Fleet driving control methods, equipment and storage media

Abstract

The present application relates to the field of autonomous driving technology, and discloses a fleet driving control method, device, and storage medium. The method includes: obtaining real-time road surface roughness characteristic data and vehicle dynamics characteristic data of vehicles in the fleet; performing dynamic driving risk analysis on the road surface on which the vehicle is currently driving and dividing the area based on the driving risk analysis results to determine the vehicle's current passable area; performing path planning on the vehicle based on the passable area to obtain several candidate paths; performing driving safety cost analysis on the candidate paths, and selecting the corresponding target path from the candidate paths based on the safety cost analysis results; dynamically configuring the vehicle's driving speed based on the vehicle's real-time vehicle adhesion coefficient, so that the vehicle travels along the target path at the configured driving speed. The embodiments of the present application can reduce the probability of speed instability of vehicles in the fleet and improve the safety of fleet driving.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a fleet driving control method, device and storage medium. Background Technology

[0002] Currently, research on autonomous driving for convoys of multiple vehicles is primarily based on ideal road conditions, such as a constant coefficient of friction. However, in actual driving, road conditions, such as the coefficient of friction and unevenness of the road surface, may change after some vehicles have moved, causing vehicle speed instability and affecting convoy safety. Summary of the Invention

[0003] The purpose of this application is to provide a convoy driving control method, device, and storage medium, which aims to reduce the probability of speed instability of vehicles in a convoy and improve the safety of convoy driving.

[0004] This application provides a fleet driving control method, including:

[0005] Acquire real-time road surface roughness characteristic data and vehicle dynamics characteristic data of vehicles in the fleet;

[0006] Based on the road surface roughness characteristic data and the vehicle dynamics characteristic data, a dynamic driving risk analysis is performed on the road surface where the vehicle is currently traveling, and the area is divided based on the driving risk analysis results to determine the current passable area of ​​the vehicle.

[0007] Based on the passable area, the vehicle is route-planned to obtain several candidate routes;

[0008] Perform a driving safety cost analysis on the candidate paths, and select the corresponding target path from the candidate paths based on the safety cost analysis results;

[0009] The vehicle's speed is dynamically configured based on its real-time vehicle adhesion coefficient, so that the vehicle travels along the target path at the configured speed.

[0010] In some embodiments, the step of performing dynamic driving risk analysis on the road surface where the vehicle is currently traveling, based on the road surface roughness characteristic data and the vehicle dynamics characteristic data, and dividing the area based on the driving risk analysis results, includes:

[0011] Risk feature data is extracted from both the road surface roughness feature data and the vehicle dynamics feature data to obtain multidimensional risk information data;

[0012] The initial passable area of ​​the vehicle is determined based on the multidimensional risk information data;

[0013] Collision risk analysis and communication interruption risk analysis are performed on the initial passable area, and areas with collision risk and communication interruption risk are eliminated to determine the current passable area of ​​the vehicle.

[0014] In some embodiments, extracting risk feature data from both the road surface roughness feature data and the vehicle dynamics feature data includes:

[0015] Based on the road surface roughness feature data and the vehicle dynamics feature data, a road surface roughness risk field is constructed for the road surface where the vehicle is currently traveling.

[0016] Extract pavement risk characteristic data and pavement evolution characteristic data from the pavement roughness risk field;

[0017] The multidimensional risk information data is obtained by splicing together the road surface risk characteristic data, the road surface evolution characteristic data, and the vehicle dynamics characteristic data.

[0018] In some embodiments, the collision risk analysis and communication interruption risk analysis of the initial passable area includes:

[0019] Based on the real-time distance data between the vehicle and other vehicles, the global communication safety coefficient and global collision safety coefficient of the vehicle relative to other vehicles are calculated to obtain the collision risk analysis results and communication interruption risk analysis results.

[0020] Based on the collision risk analysis results and the communication interruption risk analysis results, areas with collision risk and communication interruption risk are eliminated to determine the current passable area of ​​the vehicle.

[0021] In some embodiments, performing a driving safety cost analysis on the candidate paths and selecting a corresponding target path from the candidate paths based on the safety cost analysis results includes:

[0022] A driving safety cost analysis is performed on the candidate paths of the navigator vehicle, and the target path of the navigator vehicle is determined based on the safety cost analysis results of the candidate paths of the navigator vehicle.

[0023] The path points of the following vehicles are determined based on the target path of the lead vehicle and the preset formation maintenance parameters, so as to determine the target path of the following vehicles.

[0024] In some embodiments, dynamically configuring the vehicle's speed based on the vehicle's real-time vehicle adhesion coefficient includes:

[0025] Obtain the front adhesion coefficient and underbody adhesion coefficient of the vehicle;

[0026] The rate of change of the adhesion coefficient between the vehicles is calculated based on the front adhesion coefficient of the following vehicle and the undercarriage adhesion coefficient of the preceding vehicle.

[0027] The vehicle's travel speed is configured based on the rate of change of the adhesion coefficient.

