Vehicle steering control method and system based on unmanned driving

Abstract

The invention discloses a vehicle steering control method and system based on unmanned driving, and belongs to the technical field of intelligent control. Comprising the following steps: determining the proportion of a driving execution subject as a vehicle self-control center according to historical vehicle driving data; when the proportion is smaller than a proportion threshold value, a control request is sent to a vehicle administrator; otherwise, calculating a real-time processing index of the vehicle self-control center at the moment according to the real-time steering intersection traffic data; when the real-time processing index is smaller than a processing threshold value, a control request is sent to a vehicle administrator; otherwise, acquiring real-time vehicle driving data, combining the real-time vehicle driving data with the real-time steering intersection traffic data, and calculating an execution subject conversion value of the vehicle; when the steering waiting duration is smaller than the execution main body conversion value, the vehicle is controlled to steer through the vehicle automatic control center; otherwise, a control request is sent to a vehicle administrator. The task time of the unmanned vehicle can be reduced, and congestion at a steering intersection is avoided; the problem that an existing unmanned vehicle is long in running time in the steering running process is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a vehicle steering control method and system based on unmanned driving. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] Autonomous driving refers to a technology that allows vehicles to achieve autonomous control without the need for direct human control through the vehicle's own environmental perception, route planning and the vehicle's own status. It uses a variety of sensors and advanced monitoring systems to perceive and obtain dynamic changes in the external environment and the vehicle. Based on technologies such as machine learning, computer vision and deep learning, autonomous vehicles can perform driving operations autonomously and safely.

[0004] However, when an unmanned vehicle is preparing to turn, based on the judgment of unmanned driving safety, the vehicle may stay in place for a long time and wait for the safety incident to be resolved before performing driving operations. This not only increases the time for the unmanned vehicle to complete the task, but may also cause congestion at the turning intersection. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a steering control method, system, electronic device, computer-readable storage medium and computer program product based on unmanned driving, which comprehensively considers historical data of turning intersections, real-time traffic conditions and real-time driving conditions of unmanned vehicles to perform the switching of driving subjects of unmanned vehicles, thereby reducing the task completion time of unmanned vehicles and reducing the possibility of congestion at turning intersections.

[0006] In a first aspect, the present invention provides a vehicle steering control method based on unmanned driving;

[0007] A vehicle steering control method based on unmanned driving, comprising:

[0008] Obtain historical vehicle driving data, and determine the proportion of the vehicle automatic control center as the driving subject based on the historical vehicle driving data;

[0009] When the proportion is less than the preset proportion threshold, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle to turn; when the proportion is greater than the preset proportion threshold, real-time turning intersection traffic data is obtained and the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection is calculated;

[0010] When the real-time processing index is less than the preset processing threshold, a control request is sent to the vehicle administrator so that the vehicle administrator can control the vehicle steering; when the real-time processing index is greater than the preset processing threshold, real-time vehicle driving data is obtained and combined with the real-time steering intersection traffic data to calculate the execution subject conversion value of the vehicle;

[0011] When the steering waiting time is less than the execution subject conversion value, the vehicle steering is controlled by the vehicle automatic control center; otherwise, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle steering.

[0012] In some embodiments, determining the proportion of the driving subject as the vehicle autonomous control center based on historical vehicle driving data is specifically: based on historical vehicle driving data, counting the amount of historical data of the driving subject as the vehicle autonomous control center when the vehicle arrives at the turning intersection at the same time and calculating the proportion.

[0013] In some implementations, calculating the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection based on the real-time turning intersection traffic data specifically includes:

[0014] Add execution subject tags to the real-time turning intersection traffic data, and extract the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection, and the real-time number of non-motor vehicles at the turning intersection based on the added execution subject tags;

[0015] According to the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection and the real-time number of non-motor vehicles at the turning intersection, the real-time processing index of the vehicle automatic control center is obtained when the vehicle arrives at the turning intersection.

[0016] In some embodiments, before calculating the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection according to the real-time turning intersection traffic data, the method further includes:

[0017] Obtain historical road traffic data and attach execution subject labels, extract the number of motor vehicles at turning intersections, the flow of people at turning intersections, and the number of non-motor vehicles at turning intersections, and construct a training set;

[0018] The preset processing index function is iteratively optimized through the training set to determine the optimal weight parameters.

