Vehicle driving control method and device and medium
By acquiring real-time and historical data to generate virtual traffic signal control information, the problem of inflexible traffic control caused by traffic light equipment failure or absence has been solved, achieving more flexible and safer traffic management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2026-04-10
AI Technical Summary
Existing traffic light equipment may be faulty or missing, resulting in inflexible traffic control that cannot adapt to diverse traffic control scenarios, leading to traffic congestion.
By acquiring real-time vehicle driving data and historical traffic control data at the target intersection, a deep learning model is used to generate virtual traffic signal control information, which is then sent to vehicles to replace physical traffic light equipment.
It reduces reliance on physical traffic light equipment, lowers hardware costs, is applicable to more traffic control scenarios, avoids traffic congestion, and improves driving safety.
Smart Images
Figure CN121838488A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of traffic control, and particularly relates to a vehicle driving control method and device and medium. BACKGROUND
[0002] Traffic light equipment, as a kind of signal lamp for guiding traffic operation, is generally composed of red light, green light and yellow light. Based on the traffic light equipment providing driving instructions for vehicles passing through the intersection, it has become a common traffic control method.
[0003] In the related art, the control period of the traffic light equipment is set in advance, and the display time of the corresponding traffic light is controlled within the control period to indicate the vehicle to pass through the intersection. However, in actual application scenarios, the traffic light equipment may fail, and even some intersections may not have traffic light equipment. Therefore, relying on physical traffic light equipment for traffic control obviously cannot adapt to diversified traffic control scenarios, which may cause traffic congestion. SUMMARY
[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a vehicle driving control method, device and medium.
[0005] The present disclosure provides a vehicle driving control method, which comprises: acquiring real-time vehicle driving data of a target intersection, and acquiring historical traffic control data corresponding to the target intersection in a local database; acquiring virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data; and sending the virtual traffic signal control information to a current driving vehicle in the target intersection.
[0006] Optionally, the acquiring historical traffic control data corresponding to the target intersection in the local database comprises: acquiring a collection time period corresponding to the real-time driving data; and acquiring the historical traffic control data corresponding to the target intersection matching the collection time period in the local database.
[0007] Optionally, the historical traffic control data comprises historical traffic flow information and / or historical virtual traffic signal control information.
[0008] Optionally, the obtaining the virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data comprises: determining real-time driving data features corresponding to the real-time vehicle driving data; extracting historical control data features corresponding to the historical traffic control data; inputting the real-time driving data features and the historical control data features into a pre-trained deep learning model to obtain the virtual traffic signal control information output by the deep learning model.
[0009] Optionally, the determining the real-time driving data features corresponding to the real-time vehicle driving data comprises: determining driving time corresponding to the real-time vehicle driving data, and obtaining vehicle driving time features according to the driving time; obtaining vehicle driving features according to the real-time vehicle driving data; and determining the vehicle driving features and the vehicle driving time features as the real-time driving data features.
[0010] Optionally, the sending the virtual traffic signal control information to the current driving vehicle in the target intersection comprises: determining an associated lane corresponding to the virtual traffic signal control information in a plurality of lanes corresponding to the target intersection; and sending the virtual traffic signal control information to the current driving vehicle in the associated lane.
[0011] Optionally, the associated lane comprises a plurality of lanes, and the sending the virtual traffic signal control information to the current driving vehicle in the associated lane comprises: identifying driving direction information of each of the associated lanes, determining virtual traffic signal control sub-information corresponding to each of the driving direction information in the virtual traffic signal control information; and sending the corresponding virtual traffic signal control sub-information to the current driving vehicle in each of the associated lanes.
[0012] Optionally, before the obtaining the real-time vehicle driving data of the target intersection, the method further comprises: determining that the target intersection satisfies a preset virtual traffic signal control condition.
[0013] Optionally, the preset virtual traffic signal control condition comprises: the target intersection does not contain a traffic light device; or the target intersection contains a traffic light device, the traffic light device contained by the target intersection does not display signal light data; or the target intersection contains a traffic light device, a time length during which the traffic light device contained by the target intersection does not display signal light data is greater than a preset time length threshold; or
[0014] the target intersection contains a traffic light device, signal light timing information of the traffic light device displaying signal light data satisfies a preset adjustment condition.