[0028] In some embodiments, configuring the vehicle's driving speed based on the rate of change of the adhesion coefficient includes:

[0029] When the rate of change of the adhesion coefficient is not less than the preset threshold rate of change of the adhesion coefficient, the speed configuration amount of the following vehicle is calculated based on the rate of change of the adhesion coefficient.

[0030] The total speed configuration is obtained by performing a weighted summation on the speed configurations of each of the following vehicles.

[0031] Calculate the speed configuration amount of the lead vehicle based on the total speed configuration amount;

[0032] The driving speed of the following vehicle is dynamically configured based on the speed configuration of the following vehicle, and the driving speed of the lead vehicle is dynamically configured based on the speed configuration of the lead vehicle.

[0033] In some embodiments, configuring the vehicle's driving speed based on the rate of change of the adhesion coefficient further includes:

[0034] The reference acceleration of the following vehicle is generated based on the driving speed before and after the following vehicle configuration;

[0035] The baseline acceleration of the following vehicle is compensated based on the distance error data between the following vehicle and the vehicle in front, so as to obtain the actual acceleration of the following vehicle.

[0036] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0037] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0038] The beneficial effects of this application are as follows: Based on real-time road surface roughness characteristic data and vehicle dynamic characteristic data of vehicles in the convoy, dynamic driving risk analysis is performed on the road surface where the vehicles are currently traveling. Based on the driving risk analysis results, the current passable area of ​​the vehicles is determined. After generating candidate paths based on the current passable area of ​​the vehicles and determining the corresponding target path through driving safety cost analysis, the driving speed of the vehicles is dynamically configured based on the real-time vehicle adhesion coefficient. The vehicles are controlled to travel along the target path at the configured driving speed, thereby realizing automatic control of convoy driving. The current passable area of ​​the vehicles is determined by dynamic driving risk analysis based on real-time road surface roughness characteristic data and vehicle dynamics characteristic data. It also considers the dynamic changes of road surface roughness characteristic data and vehicle dynamics characteristic data, adapting to the dynamic planning of passable areas for each vehicle in the convoy, improving the rationality of the driving path planning for each vehicle in the convoy. After determining the target path of each vehicle, the driving speed of the vehicles is dynamically configured according to the real-time vehicle adhesion coefficient, ensuring that the driving speed of each vehicle adapts to the changes in the vehicle adhesion coefficient, avoiding the possibility of sudden changes in the adhesion coefficient causing vehicle instability, ensuring the movement stability of the convoy under complex road conditions, and improving the driving safety of the convoy. Attached Figure Description

[0039] Figure 1 This is a diagram illustrating the application environment of the fleet driving control method provided in the embodiments of this application.

[0040] Figure 2 This is an optional flowchart of the fleet driving control method provided in the embodiments of this application.

[0041] Figure 3 This is a flowchart of the specific method for step S202 provided in the embodiments of this application.

[0042] Figure 4 This is a flowchart of the specific method for step S204 provided in the embodiments of this application.

[0043] Figure 5 This is a flowchart of the specific method of step S205 provided in the embodiments of this application.

[0044] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and drawings are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0048] The fleet driving control method provided in this application can be executed by a computer device, which can be a terminal device or a server. The terminal device includes, but is not limited to, mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle terminals, and aircraft. The server can be a standalone physical server, a server cluster consisting of multiple physical servers, a distributed system, or a cloud server.

[0049] Furthermore, the information, data, and signals involved in the embodiments of this application are all authorized by the relevant parties or fully authorized by all parties, and the collection, use, and processing of the relevant data comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0050] To facilitate understanding of the fleet driving control method provided in this application embodiment, the following example uses the vehicle-mounted terminal of the lead vehicle in the fleet as the executing subject of the fleet driving control method to illustrate the application scenario of the fleet driving control method.

[0051] Figure 1 This diagram illustrates the application environment of the fleet driving control method provided in this embodiment. (See attached diagram.) Figure 1This convoy driving control method is applied to a convoy driving control system. The convoy driving control system includes a first on-board terminal 110 and multiple second on-board terminals 120. The first on-board terminal 110 and the second on-board terminals 120 are connected via a network. The first on-board terminal 110 is the on-board terminal for the lead vehicle in the convoy, and the second on-board terminals 120 are the on-board terminals for the following vehicles in the convoy. The second on-board terminals 120 are used to send real-time road surface roughness characteristic data and vehicle dynamic characteristic data of the following vehicles to the first on-board terminal 110. The first vehicle-mounted terminal 110 is used to acquire real-time road surface roughness feature data and vehicle dynamics feature data of vehicles in the fleet. Based on the road surface roughness feature data and vehicle dynamics feature data, it performs dynamic driving risk analysis on the road surface where the vehicle is currently traveling and divides the area based on the driving risk analysis results to determine the current passable area of ​​the vehicle. Based on the passable area, it performs path planning for the vehicle to obtain several candidate paths. It performs driving safety cost analysis on the candidate paths and selects the corresponding target path from the candidate paths based on the safety cost analysis results. Based on the real-time vehicle adhesion coefficient, it dynamically configures the real-time driving speed of the vehicle so that the vehicle travels along the target path at the real-time driving speed.

