Vehicle control method, storage medium, program product, controller and vehicle

Abstract

The invention relates to a vehicle control method, a storage medium, a program product, a controller and a vehicle, and relates to the field of vehicle control. The vehicle control method mainly comprises the steps that the target driving style of a current vehicle is determined based on the driving style of the current vehicle and the driving styles of surrounding vehicles, and the surrounding vehicles are vehicles located within the preset distance around the current vehicle; according to the technical scheme, the driving style of the current vehicle is reserved, the driving styles of the surrounding vehicles are comprehensively analyzed and considered, the driving preference and habits of the driver and the driving styles of the surrounding vehicles are fused, dynamic optimization and self-adaptive adjustment of the target driving style of the current vehicle are achieved, and the driving experience of the driver is improved. And the vehicle is intelligently controlled based on the target driving style, so that the driving intelligence is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control, and in particular to a vehicle control method, storage medium, program product, controller and vehicle. Background Art

[0002] In related technologies, vehicle driving strategies primarily rely on passively responding to environmental changes, often making decisions by simply imitating the driving styles of surrounding vehicles. This simple imitation or fixed-pattern driving approach is unlikely to meet the requirements of modern intelligent driving systems. Summary of the Invention

[0003] Embodiments of the present application provide a vehicle control method, storage medium, program product, controller, and vehicle to at least partially solve the above-mentioned technical problems.

[0004] In order to achieve the above-mentioned purpose, according to the first aspect of the present application, a vehicle control method is provided, including: determining a target driving style of the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles; controlling the vehicle based on the target driving style; wherein the surrounding vehicles are vehicles located within a preset distance around the current vehicle.

[0005] Optionally, controlling the vehicle includes at least one of the following: controlling the air-conditioning system of the vehicle, controlling the display interface of the vehicle, controlling the light display of the vehicle, and controlling the motor data of the vehicle.

[0006] Optionally, the driving style includes at least one of the following: a conservative style, a general style, and an aggressive style.

[0007] Optionally, the method further includes: when the current vehicle is in a non-automatic driving state, determining the driving style of the current vehicle based on the self-driving data of the current vehicle.

[0008] Optionally, the vehicle driving data includes real-time driving data and historical driving data.

[0009] Optionally, the self-vehicle driving data includes at least one of the following: speed, acceleration, headway, lane change frequency, lane deviation, and yaw rate.

[0010] Optionally, the method further includes: determining the driving styles of the surrounding vehicles and the weights of the surrounding vehicles based on a group potential field including the current vehicle.

[0011] Optionally, determining the weights of the surrounding vehicles based on the group potential field including the current vehicle includes: determining a preset range of the group potential field based on a preset rule; and determining the weights of different surrounding vehicles within the group potential field according to at least two different preset ranges.

[0012] Optionally, the preset rule includes: the distance between the surrounding vehicles and the current vehicle.

[0013] Optionally, the surrounding vehicles located within the same preset range have the same weight.

[0014] Optionally, the weights of the surrounding vehicles located in different preset ranges are different.

[0015] Optionally, the preset range includes at least a first preset range and a second preset range; within the first preset range, the distance between the first surrounding vehicle and the current vehicle is less than or equal to the first distance, and the first surrounding vehicle has a first weight; within the second preset range, the distance between the second surrounding vehicle and the current vehicle is greater than the first distance, and the second surrounding vehicle has a second weight; the first weight is greater than the second weight.

[0016] Optionally, the preset range has a preset shape, and the preset shape is determined according to the preset rule.

[0017] Optionally, determining the driving style of the surrounding vehicles based on the group potential field including the current vehicle includes: acquiring driving data of different surrounding vehicles in the group potential field; and determining the driving style of the surrounding vehicles based on the driving data of the surrounding vehicles.

[0018] Optionally, the surrounding vehicles include at least one of the following: a front vehicle, a rear vehicle, and left and right adjacent vehicles; wherein, along the driving direction of the current vehicle, the front vehicle is the vehicle located in front of the current vehicle, the rear vehicle is the vehicle located behind the current vehicle, and the left and right adjacent vehicles are vehicles located on the left and / or right side of the current vehicle.

[0019] Optionally, the obtaining of driving data of different surrounding vehicles in the group potential field includes at least one of the following: obtaining first driving data of the vehicle in front; obtaining second driving data of the vehicle behind; and obtaining third driving data of the left and right neighboring vehicles.

[0020] Optionally, the first driving data includes at least one of the following: longitudinal acceleration, lateral speed, lateral acceleration; the second driving data includes at least one of the following: headway, longitudinal speed, longitudinal acceleration; the third driving data includes at least one of the following: headway, longitudinal speed, longitudinal acceleration, lateral speed, lateral acceleration.

[0021] Optionally, determining the driving style of the surrounding vehicles based on the driving data of the surrounding vehicles includes at least one of the following: inputting the first driving data into a first driving style recognition model, and determining a first driving style corresponding to the vehicle in front according to a value output by the first driving style recognition model; inputting the second driving data into a second driving style recognition model, and determining a second driving style corresponding to the vehicle behind according to a value output by the second driving style recognition model; inputting the third driving data into a third driving style recognition model, and determining a third driving style corresponding to the left and right neighboring vehicles according to a value output by the third driving style recognition model.

[0022] Optionally, determining the target driving style of the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles includes: determining the target driving style of the current vehicle based on the driving style of the current vehicle, the driving styles of the surrounding vehicles and weights of the surrounding vehicles.

[0023] Optionally, controlling the vehicle based on the target driving style includes: determining a motor required torque of the current vehicle based on the target driving style.

[0024] Optionally, determining the motor required torque of the current vehicle based on the target driving style includes: determining the torque load coefficient of the current vehicle based on the target driving style and the accelerator pedal parameters of the current vehicle; and determining the motor required torque of the current vehicle based on the torque load coefficient.

