traffic information determination module, used to determine the corresponding trafficable information of the target vehicle on each lane based on the current navigation information of the target vehicle and the ground sign of the lane driving direction;
[0035] An information generating module, configured to generate second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information;
[0036] A vehicle control module is used to control the target vehicle to pass the current road based on the second signal light information.
[0037] In a third aspect, the present application provides an electronic device, comprising a processor and a memory; wherein the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the aforementioned vehicle traffic control method.
[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which implements the aforementioned vehicle traffic control method when executed by a processor.
[0039] In this application, the first signal light information of the lane driving direction ground sign of each lane on the road where the target vehicle is currently located and the corresponding physical traffic light in front of the lane is first determined, and then the corresponding passable information of the target vehicle on each lane is determined based on the navigation information of the current target vehicle and the lane driving direction ground sign, and then the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane is generated according to the first signal light information and the passable information, so as to control the target vehicle to pass through the current road based on the second signal light information. Through the above technical scheme, in this application, when the vehicle is driving on the road and is about to pass through the intersection area, the comparison result between the lane information on the road where the target vehicle is currently located and the navigation information of the current vehicle can be determined, so as to judge whether the current vehicle can continue to pass in each lane, and generate the corresponding virtual traffic signal according to the judgment result and the signal light information of the physical traffic light in front of the lane, and mount the generated virtual signal light information to the corresponding lane, so that the generated virtual signal light information can help the smart car to pass through the intersection controlled by the traffic light, and help the vehicle determine the traffic light information of each lane, so that the smart car can pass through the intersection quickly and smoothly. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0041] Figure 1 A flow chart of a vehicle traffic control method provided in this application;
[0042] Figure 2 A flow chart of a vehicle traffic control method provided in this application;
[0043] Figure 3 A schematic diagram of the structure of a vehicle traffic control device provided in this application;
[0044] Figure 4 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION
[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0046] In a complex intersection environment, there are usually traffic and pedestrians from multiple directions. At this time, smart cars need to make a decision on whether to continue driving based on real-time traffic signals. In this application, when a vehicle is driving on the road and is about to pass through an intersection, it can determine the lane information on the current road and the navigation information of the current vehicle, so as to determine whether the current vehicle can pass in each lane, and generate a virtual traffic signal based on the judgment result and the physical traffic light information and mount it to the corresponding lane, thereby helping the vehicle to determine the traffic light information of each lane, so that the smart car can pass through the intersection quickly and smoothly.
[0047] See also Figure 1 As shown, an embodiment of the present invention discloses a vehicle traffic control method, including:
[0048] Step S11, determining lane information of each lane on the road where the target vehicle is currently located; the lane information includes a ground sign of the lane driving direction and first signal light information of a physical traffic light corresponding to the front of the lane.
[0049] It can be understood that this embodiment is mainly used in the case where a smart car encounters a traffic light when passing through an intersection area and needs to pass according to the state of the traffic light. The above-mentioned intersection area is not limited to a specific intersection. Any intersection that needs to pass according to the traffic light can be used, including but not limited to a crossroads, a straight intersection, etc., and the above-mentioned traffic light is not limited to a specific red-green light, and any traffic light that can control the traffic at the intersection can be used. In addition, in this embodiment, the acquired lane information and navigation information are mainly input into the preset classification model to generate the current virtual traffic light of the target vehicle for mounting. Therefore, the data acquired in this embodiment is mainly perception data and navigation data, including the location, type, state and seconds (if any) of each traffic light; the ground arrow direction of the lane where the current vehicle is located; the driving direction of the intersection ahead (left turn, right turn, straight ahead). It can be understood that the above-mentioned perception data in a specific embodiment can be the road ground arrow data and intersection signal light data acquired by the on-board radar of the target vehicle.
[0050] Therefore, in this embodiment, the lane information of each lane on the road where the target vehicle is currently located can be determined first. The lane information includes the ground sign of the lane driving direction and the first signal light information of the physical traffic light corresponding to the front of the lane. Specifically, the driving direction of the current lane can be determined based on the ground arrow perceived by the vehicle, including but not limited to straight ahead, left turn, right turn, straight ahead left turn, straight ahead right turn, straight ahead left turn right turn.