[0052] Figure 2 This is a flowchart of a fleet driving control method provided in an embodiment of this application. (See attached document.) Figure 2 In some embodiments, the method includes, but is not limited to, steps S201 to S205.

[0053] Step S201: Obtain real-time road surface roughness characteristic data and vehicle dynamics characteristic data of vehicles in the convoy.

[0054] Road surface roughness characteristic data refers to dynamic parameters reflecting the road surface geometry and friction characteristics. Specifically, it can be achieved using lidar point cloud data combined with vibration spectrum data collected by an inertial measurement unit, used to assess the traffic risk level of different areas. In this embodiment, the road surface roughness characteristic data includes road surface texture characteristic data, humidity characteristic data, material characteristic data, temperature characteristic data, and regional range data, regional characteristic data, and regional risk data for both depressions and protrusions.

[0055] Vehicle dynamics characteristic data includes parameters such as suspension system response characteristics and tire slip ratio. Specifically, real-time data such as steering torque and longitudinal acceleration can be obtained through onboard sensors to construct a vehicle motion state model. Passable area delineation is based on spatial segmentation of multi-dimensional risk data. Specifically, it can utilize a gridded map combined with probabilistic risk assessment algorithms to dynamically exclude areas with collision or communication failure risks. In this embodiment, vehicle dynamics characteristic data includes vehicle model code data, ground clearance data, vehicle mass data, tire contact area data, wheelbase data, and vehicle adhesion coefficient.

[0056] Step S202: Based on road surface roughness characteristic data and vehicle dynamics characteristic data, perform dynamic driving risk analysis on the road surface where the vehicle is currently traveling and divide the area based on the driving risk analysis results to determine the current passable area of ​​the vehicle.

[0057] Dynamic driving risk analysis based on road surface roughness characteristic data and vehicle dynamics characteristic data refers to the process of conducting driving risk analysis for each vehicle in the fleet separately.

[0058] Specifically, after acquiring road surface roughness feature data and vehicle dynamics feature data, based on the vehicle dynamics feature data of each vehicle in the convoy and the road surface roughness feature data of the current and upcoming road surfaces, a dynamic driving risk analysis is performed on the road surface currently being traveled by each vehicle to determine the driving risk of each vehicle. This yields corresponding driving risk analysis results. Then, based on these results, the current and upcoming road surfaces for each vehicle are divided into regions, and regions meeting the driving risk criteria are designated as the vehicle's current passable area. More specifically, risk feature data can be extracted from both the road surface roughness feature data and the vehicle dynamics feature data. Then, the extracted risk feature data is coupled and analyzed to calculate the comprehensive driving risk of each region on the road surface. Based on this comprehensive driving risk, a real-time updated passable area map is generated to determine the vehicle's current passable area.

[0059] Step S203: Based on the passable area, perform route planning for the vehicle to obtain several candidate routes.

[0060] After determining the current passable area of ​​the vehicle, the corresponding path planning algorithm is used to plan the path of the vehicle within the current passable area to generate several candidate paths. When driving along the candidate paths, the lead vehicle is made to travel within the passable area to reach the destination of the convoy, and the following vehicles are made to travel within the passable area to follow the lead vehicle.

[0061] Step S204: Perform a driving safety cost analysis on the candidate paths, and select the corresponding target path from the candidate paths based on the safety cost analysis results.

[0062] After obtaining the candidate paths for each vehicle, a driving safety cost analysis is performed on each candidate path to select the candidate path that meets the safety cost criteria as the target path for the vehicle.

[0063] Specifically, the process involves traversing all candidate paths for each vehicle, evaluating the driving safety cost and driving stability performance cost of each candidate path, and selecting the candidate path with the lowest combined driving safety cost and driving stability performance cost as the vehicle's target path. More specifically, each candidate path can be input into a pre-defined driving safety cost analysis model to obtain the combined driving safety cost and driving stability performance cost, thereby selecting the candidate path with the lowest cost as the vehicle's target path.

[0064] Step S205: Dynamically configure the vehicle's driving speed based on the vehicle's real-time vehicle adhesion coefficient, so that the vehicle travels along the target path at the configured driving speed.

[0065] After determining the corresponding target path for each vehicle, control each vehicle to travel along the corresponding target path. During the journey, the vehicle's speed is dynamically configured based on the vehicle's real-time vehicle adhesion coefficient, so that the vehicle travels along the target path at the configured speed, thereby ensuring that each vehicle travels smoothly.