[0025] According to a second aspect of the present application, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps of the above-mentioned vehicle control method are implemented.

[0026] According to a third aspect of the present application, a computer program product is provided, comprising a computer program or instructions, which implement the steps of the above-mentioned vehicle control method when executed by a processor.

[0027] According to a fourth aspect of the present application, a controller is provided, on which a computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the steps of the above-mentioned vehicle control method are implemented.

[0028] According to a fifth aspect of the present application, a vehicle is provided, comprising the above-mentioned controller.

[0029] The present application relates to a vehicle control method, storage medium, program product, controller, and vehicle, and relates to the field of vehicle control. The vehicle control method primarily comprises determining a target driving style for the current vehicle based on the current vehicle's driving style and the driving styles of surrounding vehicles, where surrounding vehicles are defined as those located within a preset distance from the current vehicle. Through the above-described technical solution, while preserving the current vehicle's own driving style, the driving styles of surrounding vehicles are comprehensively analyzed and considered. By integrating the driver's driving preferences and habits with the driving styles of surrounding vehicles, dynamic optimization and adaptive adjustment of the current vehicle's target driving style are achieved, and intelligent vehicle control is performed based on the target driving style, effectively enhancing driving intelligence.

[0030] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0032] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same drawing numbers represent the same parts in the following description.

[0033] Figure 1 This is a flowchart of the steps of a vehicle control method provided by an embodiment of the present application;

[0034] Figure 2 This is a schematic diagram of a system framework of a vehicle control method provided by an embodiment of the present application;

[0035] Figure 3 is a flowchart of another vehicle control method provided by an embodiment of the present application;

[0036] Figure 4a is a schematic diagram of a group potential field provided in an embodiment of the present application;

[0037] Figure 4b is a schematic diagram of another group potential field provided in an embodiment of the present application;

[0038] Figure 5 is a three-dimensional control schematic diagram of a vehicle control method provided in an embodiment of the present application;

[0039] Figure 6 This is a schematic diagram of the architecture of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0041] This application provides a vehicle control method, please refer to Figure 1 and Figure 2 , Figure 1 This is a flow chart of a vehicle control method provided by an embodiment of the present application, including step S100 and step S200. Figure 2 This is a system framework diagram of a vehicle control method provided in an embodiment of the present application, which is introduced in detail below.

[0042] Step S100: determining a target driving style of the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles;

[0043] Step S200: Control the vehicle based on the target driving style; wherein the surrounding vehicles are vehicles located within a preset distance around the current vehicle.

[0044] The mode configuration module integrates and balances the current vehicle's own driving style and the driving styles of surrounding vehicles within a preset distance around the current vehicle, and collaboratively determines the optimal driving style, namely the target driving style. After determining the vehicle's target driving style, the vehicle can be controlled according to the target driving style to achieve intelligent control of the vehicle under the target driving style. Through the above-mentioned technical solution, the embodiment of the present application retains the current vehicle's own driving style while comprehensively analyzing and considering the driving styles of surrounding vehicles. By integrating the driver's driving preferences and habits with the driving styles of surrounding vehicles, it achieves dynamic optimization and adaptive adjustment of the current vehicle's target driving style, and intelligently controls the vehicle based on the target driving style, effectively improving the intelligence of driving.

[0045] In some embodiments, controlling the vehicle in the above step S200 may include at least one of the following: controlling the air conditioning system of the vehicle, controlling the display interface of the vehicle, controlling the lighting display of the vehicle, and controlling the motor data of the vehicle.

[0046] For example, target driving style-based vehicle control can include the following implementations: The vehicle's powertrain (e.g., motor data) can be adjusted based on the determined target driving style, optimizing the vehicle's power output to achieve smooth acceleration and deceleration, reduce energy consumption, extend range, and improve energy efficiency. Air conditioning temperature, wind speed, and seat position can be intelligently adjusted to enhance driver and passenger comfort based on different target driving styles. Interface display optimization can be implemented to provide real-time traffic information and necessary prompts to help drivers better navigate traffic conditions. The vehicle's lighting display (e.g., brightness or warning light usage) can also be controlled to provide reminders and warnings to the driver and surrounding vehicles. Applying intelligent vehicle control based on target driving style provides reliable support for smarter and safer modern driving.

[0047] In some embodiments, the driving style includes at least one of the following: a conservative style, a normal style, and an aggressive style.

[0048] Driving styles can generally be categorized into the following types, each with its own unique characteristics and applicable scenarios:

[0049] A conservative driving style is a steady and cautious approach. Drivers typically drive at lower speeds, maintain a safe distance, and avoid sudden acceleration or braking. This driving style prioritizes safety and stability, making it suitable for complex road conditions and heavy traffic, and effectively reduces the risk of traffic accidents.

[0050] A "normal" driving style is a balanced and neutral approach. The driver adjusts speed according to traffic conditions, typically maintaining a moderate speed and a safe distance from surrounding vehicles. This driving style is neither overly aggressive nor overly conservative and is often seen in daily commutes or long-distance driving.

[0051] An aggressive driving style is characterized by fast, decisive movements. The driver tends to drive at higher speeds, frequently changing lanes to overtake, and applying sudden acceleration and braking when necessary. While this style can achieve a destination quickly, it can compromise safety and comfort. It's best suited to situations where road conditions are good and time is of the essence.

[0052] These three driving styles have their own characteristics, and the appropriate driving style can be selected according to the driver's habits, preferences and traffic environment. It should be understood that the driving style of the current vehicle and the driving style of the surrounding vehicles can be one of the above three types, and this application does not limit this.