[0015] The embodiment of the present disclosure further provides a vehicle driving control device, which comprises: a data acquisition module, configured to acquire real-time vehicle driving data of a target intersection, and acquire historical traffic control data corresponding to the target intersection in a local database; a control information acquisition module, configured to acquire virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data; and a control information sending module, configured to send the virtual traffic signal control information to a current driving vehicle in the target intersection.
[0016] The embodiment of the present disclosure provides a processor-readable storage medium, which stores a program for causing a processor to execute the vehicle driving control method.
[0017] Compared with the prior art, the technical scheme provided by the embodiment of the present disclosure has the following advantages:
[0018] The vehicle driving control method provided by the embodiment of the present disclosure acquires real-time vehicle driving data of a target intersection, acquires historical traffic control data corresponding to the target intersection in a local database, acquires virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data, and then sends the virtual traffic signal control information to a current driving vehicle in the target intersection. In the technical scheme, a scheme for controlling vehicle driving based on virtual traffic signal control information is provided, which reduces the dependence on physical traffic light devices, reduces the hardware cost of traffic control, reduces unnecessary infrastructure construction, and is applicable to more traffic control scenarios, thereby avoiding traffic congestion. BRIEF DESCRIPTION OF DRAWINGS
[0019] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, same or similar reference numerals are used to represent same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale.
[0020] Figure 1 A flowchart of a vehicle driving control method provided by the embodiment of the present disclosure is shown in the figure;
[0021] Figure 2 A structural block diagram of an integrated storage and calculation multi-modal edge platform provided by the embodiment of the present disclosure is shown in the figure;
[0022] Figure 3 A schematic diagram of a target intersection provided by the embodiment of the present disclosure is shown in the figure;
[0023] Figure 4 A flowchart of another vehicle driving control method provided by the embodiment of the present disclosure is shown in the figure;
[0024] Figure 5 A schematic diagram of a vehicle travel control device according to an embodiment of the present disclosure is provided. DETAILED DESCRIPTION
[0025] Embodiments of the present disclosure will be described in more detail with reference to the drawings. It should be understood that each of the steps in the method embodiments of the present disclosure can be performed in a different order and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0026] The term "comprising" and variations thereof as used herein are used inclusively, i.e., "comprising, but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related terms are defined in a similar manner.
[0027] The term "and / or", used in the embodiments of the present disclosure, describes an associated relationship between associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects.
[0028] The term "a plurality of" in the embodiments of the present disclosure means two or more, and other quantifiers are similar.
[0029] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present disclosure.
[0030] The present disclosure proposes a vehicle travel control method applicable to more traffic control scenarios. In this method, vehicle travel is controlled based on virtual traffic signals, which no longer rely on traditional physical traffic light devices. Instead, based on real-time and historical data, accurate prediction and continuous deduction are performed to accurately predict the changes of a new round of traffic signals, virtually generate digital dynamic traffic signal control information, and send it to intelligent vehicles around the intersection. Vehicles pass through the intersection in an orderly and safe manner according to the newly generated traffic signal control information, improving intersection passing safety and avoiding traffic congestion.
[0031] Figure 1 is a flowchart of a vehicle travel control method according to an embodiment of the present disclosure, which can be applied in a vehicle travel control device, such as Figure 1As shown, the method comprises:
[0032] In step 101, real-time vehicle driving data of the target intersection is acquired, and historical traffic control data corresponding to the target intersection is acquired in a local database.
[0033] The real-time vehicle driving data can include intersection vehicle driving speed, heading angle, queue length, and residence time, and in some possible embodiments, the historical traffic control data can include historical traffic flow information and / or historical virtual traffic signal control information, wherein the historical virtual traffic signal control information includes virtual traffic signal light (red virtual traffic signal light, green virtual traffic signal light, yellow virtual traffic signal light, etc.) information and countdown information of the virtual traffic signal light in a historical control scenario of the target intersection, and the virtual traffic signal light information can include traffic light color prompt patterns or any other form such as pure text information. Since the virtual traffic control information is no longer dependent on traditional physical traffic light devices, the display of the virtual traffic control information can be more diversified, thereby breaking the application limit of the physical traffic control light, such as breaking the limit of users with “red-green color blindness”.