[0066] Specifically, after determining the corresponding target path for each vehicle, the system controls each vehicle to travel along that path. During travel, the vehicle's adhesion coefficient and speed are acquired in real time. When the adhesion coefficient meets the speed configuration conditions, the vehicle's speed is dynamically configured based on the real-time adhesion coefficient, allowing the vehicle to travel along the target path at the configured speed. More specifically, the vehicle adhesion coefficient and speed can be input into a preset speed configuration model to dynamically configure the vehicle's speed based on the real-time adhesion coefficient, generating the configured speed, and controlling the vehicle to travel along the target path at the configured speed.

[0067] The convoy driving control method provided in this application performs dynamic driving risk analysis on the road surface where the vehicles are currently traveling based on real-time road surface roughness characteristic data and vehicle dynamic characteristic data of the vehicles in the convoy. Based on the driving risk analysis results, the current passable area of ​​the vehicles is determined. After generating candidate paths based on the current passable area of ​​the vehicles and determining the corresponding target path through driving safety cost analysis, the driving speed of the vehicles is dynamically configured based on the real-time vehicle adhesion coefficient of the vehicles. The vehicles are controlled to travel along the target path at the configured driving speed, thereby realizing automatic control of convoy driving. The current passable area of ​​the vehicles is determined by dynamic driving risk analysis based on real-time road surface roughness characteristic data and vehicle dynamics characteristic data. It also considers the dynamic changes of road surface roughness characteristic data and vehicle dynamics characteristic data, adapting to the dynamic planning of passable areas for each vehicle in the convoy, improving the rationality of the driving path planning for each vehicle in the convoy. After determining the target path of each vehicle, the driving speed of the vehicles is dynamically configured according to the real-time vehicle adhesion coefficient, ensuring that the driving speed of each vehicle adapts to the changes in the vehicle adhesion coefficient, avoiding the possibility of sudden changes in the adhesion coefficient causing vehicle instability, ensuring the movement stability of the convoy under complex road conditions, and improving the driving safety of the convoy.

[0068] Figure 3 This is a flowchart illustrating the specific method of step S202 provided in the embodiments of this application. See also... Figure 3 In some embodiments, the method includes, but is not limited to, steps S301 to S303.

[0069] Step S301: Extract risk feature data from both road surface roughness feature data and vehicle dynamics feature data to obtain multidimensional risk information data.

[0070] Multidimensional risk information data refers to a comprehensive evaluation dataset formed by integrating multiple dimensions of road surface roughness feature data and vehicle dynamics feature data. Specifically, it can be achieved by using data fusion algorithms to correlate and analyze the road surface roughness risk field, driving stability performance characteristics, and road surface evolution characteristics, in order to comprehensively reflect potential safety hazards in the driving environment.

[0071] In some embodiments, step S301 specifically includes: constructing a road surface roughness risk field for the road surface where the vehicle is currently traveling based on road surface roughness feature data and vehicle dynamics feature data; extracting road surface risk feature data and road surface evolution feature data from the road surface roughness risk field; and splicing the driving stability performance feature data from the road surface risk feature data, road surface evolution feature data, and vehicle dynamics feature data to obtain multidimensional risk information data.

[0072] The expression for the road surface roughness risk field is:

[0073] ,

[0074] ,

[0075] ,

[0076] ,

[0077] In the formula, For road surface unevenness characteristic risk data, This data represents the risk characteristics of general road surface irregularities. Let these be the coordinates of discrete points on the road surface. Stable performance risk factor Speed ​​risk factor For reference to ground clearance data, This refers to the vehicle's minimum ground clearance data. It is the speed sensitivity coefficient. It is the vehicle's speed. The coordinates of the risk characteristic center are The characteristic risk peak coefficient, , , and These are the random distribution factors of the characteristic risk, representing the characteristic risk along... Positive axis direction negative axis direction positive direction of axis and Distribution range in the negative direction of the axis. The characteristic risk random decrease coefficient.

[0078] After constructing the road surface roughness risk field, road risk characteristic data and road evolution characteristic data are extracted from the road surface roughness risk field. Then, the driving stability performance characteristic data from the road surface risk characteristic data, road evolution characteristic data, and vehicle dynamics characteristic data are spliced ​​together to obtain multidimensional risk information data. The road surface risk characteristic data includes the characteristic risk peak coefficient. Risk peak Risk characteristic center coordinates Feature range and characteristic risk random decline coefficient The vehicle dynamics characteristic data includes the vehicle state matrix, which is a key feature of vehicle dynamics performance. Includes vehicle model code, ground clearance Vehicle quality Tire ground contact area Wheelbase and peak adhesion coefficient Road surface evolution characteristic data includes the number of vehicles passing through each road surface, vehicle type and vehicle load, and evolution trend coefficient. Geological softening factors and wear correction amount .

[0079] Step S302: Determine the vehicle's current initial passable area based on multi-dimensional risk information data.

[0080] The initial passable area refers to the range within which vehicles can travel based on preliminary risk screening. Specifically, it can be achieved by combining spatial grid division with a risk probability distribution model, and is used to provide a basic area for subsequent refined risk analysis.