[0053] See also Figure 3 , Figure 3 This is a flowchart of another vehicle control method provided by an embodiment of the present application. Figure 3As shown, in some embodiments, the vehicle control method further includes the following steps:

[0054] Step S110: When the current vehicle is in a non-automatic driving state, determine the driving style of the current vehicle based on the current vehicle's own driving data.

[0055] In some embodiments, the vehicle driving data includes real-time driving data and historical driving data.

[0056] In some embodiments, the self-vehicle driving data includes at least one of the following: speed, acceleration, headway, lane change frequency, lane deviation, and yaw rate.

[0057] The driving style recognition module can determine whether the current vehicle is in an autonomous driving state. If it is determined that the current vehicle is in a non-autonomous driving state, the driving style recognition module will output the current vehicle's current state driving style S based on the real-time driving data collected in real time and the stored historical driving data, such as speed, acceleration, headway, lane change frequency, lane deviation, yaw angular velocity, etc. style , such as conservative driving style, general driving style and aggressive driving style; if it is determined that the current vehicle is in the automatic driving state, the driving style recognition module directly outputs the driving style S of the current state of the current vehicle style It is automatic driving. It should be understood that speed can be used to adjust vehicle distance and judge driving behavior; acceleration can be used to evaluate the vehicle's power output and driving stability; headway can be used to ensure a safe distance and reduce collision risks; lane change frequency can be used to optimize traffic flow management and reflect the driver's lane change habits; lane deviation can be used to detect driver distraction or fatigue driving; yaw angular velocity can be used to evaluate vehicle steering stability and maneuverability. Based on the vehicle's self-driving data, the current vehicle's driving style can be determined. Currently, self-driving data can also include other driving data related to the current vehicle. The above self-driving data is used as a specific example. In actual use, specific selection can be made according to vehicle needs. This application does not limit this.

[0058] For example, codes 0 to 10 can be used to represent driving styles, where code 0 represents autonomous driving, codes 1 to 3 represent conservative driving styles, codes 4 to 6 represent normal driving styles, and codes 7 to 10 represent aggressive driving styles. Larger code values ​​indicate more aggressive driving styles. It should be understood that the above codes are merely examples, and the actual code range and the code corresponding to each driving style can be set based on actual usage requirements, and this application does not impose any limitations on this.

[0059] It should be understood that the current vehicle's self-driving data can be acquired and preliminarily processed through the data acquisition and processing module. Specifically, the data acquisition and processing module continuously receives input information from multi-source perception systems, including: an environmental perception system that captures dynamic changes in the surrounding traffic environment in real time; a driver behavior perception system that collects multimodal data such as the driver's facial features, hand movements, and driving behavior, including image data, point cloud data, and text information; a positioning and navigation system that obtains high-precision electronic map data and real-time vehicle location information; and a vehicle dynamic data transmission bus that collects key performance parameters such as vehicle speed, acceleration, throttle opening, and steering wheel angle. After receiving the above-mentioned multi-source heterogeneous data, the data acquisition and processing module will perform preliminary processing such as data fusion and spatiotemporal alignment, heterogeneous data format conversion, and structured storage.

[0060] The driving style recognition module obtains the corresponding driving data from the data acquisition and processing module according to the vehicle's needs, and processes the above driving data accordingly according to the preset model. The processed data is input into the driving style recognition module, which can accurately identify the current vehicle's own driving style S style , providing a reliable basis for the adjustment of subsequent driving strategies.

[0061] In some embodiments, continue to refer to Figure 3 , the vehicle control method further includes the following steps:

[0062] Step S120: Determine the driving styles of surrounding vehicles and the weights of surrounding vehicles based on the group potential field including the current vehicle.

[0063] The group driving style dynamic potential field construction module can construct a group potential field including the current vehicle and determine the driving style Y of the surrounding vehicles. style and the corresponding weight w.

[0064] In some embodiments, determining the weights of surrounding vehicles in step S120 includes the following steps:

[0065] Step S121: determining a preset range of the group potential field based on a preset rule;

[0066] Step S122: Determine the weights of different surrounding vehicles in the group potential field according to at least two different preset ranges.

[0067] The preset rules may be determined based on the configuration of different vehicles. In some embodiments, the preset rules include: the distance between the surrounding vehicles and the current vehicle. Exemplarily, the maximum distance that can be detected by the radar and / or video sensor and other equipment carried by the current vehicle may be set as a preset rule to determine the preset range of the group potential field, thereby ensuring that all surrounding vehicles that may affect the driving behavior of the current vehicle are covered. In addition to the distance between the surrounding vehicles and the current vehicle, the preset rules may also include the shape of the preset range. In some embodiments, the preset range has a preset shape, and the preset shape is determined according to the preset rules. Exemplarily, the preset shape may be a circle, or other regular or irregular geometric shapes such as a square. The preset range may be the range of the group potential field calibrated with a preset shape within the maximum distance that the current vehicle can detect. This application does not limit this.

[0068] After determining the preset range of the group potential field in step S121, the weights of different surrounding vehicles within the group potential field can be further determined based on at least two different preset ranges. For example, the at least two different preset ranges can be determined based on the distance between the surrounding vehicles and the current vehicle. In some embodiments, the preset ranges include at least a first preset range and a second preset range. Within the first preset range, if the distance between a first surrounding vehicle and the current vehicle is less than or equal to the first distance, the first surrounding vehicle is assigned a first weight. Within the second preset range, if the distance between a second surrounding vehicle and the current vehicle is greater than the first distance, the second surrounding vehicle is assigned a second weight. The first weight is greater than the second weight. Through step S122, different weights w are assigned to vehicles within the group potential field. The closer a neighboring vehicle is to the current vehicle, the greater its likelihood of impacting the current vehicle. Furthermore, the more accurately the current vehicle acquires data about the neighboring vehicle, and therefore, the vehicle can be assigned a higher weight w. Neighboring vehicles farther from the current vehicle are less likely to impact the current vehicle, and therefore, can be assigned a lower weight w.

