A method, system, terminal and storage medium for intelligent driving cooperative optimization

Abstract

This application relates to a collaborative optimization method, system, terminal, and storage medium for intelligent driving, and pertains to the technical field of intelligent driving control. The method includes acquiring driving road information; analyzing the driving road information to determine a stability confidence level; determining whether the stability confidence level is greater than a preset stability confidence threshold; if greater, acquiring historical stable speeds; analyzing the historical stable speeds and stability confidence levels to control a preset intelligent driving vehicle; if not greater, acquiring simultaneous fluctuation data; analyzing the simultaneous fluctuation data and stability confidence levels to control the intelligent driving vehicle. This application has the effect of reducing the energy consumption of intelligent driving vehicles.

Description

Technical Field

[0001] This application relates to the technical field of intelligent driving control, and in particular to an intelligent driving collaborative optimization method, system, terminal and storage medium. Background Technology

[0002] Intelligent driving collaborative optimization refers to the process of setting the driving parameters of intelligent driving vehicles by establishing a collaborative model of road condition perception and energy consumption optimization, and optimizing driving energy consumption under the premise of safe driving.

[0003] In related technologies, when controlling the driving of an intelligent driving vehicle, the driving conditions are obtained in real time through the perception module. Then, based on the premise of safe driving, dynamic control parameters of the intelligent driving vehicle are generated, and the intelligent driving vehicle is controlled in real time according to the dynamic control parameters.

[0004] Regarding the aforementioned technologies, when generating control parameters with safe driving as the sole planning objective, the failure to incorporate vehicle energy consumption into the decision optimization system can lead to redundant control parameters and frequent acceleration and deceleration of the vehicle, resulting in high energy consumption for intelligent driving vehicles. There is still room for improvement. Summary of the Invention

[0005] To reduce the energy consumption of intelligent driving vehicles, this application provides an intelligent driving collaborative optimization method, system, terminal, and storage medium.

[0006] Firstly, this application provides an intelligent driving cooperative optimization method, which adopts the following technical solution: A collaborative optimization method for intelligent driving includes: Obtain driving road information; Analyze the driving road information to determine the stability confidence level; Determine whether the stability confidence level is greater than the preset stability confidence threshold; If it is greater than that, then obtain the historical stable speed; Historical stable speeds and stability confidence levels are analyzed to control preset intelligent driving vehicles; If it is not greater than, then obtain the fluctuation data for the same period. Analyze the fluctuation data and stability confidence levels during the same period to control intelligent driving vehicles.

[0007] Optionally, the steps of analyzing driving road information to determine stable confidence levels include: Data extraction is performed on the driving road information to determine the vehicle adhesion coefficient, forward vehicle speed, forward traffic density, and lane line integrity. According to the preset mapping rules, the vehicle adhesion coefficient, forward vehicle speed, forward traffic density and lane line integrity are mapped to adhesion feature score, speed feature score, density feature score and lane line feature score. The adhesion feature score, velocity feature score, density feature score, and lane line feature score are normalized to determine the adhesion attention weight, velocity attention weight, density attention weight, and lane line attention weight. The adhesion feature score, velocity feature score, density feature score, and lane line feature score are weighted and summed based on the adhesion attention weight, velocity attention weight, density attention weight, and lane line attention weight to determine the stability confidence.

[0008] Optionally, the steps of analyzing historical stable speeds and stability confidence levels to control the preset intelligent driving vehicle include: Input the stability confidence level, stability confidence threshold, and preset stability safety adjustment amount into the preset weight adjustment model to determine the safety down adjustment amount; The preset stable safety weights are adjusted based on the safety reduction amount to determine the adjusted safety weights and adjusted energy consumption weights; Historical stable speeds are analyzed to determine stable safe speeds and stable energy consumption speeds; The final stable speed is determined by weighted summation of the stable safe speed and the stable energy consumption speed based on the adjusted safety weight and the adjusted energy consumption weight. The intelligent driving vehicle is controlled based on the final stable speed.

[0009] Optionally, the steps of analyzing historical stable speeds to determine stable safe speeds and stable energy consumption speeds include: Get the current minimum speed limit; The current minimum speed limit is set as the stable energy consumption speed; Based on the current minimum speed limit, historical stable speeds are filtered to determine the speed at the same speed limit; Calculate the arithmetic mean of the speeds with the same speed limit to determine a stable and safe speed.

[0010] Optionally, the steps of analyzing concurrent fluctuation data and stability confidence levels to control autonomous vehicles include: Input the stability confidence level, stability confidence threshold, and preset fluctuation safety adjustment amount into the preset weight correction model to determine the safety adjustment amount; The preset fluctuation safety weight is adjusted according to the safety adjustment amount to determine the corrected safety weight and corrected energy consumption weight. Analyze the fluctuation data during the same period to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration; The final fluctuation acceleration is determined by weighting and summing the fluctuation safety acceleration and fluctuation energy consumption acceleration according to the modified safety weight and modified energy consumption weight. Analyze road condition fluctuation factors and final fluctuation acceleration to determine the vehicle's target speed and following distance; Intelligent driving vehicles are controlled based on the target vehicle speed, following distance, and final fluctuating acceleration.