[0034] In one embodiment of the present disclosure, before acquiring the real-time vehicle driving data of the target intersection, it is further determined whether the target intersection meets a preset virtual traffic signal control condition, and after the preset virtual traffic signal control condition is met, subsequent steps of the vehicle driving control method of the embodiment of the present disclosure are executed to determine the virtual traffic signal control information.
[0035] In different application scenarios, the preset virtual traffic signal control condition is different, and examples are as follows:
[0036] In some possible examples, the target intersection does not include a traffic light device, that is, if the target intersection does not include a traffic light device, it is determined that the preset virtual traffic signal control condition is met.
[0037] In this example, when the target intersection does not include a traffic light device, the vehicle cannot receive intersection traffic light state information, and the vehicle and the intersection cannot realize real-time cooperative perception. In the absence of traffic light indication, vehicles are confused because they do not know when they should pass, which easily causes congestion and increases the probability of collision accidents, especially at some intersections with heavy traffic. In order to reduce the influence of the above problems, it is determined that the target intersection meets the preset virtual traffic signal control condition, and virtual traffic signal control information is determined, and vehicle driving control is performed based on the virtual traffic signal control information.
[0038] In some possible examples, the target intersection contains a traffic light device, the traffic light device contained in the target intersection does not display signal lamp data, i.e., the traffic light device of the target intersection can not display signals due to a malfunctioning light, in this case, it is determined that the target intersection meets the preset virtual traffic signal control condition, to determine the virtual traffic signal control information, and the vehicle driving control is performed based on the virtual traffic signal control information.
[0039] In some possible embodiments, the target intersection contains a traffic light device, the duration for which the traffic light device contained in the target intersection does not display signal lamp data is greater than a preset duration threshold, wherein the preset duration threshold can be set according to the scene requirement, in this case, it is determined that the target intersection meets the preset virtual traffic signal control condition, to determine the virtual traffic signal control information, and the vehicle driving control is performed based on the virtual traffic signal control information.
[0040] In an embodiment of the present disclosure, real-time vehicle driving data of the target intersection can also be acquired, and then subsequent steps of the vehicle driving control method of the embodiment of the present disclosure are performed to determine the virtual traffic signal control information, in this embodiment, if the target intersection does not contain a traffic light device, the virtual traffic signal control information is directly sent to the corresponding vehicle, if the target intersection contains a traffic light device and the traffic light device is working normally, i.e., the traffic light device displays signal lamp data, if it is determined that the signal lamp timing information of the signal lamp data meets the preset adjustment condition, it is determined that the traffic light device meets the preset traffic signal control condition. Wherein, the virtual traffic signal control information can also be determined in advance, and then the virtual traffic signal control information is sent to the controller of the traffic light device, for example, the virtual traffic signal control information is sent to the local signal lamp control system through the intersection local area network, the signal lamp control system judges whether to allow adjusting the current timing scheme of the traffic light, if it is allowed, it is determined that the signal lamp timing information meets the preset adjustment condition, the virtual traffic signal control information is sent to the controller of the traffic light device, so that the traffic light device synchronously displays the traffic light signal corresponding to the virtual traffic signal control information, etc. For another example, the average waiting duration of each lane of the target intersection can be calculated, if there is a lane with an average waiting duration greater than a preset waiting duration threshold, it is determined that the signal lamp timing information of the signal lamp data displayed by the traffic light device needs to be adjusted, and the preset adjustment condition is met; for another example, the difference between the average waiting durations of the lanes in each direction of travel in the target intersection can be calculated, if the difference between the average waiting durations is greater than a preset difference threshold, it is determined that the signal lamp timing information of the signal lamp data displayed by the traffic light device needs to be adjusted, and the preset adjustment condition is met. Wherein, the subject determining whether the signal lamp timing information of the signal lamp data displayed by the traffic light device meets the preset adjustment condition can be a processor that can make the judgment, etc., in addition to the above-mentioned signal lamp control system, which is not limited here.