[0019] In some embodiments, real-time vehicle driving data is combined with real-time turning intersection traffic data to calculate the vehicle's execution subject conversion value specifically as follows: extract the timestamp of the vehicle arriving at the sidewalk stop line at the turning intersection and the timestamp of the vehicle arriving at the second end of the green light at the turning intersection in the real-time vehicle driving data, and calculate the subject conversion value based on the timestamp of the vehicle arriving at the sidewalk stop line at the turning intersection and the timestamp of the vehicle arriving at the second end of the green light at the turning intersection.

[0020] In some embodiments, the real-time processing index is expressed as:

[0021] p=w1p1+w2p2+w3p3+w4;

[0022] In the formula, p represents the real-time processing index, p1 represents the motor vehicle processing index, p2 represents the pedestrian processing index, p3 represents the non-motor vehicle processing index, and w1, w2, w3, and w4 represent weight parameters;

[0023] Among them, the motor vehicle quantity processing index is expressed as:

[0024] p1=exp{-CA y};

[0025] The people handling index is expressed as:

[0026] p2=exp{-PA y};

[0027] The non-motor vehicle quantity treatment index is expressed as:

[0028] p3=exp{-FA y};

[0029] In the formula, CA y represents the number of vehicles turning at the intersection at time y, PA y represents the flow of people turning to the intersection at time y, FA y Represents the number of non-motor vehicles turning at the intersection at time y.

[0030] In a second aspect, the present invention provides a vehicle steering control system based on unmanned driving;

[0031] A vehicle steering control system based on unmanned driving, comprising:

[0032] The proportion statistics module is configured to: obtain historical vehicle driving data, and determine the proportion of the vehicle automatic control center as the driving subject according to the historical vehicle driving data; when the proportion is less than a preset proportion threshold, send a control request to the vehicle administrator so that the vehicle administrator controls the vehicle steering;

[0033] The real-time processing module is configured to: when the proportion is greater than a preset proportion threshold, obtain real-time turning intersection traffic data and calculate the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection; when the real-time processing index is less than the preset processing threshold, send a control request to the vehicle administrator so that the vehicle administrator controls the vehicle to turn;

[0034] The subject conversion module is configured as follows: when the real-time processing index is greater than a preset processing threshold, real-time vehicle driving data is obtained, and combined with real-time turning intersection traffic data, the vehicle's execution subject conversion value is calculated; when the turning waiting time is less than the execution subject conversion value, the vehicle steering is controlled by the vehicle automatic control center; otherwise, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle steering.

[0035] In a third aspect, the present invention provides an electronic device;

[0036] An electronic device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned unmanned driving-based vehicle steering control method.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium;

[0038] A computer-readable storage medium stores a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned unmanned vehicle steering control method.

[0039] In a fifth aspect, the present invention provides a computer program product;

[0040] A computer program product includes a computer program / instruction, which implements the steps of the above-mentioned unmanned vehicle steering control method when executed by a processor.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The technical solution provided by the present invention comprehensively considers road traffic data and vehicle driving data, utilizes the regularity of traffic conditions in real life such as morning rush hour and evening rush hour, and combines the actual driving conditions of the unmanned vehicle to switch the driving execution subject of the unmanned vehicle, which not only reduces the task completion time of the unmanned vehicle, but also avoids the possibility of congestion at turning intersections. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0044] Figure 1 A schematic flow chart of a method for controlling a vehicle steering based on unmanned driving provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the system framework of an unmanned vehicle steering control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0047] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0048] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0049] Embodiment 1

[0050] During the turning process of existing unmanned vehicles, due to the judgment of the safety driving system of the unmanned vehicle, the turning waiting time is too long, resulting in congestion risk at the turning intersection; therefore, the present invention provides a vehicle steering control method based on unmanned driving.

[0051] Next, combine Figure 1 , a vehicle steering control method based on unmanned driving disclosed in this embodiment is described in detail. The vehicle steering control method based on unmanned driving comprises the following steps:

[0052] S1. Obtain road traffic data and vehicle driving data and store them in a constructed unmanned vehicle steering storage database.