[0011] Optionally, the steps of analyzing the fluctuation data during the same period to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration include: Data extraction is performed on the fluctuation data of the same period to determine the fluctuation velocity, the average fluctuation acceleration, and the minimum energy consumption acceleration of the same period. The minimum energy consumption acceleration is defined as the fluctuating energy consumption acceleration. Calculate the variance of the fluctuation velocity during the same period to determine the velocity fluctuation variance; The speed fluctuation variance is normalized according to the preset speed fluctuation upper limit to determine the road condition fluctuation factor. Input the preset acceleration adjustment factor, road condition fluctuation factor, and average fluctuation acceleration into the preset safe acceleration model to determine the fluctuation safe acceleration.

[0012] Optionally, the steps of analyzing road condition fluctuation factors and final fluctuation acceleration to determine the vehicle's target speed and following distance include: Obtain the forward running speed; The forward running speed is determined as the vehicle's target speed; The forward running speed is extended based on a preset redundancy judgment value to determine the speed range of the preceding vehicle. Get the real-time speed of the vehicle in front; Determine whether the real-time speed of the vehicle in front is within the speed range of the vehicle in front; If so, the final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, preset minimum vehicle spacing and preset maximum following increment are input into the preset vehicle distance model to determine the vehicle following distance. If not, the target speed of the vehicle and the speed range of the vehicle in front are updated based on the real-time speed of the vehicle in front, and the real-time speed of the vehicle in front is continuously obtained for iterative judgment.

[0013] Secondly, this application provides an intelligent driving cooperative optimization system, which adopts the following technical solution: An intelligent driving cooperative optimization system includes: The acquisition module is used to acquire driving road information, historical stable speed, and simultaneous fluctuation data. A memory for storing a program of an intelligent driving cooperative optimization method as described in any of the preceding items; The processor and the program in the memory can be loaded and executed by the processor to implement an intelligent driving cooperative optimization method as described in any of the above.

[0014] Thirdly, this application provides a smart terminal, which adopts the following technical solution: A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any of the preceding claims.

[0015] Fourthly, this application provides a computer storage medium capable of storing corresponding programs, which facilitates the reduction of energy consumption in intelligent driving vehicles, and adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed any of the above-described intelligent driving cooperative optimization methods.

[0016] In summary, this application includes at least one of the following beneficial technical effects: 1. By analyzing the driving road information, a stability confidence level is determined, which in turn determines the current road condition. When the stability confidence level is greater than the stability confidence threshold, it indicates that the current road condition is stable. Therefore, historical stable speeds are obtained, and the historical stable speeds and stability confidence levels are analyzed to control the intelligent driving vehicle. When the stability confidence level is not greater than the stability confidence threshold, it indicates that the road condition is fluctuating significantly. Therefore, fluctuation data for the same period is obtained, and the intelligent driving vehicle is controlled based on the fluctuation data for the same period. This allows for the selection of different vehicle control methods according to the actual road conditions, thereby improving the control accuracy of the intelligent driving vehicle. 2. By adjusting the stability and safety weights through stability confidence, the adjustment safety weights and adjustment energy consumption weights are determined. Then, based on historical stable speeds, stable safety speeds and stable energy consumption speeds are determined. Finally, the stable safety speeds and stable energy consumption speeds are weighted and summed according to the adjustment safety weights and adjustment energy consumption weights to determine the final stable speed. The intelligent driving vehicle is then controlled based on the final stable speed, thereby optimizing intelligent driving with the dual objectives of safety and energy consumption, and reducing the energy consumption of intelligent driving vehicles while ensuring safety. 3. By defining the forward travel time as the vehicle's target speed and then expanding the forward travel speed to the range of the preceding vehicle's speed based on redundant judgments, frequent gear changes by the intelligent driving vehicle are avoided, reducing its energy consumption. If the real-time speed of the preceding vehicle is within the preceding vehicle's speed range, it indicates that the preceding vehicle's speed has no significant fluctuations, so there is no need to change the vehicle's target speed. The final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, minimum vehicle spacing, and maximum following increment are input into the vehicle distance model to determine the vehicle's following distance. If the real-time speed of the preceding vehicle is not within the forward travel speed range, it indicates that the preceding vehicle's speed has changed, and the vehicle's target speed needs to be updated. Therefore, the vehicle target speed and the preceding vehicle's speed range are updated based on the real-time preceding vehicle speed, and the real-time preceding vehicle speed is continuously acquired for iterative judgment. This allows for dynamic adjustment of the vehicle's following distance based on the intelligent driving vehicle's operating parameters, improving the safety of intelligent driving. Attached Figure Description

[0017] Figure 1 This is a flowchart of an intelligent driving cooperative optimization method in an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating the analysis of driving road information to determine the stability confidence level in this embodiment of the application.

[0019] Figure 3 This is a flowchart in this application embodiment of analyzing historical stable speed and stability confidence to control a preset intelligent driving vehicle.

[0020] Figure 4 This is a flowchart illustrating the analysis of historical stable speeds in this application embodiment to determine stable safe speeds and stable energy consumption speeds.