[0051] Step S12: based on the current navigation information of the target vehicle and the ground sign of the lane driving direction, determine the corresponding passable information of the target vehicle on each lane.
[0052] In this embodiment, the corresponding passable information of the target vehicle in each lane can be determined based on the navigation information of the current target vehicle and the ground signs of the lane driving direction. That is to say, in this embodiment, the corresponding passable information of the target vehicle in each lane can be further determined in combination with the driving direction of the front intersection in the navigation data. The corresponding passable information can be determined by comparing the driving direction in the navigation data with the ground signs of the lane driving direction. It can be understood that the above navigation data can be satellite data received by the target vehicle, or navigation data sent to the current vehicle from the cloud, which is not specifically limited here. In a specific embodiment, the above passable information can include passable and impassable.
[0053] Step S13: generating second signal light information of the virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information.
[0054] In this embodiment, the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane can be generated according to the first signal light information and passable information obtained above. Specifically, the first signal light information and passable information can be input into a preset machine learning model, and then the lanes are classified according to the first signal light information and passable information through the decision tree of the preset machine learning model to obtain corresponding classification results, and the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane is generated based on the classification results.
[0055] In a specific embodiment, the preset machine learning model can be specifically an XGboost model, that is, in this embodiment, the first signal light information and the passable information can be input into the XGboost model to mount the traffic light. The input information of the model includes the lane traffic direction, the position, type, state and seconds (if any) of each traffic light of the traffic light, and the output is the traffic light state of each lane. In this way, based on the characteristics of the XGboost model for processing nonlinear relationships and complex structure data, the classified mounting of traffic lights can be effectively realized, and the mounting of lane traffic lights in most traffic light-controlled intersections can be processed.
[0056] Specifically, the above model uses CART tree training to obtain an initial model. In this way, a deviation value will be generated for each sample during the above training process, and then the deviation value is used as a new training set to continue using CART tree training to obtain an updated model. The above steps are then repeated until a preset model training exit condition is reached. After the CART tree obtained by the current training meets the training exit condition, the tree structure of the current CART tree can be fixed. When the tree structure is fixed, the node into which each sample falls is immediately determined.
[0057] Step S14: controlling the target vehicle to pass the current road based on the second signal light information.
[0058] In this embodiment, after the second signal light signal generated by the XGboost algorithm in combination with the ground arrow information and the navigation direction information is mounted on the target vehicle, the target vehicle can be controlled to pass through the current road based on the second signal light information. And after generating the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane, it is also possible to determine the information error of the target vehicle on the current road based on the comparison result between the first signal light information and the second signal light information, and optimize the preset machine learning model using the target training set generated based on the information error, so as to continue to use the optimized preset machine learning model to generate the second signal light information of the target vehicle. For example, if the physical signal light at the current intersection is green, and the second signal information output by the model is red, the error information of the current signal light information is determined, and the model is optimized based on the determined error.
[0059] At this point, the following objective function can be defined to measure the error of the XGboost model for the overall traffic light mounting:
[0060] ;
[0061] Among them, the first represents the error of the traffic light itself, n represents the number of traffic lights, R represents RMSE (Root Mean Squared Error), y i Represents the initial value of the i-th traffic light; Represents the mounting value of the i-th traffic light, the second item Represents a regular term, which is used to reduce the risk of overfitting. Specifically:
[0062] ;
[0063] in, ;
[0064] In the above formula, γ and τ are both penalty terms, and T is the total number of leaf nodes in the tree. In the above model, when the depth of the tree is deeper, the probability of overfitting will become higher, so a penalty is required.