[0053] In this embodiment, the road traffic data includes the number of motor vehicles, pedestrian flow, number of non-motor vehicles and real-time data of traffic lights at turning intersections, and the vehicle driving data includes the vehicle arrival timestamp, the arrival timestamp of the sidewalk stop line and the turning waiting time.

[0054] Radar sensors and on-board cameras are used to identify the distance between the front wheels of the driverless vehicle and the sidewalk stop line, the timestamp of arrival at the sidewalk stop line, and the waiting time for turning within the sensing range; the vehicle arrival timestamp, real-time data of traffic lights, the number of motor vehicles at the turning intersection, the flow of people, and the number of non-motor vehicles are obtained through the GPS system. The timestamp of arrival at the sidewalk stop line is generated by the distance between the front wheels of the driverless vehicle and the sidewalk stop line and the real-time time.

[0055] S2. Determine the proportion of the driving subject being the vehicle automatic control center based on the historical vehicle driving data in the unmanned vehicle steering storage database; when the proportion is less than the preset proportion threshold, send a control request to the vehicle administrator to enable the vehicle administrator to control the vehicle steering and update the driving subject data at the same time; when the proportion is greater than the preset proportion threshold, execute S3.

[0056] In this embodiment, the driving subjects of the unmanned vehicle include the vehicle manager and the vehicle automatic control center. In the unmanned vehicle turning storage database, the timestamp t when the unmanned vehicle arrives at the turning intersection and the driving subject A are in a one-to-one correspondence, that is, t→A.

[0057] In real life, traffic conditions have regularities, such as morning rush hour and evening rush hour. Therefore, in this embodiment, the regularity of traffic conditions is utilized in combination with historical data. According to the proportion of the executing subject being the vehicle automatic control center at the target turning intersection at the same time, a preliminary judgment is made in advance whether the executing subject needs to be replaced, thereby further improving the response speed of the unmanned vehicle during driving.

[0058] As an implementation mode, S2 specifically includes:

[0059] S201, counting the historical data volume of the vehicle automatic control center when the vehicle arrives at the turning intersection at the same time and calculating the proportion, expressed as:

[0060]

[0061] Where n represents the number of historical data when the driverless vehicle arrives at the turning intersection at time t and the driving subject is the vehicle automatic control center, and N represents the number of historical data when the driverless vehicle arrives at the turning intersection.

[0062] S202. When the proportion of the driving subjects that are the vehicle automatic control center is less than the proportion threshold, a control request is sent to the administrator and the driving subject data is updated at the same time; otherwise, S3 is executed.

[0063] For example, the preset ratio threshold is 0.5, n[i] = {2, 3, 6, 8, 4}, N[i] = {6, 8, 9, 16, 4}, then the ratio of the driving subject to the vehicle autonomous control center is Ut [i] = {0.333, 0.375, 0.333, 0.5, 1}, i represents the i-th example. In the 1st, 2nd and 3rd examples, the vehicle directly sends a control request to the administrator and updates the driving subject data at the same time; in the 4th and 5th examples, S3 is executed.

[0064] S3. Calculate the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection based on the real-time turning intersection traffic data in the unmanned vehicle turning storage database; when the real-time processing index is less than the preset processing threshold, send a control request to the vehicle administrator to enable the vehicle administrator to control the vehicle turning; when the real-time processing index is greater than the preset processing threshold, execute S4.

[0065] Under different traffic conditions, such as heavy traffic, heavy pedestrian traffic at turning intersections, and many non-motor vehicles, the processing capacity of unmanned vehicles will decrease, making it impossible to perform steering operations in time. Therefore, in this embodiment, the real-time driving situation is judged by comprehensively considering the traffic flow and pedestrian flow, and when the processing capacity of the unmanned vehicle decreases, it is controlled by the vehicle manager.

[0066] As an implementation method, S3 specifically includes:

[0067] S301. Add an execution subject tag to the real-time turning intersection traffic data.