[0081] Determining the initial passable area for each vehicle is achieved by analyzing multidimensional risk information data across various regions of the road surface where each vehicle in the convoy will soon travel. Specifically, this can be done by constructing a road surface roughness risk field using road roughness feature data and vehicle dynamics feature data as inputs, extracting corresponding multidimensional risk information data, and then analyzing this multidimensional risk information data using a spatial grid partitioning method combined with a risk probability distribution model to determine the risk index of each region of the road surface where the vehicle will soon travel. Regions whose risk indices meet preset risk conditions are selected as the initial passable areas for each vehicle.

[0082] Step S303: Perform collision risk analysis and communication interruption risk analysis on the initial passable area, and eliminate areas with collision risk and communication interruption risk to determine the current passable area of ​​the vehicle.

[0083] Collision risk analysis refers to assessing whether the dynamic distance and relative speed between vehicles in a convoy meet safety thresholds. Specifically, it can be achieved by combining real-time distance monitoring and speed prediction algorithms with a safe distance model to identify potential areas where collisions may occur.

[0084] Communication interruption risk analysis refers to determining whether the communication link between vehicles in a convoy has failed due to excessive distance between vehicles. Specifically, it can be achieved by combining real-time distance monitoring and channel quality assessment with a communication coverage prediction algorithm to exclude areas where coordinated control fails due to communication failure.

[0085] In some embodiments, step S303 specifically includes: calculating the global communication safety coefficient and global collision safety coefficient of the vehicle relative to other vehicles based on the real-time distance data between the vehicle and other vehicles, and obtaining the collision risk analysis result and the communication interruption risk analysis result; eliminating areas with collision risk and communication interruption risk based on the collision risk analysis result and the communication interruption risk analysis result, so as to determine the current passable area of ​​the vehicle.

[0086] The global communication safety factor is a quantitative indicator generated based on the correlation between real-time vehicle-to-vehicle distance and communication signal strength. Specifically, it can be calculated by combining the ratio of vehicle distance to a preset communication distance threshold with a signal attenuation model, and is used to assess the stability of the inter-vehicle communication link. The global collision safety factor is a dynamic risk indicator generated based on the relative speed between vehicles and real-time vehicle distance. Specifically, it can be calculated by combining the difference between vehicle distance and vehicle braking distance with the rate of change of relative speed, and is used to predict the probability of collisions between vehicles.

[0087] Specifically, when vehicles are traveling in platoons, sensors installed on the vehicle body collect real-time three-dimensional position data of adjacent vehicles to calculate longitudinal and lateral safe distances. For communication interruption risk analysis, a communication signal attenuation model is established based on vehicle distance data. When the vehicle distance exceeds a preset communication stability threshold, a communication interruption risk is identified. For collision risk analysis, the safe vehicle distance threshold is dynamically adjusted based on the current vehicle speed and road adhesion conditions. When the actual vehicle distance is lower than the dynamic safe threshold, a collision warning is triggered. By simultaneously executing the above two risk assessments, the system will simultaneously eliminate dangerous areas that may lead to communication failure or physical collision. For example, when the distance between the following vehicle and the preceding vehicle shortens to 2 meters, the system will automatically mark this area as a collision risk area. When the communication signal strength between the following vehicle and the preceding vehicle is lower than -90dBm, the system will automatically mark this area as a communication interruption risk area.

[0088] The formula for calculating the global collision safety factor is:

[0089] ,

[0090] ,

[0091] in, Let be the global collision safety factor for vehicle i. Let i be the center coordinates of vehicle i. Let be the local collision safety factor for vehicle i. This refers to the distance data between vehicle i and vehicle k. , and These are the collision distance boundaries, This is the critical collision distance data. To provide obstacle avoidance buffer distance data, This represents the total number of other vehicles.

[0092] The formula for calculating the global communication security factor is:

[0093] ,

[0094] ,

[0095] in, Let be the global communication security factor for vehicle i. Let be the local communication security factor for vehicle i. and Let R be the communication distance boundary and R be the maximum communication radius of vehicle i.

[0096] Based on the calculation formulas for the global collision safety factor and the global communication safety factor, as well as the predefined collision distance boundaries corresponding to areas without collision risk and the communication distance boundaries corresponding to areas without communication interruption risk, the collision risk and communication interruption risk of each vehicle are comprehensively analyzed. This process eliminates areas with collision risk and communication interruption risk, and the remaining areas in the initial passable area are taken as the current passable areas for the vehicles.

[0097] Figure 4 This is a flowchart illustrating the specific method of step S204 provided in the embodiments of this application. See also... Figure 4 In some embodiments, the method includes, but is not limited to, steps S401 to S402.

[0098] Step S401: Perform a driving safety cost analysis on the candidate paths of the navigator vehicle, and determine the target path of the navigator vehicle based on the safety cost analysis results of the candidate paths.

[0099] Driving safety cost analysis refers to calculating the safety factor of a path by quantifying potential risk factors along the route. This can be achieved using a multi-dimensional weighted superposition model. For example, the rate of change of road surface adhesion coefficient, obstacle distribution density, and communication signal strength can be used as evaluation parameters.