[0065] This embodiment can first determine the first signal light information of the lane driving direction ground sign of each lane on the road where the target vehicle is currently located and the corresponding physical traffic light in front of the lane, and then determine the passable information corresponding to the target vehicle on each lane based on the navigation information of the current target vehicle and the lane driving direction ground sign, and then generate the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane based on the first signal light information and the passable information, so as to control the target vehicle to pass through the current road based on the second signal light information. Through the above technical solution, when the vehicle is driving on the road and is about to pass through the intersection area, the comparison result between the lane information on the road where the target vehicle is currently located and the navigation information of the current vehicle can be determined, so as to determine whether the current vehicle can continue to pass in each lane, and generate the corresponding virtual traffic signal based on the judgment result and the signal light information of the physical traffic light in front of the lane, and mount the generated virtual signal light information to the corresponding lane, so that the virtual signal light information generated can help the smart car to determine the traffic light information of each lane when passing through the intersection controlled by the traffic light, so as to facilitate the smart car to pass through the intersection quickly and smoothly.
[0066] Based on the previous embodiment, it can be seen that the present application can use the lane information on the road and the navigation information of the current vehicle, and the physical traffic lights to generate virtual traffic signals, so that the smart car can drive according to the virtual traffic signal of each lane. Next, the present embodiment will elaborate on the process of determining the lane passable information after obtaining the lane information on the current road and the navigation information of the current vehicle. Figure 2 As shown, the embodiment of the present application discloses a vehicle traffic control method, including:
[0067] Step S21, determining lane information of each lane on the road where the target vehicle is currently located; the lane information includes a ground sign of the lane driving direction and first signal light information of a physical traffic light corresponding to the front of the lane.
[0068] Step S22: determine the current navigation direction of the target vehicle based on the navigation information of the current target vehicle, determine the lane travel direction of each lane based on the lane travel direction ground signs, and determine the corresponding passable information of the target vehicle in each lane according to the navigation direction and the lane travel direction.
[0069] In this embodiment, when determining the traffic information of the target vehicle on each lane of the current road, the current navigation direction of the target vehicle can be determined based on the navigation information of the current target vehicle, and the lane traffic direction of each lane can be determined based on the lane driving direction ground sign, and the corresponding passable information of the target vehicle on each lane is determined according to the navigation direction and the lane traffic direction. And it can be understood that before determining the passable information corresponding to the target vehicle on each lane, the target distance between the current target vehicle and the intersection stop line of the first intersection to be passed on the current road can also be determined based on the lane information, and then the target distance is compared with the preset distance threshold, so as to determine the passable information of the target vehicle on each lane when the target distance is not greater than the preset distance threshold. It can be understood that the above-mentioned first intersection to be passed is the intersection where the lane driving direction ground sign and / or physical traffic light first appear in front of the target vehicle. For example, in a specific embodiment, when the current navigation direction of the target vehicle is straight / left turn / right turn, you can choose to judge the ground arrow direction of each lane within 50 meters from the stop line of the intersection. At this time, the preset distance threshold is 50 meters, and the threshold can be adjusted according to actual conditions. For example, if it is judged that the traffic on the current road is relatively congested, the above threshold can be increased so that the target vehicle has more sufficient time to determine the passable information of each road for passage.
[0070] Specifically, in a specific embodiment, if the lane traffic direction of the currently determined passable information lane is unidirectional, it is determined whether the navigation direction is consistent with the lane traffic direction of each lane on the road where the target vehicle is currently located, and the first lane is determined to be impassable, and the first lane is a lane where the navigation direction and the lane traffic direction are inconsistent; and the second lane is determined to be passable, and the second lane is a lane where the navigation direction and the lane traffic direction are consistent. In another specific embodiment, if the lane traffic direction of the currently determined passable information lane is multi-directional, it is determined whether there is a lane where the lane traffic direction is consistent with the navigation direction on the road where the target vehicle is currently located, and the third lane is determined to be impassable, and the third lane is a lane where the lane traffic direction is inconsistent with the navigation direction; and the fourth lane is determined to be passable, and the driving direction of the target vehicle in the fourth lane is determined based on the navigation direction, and the fourth lane is a lane where the lane traffic direction is consistent with the navigation direction. For example, when the current navigation direction of the target vehicle is straight / left turn / right turn, if the lane of the current road does not have straight / left turn / right turn, the current lane can be assigned a red light (i.e., impassable); if the navigation direction is contained in the ground arrow of the current road, the navigation direction is assigned to each lane, otherwise it is assigned as impassable.