[0068] In this embodiment, the real-time turning intersection traffic data set after adding the execution subject label is expressed as:

[0069] {CA y , P.A. y , F.A. y}|a y ;

[0070] Among them, a y Indicates that at time y, the vehicle's execution subject is a, CA y represents the value of the number of vehicles turning at the intersection at time y, PA y represents the value of the traffic flow at the intersection at time y, FA y Represents the value of the number of non-motor vehicles turning at the intersection at time y.

[0071] The real-time turning intersection traffic data set includes traffic data of multiple unmanned vehicles. By adding execution subject labels to the turning intersection traffic data set, it is convenient to query the execution subject of the traffic conditions at different turning intersections, thereby facilitating the calculation of the processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection.

[0072] S302. Based on the additional execution subject tag, extract the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection, and the real-time number of non-motor vehicles at the turning intersection when the execution subject is the vehicle automatic control center.

[0073] According to the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection, and the real-time number of non-motor vehicles at the turning intersection, the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection is obtained. The real-time processing index is expressed as:

[0074] p=w1p1+w2p2+w3p3+w4;

[0075] In the formula, p represents the real-time processing index, p1 represents the motor vehicle processing index, p2 represents the pedestrian processing index, p3 represents the non-motor vehicle processing index, and w1, w2, w3, and w4 represent weight parameters;

[0076] Among them, the motor vehicle quantity processing index is expressed as:

[0077] p1=exp{-CA y};

[0078] The people handling index is expressed as:

[0079] p2=exp{-PA y};

[0080] The non-motor vehicle quantity treatment index is expressed as:

[0081] p3=exp{-FA y};

[0082] In the formula, CA y represents the number of vehicles turning at the intersection at time y, PA y represents the flow of people turning to the intersection at time y, FA y Represents the number of non-motor vehicles turning at the intersection at time y.

[0083] S303. When the real-time processing index is less than the preset processing threshold, a control request is sent to the vehicle administrator so that the vehicle administrator controls the vehicle steering; when the real-time processing index is greater than the preset processing threshold, S4 is executed.

[0084] As an implementation method, before calculating the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection according to the real-time turning intersection traffic data, it also includes:

[0085] (1) Obtain historical road traffic data and attach execution subject labels to extract the number of motor vehicles at turning intersections, the flow of people at turning intersections, and the number of non-motor vehicles at turning intersections to construct a training set.

[0086] (2) The preset processing index function is iteratively optimized through the training set, and w1, w2, w3, and w4 are continuously updated until the optimal weight parameters are found.

[0087] Specifically, there are K processing index functions recorded in the training set, and the fth processing index function is recorded as P f =w 1f x1+w 2f x2+w 3f x3+w 4f , w 1f 、w 2f 、w 3f and w 4f They are respectively the preset processing index function P f , x1, x2 and x3 are all sample independent variables.

[0088] Take p1, p2 and p3 as sample independent variables, and substitute them into x1, x2 and x3 respectively. f Calculate the fth real-time processing index; let f = f + 1, iteratively calculate the real-time processing index, obtain a total of K real-time processing indexes, and select the processing index function P corresponding to the smallest real-time processing index f , and lock the weight parameter w 1f 、w 2f 、w 3f and w 4f as the optimal weight parameter.

[0089] S4. Calculate the execution subject conversion value of the vehicle according to the real-time vehicle driving data and the real-time turning intersection traffic data; when the turning waiting time is less than the execution subject conversion value, control the vehicle turning through the vehicle automatic control center; otherwise, send a control request to the vehicle administrator to enable the vehicle administrator to control the vehicle turning.

[0090] Specifically include:

[0091] S401, extracting the timestamp of the vehicle arriving at the pedestrian stop line at the turning intersection and the timestamp of the vehicle arriving at the second end of the green light at the turning intersection from the real-time vehicle driving data, and calculating the subject conversion value according to the timestamp of the vehicle arriving at the pedestrian stop line at the turning intersection and the timestamp of the vehicle arriving at the second end of the green light at the turning intersection. The subject conversion value is expressed as:

[0092] TP = T2 - T1;

[0093] Among them, TP represents the execution subject conversion value, T1 represents the timestamp when the vehicle reaches the pedestrian stop line at the turning intersection, and T2 represents the timestamp when the vehicle reaches the second end of the green light at the turning intersection.