[0100] The target path for the lead vehicle refers to the candidate path with the lowest risk value after being screened through driving safety cost analysis. Specifically, this can be achieved using a cost function minimum comparison algorithm. For example, a dynamic programming algorithm can be used to iterate through the cost calculation results of all candidate paths.

[0101] The expression for analyzing the driving safety cost of the candidate paths for the lead vehicle is as follows:

[0102] ,

[0103] ,

[0104] ,

[0105] ,

[0106] in, The total cost index of the candidate paths for the lead vehicle. The safety cost index of the candidate path for the lead vehicle. The driving cost index for the candidate routes of the lead vehicle. and These are the cost weights, , Let $o$ be the $o$-th path point of the candidate path, $o \in [1, 2000, ], This represents the total number of path points for the candidate paths. Let $\frac{ ... This provides the road surface roughness feature risk data for the o-th path point of the candidate path. This refers to the vehicle's minimum ground clearance data. Let be the curvature of the o-th path point of the candidate path.

[0107] Step S402: Determine the path points of the following vehicles based on the target path of the lead vehicle and the preset formation maintenance parameters, so as to determine the target path of the following vehicles.

[0108] Formation maintenance parameters refer to the constraints that maintain the spacing and relative positions between vehicles in a convoy. Specifically, these can be achieved by setting preset lateral offset thresholds and longitudinal following distance ranges. For example, the lateral deviation between the following vehicle and the lead vehicle can be set to no more than 0.5 meters, and the longitudinal spacing can be maintained in the range of 3-5 meters.

[0109] After obtaining the target path of the lead vehicle, a formation target point is set. Based on preset formation maintenance parameters, waypoints for the following vehicles are generated within their current passable area to determine their target paths. Specifically, a formation control potential field and gravity are constructed to provide gravity for the following vehicles, pulling them to the waypoints. The expressions for the formation control potential field and gravity are:

[0110] ,

[0111] ,

[0112] in, To determine the gravitational potential field between the following vehicle and the target point in the formation, Let be the gravitational potential field constant generated by the path point of the following vehicle on the following vehicle. This represents the Euclidean distance between the current position of the following vehicle and the waypoints of the following vehicle. To control the gravitational potential field of the formation, To find the derivative of the control potential field of the formation.

[0113] Figure 5 This is a flowchart illustrating the specific method of step S205 provided in the embodiments of this application. (See attached document.) Figure 5In some embodiments, the method includes, but is not limited to, steps S501 to S503.

[0114] Step S501: Obtain the front adhesion coefficient and underbody adhesion coefficient of the vehicle.

[0115] Step S502: Calculate the rate of change of adhesion coefficient between vehicles based on the front adhesion coefficient of the following vehicle and the under-vehicle adhesion coefficient of the preceding vehicle.

[0116] Step S503: Configure the vehicle's driving speed based on the rate of change of the adhesion coefficient.

[0117] The front adhesion coefficient refers to the friction coefficient of the area where the front wheels of a vehicle contact the road surface. Specifically, it is calculated by real-time collection of tire-ground contact force data using force sensors installed on the front wheels, combined with a wheel slip ratio model. It characterizes the vehicle's front wheel adhesion capability during driving. The undercarriage adhesion coefficient refers to the road surface friction coefficient of the corresponding area beneath the vehicle chassis. Specifically, it is estimated by scanning road texture information using LiDAR or vision sensors deployed under the vehicle and combining this with a pre-trained road surface friction coefficient prediction model. It reflects the real-time adhesion status of the road surface behind the vehicle. The adhesion coefficient change rate refers to the difference in adhesion coefficient in a road area before and after a vehicle passes. Specifically, it is calculated using time-series data of the adhesion coefficients of adjacent vehicles through difference operations and sliding window averaging. It is used to quantify the impact of dynamic changes in road surface adhesion status on the overall stability of the convoy.

[0118] After obtaining the front and undercarriage adhesion coefficients of each vehicle, these are constructed into corresponding matrix forms, resulting in the front and undercarriage adhesion coefficient matrices. Then, the rate of change of adhesion coefficients between vehicles is calculated based on these matrices. When there is a significant difference between the front and undercarriage adhesion coefficients of a following vehicle and the preceding vehicle, the vehicle speed is adjusted according to the rate of change of adhesion coefficients to mitigate potential risks in the longitudinal dynamics of the convoy. For example, if the following vehicle drives through a flooded area, causing a sudden drop in undercarriage adhesion coefficient, while the front wheels of the following vehicles remain on dry surfaces, the rate of change of adhesion coefficients will rise sharply. In this case, the system determines whether to trigger a speed adjustment mechanism based on a preset threshold rate of change of adhesion coefficients. By weighted calculation of the speed configuration for each following vehicle and reverse derivation of the speed limit value for the lead vehicle, the overall speed of the convoy is ultimately controlled collaboratively.