[0069] For example, see Figure 4a and Figure 4b The preset shape is a circle, and the first preset range can be a circle with a radius of 5m and a center of mass of the current vehicle. Figure 4a and Figure 4b As shown in the green circle area, the first weight is assigned to the first surrounding vehicle within the first preset range; the second preset range can be a circle with a radius of 9m and a center of mass of the current vehicle, such as Figure 4a and Figure 4b As shown in the red circle area, a second weight is assigned to the second surrounding vehicle located within the second preset range.

[0070] It should be understood that in some embodiments, the weights of surrounding vehicles within the same preset range are the same. Figure 4a and Figure 4b As shown in the middle green circle area, the first surrounding vehicles located within the first preset range are assigned the same first weight, and the second surrounding vehicles located within the second preset range are assigned the same second weight.

[0071] In some embodiments, the weights of surrounding vehicles within different preset ranges are different.

[0072] For example, Figure 4a and Figure 4b As shown in the middle green circle area, a first weight is assigned to a first surrounding vehicle located within the first preset range, and a second weight is assigned to a second surrounding vehicle located within the second preset range. The first weight and the second weight are different, so that the weights of surrounding vehicles located within different first preset ranges and second preset ranges are different.

[0073] The same first weight can be assigned to the first surrounding vehicle within the first preset range, and the same second weight can be assigned to the second surrounding vehicle within the second preset range, with the first weight being greater than the second weight. This allows vehicles closer to the current vehicle to be assigned a higher weight w, and vehicles farther from the current vehicle to be assigned a lower weight w, based on the magnitude of the impact that the surrounding vehicles may have on the current vehicle. Of course, different weights can also be assigned to surrounding vehicles within the same preset range, or the same weight can be assigned to surrounding vehicles within different preset ranges. This can be flexibly adjusted based on actual vehicle needs, and this application does not limit this.

[0074] Through the above steps, a scientific assessment can be made based on the degree of influence of surrounding vehicles on the current vehicle in a complex traffic environment, providing reliable data support for the subsequent adaptive adjustment of the current vehicle's driving style.

[0075] In some embodiments, determining the driving styles of surrounding vehicles in step S120 includes the following steps:

[0076] Step S123: Acquire driving data of different surrounding vehicles in the group potential field;

[0077] Step S124: Determine the driving style of the surrounding vehicles based on the driving data of the surrounding vehicles.

[0078] The group driving style dynamic potential field construction module extracts different driving data for different surrounding vehicles within a preset range of the group potential field, and determines the driving styles of the different surrounding vehicles based on the driving data of the different surrounding vehicles. In some embodiments, the surrounding vehicles include at least one of the following: a front vehicle, a rear vehicle, and left and right neighboring vehicles; wherein, along the current vehicle's direction of travel, the front vehicle is the vehicle located in front of the current vehicle, the rear vehicle is the vehicle located behind the current vehicle, and the left and right neighboring vehicles are the vehicles located to the left and / or right of the current vehicle. Within the preset range of the current vehicle, there may be neighboring vehicles located in different directions of the current vehicle, specifically including one or more of the front vehicle, the rear vehicle, and the left and right neighboring vehicles. For example, within the preset range of the current vehicle, there may be other vehicles driving only in front or behind, only on the left and right sides, or there may be other vehicles driving in front, behind, and on both the left and right sides, and this application does not limit this.

[0079] In some embodiments, the above step S123 includes at least one of the following steps:

[0080] Step S1231: Acquire first driving data of the vehicle ahead;

[0081] Step S1232: Acquire second driving data of the rear vehicle;

[0082] Step S1233: Acquire the third driving data of the left and right neighboring vehicles.

[0083] Neighboring vehicles at different positions in front, behind, left, and right of the current vehicle within the preset range will have different degrees of impact on the driving of the current vehicle and present different risk characteristics. Therefore, different driving data needs to be selected for neighboring vehicles at different positions in front, behind, left, and right of the current vehicle within the preset range to accurately assess the impact of the neighboring vehicle on the current vehicle.

[0084] It should be understood that the driving data of the surrounding vehicles can be extracted by the data acquisition and processing module, which can input the driving data related to the surrounding vehicles it has acquired into the group driving style dynamic potential field construction module. The group driving style dynamic potential field construction module extracts the first driving data, the second driving data and the third driving data for the front vehicle, the rear vehicle and the left and right neighboring vehicles at different positions of the current vehicle in the group potential field. The first driving data can be expressed as The second driving data can be expressed as The third driving data can be expressed as in, is the i-th first driving data, is the i-th second driving data, is the third driving data of the i-th time. It should be noted that real-time driving data is random, and driving data over a period of time is more meaningful for measuring the target driving style of the current vehicle. Therefore, the driving data can be the feature data of the original driving data s after time window processing For example, the original driving data of the vehicle's yaw rate is processed into the maximum yaw rate within 5 seconds before the current time point, and the corresponding driving data at this time is the maximum yaw rate.

[0085] In some embodiments, the first driving data includes at least one of the following: longitudinal acceleration, lateral speed, lateral acceleration; the second driving data includes at least one of the following: headway, longitudinal speed, longitudinal acceleration; the third driving data includes at least one of the following: headway, longitudinal speed, longitudinal acceleration, lateral speed, lateral acceleration.

[0086] For example, when selecting driving data of neighboring vehicles at different positions in front, behind, left, and right of the current vehicle within a preset range, it is necessary to consider the risks they may bring to the current vehicle and make appropriate selections.