[0041] In the embodiment, the signal lamp control system judges whether to allow adjustment of the current timing scheme of the traffic light, and the average waiting time of vehicles at the target intersection can be collected. If the average waiting time is greater than the preset time threshold, it is determined that the current timing scheme of the traffic light is allowed to be adjusted. Correspondingly, in the embodiment, the preset virtual traffic signal control condition can also include that the average waiting time of vehicles at the target intersection is greater than the preset time threshold.
[0042] In the embodiment, the real-time driving data can be obtained by cameras, radars and other devices erected at the intersection.
[0043] In the embodiment of the present disclosure, in order to ensure the reliability of the determined virtual traffic signal control information, historical traffic control data corresponding to the target intersection is also obtained in the local database. In some possible embodiments, a storage-computing integrated multi-modal edge platform can be erected at the edge of the target intersection, and the historical traffic control data corresponding to the target intersection in the local database is obtained by referring to Figure 2 The storage-computing integrated multi-modal edge platform can include a software algorithm unit, a computing storage unit and a multi-modal communication unit. The computing storage unit includes a local database, which stores historical traffic control data.
[0044] In some possible embodiments, the collection time period corresponding to the real-time driving data can be obtained, and the historical traffic control data corresponding to the target intersection in the local database is obtained by matching the collection time period. The collection time period here not only refers to a time point, but also corresponds to a time period type, including weekdays, holidays, etc. For example, if the collection time period is 8:00-9:00 on weekdays, the historical traffic control data corresponding to 8:00-9:00 on weekdays is determined in the local database.
[0045] Step 102, obtaining virtual traffic signal control information for controlling vehicle driving according to real-time vehicle driving data and historical traffic control data.
[0046] In one embodiment of the present disclosure, virtual traffic signal control information for controlling vehicle driving is obtained according to real-time vehicle driving data and historical traffic control data, that is, not only virtual traffic signal control information is generated based on real-time vehicle driving data, but also virtual traffic signal control information is generated by combining historical traffic control data and real-time vehicle driving data, multi-dimensional information is combined to generate virtual traffic signal control information, and the reliability of virtual traffic signal control information is ensured.
[0047] Step 103, sending the virtual traffic signal control information to the current driving vehicle in the target intersection.
[0048] After determining the virtual traffic signal control information, the virtual traffic signal control information can be directly sent to the current driving vehicle in the target intersection without relying on the traffic light device, that is, in the era of intelligent vehicles, the vehicle includes a communication unit, which includes a 4G, 5G, LTE-V2X, EUHT, etc. Communication system, refer to Figure 2 , the multi-mode communication unit can include 4G, 5G, LTE-V2X, EUHT, etc. Communication module, therefore, in this embodiment, the virtual traffic signal control information is sent to the current driving vehicle based on the corresponding communication module, and the current driving vehicle can display the corresponding virtual traffic signal control information on the vehicle machine screen of the vehicle.
[0049] In some possible embodiments, in order to improve the degree of control refinement and reduce control cost, in the corresponding multiple lanes of the target intersection, the associated lane corresponding to the virtual traffic signal control information is determined, that is, the target intersection only controls the lane corresponding to the vehicle that will pass through the target intersection, and the lane where the vehicle that has passed through the target intersection does not need to be controlled, for example, refer to Figure 3 For a target intersection with a traffic light failure, the associated lane includes the lane indicated by the circle in the figure, and the vehicles in other lanes have passed through the intersection, so there is no need to send virtual traffic signal control information again.
[0050] Of course, as Figure 3 shows, in some possible embodiments, the associated lane includes multiple lanes, and the driving direction information of each lane is different, and the virtual traffic signal control information it needs to understand is also different, so in this embodiment, the driving direction information of each associated lane also needs to be identified, and the virtual traffic signal control sub-information corresponding to each driving direction information is determined in the virtual traffic signal control information, that is, the virtual traffic signal control information includes virtual traffic signal control sub-information corresponding to each lane. In addition to including traffic light signals, virtual traffic signal control sub-information can also include corresponding countdown information, etc. Further, the corresponding virtual traffic signal control sub-information is sent to the current driving vehicle in each associated lane. Thus, the amount of data sent is further reduced, achieving the purpose of precise control.