[0071] Step S23: generating second signal light information of the virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information.
[0072] Step S24: Control the target vehicle to pass the current road based on the second signal light information.
[0073] After the second signal light information is determined in this embodiment, during the process of controlling the target vehicle to pass through the current road, if the lane where the target vehicle is currently located is impassable, the target vehicle is controlled to travel to the currently passable lane, so as to control the target vehicle to pass through the current road on the currently passable lane based on the second signal light information. And if there is no communicable lane on the road at this time, the target vehicle is controlled to travel to the corresponding parking area. In a specific embodiment, if there are three lanes on the current road, namely left turn, straight ahead, and right turn, and the current navigation direction of the target vehicle is right turn, the passable information of the left turn lane and the straight ahead lane is determined as impassable, and the passable information of the right turn lane is determined as passable. If the target vehicle is traveling on the left turn lane at this time, the target vehicle can be controlled to travel to the right turn lane and continue to pass the intersection ahead.
[0074] For more specific processing procedures of the above steps S21 and S23, reference may be made to the corresponding contents disclosed in the above embodiments, which will not be described in detail here.
[0075] Through the above technical scheme, this embodiment can determine the comparison result between the lane information on the road where the target vehicle is currently located and the navigation information of the current vehicle, so as to judge whether the current vehicle can continue to pass through each lane, and generate a corresponding virtual traffic signal according to the judgment result and the signal light information of the physical traffic light in front of the lane, and mount the generated virtual traffic light information to the corresponding lane. In this way, it can help the smart car to obtain the traffic light information of each lane when passing through the intersection controlled by the traffic light, and mount the traffic light at the intersection to the corresponding lane and combine it with the ground arrow to realize the intersection passage judgment, so as to help the vehicle determine the traffic light information of each lane, so as to facilitate the smart car to pass through the intersection smoothly.
[0076] See also Figure 3 As shown, the embodiment of the present application also discloses a vehicle traffic control device, including:
[0077] The lane information determination module 11 is used to determine the lane information of each lane on the road where the target vehicle is currently located; the lane information includes the ground sign of the lane driving direction and the first signal light information of the physical traffic light corresponding to the front of the lane;
[0078] A traffic information determination module 12 is used to determine the corresponding trafficable information of the target vehicle on each lane based on the current navigation information of the target vehicle and the ground sign of the lane driving direction;
[0079] An information generating module 13, configured to generate second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information;
[0080] The vehicle control module 14 is used to control the target vehicle to pass the current road based on the second signal light information.
[0081] This embodiment first determines the first signal light information of the lane driving direction ground sign of each lane on the road where the target vehicle is currently located and the corresponding physical traffic light in front of the lane, then determines the passable information corresponding to the target vehicle on each lane based on the navigation information of the current target vehicle and the lane driving direction ground sign, and then generates the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane based on the first signal light information and the passable information, so as to control the target vehicle to pass through the current road based on the second signal light information. Through the above technical solution, when the vehicle is driving on the road and is about to pass through the intersection area, the comparison result between the lane information on the road where the target vehicle is currently located and the navigation information of the current vehicle can be determined, so as to judge whether the current vehicle can continue to pass in each lane, and generate the corresponding virtual traffic signal according to the judgment result and the signal light information of the physical traffic light in front of the lane, and mount the generated virtual signal light information to the corresponding lane, so that the generated virtual signal light information can help the intelligent car to determine the traffic light information of each lane when passing through the intersection controlled by the traffic light, so as to facilitate the intelligent car to pass through the intersection quickly and smoothly.
[0082] In some specific embodiments, the information generating module 13 specifically includes:
[0083] An information transmission unit, used for inputting the first signal light information and the passable information into a preset machine learning model;
[0084] a vehicle classification unit, configured to classify each lane according to the first signal light information and the passable information through a decision tree of the preset machine learning model, and obtain a corresponding classification result;
[0085] An information generating unit is used to generate the second traffic light information of the virtual traffic light corresponding to the target vehicle on each lane based on the classification result.