[0094] S402. Obtain the steering waiting duration in the real-time road traffic data. When the steering waiting duration YP > TP or YP = TP, the vehicle directly sends a control request to the vehicle administrator and updates the executing driving entity data simultaneously; otherwise, the vehicle continues to be controlled by the vehicle automatic control center until the vehicle turns successfully, and the executing driving entity data is updated.

[0095] Exemplarily, the timestamp T1 when the vehicle arrives at the stop line of the turning intersection is 08:00:00, the timestamp T2 when the vehicle arrives at the end of the second green light at the turning intersection is 8:01:06, and the actual waiting duration YP of the vehicle at the stop line is 1 minute and 7 seconds. Then the executing entity conversion value TP = T2 - T1 = 1 minute and 6 seconds. Then YP > TP, that is, the vehicle directly sends a control request to the vehicle administrator and updates the executing driving entity data simultaneously.

[0096] The timestamp T1 when the vehicle arrives at the stop line of the turning intersection is 10:00:00, the timestamp T2 when the vehicle arrives at the end of the second green light at the turning intersection is 10:01:06, and the actual waiting duration YP of the vehicle at the stop line is 1 minute and 0 seconds. Then the executing entity conversion value TP = T2 - T1 = 1 minute and 6 seconds. Then YP < TP, that is, the vehicle continues to be controlled by the vehicle automatic control center until the vehicle turns successfully, and the executing driving entity data is updated.

[0097] The timestamp T1 when the vehicle arrives at the stop line of the turning intersection is 18:00:00, the timestamp T2 when the vehicle arrives at the end of the second green light at the turning intersection is 18:02:15, and the actual waiting duration YP of the vehicle at the stop line is 2 minutes and 15 seconds. Then the executing entity conversion value TP = T2 - T1 = 2 minutes and 15 seconds. Then YP = TP, that is, the vehicle directly sends a control request to the vehicle administrator and updates the executing driving entity data simultaneously.

[0098] Embodiment 2

[0099] Combined with Figure 2 , this embodiment discloses a vehicle steering control system based on driverless driving, including:

[0100] A proportion statistics module, configured to: obtain historical vehicle driving data, and determine the proportion of the executing driving entity being the vehicle automatic control center according to the historical vehicle driving data; when the proportion is less than a preset proportion threshold, send a control request to the vehicle administrator to enable the vehicle administrator to control the vehicle to turn;

[0101] A real-time processing module, configured to: when the proportion is greater than a preset proportion threshold, obtain the real-time traffic data of the turning intersection and calculate the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection; when the real-time processing index is less than a preset processing threshold, send a control request to the vehicle administrator to enable the vehicle administrator to control the vehicle to turn;

[0102] The subject conversion module is configured as follows: when the real-time processing index is greater than a preset processing threshold, real-time vehicle driving data is obtained, and combined with real-time turning intersection traffic data, the vehicle's execution subject conversion value is calculated; when the turning waiting time is less than the execution subject conversion value, the vehicle steering is controlled by the vehicle automatic control center; otherwise, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle steering.

[0103] It should be noted that the above-mentioned proportion statistics module, real-time processing module and subject conversion module correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Embodiment 1. It should be noted that the above-mentioned modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0104] Embodiment 3

[0105] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned unmanned vehicle steering control method are completed.

[0106] Embodiment 4

[0107] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned unmanned vehicle steering control method are completed.

[0108] Embodiment 5

[0109] Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned unmanned driving-based vehicle steering control method when executed by a processor.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle steering control method based on unmanned driving, characterized in that: include: Obtain historical vehicle driving data, and determine the proportion of the vehicle automatic control center as the driving subject based on the historical vehicle driving data; When the proportion is less than the preset proportion threshold, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle turning; when the proportion is greater than the preset proportion threshold, real-time turning intersection traffic data is obtained and the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection is calculated; When the real-time processing index is less than a preset processing threshold, a control request is sent to the vehicle administrator so that the vehicle administrator controls the steering of the vehicle; When the real-time processing index is greater than a preset processing threshold, real-time vehicle driving data is obtained and combined with real-time turning intersection traffic data to calculate the execution subject conversion value of the vehicle; When the steering waiting time is less than the execution subject conversion value, the vehicle steering is controlled by the vehicle automatic control center; otherwise, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle steering.