[0051] In the technical solution, on one hand, the physical traffic light device is not needed at some intersections in the era of intelligent vehicles, especially for the traffic light device for the separation of vehicles and pedestrians. The virtual traffic signal control information can replace the physical traffic light device, reduce unnecessary infrastructure construction, and save construction and maintenance costs. On the other hand, for the intersection with a faulty traffic light device, the virtual traffic signal control information can be generated based on the judgment of whether the preset virtual traffic signal control condition is met, so as to reduce traffic congestion, relieve the anxiety of drivers, and improve driving safety, especially for colorblind or visually impaired drivers.
[0052] In summary, the vehicle driving control method provided in the embodiments of the present disclosure obtains real-time vehicle driving data of a target intersection, obtains historical traffic control data corresponding to the target intersection in a local database, obtains virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data, and then sends the virtual traffic signal control information to a currently driving vehicle in the target intersection. In the technical solution, a scheme for controlling vehicle driving based on virtual traffic signal control information is provided, which reduces the dependence on physical traffic light devices, reduces the hardware cost of traffic control, reduces unnecessary infrastructure construction, and is applicable to more traffic control scenarios, thereby avoiding traffic congestion.
[0053] Based on the above embodiments, in different application scenarios, the virtual traffic signal control information for controlling vehicle driving is obtained according to the real-time vehicle driving data and the historical traffic control data in different ways, for example as follows:
[0054] In one embodiment of the present disclosure, as shown in Figure 4 the virtual traffic signal control information for controlling vehicle driving is obtained according to the real-time vehicle driving data and the historical traffic control data, including:
[0055] In step 401, real-time driving data features corresponding to the real-time vehicle driving data are determined.
[0056] In this embodiment, the real-time driving data features corresponding to the real-time vehicle driving data are determined. In order to ensure the effectiveness of the driving data features, the effective data features can be set in advance, the data corresponding to the effective data features is filtered from the real-time vehicle driving data, and then the filtered data is extracted to obtain the corresponding real-time driving data features.
[0057] In addition to existing features extracted from existing data, real-time driving data features may also include derived features. In one embodiment of this disclosure, the driving time corresponding to the real-time vehicle driving data can be determined. This driving time may include specific dates and times. Then, vehicle driving time features are obtained based on the driving time. These vehicle driving time features can be any features that describe driving time characteristics, such as morning and evening rush hours, weekdays and weekends, daytime and nighttime, etc. Furthermore, vehicle driving features are obtained based on the real-time vehicle driving data itself, including features such as average vehicle speed, heading angle, queue length, and average waiting time. Finally, the vehicle driving features and vehicle driving time features are determined as real-time driving data features.
[0058] In some possible embodiments, in order to improve prediction efficiency, after obtaining real-time driving data features, there are multiple real-time driving data features, and the feature weight of each pre-calibrated real-time driving data feature can also be obtained, and real-time driving data features with feature weights lower than a preset weight threshold are deleted.
[0059] Step 402: Extract the historical control data features corresponding to the historical traffic control data.
[0060] In this embodiment, the historical control data features corresponding to the historical traffic control data are also extracted.
[0061] Step 403: Input the real-time driving data features and historical control data features into the pre-trained deep learning model to obtain the virtual traffic signal control information output by the deep learning model.
[0062] In this embodiment, a deep learning model is pre-trained, and then real-time driving data features and historical control data features are input into the pre-trained deep learning model to obtain virtual traffic signal control information output by the deep learning model.
[0063] In this embodiment, referring to the above Figure 3 It can detect real-time vehicle driving data in the software algorithm unit of the in-memory computing multimodal edge platform, and obtain virtual traffic signal control information for controlling vehicle driving based on the pre-trained deep learning model, real-time vehicle driving data and historical traffic control data.