[0021] Figure 5 This is a flowchart in this application embodiment of analyzing simultaneous fluctuation data and stability confidence to control intelligent driving vehicles.

[0022] Figure 6 This is a flowchart in this application embodiment of analyzing simultaneous fluctuation data to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration.

[0023] Figure 7 This is a flowchart in this application embodiment that analyzes road condition fluctuation factors and final fluctuation acceleration to determine the vehicle target speed and vehicle following distance. Detailed Implementation

[0024] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1 to 7The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0025] This application discloses an intelligent driving cooperative optimization method, system, terminal, and storage medium. Specifically, it discloses a processing terminal and an intelligent driving vehicle, which are communicatively connected to achieve information interaction and control. The processing terminal acquires driving road information, analyzes the driving road information to determine a stability confidence level, and then determines the current driving road condition based on the stability confidence level. When the stability confidence level is greater than a stability confidence threshold, it indicates that the current road condition is stable. Therefore, historical stable speeds are acquired, and the historical stable speeds and stability confidence levels are analyzed to control the intelligent driving vehicle. When the stability confidence level is not greater than the stability confidence threshold, it indicates that the road condition is fluctuating significantly. Therefore, simultaneous fluctuation data is acquired, and the intelligent driving vehicle is controlled based on the simultaneous fluctuation data. This allows for the selection of different vehicle control methods according to the actual road conditions, thereby improving the control accuracy of the intelligent driving vehicle.

[0026] Reference Figure 1 This application discloses an intelligent driving cooperative optimization method, which includes the following steps: Step S100: Obtain driving road information.

[0027] Among them, driving road information refers to road condition-related information during the driving process of intelligent driving vehicles, including vehicle adhesion coefficient, forward vehicle speed, forward traffic density, and lane line integrity. The processing terminal first retrieves detection data from sensing devices such as high-definition cameras, millimeter-wave radar, integrated lidar, and inertial measurement units deployed on the intelligent driving vehicle, then processes the monitoring data, calculates data such as traffic density and lane line integrity, and finally integrates and determines the analyzed monitoring data.

[0028] Step S101: Analyze the driving road information to determine the stability confidence level.

[0029] Among them, stability confidence refers to the confidence level that the current road conditions are stable, which is determined by the processing terminal through analysis of the road information. The specific analysis steps are as follows: Figure 2 The steps in the process.

[0030] Step S102: Determine whether the stability confidence level is greater than the preset stability confidence threshold.

[0031] Among them, the stable confidence threshold refers to the lower limit of confidence in stable road conditions, which is determined by the operator in combination with the working performance, operating requirements and actual operating data of the intelligent driving vehicle.

[0032] By processing the terminal to determine whether the stability confidence level is greater than the stability confidence level threshold, the stability of the road conditions of the current driving segment is determined. Based on the stability of the road conditions, different control weights are selected to control the intelligent driving vehicle, thereby reducing the energy consumption of the intelligent driving vehicle.

[0033] Step S1021: If it is greater than, then obtain the historical stable speed.

[0034] If the processing terminal determines that the stability confidence level is greater than the stability confidence threshold, it indicates that the intelligent driving vehicle is in a road section with stable road conditions and low traffic density. Therefore, historical stable speeds are obtained to provide data support for controlling the intelligent driving vehicle under stable road conditions in the future.

[0035] Historical stable speed refers to the stable operating speed of an intelligent driving vehicle under stable road conditions. The processing terminal first preprocesses the historical operating data of the intelligent driving vehicle, removes abnormal data, and then filters the preprocessed driving data according to the stability confidence threshold to determine the speed at which the vehicle runs smoothly under stable road conditions, which is the historical stable speed.

[0036] Step S1022: Analyze the historical stable speed and stability confidence to control the preset intelligent driving vehicle.

[0037] Among them, intelligent driving vehicles refer to vehicles equipped with intelligent driving systems. The intelligent driving system generates vehicle operating parameters such as vehicle speed, vehicle acceleration, and following distance through perception and decision-making modules, and controls the operation of intelligent driving vehicles.

[0038] After determining the historical stable speed and stability confidence level, the historical stable speed and stability confidence level are analyzed to control the autonomous driving vehicle. Specific analysis steps are detailed below. Figure 3 The steps in the process.

[0039] Step S1023: If it is not greater than, then obtain the fluctuation data of the same period.

[0040] If the processing terminal determines that the stability confidence level is not greater than the stability confidence threshold, it indicates that the intelligent driving vehicle is in a road section with large road condition fluctuations and high traffic density. Therefore, acquiring the fluctuation data at the same time provides data support for controlling the intelligent driving vehicle under fluctuating road conditions.

[0041] Simultaneous fluctuation data refers to the historical driving data of vehicles under fluctuating road conditions within the same time period as the current vehicle's driving time. This includes the driving speed and acceleration of intelligent driving vehicles. The processing terminal first divides the current driving time into time periods. After determining the current driving time period, it searches the pre-processed historical database based on the current driving time period to determine the historical driving data of intelligent driving vehicles under fluctuating road conditions within the same time period. This is the simultaneous fluctuation data.

[0042] Step S1024: Analyze the fluctuation data and stability confidence during the same period to control the intelligent driving vehicle.