[0119] In some embodiments, step S503 specifically includes: when the rate of change of the adhesion coefficient is not less than a preset threshold rate of change of the adhesion coefficient, calculating the speed configuration amount of the following vehicle based on the rate of change of the adhesion coefficient; performing a weighted summation operation on the speed configuration amounts of each following vehicle to obtain the total speed configuration amount; calculating the speed configuration amount of the lead vehicle based on the total speed configuration amount; dynamically configuring the driving speed of the following vehicle based on the speed configuration amount of the following vehicle, and dynamically configuring the driving speed of the lead vehicle based on the speed configuration amount of the lead vehicle.

[0120] The formula for calculating the speed configuration of the following vehicle is:

[0121] ,

[0122] in, The amount of fuel to be allocated according to the speed of the vehicle. This is the global scaling factor. The maximum permissible speed for the convoy. This represents the total number of vehicles in the fleet. It is the difference in the maximum expected adhesion coefficient. For symbol vectors, These are the weighting coefficients. This represents the rate of change of the adhesion coefficient threshold.

[0123] After obtaining the speed configuration value of the following vehicle, the following vehicle is controlled to adjust from its current speed to the speed after adding the speed configuration value, thus obtaining the configured speed of the following vehicle. To ensure a smooth speed configuration of the following vehicle, its acceleration is limited, and the calculation formula is as follows:

[0124] ,

[0125] ,

[0126] in, The maximum acceleration of the following vehicle. To configure the following vehicle's speed, To configure the driving speed of the vehicle following ahead, The maximum permissible acceleration for the convoy. Configure the duration for the speed.

[0127] After configuring the following vehicle's speed, the following vehicle's speed is dynamically configured based on its configured speed amount. Then, the lead vehicle's speed is dynamically configured based on its configured speed amount. The formula for calculating the lead vehicle's speed is:

[0128] ,

[0129] in, To configure the driving speed of the rear lead vehicle, To configure the driving speed of the lead vehicle, As a normalized weighting factor, when the rate of change of the adhesion coefficient is not less than the preset threshold rate of change of the adhesion coefficient. When the rate of change of the adhesion coefficient is less than the preset threshold rate of change of the adhesion coefficient .

[0130] In some embodiments, step S503 further includes: generating a reference acceleration of the following vehicle based on the driving speed before and after the following vehicle configuration; compensating the reference acceleration of the following vehicle based on the distance error data between the following vehicle and the vehicle in front to obtain the actual acceleration of the following vehicle.

[0131] First, state-space modeling is performed for each vehicle in the convoy, resulting in a longitudinal dynamic state-space model for each vehicle:

[0132] ,

[0133] in, This is the state vector of vehicle i. Let i be the position of vehicle i. Let i be the speed of vehicle i. For process noise, To observe noise.

[0134] Based on feedforward-feedback speed synchronization, the speed controller for vehicle i adopts a two-layer structure:

[0135] 1. Feedforward control: Based on the configuration information transmitted by the lead vehicle, the following vehicle's speed is adjusted accordingly. 1. Generate a reference acceleration; 2. Based on the real-time distance error between vehicle i and vehicle i-1 Acceleration is compensated by a PID controller:

[0136]

[0137] in, To follow the actual acceleration of the vehicle, For proportional parameters, is the differential parameter.

[0138] Figure 6 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Referring below... Figure 6 To describe an electronic device 600 according to such an embodiment of the present disclosure. Figure 6 The electronic device 600 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0139] like Figure 6As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0140] The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the steps of the various exemplary embodiments of this disclosure as described in the methods described above.

[0141] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0142] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0143] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0144] Electronic device 600 can also communicate with one or more external devices 600' (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0145] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0146] The convoy driving control method, device, and storage medium provided in this application embodiment perform dynamic driving risk analysis on the road surface where the vehicles are currently traveling based on real-time road surface roughness characteristic data and vehicle dynamic characteristic data of vehicles in the convoy. Based on the driving risk analysis results, the current passable area of ​​the vehicles is determined. After generating candidate paths based on the current passable area of ​​the vehicles and determining the corresponding target path through driving safety cost analysis, the driving speed of the vehicles is dynamically configured based on the real-time vehicle adhesion coefficient of the vehicles. The vehicles are controlled to travel along the target path at the configured driving speed, thereby realizing automatic control of convoy driving. The current passable area of ​​the vehicles is determined by dynamic driving risk analysis based on real-time road surface roughness characteristic data and vehicle dynamics characteristic data. It also considers the dynamic changes of road surface roughness characteristic data and vehicle dynamics characteristic data, adapting to the dynamic planning of passable areas for each vehicle in the convoy, improving the rationality of the driving path planning for each vehicle in the convoy. After determining the target path of each vehicle, the driving speed of the vehicles is dynamically configured according to the real-time vehicle adhesion coefficient, ensuring that the driving speed of each vehicle adapts to the changes in the vehicle adhesion coefficient, avoiding the possibility of sudden changes in the adhesion coefficient causing vehicle instability, ensuring the movement stability of the convoy under complex road conditions, and improving the driving safety of the convoy.