[0087] The risk to the current vehicle from a vehicle ahead of it, along its travel direction, primarily stems from its longitudinal motion. This vehicle is difficult to predict, and its variable deceleration and braking behavior increases the risk of collision with the current vehicle. Therefore, the longitudinal acceleration of the vehicle ahead is used as the first driving data. Furthermore, attention should be paid to the lateral motion of the vehicle ahead. If the lateral velocity and lateral acceleration of the vehicle ahead are high, this indicates that the driver of the vehicle ahead may have an impatient driving style, tending to pursue high speeds through lane changes and overtaking. This driver may have poor control over the vehicle, making the vehicle ahead more prone to skidding or rolling over, and thus increasing the risk of collision with the current vehicle. Therefore, the lateral velocity and lateral acceleration of the vehicle ahead are used as the first driving data. Based on the above analysis, the first driving data for the vehicle ahead can be determined as {longitudinal acceleration, lateral velocity, lateral acceleration}. It should be understood that the first driving data may include only longitudinal acceleration, or may include lateral speed, lateral acceleration and longitudinal acceleration. Of course, the first driving data may also include other driving data related to the vehicle in front, which is not limited in this application.

[0088] The risk posed to the current vehicle by a vehicle behind it in its direction of travel primarily stems from its ability to maintain a safe distance. The headway distance directly reflects the safe distance between the vehicle behind and the current vehicle, so the headway distance is used as the second driving data. Furthermore, the longitudinal velocity and longitudinal acceleration, which are directly related to longitudinal motion, reflect the longitudinal stability of the vehicle behind and can also measure the driver's tendency to reduce the distance between the vehicle behind and the current vehicle. Poorer longitudinal stability indicates a greater tendency for the driver of the vehicle behind to reduce the distance between the vehicle behind and the current vehicle, which increases the risk of a rear-end collision. Therefore, the longitudinal velocity and longitudinal acceleration of the vehicle behind can be used as the second driving data. Based on the above analysis, the second driving data of the vehicle behind can be determined as {headway distance, longitudinal velocity, longitudinal acceleration}. It should be understood that the second driving data may include only the headway distance, or it may include the headway distance, longitudinal velocity, and longitudinal acceleration. Of course, the second driving data may also include other driving data related to the vehicle behind, and this is not limited in this application.

[0089] Along the direction of travel of the current vehicle, the risk to the current vehicle from the left and / or right neighboring vehicles on the current vehicle mainly comes from lateral movement, and their longitudinal movement also needs to be paid attention to. The left and right neighboring vehicles with poor longitudinal stability are more likely to collide with the vehicle in front or behind them, etc. Friction. When the left and right neighboring vehicles suddenly brake, stop, or collide, they may often affect other vehicles in a certain area around them due to a chain reaction. Therefore, the third driving data of the left and right neighboring vehicles can be determined as {headway distance, longitudinal speed, longitudinal acceleration, lateral speed, lateral acceleration}. It should be understood that the third driving data can only include the headway distance, or only include the headway distance, longitudinal speed and longitudinal acceleration, or can also include the headway distance, longitudinal speed, longitudinal acceleration, lateral speed and lateral acceleration. Of course, the third driving data can also include other driving data related to the left and right neighboring vehicles, and this application does not limit this.

[0090] Different driving data is selected for the vehicle in front, the vehicle behind, and the left and right adjacent vehicles based on the possible risks they may bring to the current vehicle. This not only reflects the dynamic relationship between the relative effects of vehicles, but is also not restricted by working conditions and the number of surrounding vehicles, providing an accurate and real-time basis for deciding the target driving style of the current vehicle.

[0091] In some embodiments, the above step S124 includes at least one of the following steps:

[0092] Step S1241: inputting the first driving data into a first driving style recognition model, and determining a first driving style corresponding to the preceding vehicle based on a value output by the first driving style recognition model;

[0093] Step S1242: inputting the second driving data into a second driving style recognition model, and determining a second driving style corresponding to the rear vehicle based on a value output by the second driving style recognition model;

[0094] Step S1243: inputting the third driving data into a third driving style recognition model, and determining the third driving styles corresponding to the left and right neighboring vehicles based on the values ​​output by the third driving style recognition model.

[0095] The group driving style dynamic potential field construction module extracts the first driving data, the second driving data and the third driving data for the front vehicle, the rear vehicle and the left and right neighboring vehicles at different positions of the current vehicle, and inputs them into the pre-trained and verified first driving style recognition model J. a , the second driving style recognition model J b And the third driving style recognition model J c In the example, the first driving style of the front vehicle, the second driving style of the rear vehicle, and the third driving style of the left and right neighboring vehicles are obtained respectively.

[0096] For example, to accurately capture and analyze the driving characteristics of the drivers of surrounding vehicles, a special type of neural network method, Generalized Regression Neural Network (GRNN), can be used. It can approximate any complex nonlinear relationship through non-parametric methods and process the complex driving style data of surrounding vehicles. As a specific example, taking the vehicle in front as an example, a first driving data set S with a sample number n is constructed. a , forming a [n×m] data matrix as input X, and the corresponding driving style observations constitute the input X0. The number of these driving style observations is n, and the true value of the driving style of the vehicle is obtained by the driving style recognition system of the vehicle in front. Figure 4a and 4b As shown in the figure, the numbers on the surrounding vehicles within the group potential field represent the driving style observations corresponding to these vehicles. During the prediction phase, X0 is input into the GRNN model, and the predicted output Y(X0) is calculated using the internal weights and biases. To establish the regression relationship, a joint probability density function f(X, Y) is used to represent the regression relationship between input X and predicted output Y. The Parzen nonparametric estimation method is used to estimate the joint probability density function f(X0, Y), without assuming the form of the data distribution.