[0043] After determining the fluctuation data for the same period, the fluctuation data and stability confidence level are analyzed to control the autonomous driving vehicle. Specific analysis steps are detailed below. Figure 5 The steps in the process.

[0044] Reference Figure 2 The steps for analyzing road information to determine stable confidence levels include: Step S200: Extract road information to determine vehicle adhesion coefficient, forward vehicle speed, forward traffic density, and lane integrity.

[0045] Among these, the vehicle adhesion coefficient refers to the quantified value of the adhesion between the vehicle's tires and the ground. Forward vehicle speed refers to the speed of vehicles ahead of the autonomous vehicle. Forward traffic density refers to the vehicle density within the field of view of the autonomous vehicle's camera. Lane integrity refers to the degree of integrity of lane lines on the road. All of the above data are determined by the processing terminal through data extraction from the driving road information.

[0046] Step S201: Map the vehicle adhesion coefficient, forward vehicle speed, forward traffic density, and lane line integrity into adhesion feature score, speed feature score, density feature score, and lane line feature score according to the preset mapping rules.

[0047] Among them, the mapping rule refers to the transformation rule that converts specific vehicle adhesion coefficient, forward vehicle speed, forward vehicle density and lane line integrity into feature scores used to evaluate stability confidence. The operator determines the transformation rule that maps the specific data of each scoring dimension into the score data of the same dimension based on the judgment rules of stable road conditions and the numerical differences of each evaluation dimension.

[0048] The adhesion feature score refers to the feature score of the vehicle adhesion coefficient. The speed feature score refers to the feature score of the forward vehicle speed. The density feature score refers to the feature score of the forward traffic flow density. The lane line feature score refers to the feature score of the lane line integrity. All of the above data are determined by the processing terminal by converting the vehicle adhesion coefficient, forward vehicle speed, forward traffic flow density, and lane line integrity into corresponding mapping rules according to the relevant mapping rules.

[0049] Step S202: Normalize the attachment feature score, velocity feature score, density feature score, and lane line feature score to determine the attachment attention weight, velocity attention weight, density attention weight, and lane line attention weight.

[0050] Among them, attachment attention weight refers to the weight of the attachment feature score. Speed ​​attention weight refers to the weight of the speed feature score. Density attention weight refers to the weight of the density feature score. Lane line attention weight refers to the weight of the lane line feature score. All the above data are determined by the processing terminal by first calculating the sum of feature scores of attachment feature score, speed feature score, density feature score and lane line feature score, and then normalizing the attachment feature score, speed feature score, density feature score and lane line feature score according to the feature score sum to obtain the normalized weight corresponding to each feature score.

[0051] Step S203: The attachment feature score, velocity feature score, density feature score, and lane line feature score are weighted and summed according to the attachment attention weight, velocity attention weight, density attention weight, and lane line attention weight to determine the stability confidence.

[0052] The stability confidence level is consistent with the stability confidence level in step S101, and is determined by the processing terminal by weighting and summing the attachment feature score, speed feature score, density feature score and lane line feature score according to the attachment attention weight, speed attention weight, density attention weight and lane line attention weight.

[0053] Reference Figure 3 The steps for controlling a pre-defined intelligent driving vehicle by analyzing historical stable speeds and stability confidence levels include: Step S300: Input the stability confidence level, stability confidence threshold, and preset stability safety adjustment amount into the preset weight adjustment model to determine the safety down adjustment amount.

[0054] Among them, the stability and safety adjustment amount refers to the weight that can be adjusted up or down from the base weight under stable road conditions. It is determined by the operator based on the driving requirements of the intelligent driving vehicle under stable road conditions.

[0055] The stability and safety adjustment is a formulaic model that transforms the deviation between the stability confidence level and the stability confidence threshold into an adjustment amount for safety weights. The specific calculation formula is as follows: .

[0056] In the formula, To ensure safety, the quantity was reduced. To stabilize the confidence level, To stabilize the confidence threshold, Adjust the amount to ensure stability and safety.

[0057] The safety reduction amount refers to the amount by which the stability and safety weights are reduced under the current stability confidence level. It is calculated and determined by the processing terminal by inputting the stability confidence level, stability confidence threshold, and stability and safety adjustment amount into the weight adjustment model.

[0058] Step S301: Adjust the preset stable safety weight according to the safety reduction amount to determine the adjusted safety weight and the adjusted energy consumption weight.

[0059] Among them, the stability safety weight refers to the basic weight of safety decision when intelligent driving vehicles make decisions under stable road conditions. It is determined by the operator through driving experiments on intelligent driving vehicles with different safety weights under stable road conditions and with a stability confidence level of the stability confidence threshold.

[0060] Adjusting the security weight refers to adjusting the stable security weight based on the stability confidence level. The processing terminal determines the stable security weight by calculating the difference between the stable security weight and the security reduction amount after determining the security reduction amount.

[0061] The adjusted energy consumption weight refers to the stable energy consumption weight adjusted based on the stability confidence level. It is determined by the processing terminal by subtracting the adjusted safety weight from 1 after determining the adjusted safety weight.