[0086] In some specific embodiments, the vehicle traffic control device further includes:
[0087] an error determination module, configured to determine an information error of the target vehicle on a current road based on a comparison result between the first signal light information and the second signal light information;
[0088] A model optimization module is used to optimize the preset machine learning model using a target training set generated based on the information error, so as to continue to use the optimized preset machine learning model to generate the second signal light information of the target vehicle.
[0089] In some specific embodiments, the traffic information determination module 12 specifically includes:
[0090] A direction determination unit, used to determine the current navigation direction of the target vehicle based on the navigation information of the current target vehicle, and determine the lane travel direction of each lane based on the lane travel direction ground mark;
[0091] The information determination submodule is used to determine the corresponding passable information of the target vehicle on each lane according to the navigation direction and the lane passing direction.
[0092] In some specific embodiments, the vehicle traffic control device further includes:
[0093] A distance determination module is used to determine a target distance between the current target vehicle and the stop line of the first intersection to be passed on the current road based on the lane information; the first intersection to be passed is the intersection where the ground sign of the lane travel direction and / or the physical traffic light first appears in front of the target vehicle;
[0094] The distance comparison module is used to compare the target distance with a preset distance threshold so as to determine the passable information of the target vehicle on each lane when the target distance is not greater than the preset distance threshold.
[0095] In some specific embodiments, the information determination submodule specifically includes:
[0096] A first direction determination unit, configured to determine whether the navigation direction is consistent with the direction of travel of each lane on the road where the target vehicle is currently located if the lane travel direction of the lane is unidirectional;
[0097] A first information determination unit, configured to determine a first lane as impassable; the first lane being a lane where the navigation direction and the lane passing direction are inconsistent;
[0098] The second information determination unit is used to determine the second lane as passable; the second lane is a lane where the navigation direction and the lane passing direction are consistent.
[0099] In some specific embodiments, the information determination submodule specifically includes:
[0100] A second direction determination unit is used to determine whether there is a lane on the road where the target vehicle is currently located with a lane having a lane direction consistent with the navigation direction if the lane travel direction of the lane is multi-directional;
[0101] A third information determination unit, configured to determine a third lane as impassable; the third lane being a lane whose passing direction is inconsistent with the navigation direction;
[0102] The fourth information determination unit is used to determine the fourth lane as passable and determine the driving direction of the target vehicle in the fourth lane based on the navigation direction; the fourth lane is a lane whose lane driving direction is consistent with the navigation direction.
[0103] In some specific embodiments, the vehicle control module 14 specifically includes:
[0104] A lane changing unit is used to control the target vehicle to travel to a currently passable lane if the lane currently in which the target vehicle is located is not passable, so as to control the target vehicle to pass the current road in the currently passable lane based on the second signal light information.
[0105] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.
[0106] Figure 4 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle traffic control method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.
[0107] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.
[0108] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.
[0109] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and may be Windows Server, Netware, Unix, Linux, etc. In addition to computer programs that can be used to complete the vehicle traffic control method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 may further include computer programs that can be used to complete other specific tasks.
[0110] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the vehicle traffic control method disclosed above. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, and will not be repeated here.
[0111] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0112] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0113] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0114] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0115] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A vehicle traffic control method, characterized in that: include: Determine the lane information of each lane on the road where the target vehicle is currently located; The lane information includes a ground sign of the lane driving direction and first signal light information of a physical traffic light corresponding to the lane in front; Determine the passable information corresponding to the target vehicle on each lane based on the current navigation information of the target vehicle and the ground sign of the lane driving direction; Generating second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information; The target vehicle is controlled to pass through the current road based on the second signal light information.
2. The vehicle traffic control method according to claim 1, characterized in that: The step of generating second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information includes: Inputting the first traffic light information and the passable information into a preset machine learning model; Classifying each lane according to the first signal light information and the passable information through the decision tree of the preset machine learning model to obtain a corresponding classification result; Based on the classification result, the second traffic light information of the virtual traffic light corresponding to the target vehicle on each lane is generated.