[0097] Through a series of mathematical derivations and simplifications, we can obtain two formulas:

[0098] Formula (1), distance measurement formula:

[0099]

[0100] Where m is the dimension of the input variable X, and σ is the smoothing factor (similar to the standard deviation in the Gaussian function). i is the neural network input corresponding to the i-th calculation sample, X 0j Input the jth dimension of X0 for the training sample dataset, X ij The input X corresponding to the i-th calculation sample i The jth dimension of .

[0101] Formula (2), prediction output formula:

[0102]

[0103] Among them, Y is the calculated driving style prediction value, Y i represents the neural network output corresponding to the i-th calculation sample. The numerator of formula (2) is Y obtained from all samples in the training set. i The weighted sum of is the weight.

[0104] Using the above formula, a predicted driving style value Y(X0) can be calculated, i.e., the value output by the first driving style recognition model, thereby determining the first driving style of the preceding vehicle. For example, the value can range from 0 to 10, representing different driving styles of the preceding vehicle, but this application does not limit this. Using the above method, the non-parametric GRNN method can be used to predict the driving styles of surrounding vehicles based on input data, improving prediction accuracy and increasing flexibility, making it applicable to different application scenarios and data types.

[0105] It should be understood that the above prediction process is only used as the first driving style recognition model J a A construction example, specifically, the first driving style recognition model J a , the second driving style recognition model J b And the third driving style recognition model J c A variety of deep learning and traditional machine learning model frameworks can also be used, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and pre-trained deep learning models. The appropriate model can be selected based on the application scenario and the type of driving data to optimize prediction accuracy and system performance.

[0106] Through the above steps, the driving characteristics of the drivers of surrounding vehicles can be effectively captured and analyzed, thereby constructing an accurate group potential field and providing reliable support for autonomous driving decision-making.

[0107] In some embodiments, the above step S100 includes the following steps:

[0108] Step S130: Determine a target driving style of the current vehicle based on the driving style of the current vehicle, the driving styles of surrounding vehicles, and the weights of the surrounding vehicles.

[0109] The driving styles of surrounding vehicles and their corresponding weight sets are in, is the driving style of the i-th surrounding vehicle, W i The weight corresponding to the i-th surrounding vehicle. The driving style of surrounding vehicles and the corresponding weight set A dynamic driving style that constitutes a group potential field.

[0110] The mode configuration module is based on the current vehicle's own driving style S style and the dynamic driving style of the group potential field (i.e., the set of driving styles and corresponding weights of the surrounding vehicles in the current vehicle group potential field) Determine the target driving style Z of the current vehicle style , target driving style Z style The optimal driving style is determined by balancing the current vehicle and group potential fields, and collaboratively deciding on the optimal driving style. This decision-making method can employ various machine learning methods, such as multivariate linear weighting and neural networks.

[0111] For example, a neural network method is used to achieve collaborative decision-making of the current vehicle and the group potential field. The input layer of the neural network receives the current vehicle's own driving style S style Dynamic driving style with group potential field As input, the hidden layer of the neural network uses a multi-layer perceptron structure to perform nonlinear transformation and feature extraction on the input data to capture the complex relationship between driving styles. The output layer of the neural network outputs the optimal target driving style Z style To make the output of the neural network approach the optimal target driving style, a large amount of actual driving data can be used as samples. Through the backpropagation algorithm and gradient descent optimization method, the weights and biases of the neural network are continuously adjusted to train the model. At the same time, regularization, dropout and other techniques are used to prevent overfitting of the neural network model and improve generalization ability.

[0112] Through the above steps, the weighted fusion decision of the current vehicle's own driving style and the dynamic driving style of the group potential field can not only reflect the dynamic relationship between the relative effects of vehicles in the group potential field, but also comprehensively and in real time show the dynamic changes of the driving style environment including the current vehicle, without being restricted by working conditions and the number of surrounding vehicles, providing an accurate and real-time basis for deciding the optimal target driving style for the current vehicle.

[0113] In some embodiments, the above step S200 may include the following steps:

[0114] Step S140: Determine the motor torque required by the current vehicle based on the target driving style.

[0115] The mode configuration module determines the optimal target driving style Z for the current vehicle style The driving torque decision and calculation module can be based on the target driving style Z style Determine the motor torque T of the current vehicle, so as to drive the current vehicle using the motor torque T with the target driving style Z style Driving, thus completing the entire control process.

[0116] In some embodiments, the above step S140 includes the following steps:

[0117] Step S141: determining a torque load factor of the current vehicle based on the target driving style and the accelerator pedal parameters of the current vehicle;

[0118] Step S142: Determine the current motor torque required by the vehicle based on the torque load coefficient.

[0119] It should be understood that throttle pedal parameters may include throttle opening (i.e., accelerator pedal opening) and throttle pedal acceleration. Throttle opening (i.e., accelerator pedal opening) refers to the degree or angle to which the driver depresses the accelerator pedal, directly reflecting the driver's intention to accelerate the vehicle, and can be measured using sensor signals such as position sensors or angle sensors. Accelerator pedal acceleration refers to the vehicle acceleration caused by the driver operating the accelerator, reflecting the actual power changes of the vehicle, and real-time acceleration data can be obtained using an on-board accelerometer.

[0120] In step S141, the driving torque decision and calculation module obtains the target driving style Z style The current vehicle's accelerator pedal parameters are used to determine the current vehicle's medium torque load coefficient L. For example, the current vehicle's accelerator pedal parameters use the accelerator pedal opening, referring to Figure 5 As shown, Figure 5 is a three-dimensional control schematic diagram of a vehicle control method provided in an embodiment of the present application. Specifically, Figure 5It is a preset driving style-accelerator pedal opening-torque load factor three-dimensional diagram based on the current vehicle's target driving style Z style The appropriate torque load coefficient L for the current vehicle is obtained by interpolating the above three-dimensional graph with the accelerator pedal opening. style The value range is from 0 to 10, where 0 represents automatic driving and the larger the value, the more aggressive the driving style. The unit of accelerator pedal opening is %, which reflects the degree of opening of the throttle system. The torque load coefficient L ranges from 0 to 1.