[0062] Step S302: Analyze the historical stable speed to determine the stable safe speed and stable energy consumption speed.

[0063] Among them, stable safe speed refers to the vehicle's cruising speed generated based on current road conditions when only safety decisions are considered. Stable energy consumption speed refers to the vehicle's cruising speed generated based on current road conditions when only energy consumption decisions are considered. Both are determined by the processing terminal through analysis of historical stable speeds; the specific analysis steps are described in [reference needed]. Figure 4 The steps in the process.

[0064] Step S303: The stable safe speed and the stable energy consumption speed are weighted and summed according to the adjusted safety weight and the adjusted energy consumption weight to determine the final stable speed.

[0065] The final stable speed refers to the final vehicle speed determined under the current stable road conditions after safety and energy consumption co-optimization. It is determined by the processing terminal by weighted summation of the stable safe speed and the stable energy consumption speed based on the adjustment of safety weight and energy consumption weight.

[0066] Step S304: Control the intelligent driving vehicle based on the final stable speed.

[0067] Once the final stable speed is determined, it is set as the vehicle's cruising speed. Under conditions of low traffic density, long distance to oncoming vehicles, and stable road conditions, the intelligent driving vehicle is controlled to drive. This optimizes the control of the intelligent driving vehicle based on a two-way synergy between safety and energy efficiency, thereby reducing the energy consumption of the intelligent driving vehicle while ensuring safety.

[0068] Reference Figure 4 The steps for analyzing historical stable speeds to determine stable safe speeds and stable energy consumption speeds include: Step S400: Obtain the current minimum speed limit.

[0069] The current minimum speed limit refers to the minimum speed limit for the current road segment. The processing terminal determines the minimum speed limit for the current road segment by performing location analysis.

[0070] Step S401: Determine the current minimum speed limit as the stable energy consumption speed.

[0071] The stable energy consumption speed is consistent with the stable energy consumption speed in step S302. After determining the current minimum speed limit, the processing terminal determines the current minimum speed limit as the stable energy consumption speed.

[0072] Step S402: Filter historical stable speeds based on the current minimum speed limit to determine the speed with the same speed limit.

[0073] Among them, the speed with the same speed limit refers to the historical stable speed that is consistent with the current minimum speed limit of the corresponding road. It is determined by the processing terminal by filtering the historical stable speeds based on the current minimum speed limit.

[0074] Step S403: Calculate the arithmetic mean of the speeds with the same speed limit to determine a stable and safe speed.

[0075] The stable safe speed is consistent with the stable safe speed in step S302. It is determined by the processing terminal by calculating the arithmetic mean of the speeds with the same speed limit, thereby determining the stable safe speed based on the mean of the speeds with the same speed limit and improving the driving safety of intelligent driving vehicles.

[0076] Reference Figure 5 The steps for controlling autonomous vehicles, which involve analyzing concurrent fluctuation data and stability confidence levels, include: Step S500: Input the stability confidence level, stability confidence threshold, and preset fluctuation safety adjustment amount into the preset weight correction model to determine the safety adjustment amount.

[0077] Among them, the fluctuation safety threshold refers to the weight that can be adjusted up or down from the basic weight under fluctuating road conditions. It is determined by the operator based on the driving requirements of the intelligent driving vehicle under fluctuating road conditions.

[0078] The weight correction model is consistent with the weight adjustment model in step S300, and is used to convert the deviation rate between the stable confidence level and the stable confidence threshold into the adjustment amount of the safety weight.

[0079] The safety adjustment amount refers to the amount by which the fluctuation safety weight is increased under the current stability confidence level. It is calculated and determined by the processing terminal by inputting the stability confidence level, stability confidence threshold and fluctuation safety adjustment amount into the weight correction model.

[0080] Step S501: Adjust the preset fluctuation safety weight according to the safety adjustment amount to determine the corrected safety weight and the corrected energy consumption weight.

[0081] Among them, the fluctuation safety weight refers to the basic weight of safety decision when intelligent driving vehicles make decisions under fluctuating road conditions. It is determined by the operator through driving experiments on intelligent driving vehicles with different safety weights under road conditions with fluctuating road conditions and a stability confidence level close to the stability confidence threshold.

[0082] The corrected safety weight refers to the fluctuation safety weight adjusted based on the stability confidence level. It is determined by the processing terminal after determining the safety increase amount, by calculating the sum of the stability safety weight and the safety increase amount.

[0083] The corrected energy consumption weight refers to the fluctuating energy consumption weight adjusted according to the stability confidence level. It is determined by the processing terminal by subtracting the corrected safety weight from 1 after determining the corrected safety weight.

[0084] Step S502: Analyze the fluctuation data of the same period to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration.

[0085] Among them, the road condition fluctuation factor refers to the quantitative factor of the degree of road condition fluctuation. Fluctuation safety acceleration refers to the acceleration value of an autonomous vehicle under fluctuating road conditions, considering only safety decisions. Fluctuation energy consumption acceleration refers to the acceleration value of an autonomous vehicle under fluctuating road conditions, considering only energy consumption decisions. All the above data are determined by the processing terminal through analysis of fluctuation data from the same period. Specific analysis steps are described in [reference needed]. Figure 6 The steps in the process.