[0064] In one embodiment of the present disclosure, when training the deep learning model, the deep learning model can be cross-validated using various validation methods to avoid overfitting of the deep learning model. During the training process, the model parameters need to be constantly adjusted until the optimal model configuration is found. After training is completed, an independent test data set is used to evaluate the performance of the deep learning model, including accuracy, recall rate, etc., which will be used to measure the accuracy and reliability of the model prediction. For example, the test data set is input into the deep learning model to obtain the test traffic signal control information output by the deep learning model, and the error between the test traffic signal control information and the preset standard traffic signal control information is determined. If the error is greater than a preset threshold, it is determined that the performance of the model is not high, and the model parameters of the deep learning model can be further optimized.
[0065] In one embodiment of the present disclosure, in order to further ensure the reliability of the trained deep learning model, a simulation environment can also be established, in which various different traffic scene big data are input, and the virtual traffic signal control information generated by the deep learning model under this simulation condition is observed, and the vehicle model is controlled to drive based on the virtual traffic signal control information. During the simulation operation, attention is paid to whether the virtual traffic signal control information generated by the deep learning model is reasonable and can effectively alleviate traffic congestion and improve traffic efficiency. According to the simulation results, the system automatically and continuously adjusts and optimizes the model to achieve the optimal effect, ensuring that its performance in real applications is more stable and efficient.
[0066] In one embodiment of the present disclosure, after the virtual traffic signal control information is generated, the virtual traffic control information contains traffic signals and corresponding countdowns, such as red traffic signals and corresponding countdowns, green traffic signals and corresponding countdowns, yellow traffic signals and corresponding countdowns, etc. Based on the virtual traffic control information, the traffic signal cycle can be determined according to the countdown information, etc. In this embodiment, the traffic signal cycle can be changed, i.e., when controlling the vehicles at the target intersection to drive according to the virtual traffic control information, the real-time vehicle driving data of the target intersection can be monitored to determine whether the target intersection meets the preset congestion condition according to the real-time vehicle driving data.
[0067] For example, the average waiting time of vehicles in each driving lane is determined according to the real-time vehicle driving data. If there is a driving lane with an average waiting time greater than a preset average waiting time threshold, it is determined that the preset congestion condition is met.
[0068] For example, the real-time vehicle driving data can also be input into a pre-trained convolutional neural network model, and the real-time driving data is input into the convolutional neural network model to determine whether the preset congestion condition is met, etc.
[0069] Further, if the preset congestion condition is met, the traffic signal cycle is changed, and the specific change manner can include: determining a congestion lane that meets the preset congestion condition, increasing the countdown time length of the communication-allowed traffic signal of the congestion lane according to a preset unit value, and correspondingly decreasing the countdown time length of the communication-not-allowed traffic signal of the congestion lane according to the preset unit value. In this embodiment, other lanes associated with the driving lane can also be determined, and the countdown time length of the other lanes is correspondingly modified according to the countdown time length of the driving lane after the change.
[0070] For example, after the preset congestion condition is met, the virtual traffic control information can also be triggered to be regenerated, that is, the real-time vehicle driving data of the target intersection is re-collected, the historical traffic control data corresponding to the target intersection is obtained in the local database, and the virtual traffic signal control information for controlling vehicle driving is obtained according to the real-time vehicle driving data and the historical traffic control data. In this way, the virtual traffic signal control information is regenerated when needed, balancing the contradiction between the reliability of the virtual traffic signal control information and the consumption of computing power.
[0071] Of course, in actual execution, the real-time vehicle driving data and the historical traffic control data can also be obtained according to a preset period, and the virtual traffic signal control information of each period is generated, realizing dynamic generation of the virtual traffic signal control information and ensuring real-time effectiveness of the virtual traffic signal control information.
[0072] In some possible embodiments, in an actual traffic scene, some environmental factors that affect traffic can also be included, such as weather conditions and special events such as traffic accidents, and the like. Therefore, in an embodiment of the present disclosure, it can also be monitored whether the target intersection contains some environmental factors that affect traffic. If it contains, specific factor data corresponding to the environmental factors is collected, such as weather type data, traffic accident type data, and the like. After the virtual traffic signal control information is obtained, the virtual traffic signal control information and the environmental factor value are input into another pre-trained deep learning model to obtain updated virtual traffic signal control information output by the another deep learning model, and then the updated virtual traffic signal control information is sent to the current driving vehicle in the target intersection. Further, driving congestion is avoided.