2. The unmanned vehicle steering control method according to claim 1, characterized in that: The method of determining the proportion of the vehicle autonomous control center as the driving subject based on historical vehicle driving data is specifically as follows: based on historical vehicle driving data, the amount of historical data of the vehicle autonomous control center as the driving subject when the vehicle arrives at the turning intersection at the same time is counted and the proportion is calculated.

3. The unmanned vehicle steering control method according to claim 1, characterized in that: The real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection is calculated based on the real-time turning intersection traffic data, which specifically includes: Add execution subject tags to the real-time turning intersection traffic data, and extract the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection, and the real-time number of non-motor vehicles at the turning intersection based on the added execution subject tags; According to the real-time number of motor vehicles at the turning intersection, the real-time flow of people at the turning intersection and the real-time number of non-motor vehicles at the turning intersection, the real-time processing index of the vehicle automatic control center is obtained when the vehicle arrives at the turning intersection.

4. The unmanned vehicle steering control method according to claim 1, characterized in that: Before calculating the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection according to the real-time turning intersection traffic data, it also includes: Obtain historical road traffic data and attach execution subject labels, extract the number of motor vehicles at turning intersections, the flow of people at turning intersections, and the number of non-motor vehicles at turning intersections, and construct a training set; The preset processing index function is iteratively optimized through the training set to determine the optimal weight parameters.

5. The unmanned vehicle steering control method according to claim 1, characterized in that: The real-time vehicle driving data is combined with the real-time turning intersection traffic data to calculate the vehicle's execution subject conversion value specifically as follows: extract the timestamp when the vehicle arrives at the sidewalk stop line at the turning intersection and the timestamp when the vehicle arrives at the second end of the green light at the turning intersection in the real-time vehicle driving data, and calculate the subject conversion value based on the timestamp when the vehicle arrives at the sidewalk stop line at the turning intersection and the timestamp when the vehicle arrives at the second end of the green light at the turning intersection.

6. The unmanned vehicle steering control method according to claim 1, characterized in that: The real-time processing index is expressed as: p=w1p1+w2p2+w3p3+w4; In the formula, p represents the real-time processing index, p1 represents the motor vehicle processing index, p2 represents the pedestrian processing index, p3 represents the non-motor vehicle processing index, and w1, w2, w3, and w4 represent weight parameters; Among them, the motor vehicle quantity processing index is expressed as: p1=exp{-CA y }; The people handling index is expressed as: p2=exp{-PA y }; The non-motor vehicle quantity treatment index is expressed as: p3=exp{-FA y }; Where, CA y represents the number of vehicles turning at the intersection at time y, PA y represents the flow of people turning to the intersection at time y, FA y Represents the number of non-motor vehicles turning at the intersection at time y.

7. The vehicle steering control system based on unmanned driving is characterized in that: include: The proportion statistics module is configured to: obtain historical vehicle driving data, and determine the proportion of the vehicle automatic control center as the driving subject according to the historical vehicle driving data; When the proportion is less than a preset proportion threshold, a control request is sent to the vehicle administrator so that the vehicle administrator can control the steering of the vehicle; The real-time processing module is configured to: when the proportion is greater than a preset proportion threshold, obtain real-time turning intersection traffic data and calculate the real-time processing index of the vehicle automatic control center when the vehicle arrives at the turning intersection; when the real-time processing index is less than the preset processing threshold, send a control request to the vehicle administrator so that the vehicle administrator controls the vehicle to turn; The subject conversion module is configured as follows: when the real-time processing index is greater than a preset processing threshold, real-time vehicle driving data is obtained, and combined with real-time turning intersection traffic data, the vehicle's execution subject conversion value is calculated; when the turning waiting time is less than the execution subject conversion value, the vehicle steering is controlled by the vehicle automatic control center; otherwise, a control request is sent to the vehicle administrator to enable the vehicle administrator to control the vehicle steering.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the unmanned driving-based vehicle steering control method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the unmanned vehicle steering control method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the unmanned vehicle steering control method according to any one of claims 1 to 6 are implemented.

Images