[0086] Step S503: The fluctuation safety acceleration and fluctuation energy consumption acceleration are weighted and summed according to the modified safety weight and the modified energy consumption weight to determine the final fluctuation acceleration.

[0087] The final fluctuation acceleration refers to the final vehicle acceleration determined after safety and energy consumption co-optimization under the current fluctuating road conditions. It is determined by the processing terminal by weighting and summing the fluctuation safety acceleration and fluctuation energy consumption acceleration according to the corrected safety weight and corrected energy consumption weight.

[0088] Step S504: Analyze the road condition fluctuation factor and final fluctuation acceleration to determine the vehicle target speed and following distance.

[0089] Here, the target vehicle speed refers to the target speed of the vehicle under fluctuating road conditions. The following distance refers to the fixed following distance between the autonomous driving vehicle and the vehicle in front under fluctuating road conditions. Both are determined by the processing terminal through analysis of road condition fluctuation factors and final fluctuation acceleration; the specific analysis steps are detailed below. Figure 7 The steps in the process.

[0090] Step S505: Control the intelligent driving vehicle based on the vehicle target speed, vehicle following distance, and final fluctuation acceleration.

[0091] Among them, after determining the target speed and following distance of the vehicle, the intelligent driving vehicle is controlled based on the target speed, following distance and final fluctuating acceleration, thereby reducing the energy consumption of the intelligent driving vehicle.

[0092] Reference Figure 6 The steps for analyzing fluctuation data during the same period to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration include: Step S600: Extract data from the fluctuation data of the same period to determine the fluctuation velocity, the average fluctuation acceleration, and the minimum energy consumption acceleration of the same period.

[0093] Among them, the simultaneous fluctuation speed refers to the target speed of vehicles in the historical simultaneous period in the simultaneous period data, which is determined by the processing terminal by extracting the speed data in the simultaneous fluctuation data.

[0094] The mean of fluctuating acceleration refers to the average of vehicle acceleration during the same historical period in the data of the same period. It is determined by the processing terminal by first extracting the acceleration data from the fluctuating data of the same period and then calculating the mean of acceleration.

[0095] Minimum energy consumption acceleration refers to the acceleration value corresponding to the minimum energy consumption rate among the fluctuating data of the same period. It is determined by the processing terminal by first extracting the total energy consumption and distance value of the fluctuating data of the same period, calculating the quotient of the total energy consumption and distance value, determining the energy consumption rate of the intelligent driving vehicle for each trip under fluctuating road conditions, and then determining the acceleration value of the fluctuating data of the same period with the lowest energy consumption rate.

[0096] Step S601: Determine the minimum energy consumption acceleration as the fluctuating energy consumption acceleration.

[0097] Among them, the fluctuation energy consumption acceleration is consistent with the fluctuation energy consumption acceleration in step S502. After determining the minimum energy consumption acceleration, the processing terminal determines the minimum energy consumption acceleration as the fluctuation energy consumption acceleration.

[0098] Step S602: Calculate the variance of the fluctuation speed during the same period to determine the variance of the speed fluctuation.

[0099] Among them, the velocity fluctuation variance refers to the variance of the fluctuation velocity during the same period, which is determined by the processing terminal by calculating the variance of the fluctuation velocity during the same period.

[0100] Step S603: Normalize the speed fluctuation variance according to the preset speed fluctuation upper limit to determine the road condition fluctuation factor.

[0101] Among them, the speed fluctuation limit refers to the maximum variance of the speed of the intelligent driving vehicle under fluctuating road conditions, which is determined by the operator based on the actual operation of the intelligent driving vehicle under fluctuating road conditions.

[0102] The road condition fluctuation factor is consistent with the road condition fluctuation factor in step S502, and is determined by the processing terminal through normalization of the speed fluctuation variance based on the upper limit of speed fluctuation.

[0103] Step S604: Input the preset acceleration adjustment factor, road condition fluctuation factor and average fluctuation acceleration into the preset safe acceleration model to determine the fluctuation safe acceleration.

[0104] The acceleration adjustment factor refers to the adjustment range when adjusting vehicle acceleration based on road condition fluctuation factors. The operator conducts experiments with different vehicle accelerations under the same road condition fluctuation factors to determine the acceleration adjustment range with the highest safety.

[0105] The safe acceleration model is a formulaic model that adjusts the mean of fluctuation acceleration based on road condition fluctuation factors to ultimately determine the safe fluctuation acceleration. The specific model formula is as follows: .

[0106] In the formula, For fluctuation safety acceleration, As an acceleration adjustment factor, The mean of the fluctuation acceleration, This is the road condition fluctuation factor.

[0107] The fluctuation safety acceleration is consistent with the fluctuation safety acceleration in step S502, and is calculated and determined by the processing terminal by inputting the acceleration adjustment factor, road condition fluctuation factor and fluctuation acceleration mean into the safety acceleration model.

[0108] Reference Figure 7 The steps for analyzing road condition fluctuation factors and final fluctuation acceleration to determine the vehicle's target speed and following distance include: Step S700: Obtain the forward running speed.