[0121] In step S142, based on the current vehicle suitable torque load factor L obtained in step S141, the current vehicle motor required torque T is determined. Specifically, the current vehicle motor required torque T can be calculated according to the electric vehicle drive torque control characteristic formula to complete the entire control process.

[0122] The electric vehicle driving torque control characteristic formula satisfies the following relationship:

[0123]

[0124] Where: T(L,n) is the motor required torque; L is the torque load factor; T max is the maximum torque corresponding to the current motor speed; n represents the motor speed; n0 represents the rated speed.

[0125] Through the above steps, the motor torque required by the current vehicle can be obtained, and the current vehicle can be driven using the motor torque required T with the target driving style Z style Driving, thus completing the entire control process.

[0126] An embodiment of the present application provides a vehicle control method that, while retaining the current vehicle's own driving style, comprehensively analyzes and takes into account the driving styles of surrounding vehicles. By integrating the driver's driving preferences and habits, as well as the driving styles of surrounding vehicles, dynamic optimization and adaptive adjustment of the current vehicle's target driving style are achieved, and the vehicle is intelligently controlled based on the target driving style, effectively improving the intelligence of driving.

[0127] The vehicle control method provided in the embodiment of the present application also uses a weighted fusion decision of the current vehicle's own driving style and the dynamic driving style of the group potential field. It can not only reflect the dynamic relationship between the relative actions of vehicles in the group potential field, but also comprehensively and in real time display the dynamic changes of the driving style environment including the current vehicle, without being restricted by working conditions and the number of surrounding vehicles, and provides an accurate and real-time basis for deciding the optimal target driving style for the current vehicle.

[0128] The vehicle control method provided in the embodiments of the present application uses the vehicle's high-performance perception of neighboring vehicles' driving behavior to achieve rapid analysis and decision-making calculations that balance the vehicle's own driving style with the group's driving style. During application, there is no need to rely on external communication, effectively avoiding recognition delays and errors caused by communication problems. This ensures the continuity and stability of driving styles, especially in areas with poor signal quality, such as mountainous areas and forests. By constructing a weighted driving style group potential field, neighboring vehicles that are farther away or more severely obscured are assigned lower calculation weights, reducing problems caused by the vehicle's own perception limitations.

[0129] According to a second aspect of the present application, embodiments of the present application further provide a non-transitory computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described vehicle control method. This non-transitory computer-readable storage medium has all the beneficial effects of the above-described vehicle control method, and this application will not further elaborate on them.

[0130] According to the third aspect of the present application, an embodiment of the present application also provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed by a processor, the above-mentioned vehicle control method is implemented and has all the beneficial effects of the above-mentioned vehicle control method. This application will not go into details here.

[0131] According to a fourth aspect of the present application, embodiments of the present application further provide a controller having a computer program or instructions stored thereon; when executed by a processor, the computer program or instructions implement the steps of the aforementioned vehicle control method. The controller has all the beneficial effects of the aforementioned vehicle control method, which are not further detailed herein.

[0132] See also Figure 2 , Figure 2 This is a schematic diagram of the system framework of a vehicle control method provided in an embodiment of the present application. Figure 2As shown, in some embodiments, the controller may include a group driving style dynamic potential field construction module, a self-driving style recognition module, a mode configuration module, and a drive torque decision and calculation module. The self-driving style recognition module may be configured to execute step S110 above, determining the driving style of the current vehicle based on the self-driving data of the current vehicle when the current vehicle is in a non-autonomous driving state. The group driving style dynamic potential field construction module may be configured to construct a group potential field including the current vehicle and execute step S120 above, determining the driving styles and weights of surrounding vehicles based on the group potential field including the current vehicle. The mode configuration module may be configured to execute step S130 above, determining the target driving style of the current vehicle based on the driving style of the current vehicle, the driving styles of surrounding vehicles, and the weights of surrounding vehicles. The drive torque decision and calculation module may be configured to execute step S140 above, determining the motor required torque of the current vehicle based on the target driving style. The controller completes the entire control process through the coordinated operation of the above modules and outputs the final motor required torque for driving the vehicle.

[0133] In some embodiments, the data acquisition and processing module continuously receives input information from the multi-source perception system, and transmits the data after completing preliminary processing such as data fusion and spatiotemporal alignment, heterogeneous data format conversion, and structured storage to the driving style recognition module and the group driving style dynamic potential field construction module in the controller, respectively, to provide vehicle-related data sources.

[0134] The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof, and this application does not specifically limit this. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0135] In some embodiments of the present application, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0136] The computer-readable storage medium may be included in the controller or may exist independently without being incorporated into the controller. The computer-readable storage medium carries one or more programs, which, when executed by the controller, cause the controller to:

[0137] Determining a target driving style for the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles;

[0138] The surrounding vehicles are vehicles located within a preset distance around the current vehicle.

[0139] Computer program code for performing the operations of some embodiments of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or can be connected to an external computer (for example, using an Internet service provider to connect via the Internet).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function.

[0141] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures.

[0142] For example, two blocks shown in succession may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flow charts, and combinations of blocks in the block diagrams and / or flow charts, may be implemented using a dedicated hardware-based system that performs the specified functions or operations, or may be implemented using a combination of dedicated hardware and computer instructions.

[0143] The units described in some embodiments of the present application may be implemented in software or hardware, and may also be provided in a processor.