3. The vehicle traffic control method according to claim 2, characterized in that: After generating the second signal light information of the virtual traffic light corresponding to the target vehicle on each lane, the method further includes: Determining an information error of the target vehicle on a current road based on a comparison result between the first signal light information and the second signal light information; The preset machine learning model is optimized using a target training set generated based on the information error, so as to continue to use the optimized preset machine learning model to generate the second signal light information of the target vehicle.
4. The vehicle traffic control method according to claim 1, characterized in that: The determining, based on the current navigation information of the target vehicle and the ground mark of the lane driving direction, the corresponding passable information of the target vehicle on each lane includes: Determine the current navigation direction of the target vehicle based on the navigation information of the current target vehicle, and determine the lane travel direction of each lane based on the lane travel direction ground sign; The corresponding passable information of the target vehicle on each lane is determined according to the navigation direction and the lane passing direction.
5. The vehicle traffic control method according to claim 4, characterized in that: Before determining the passable information corresponding to the target vehicle on each lane based on the current navigation information of the target vehicle and the ground mark of the lane driving direction, the method further includes: Determine a target distance between the current target vehicle and the stop line of the first intersection to be passed on the current road based on the lane information; the first intersection to be passed is an intersection where the lane travel direction ground sign and / or the physical traffic light first appear in front of the target vehicle; The target distance is compared with a preset distance threshold, so as to determine the passable information of the target vehicle on each lane when the target distance is not greater than the preset distance threshold.
6. The vehicle traffic control method according to claim 4, characterized in that: The determining, according to the navigation direction and the lane passing direction, the corresponding passable information of the target vehicle on each lane includes: If the lane traffic direction of the lane is unidirectional, determining whether the navigation direction is consistent with the traffic directions of each lane on the road where the target vehicle is currently located; Determine a first lane as impassable; the first lane is a lane where the navigation direction and the lane passing direction are inconsistent; The second lane is determined to be passable; the second lane is a lane where the navigation direction and the lane passing direction are consistent.
7. The vehicle traffic control method according to claim 4, characterized in that: The determining, according to the navigation direction and the lane passing direction, the corresponding passable information of the target vehicle on each lane includes: If the lane has a multi-directional traffic direction, determining whether there is a lane on the road where the target vehicle is currently located whose lane traffic direction is consistent with the navigation direction; Determine the third lane as impassable; the third lane is a lane whose passing direction is inconsistent with the navigation direction; The fourth lane is determined to be passable, and the driving direction of the target vehicle on the fourth lane is determined based on the navigation direction; the fourth lane is a lane whose lane driving direction is consistent with the navigation direction.
8. The vehicle traffic control method according to claim 6 or 7, characterized in that: The process of controlling the target vehicle to pass through the current road based on the second signal light information includes: If the lane currently in which the target vehicle is located is not passable, the target vehicle is controlled to travel to a currently passable lane, so that based on the second signal light information, the target vehicle is controlled to pass the current road in the currently passable lane.
9. A vehicle traffic control device, characterized in that: include: A lane information determination module is used to determine the lane information of each lane on the road where the target vehicle is currently located; The lane information includes a ground sign of the lane driving direction and first signal light information of a physical traffic light corresponding to the lane in front; A traffic information determination module, used to determine the corresponding trafficable information of the target vehicle on each lane based on the current navigation information of the target vehicle and the ground sign of the lane driving direction; An information generating module, configured to generate second signal light information of a virtual traffic light corresponding to the target vehicle on each lane according to the first signal light information and the passable information; A vehicle control module is used to control the target vehicle to pass the current road based on the second signal light information.
10. An electronic device, characterized in that: The electronic device includes a processor and a memory; wherein the memory is used to store a computer program, and the computer program is loaded and executed by the processor to implement the vehicle traffic control method as described in any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the vehicle traffic control method as described in any one of claims 1 to 8.