[0109] The forward operating speed refers to the speed of the vehicle in front of the intelligent driving vehicle, which is determined by the processing terminal based on millimeter-wave radar measurement data.

[0110] Step S701: Determine the forward running speed as the vehicle target speed.

[0111] The target vehicle speed is consistent with the target vehicle speed in step S504. After determining the forward running speed, the processing terminal determines the forward running speed as the target vehicle speed.

[0112] Step S702: Expand the forward running speed according to the preset redundancy judgment amount to determine the speed range of the preceding vehicle.

[0113] Among them, the redundancy judgment quantity refers to the judgment redundancy quantity of forward running speed, which is used to expand the judgment range of target speed of intelligent driving vehicle and avoid frequent switching of vehicle target speed of intelligent driving vehicle. It is determined by the operator based on the speed fluctuation range during the uniform speed driving process.

[0114] The forward vehicle speed range refers to the range of speed changes of the vehicle in front of the intelligent driving vehicle in a stable operating state without significant speed changes. It is determined by the processing terminal based on the redundancy judgment amount to extend the forward operating speed.

[0115] Step S703: Obtain the real-time speed of the vehicle in front.

[0116] Among them, the real-time speed of the vehicle in front refers to the real-time speed of the vehicle in front during the operation of the intelligent driving vehicle, which is determined by the processing terminal by retrieving the measured data of the millimeter-wave radar.

[0117] Step S704: Determine whether the real-time speed of the vehicle in front is within the speed range of the vehicle in front.

[0118] Specifically, the processing terminal determines whether the real-time speed of the vehicle in front is within the speed range of the vehicle in front, thereby determining whether the speed of the vehicle in front has changed significantly, and then dynamically adjusts the target speed of the vehicle based on the speed change of the vehicle in front, thereby improving the safety of intelligent driving.

[0119] Step S7041: If so, input the final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, preset minimum vehicle spacing and preset maximum following increment into the preset vehicle distance model to determine the vehicle following distance.

[0120] If the processing terminal determines that the real-time speed of the vehicle in front is within the range of the vehicle in front's speed, it indicates that the vehicle in front is driving smoothly without significant speed fluctuations. Therefore, it is not necessary to change the vehicle's target speed. The final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, minimum vehicle spacing, and maximum following increment are input into the vehicle distance model to determine the vehicle following distance. Thus, the vehicle following distance is dynamically determined based on the actual operating data of the vehicle and the degree of road condition fluctuations, thereby improving the safety of intelligent driving.

[0121] Minimum vehicle spacing refers to the minimum safe distance between an autonomous driving vehicle and the vehicle in front, which is determined by the operator based on the performance of the autonomous driving vehicle and the actual road conditions.

[0122] Maximum following increment refers to the maximum expansion of the minimum following distance under fluctuating congested road conditions. It is determined by the operator based on the performance of the intelligent driving vehicle and the actual road conditions under fluctuating congested road conditions.

[0123] The vehicle distance model is a formulaic model that determines the following distance of a vehicle based on the road condition fluctuation factor, final fluctuation acceleration, and the target speed of the vehicle. The specific model formula is as follows: .

[0124] In the formula, For vehicle following distance, For the target speed of the vehicle, To minimize vehicle spacing, For the final fluctuation acceleration, To maximize the increase in following vehicle volume, This is the road condition fluctuation factor.

[0125] The vehicle following distance is consistent with the vehicle following distance in step S504, and is determined by the processing terminal by inputting the final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, minimum vehicle spacing and maximum following increment into the vehicle distance model.

[0126] Step S7042: If not, update the vehicle target speed and the speed range of the vehicle in front based on the real-time speed of the vehicle in front, and continuously obtain the real-time speed of the vehicle in front for cyclic judgment.

[0127] If the processing terminal determines that the real-time speed of the vehicle in front is not within the range of the vehicle in front's speed, it indicates that the speed of the vehicle in front has fluctuated significantly and the target speed of the vehicle needs to be adjusted. Therefore, the target speed of the vehicle and the speed range of the vehicle in front are updated according to the real-time speed of the vehicle in front, and the real-time speed of the vehicle in front is continuously acquired for iterative judgment.

[0128] Based on the same inventive concept, embodiments of this application provide an intelligent driving cooperative optimization system, including: The acquisition module is used to acquire driving road information, historical stable speed, simultaneous fluctuation data, current minimum speed limit, forward running speed and real-time speed of the vehicle in front; A memory for storing a program for a cooperative optimization method for intelligent driving; The processor can load and execute programs in memory to implement a collaborative optimization method for intelligent driving.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed to provide a method for cooperative optimization of intelligent driving.

[0131] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0132] Based on the same inventive concept, embodiments of this application provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor to provide a method for intelligent driving cooperative optimization.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for cooperative optimization in intelligent driving, characterized in that, include: Obtain driving road information; Analyze the driving road information to determine the stability confidence level; Determine whether the stability confidence level is greater than the preset stability confidence threshold; If it is greater than that, then obtain the historical stable speed; Historical stable speeds and stability confidence levels are analyzed to control preset intelligent driving vehicles; If it is not greater than, then obtain the fluctuation data for the same period. Analyze the fluctuation data and stability confidence levels during the same period to control intelligent driving vehicles.