[0144] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and the like.

[0145] According to the sixth aspect of this application, Figure 6 As shown, the embodiment of the present application further provides a vehicle 100, comprising the above-mentioned controller. The vehicle 1000 has all the beneficial effects of the above-mentioned controller, which will not be described in detail in this application.

[0146] The vehicle 100 may be a fuel vehicle, a plug-in hybrid vehicle, or a new energy vehicle, etc., and this application does not make any specific limitation thereto.

[0147] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0148] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0150] The above are merely preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A vehicle control method, characterized in that: include: determining a target driving style of the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles; controlling the vehicle based on the target driving style; The surrounding vehicles are vehicles located within a preset distance around the current vehicle.

2. The method according to claim 1, characterized in that The controlling the vehicle includes at least one of the following: Control the vehicle's air conditioning system, control the vehicle's display interface, control the vehicle's lighting display, and control the vehicle's motor data.

3. The method according to claim 1, characterized in that The driving style includes at least one of the following: Conservative style, general style, radical style.

4. The method according to claim 1, wherein The method further comprises: When the current vehicle is in a non-automatic driving state, the driving style of the current vehicle is determined based on the self-driving data of the current vehicle.

5. The method according to claim 4, characterized in that The self-driving data includes: Real-time and historical driving data.

6. The method according to claim 4 or 5, characterized in that The self-driving data includes at least one of the following: Speed, acceleration, headway, lane change frequency, lane deviation, and yaw rate.

7. The method according to claim 1, characterized in that The method further comprises: The driving styles of the surrounding vehicles and the weights of the surrounding vehicles are determined based on a group potential field including the current vehicle.

8. The method according to claim 7, characterized in that The determining the weights of the surrounding vehicles based on the group potential field including the current vehicle includes: Determining a preset range of the group potential field based on preset rules; The weights of different surrounding vehicles in the group potential field are determined according to at least two different preset ranges.

9. The method according to claim 8, characterized in that The preset rules include: The distance between the surrounding vehicles and the current vehicle.

10. The method according to claim 8 or 9, characterized in that The surrounding vehicles located within the same preset range have the same weight.

11. The method according to claim 8 or 9, characterized in that The weights of the surrounding vehicles located in different preset ranges are different.

12. The method according to claim 11, characterized in that The preset range includes at least a first preset range and a second preset range; Within the first preset range, a distance between a first surrounding vehicle and the current vehicle is less than or equal to a first distance, and the first surrounding vehicle has a first weight; In the second preset range, the distance between the second surrounding vehicle and the current vehicle is greater than the first distance, and the second surrounding vehicle has a second weight; The first weight is greater than the second weight.

13. The method according to claim 8, characterized in that The preset range has a preset shape, and the preset shape is determined according to the preset rule.

14. The method according to claim 7, wherein: The determining the driving styles of the surrounding vehicles based on the group potential field including the current vehicle includes: Acquiring driving data of different surrounding vehicles within the group potential field; The driving style of the surrounding vehicle is determined based on the driving data of the surrounding vehicle.

15. The method according to claim 14, characterized in that The surrounding vehicles include at least one of the following: Vehicles in front, vehicles behind, and adjacent vehicles on the left and right; Among them, along the driving direction of the current vehicle, the front vehicle is the vehicle located in front of the current vehicle, the rear vehicle is the vehicle located behind the current vehicle, and the left and right neighboring vehicles are vehicles located on the left and / or right side of the current vehicle.

16. The method according to claim 15, characterized in that The acquiring of driving data of different surrounding vehicles in the group potential field includes at least one of the following: Acquiring first driving data of the front vehicle; acquiring second driving data of the rear vehicle; Acquire third driving data of the left and right neighboring vehicles.

17. The method according to claim 16, characterized in that The first driving data includes at least one of the following: longitudinal acceleration, lateral speed, and lateral acceleration; The second driving data includes at least one of the following: headway, longitudinal speed, and longitudinal acceleration; The third driving data includes at least one of the following: headway, longitudinal speed, longitudinal acceleration, lateral speed, and lateral acceleration.

18. The method according to claim 16, characterized in that The determining of the driving style of the surrounding vehicles based on the driving data of the surrounding vehicles includes at least one of the following: inputting the first driving data into a first driving style recognition model, and determining a first driving style corresponding to the leading vehicle based on a value output by the first driving style recognition model; inputting the second driving data into a second driving style recognition model, and determining a second driving style corresponding to the rear vehicle based on a value output by the second driving style recognition model; The third driving data is input into a third driving style recognition model, and the third driving styles corresponding to the left and right neighboring vehicles are determined according to a value output by the third driving style recognition model.

19. The method according to any one of claims 7 to 18, characterized in that The determining the target driving style of the current vehicle based on the driving style of the current vehicle and the driving styles of surrounding vehicles includes: A target driving style of the current vehicle is determined based on the driving style of the current vehicle, the driving styles of the surrounding vehicles, and weights of the surrounding vehicles.

20. The method according to claim 1, wherein The controlling the vehicle based on the target driving style includes: Based on the target driving style, a motor torque required by the current vehicle is determined.

21. The method according to claim 20, characterized in that The determining, based on the target driving style, the motor required torque of the current vehicle includes: determining a torque load factor of the current vehicle based on the target driving style and an accelerator pedal parameter of the current vehicle; The motor required torque of the current vehicle is determined based on the torque load factor.

22. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 21 are implemented.

23. A computer program product, characterized in that The method comprises a computer program or instructions, which implement the steps of the vehicle control method according to any one of claims 1 to 21 when executed by a processor.

24. A controller having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 21 are implemented.

25. A vehicle, characterized in that: Comprising a controller as claimed in claim 24.

Images