[0147] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the methods described above according to the embodiments of this disclosure.

[0148] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0149] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0150] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified accordingly and placed in one or more devices that are unique to this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0151] Exemplary embodiments of this disclosure have been specifically shown and described above. It should be understood that this disclosure is not limited to the detailed structures, arrangements, or implementations described herein; rather, this disclosure is intended to cover various modifications and equivalent arrangements contained within the spirit and scope of the appended claims.

Claims

1. A method for controlling the movement of a convoy, characterized in that, include: Acquire real-time road surface roughness characteristic data and vehicle dynamics characteristic data of vehicles in the fleet; Based on the road surface roughness characteristic data and the vehicle dynamics characteristic data, a dynamic driving risk analysis is performed on the road surface where the vehicle is currently traveling, and the area is divided based on the driving risk analysis results to determine the current passable area of ​​the vehicle. Based on the passable area, the vehicle is route-planned to obtain several candidate routes; Perform a driving safety cost analysis on the candidate paths, and select the corresponding target path from the candidate paths based on the safety cost analysis results; The vehicle's speed is dynamically configured based on the vehicle's real-time vehicle adhesion coefficient, so that the vehicle travels along the target path at the configured speed. The step of performing dynamic driving risk analysis on the road surface where the vehicle is currently traveling, based on the road surface roughness characteristic data and the vehicle dynamics characteristic data, and dividing the area based on the driving risk analysis results, includes: Risk feature data is extracted from both the road surface roughness feature data and the vehicle dynamics feature data to obtain multidimensional risk information data; The initial passable area of ​​the vehicle is determined based on the multidimensional risk information data; Collision risk analysis and communication interruption risk analysis are performed on the initial passable area, and areas with collision risk and communication interruption risk are eliminated to determine the current passable area of ​​the vehicle. The collision risk analysis and communication interruption risk analysis of the initial passable area include: Based on the real-time distance data between the vehicle and other vehicles, the global communication safety coefficient and global collision safety coefficient of the vehicle relative to other vehicles are calculated to obtain the collision risk analysis results and communication interruption risk analysis results. Based on the collision risk analysis results and the communication interruption risk analysis results, areas with collision risk and communication interruption risk are eliminated to determine the current passable area of ​​the vehicle.

2. The convoy driving control method according to claim 1, characterized in that, The extraction of risk feature data from both the road surface roughness feature data and the vehicle dynamics feature data includes: Based on the road surface roughness feature data and the vehicle dynamics feature data, a road surface roughness risk field is constructed for the road surface where the vehicle is currently traveling. Extract pavement risk characteristic data and pavement evolution characteristic data from the pavement roughness risk field; The multidimensional risk information data is obtained by splicing together the road surface risk characteristic data, the road surface evolution characteristic data, and the vehicle dynamics characteristic data.

3. The convoy driving control method according to claim 1, characterized in that, The step of performing a driving safety cost analysis on the candidate paths and selecting a corresponding target path from the candidate paths based on the safety cost analysis results includes: A driving safety cost analysis is performed on the candidate paths of the navigator vehicle, and the target path of the navigator vehicle is determined based on the safety cost analysis results of the candidate paths of the navigator vehicle. The path points of the following vehicles are determined based on the target path of the lead vehicle and the preset formation maintenance parameters, so as to determine the target path of the following vehicles.

4. The convoy driving control method according to claim 1, characterized in that, The method of dynamically configuring the vehicle's speed based on the vehicle's real-time vehicle adhesion coefficient includes: Obtain the front adhesion coefficient and underbody adhesion coefficient of the vehicle; The rate of change of the adhesion coefficient between the vehicles is calculated based on the front adhesion coefficient of the following vehicle and the undercarriage adhesion coefficient of the preceding vehicle. The vehicle's travel speed is configured based on the rate of change of the adhesion coefficient.

5. The convoy driving control method according to claim 4, characterized in that, The step of configuring the vehicle's driving speed based on the rate of change of the adhesion coefficient includes: When the rate of change of the adhesion coefficient is not less than the preset threshold rate of change of the adhesion coefficient, the speed configuration amount of the following vehicle is calculated based on the rate of change of the adhesion coefficient. The total speed configuration is obtained by performing a weighted summation on the speed configurations of each of the following vehicles. Calculate the speed configuration amount of the lead vehicle based on the total speed configuration amount; The driving speed of the following vehicle is dynamically configured based on the speed configuration of the following vehicle, and the driving speed of the lead vehicle is dynamically configured based on the speed configuration of the lead vehicle.

6. The convoy driving control method according to claim 5, characterized in that, The method of configuring the vehicle's driving speed based on the rate of change of the adhesion coefficient further includes: The reference acceleration of the following vehicle is generated based on the driving speed before and after the following vehicle configuration; The baseline acceleration of the following vehicle is compensated based on the distance error data between the following vehicle and the vehicle in front, so as to obtain the actual acceleration of the following vehicle.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images