2. The intelligent driving cooperative optimization method according to claim 1, characterized in that, The steps for analyzing road information to determine stable confidence levels include: Data extraction is performed on the driving road information to determine the vehicle adhesion coefficient, forward vehicle speed, forward traffic density, and lane line integrity. According to the preset mapping rules, the vehicle adhesion coefficient, forward vehicle speed, forward traffic density and lane line integrity are mapped to adhesion feature score, speed feature score, density feature score and lane line feature score. The adhesion feature score, velocity feature score, density feature score, and lane line feature score are normalized to determine the adhesion attention weight, velocity attention weight, density attention weight, and lane line attention weight. The adhesion feature score, velocity feature score, density feature score, and lane line feature score are weighted and summed based on the adhesion attention weight, velocity attention weight, density attention weight, and lane line attention weight to determine the stability confidence.

3. The intelligent driving cooperative optimization method according to claim 1, characterized in that, The steps for analyzing historical stable speeds and stability confidence levels to control a pre-defined autonomous vehicle include: Input the stability confidence level, stability confidence threshold, and preset stability safety adjustment amount into the preset weight adjustment model to determine the safety down adjustment amount; The preset stable safety weights are adjusted based on the safety reduction amount to determine the adjusted safety weights and adjusted energy consumption weights; Historical stable speeds are analyzed to determine stable safe speeds and stable energy consumption speeds; The final stable speed is determined by weighted summation of the stable safe speed and the stable energy consumption speed based on the adjusted safety weight and the adjusted energy consumption weight. The intelligent driving vehicle is controlled based on the final stable speed.

4. The intelligent driving cooperative optimization method according to claim 3, characterized in that, The steps for analyzing historical stable speeds to determine stable safe speeds and stable energy consumption speeds include: Get the current minimum speed limit; The current minimum speed limit is set as the stable energy consumption speed; Based on the current minimum speed limit, historical stable speeds are filtered to determine the speed at the same speed limit; Calculate the arithmetic mean of the speeds with the same speed limit to determine a stable and safe speed.

5. The intelligent driving cooperative optimization method according to claim 1, characterized in that, The steps for controlling autonomous vehicles include analyzing concurrent fluctuation data and stability confidence levels: Input the stability confidence level, stability confidence threshold, and preset fluctuation safety adjustment amount into the preset weight correction model to determine the safety adjustment amount; The preset fluctuation safety weight is adjusted according to the safety adjustment amount to determine the corrected safety weight and corrected energy consumption weight. Analyze the fluctuation data during the same period to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration; The final fluctuation acceleration is determined by weighting and summing the fluctuation safety acceleration and fluctuation energy consumption acceleration according to the modified safety weight and modified energy consumption weight. Analyze road condition fluctuation factors and final fluctuation acceleration to determine the vehicle's target speed and following distance; Intelligent driving vehicles are controlled based on the target vehicle speed, following distance, and final fluctuating acceleration.

6. The intelligent driving cooperative optimization method according to claim 5, characterized in that, The steps for analyzing concurrent fluctuation data to determine the road condition fluctuation factor, fluctuation safety acceleration, and fluctuation energy consumption acceleration include: Data extraction is performed on the fluctuation data of the same period to determine the fluctuation velocity, the average fluctuation acceleration, and the minimum energy consumption acceleration of the same period. The minimum energy consumption acceleration is defined as the fluctuating energy consumption acceleration. Calculate the variance of the fluctuation velocity during the same period to determine the velocity fluctuation variance; The speed fluctuation variance is normalized according to the preset speed fluctuation upper limit to determine the road condition fluctuation factor. Input the preset acceleration adjustment factor, road condition fluctuation factor, and average fluctuation acceleration into the preset safe acceleration model to determine the fluctuation safe acceleration.

7. The intelligent driving cooperative optimization method according to claim 5, characterized in that, The steps for analyzing road condition fluctuation factors and final fluctuation acceleration to determine the vehicle's target speed and following distance include: Obtain the forward running speed; The forward running speed is determined as the vehicle's target speed; The forward running speed is extended based on a preset redundancy judgment value to determine the speed range of the preceding vehicle. Get the real-time speed of the vehicle in front; Determine whether the real-time speed of the vehicle in front is within the speed range of the vehicle in front; If so, the final fluctuation acceleration, vehicle target speed, road condition fluctuation factor, preset minimum vehicle spacing and preset maximum following increment are input into the preset vehicle distance model to determine the vehicle following distance. If not, the target speed of the vehicle and the speed range of the vehicle in front are updated based on the real-time speed of the vehicle in front, and the real-time speed of the vehicle in front is continuously obtained for iterative judgment.

8. An intelligent driving cooperative optimization system, characterized in that, include: The acquisition module is used to acquire driving road information, historical stable speed, and simultaneous fluctuation data. A memory for storing a program of an intelligent driving cooperative optimization method as described in any one of claims 1 to 7; The processor and the program in the memory can be loaded and executed by the processor to implement the intelligent driving cooperative optimization method as described in any one of claims 1 to 7.

9. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images