[0073] In summary, the vehicle driving control method of the embodiment of the present disclosure is based on the pre-trained deep learning model, and the virtual traffic signal control information is more accurately determined based on the real-time vehicle driving data and the historical traffic control data, effectively relieving traffic congestion.
[0074] In order to realize the above-mentioned embodiments, the present disclosure also proposes a vehicle driving control device. Figure 5 is a structural schematic diagram of a vehicle driving control device according to an embodiment of the present disclosure, likeFigure 5 As shown in the figure, the vehicle driving control device comprises a data acquisition module 510, a control information acquisition module 520 and a control information sending module 530, wherein,
[0075] The data acquisition module 510 is configured to acquire real-time vehicle driving data of a target intersection, and acquire historical traffic control data corresponding to the target intersection in a local database;
[0076] The control information acquisition module 520 is configured to acquire virtual traffic signal control information for controlling vehicle driving according to the real-time vehicle driving data and the historical traffic control data;
[0077] The control information sending module 530 is configured to send the virtual traffic signal control information to a current driving vehicle in the target intersection.
[0078] In an embodiment of the present disclosure, the data acquisition module 510 is specifically configured to:
[0079] acquire a collection time period corresponding to the real-time driving data;
[0080] acquire historical traffic control data corresponding to the target intersection matching the collection time period in the local database.
[0081] In an embodiment of the present disclosure, the control information acquisition module 520 is specifically configured to:
[0082] determine real-time driving data features corresponding to the real-time vehicle driving data;
[0083] extract historical control data features corresponding to the historical traffic control data;
[0084] input the real-time driving data features and the historical control data features into a pre-trained deep learning model to acquire virtual traffic signal control information output by the deep learning model.
[0085] In an embodiment of the present disclosure, the control information acquisition module 520 is specifically configured to:
[0086] determine a driving time corresponding to the real-time vehicle driving data, and acquire vehicle driving time features according to the driving time;
[0087] acquire vehicle driving features according to the real-time vehicle driving data;
[0088] determine that the vehicle driving features and the vehicle driving time features are real-time driving data features.
[0089] In an embodiment of the present disclosure, the control information sending module 530 is specifically configured to:
[0090] In the plurality of lanes corresponding to the target intersection, determine the associated lane corresponding to the virtual traffic signal control information;
[0091] Send the virtual traffic signal control information to the current driving vehicle in the associated lane.
[0092] In an embodiment of the present disclosure, the associated lane includes a plurality, and the control information sending module 530 is specifically configured to:
[0093] Identify the driving direction information of each associated lane, and determine the virtual traffic signal control sub-information corresponding to each driving direction information in the virtual traffic signal control information;
[0094] Send the corresponding virtual traffic signal control sub-information to the current driving vehicle in each associated lane.
[0095] In an embodiment of the present disclosure, further comprising: a control condition judging module, configured to:
[0096] Before obtaining the real-time vehicle driving data of the target intersection, determine that the target intersection meets the preset virtual traffic signal control condition.
[0097] It should be noted that the division of units in the embodiments of the present disclosure is illustrative, and is only a logical function division. When actually implemented, another division mode can be used. In addition, each functional unit in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.
[0098] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solutions of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of various embodiments of the present disclosure.
[0099] It should be noted that the above-described device provided by the embodiments of the present disclosure can realize all the method steps realized by the above-described method embodiments, and can achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments will not be described in detail.
[0100] The embodiment of the present disclosure further provides a processor-readable storage medium, which stores a program for causing a processor to execute the vehicle driving control method. The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor including but not limited to a magnetic storage (e.g., floppy diskette, hard disk, magnetic tape, magneto-optical disk (MO), etc.), an optical storage (e.g., CD, DVD, BD, HVD, etc.), and a semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid state disk (SSD), etc.), etc.
[0101] Those skilled in the art will appreciate that embodiments of the present disclosure can be provided as methods, apparatus, or computer program products. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure can take the form of a computer program product on one or more computer-usable storage media (including but not limited to magnetic disks, optical storage media, and the like) embodying computer usable program code.
[0102] The present disclosure is described with reference to the drawings and / or flowcharts and / or block diagrams of methods, apparatus, and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowchart
[0103] These processor executable instructions can also be stored in a processor readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the processor readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in the flowchart
[0104] Obviously, those skilled in the art can make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.
Claims
1. A vehicle driving control method, characterized in that, Includes the following steps: Obtain real-time vehicle driving data at the target intersection and retrieve historical traffic control data corresponding to the target intersection from the local database; Based on the real-time vehicle driving data and the historical traffic control data, virtual traffic signal control information for controlling vehicle driving is obtained; The virtual traffic signal control information is sent to the vehicles currently traveling within the target intersection.
2. The method as described in claim 1, characterized in that, The step of retrieving historical traffic control data corresponding to the target intersection from the local database includes: Obtain the collection time period corresponding to the real-time driving data; Retrieve the historical traffic control data corresponding to the target intersection that matches the collection time period from the local database.
3. The method as described in claim 2, characterized in that, The historical traffic control data includes: Historical traffic flow information, and / or historical virtual traffic signal control information.
4. The method as described in claim 1, characterized in that, The step of obtaining virtual traffic signal control information for controlling vehicle movement based on the real-time vehicle driving data and the historical traffic control data includes: Determine the real-time driving data characteristics corresponding to the real-time vehicle driving data; Extract the historical control data features corresponding to the historical traffic control data; The real-time driving data features and the historical control data features are input into a pre-trained deep learning model to obtain the virtual traffic signal control information output by the deep learning model.
5. The method as described in claim 4, characterized in that, The step of determining the real-time driving data features corresponding to the real-time vehicle driving data includes: Determine the driving time corresponding to the real-time vehicle driving data, and obtain vehicle driving time characteristics based on the driving time; Vehicle driving characteristics are obtained based on the real-time vehicle driving data; The vehicle driving characteristics and the vehicle driving time characteristics are determined as the real-time driving data characteristics.
6. The method as described in claim 1, characterized in that, Sending the virtual traffic signal control information to currently traveling vehicles within the target intersection includes: Among the multiple lanes corresponding to the target intersection, determine the associated lane that corresponds to the virtual traffic signal control information; The virtual traffic signal control information is sent to the currently traveling vehicles in the associated lane.
7. The method as described in claim 6, characterized in that, The associated lanes include multiple lanes, and sending the virtual traffic signal control information to currently traveling vehicles in the associated lanes includes: Identify the driving direction information of each of the associated lanes, and determine the virtual traffic signal control sub-information corresponding to each of the driving direction information in the virtual traffic signal control information; Send corresponding virtual traffic signal control sub-information to the currently traveling vehicles in each of the associated lanes.
8. The method according to any one of claims 1-7, characterized in that, Before acquiring the real-time vehicle driving data at the target intersection, the method further includes: The target intersection is determined to meet the preset virtual traffic signal control conditions.
9. The method as described in claim 8, characterized in that, The preset virtual traffic signal control conditions include: The target intersection does not include traffic lights; or... The target intersection includes traffic light equipment, which does not display traffic light data; or, The target intersection includes traffic light equipment, and the duration for which the traffic light equipment at the target intersection does not display traffic light data exceeds a preset duration threshold; or, The target intersection includes traffic light equipment, and the traffic light equipment displays signal timing information that meets preset adjustment conditions.
10. A vehicle driving control device, characterized in that, include: The data acquisition module is used to acquire real-time vehicle driving data at the target intersection and to acquire historical traffic control data corresponding to the target intersection from the local database. The control information acquisition module is used to acquire virtual traffic signal control information for controlling vehicle driving based on the real-time vehicle driving data and the historical traffic control data. The control information sending module is used to send the virtual traffic signal control information to the vehicles currently traveling within the target intersection.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for performing the vehicle driving control method according to any one of claims 1-9.