A method, system, and medium for correction of deceleration for an intelligent driving vehicle

Abstract

The application relates to a correction method, system and medium for deceleration of an intelligent driving vehicle, the method comprising the following steps: M1. The vehicle travels on a road, real-time data information of deceleration of the vehicle is acquired based on a vehicle-mounted deceleration sensor, real-time data information of speed of the vehicle is acquired based on a vehicle-mounted speed sensor, and real-time data information of wheel rotation speed of the vehicle is acquired based on a vehicle-mounted tachometer; M2. Based on the data information of speed, the data information of wheel rotation speed and the data information of deceleration of the vehicle, a total deceleration polynomial of the vehicle is constructed, the total deceleration of the vehicle is calculated, and data information of the total deceleration of the vehicle is obtained. The application not only corrects the acceleration and deceleration of the intelligent driving vehicle, controls the deviation between a target value and a request value, and realizes more accurate control, but also realizes real-time monitoring of the whole deceleration process, and improves the safety of vehicle driving and the riding experience of passengers.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle technology, and in particular to a method, system, and medium for correcting deceleration in intelligent driving vehicles. Background Technology

[0002] Most current vehicle control methods focus on speed or distance control. For intelligent driving vehicles, existing acceleration and deceleration detection methods mainly include: 1. installing deceleration sensors; 2. speed versus time slope; 3. wheel speed versus time slope. Using only one of these methods results in a large deviation between the control target and the requested value. Using deceleration sensors alone is inaccurate due to factors such as installation location and changes in vehicle mass, and has poor adaptability. The speed versus time slope method suffers from significant time lag; the wheel speed versus time slope method also has time lag issues and is further affected by changes in wheel radius caused by changes in vehicle mass. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method, system and medium for correcting the deceleration of intelligent driving vehicles. It not only corrects the acceleration and deceleration of intelligent driving vehicles and controls the deviation between target value and requested value to achieve more precise control, but also monitors the entire deceleration process in real time, thereby improving the safety of vehicle driving and the passenger riding experience.

[0004] To achieve the above and other related objectives, the present invention provides the following technical solution: A method for correcting deceleration in an intelligent driving vehicle, the method comprising: M1. When the vehicle is driving on the road, the vehicle's deceleration data is obtained in real time based on the on-board deceleration sensor, the vehicle's speed data is obtained in real time based on the on-board speed sensor, and the vehicle's wheel speed data is obtained in real time based on the on-board wheel speed meter. M2. Based on the vehicle's speed data, wheel speed data, and deceleration data, construct a total deceleration polynomial for the vehicle, calculate the total deceleration of the vehicle, and obtain the total deceleration data of the vehicle. M3. Based on the total deceleration data of the vehicle and combined with the deceleration request data of the vehicle, the improved fox optimization algorithm is used to optimize the total deceleration of the vehicle to obtain the optimized total deceleration data of the vehicle. M4. Based on the optimized total deceleration data of the vehicle, set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle's comfort requirements are not met, and return to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle's comfort requirements are met, and output the vehicle's total deceleration value.

[0005] Furthermore, in step M2, the construction of the vehicle's total deceleration polynomial and the calculation of the vehicle's total deceleration include: M21. Based on the vehicle's speed data, wheel speed data, and deceleration data, perform data preprocessing to obtain preprocessed vehicle speed, wheel speed, and deceleration data. M22. Based on the preprocessed vehicle speed and wheel speed data, construct the vehicle's average deceleration function a. 平 and wheel deceleration function a 轮 , , , Among them, v t+Δt Let v be the preprocessed speed of the vehicle at time t+Δt. t Let be the preprocessed vehicle speed at time t. The preprocessed wheel speed at time t+Δt. Given the preprocessed wheel speed at time t, the average deceleration and wheel deceleration of the vehicle are calculated to obtain the data information of the average deceleration and wheel deceleration of the vehicle. M23. Based on the data of the vehicle's average deceleration and wheel deceleration, and combined with the data of the vehicle's total deceleration, construct the vehicle's total deceleration polynomial a. 总 , a_total = w1 * a 平 +w2*a 轮 +w3*a1, Among them, w1, w2 and w3 are weighting coefficients, and a1 is the vehicle deceleration data. The total deceleration of the vehicle is calculated to obtain the total deceleration data of the vehicle.

[0006] Furthermore, the constraints on the weighting coefficients w1, w2, and w3 are as follows: w1+w2+w3=1.

[0007] Furthermore, the data preprocessing includes data cleaning and data standardization. Data cleaning removes outliers from the data, and data standardization standardizes the units in the data.

[0008] Furthermore, in step M3, optimizing the total deceleration of the vehicle using the improved fox optimization algorithm includes: M31. Based on the data information of the total deceleration of the vehicle and the data information of the vehicle's deceleration request value, the fox population is initialized to determine the population parameters and the maximum number of iterations L, and the data information of the initialized fox population is obtained. M32. Based on the data information of the initialized fox population, it is necessary to find the new location of the fox. To find the new location, the optimal location is found by measuring the time required for sound to travel between the fox and its prey. In step M33, the fox randomly searches based on the best location found, obtains the optimal solution, substitutes the optimal solution into step M32, and iterates until the maximum number of iterations L is reached, optimizing the total deceleration of the vehicle and obtaining the optimized data information of the total deceleration of the vehicle.

[0009] Furthermore, the optimal location found by measuring the time required for sound to travel between the fox and its prey is determined by setting a preset range value based on the time required for sound to travel between the fox and its prey. If the time required for sound to travel between the fox and its prey is within the preset range value, it is considered the optimal location; if the time required for sound to travel between the fox and its prey is not within the preset range value, it is rejected.

[0010] To achieve the above and other related objectives, the present invention also provides a deceleration correction system for intelligent driving vehicles, for implementing the aforementioned deceleration correction method for intelligent driving vehicles, the system comprising: The data acquisition module is used to acquire real-time data on the vehicle's deceleration based on the onboard deceleration sensor, real-time data on the vehicle's speed based on the onboard speed sensor, and real-time data on the vehicle's wheel rotation speed based on the onboard wheel speed meter. The vehicle total deceleration calculation module is connected to the data acquisition module and is used to construct the vehicle total deceleration polynomial, calculate the vehicle total deceleration, and obtain the vehicle total deceleration data information. The vehicle total deceleration optimization module is connected to the vehicle total deceleration calculation module and is used to optimize the vehicle's total deceleration using an improved fox optimization algorithm to obtain the optimized vehicle total deceleration data. The vehicle comfort threshold module is connected to the vehicle total deceleration optimization module and is used to set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle comfort requirements are not met, and the process returns to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle comfort requirements are met, and the total deceleration value of the vehicle is output.

[0011] Furthermore, the system also includes a human-machine interaction module connected to the vehicle comfort threshold module, used to display the vehicle's total deceleration data in real time.

[0012] Furthermore, the system also includes a voice broadcast module connected to the vehicle comfort threshold module, used to announce that the vehicle is about to decelerate and remind passengers to sit properly.

[0013] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the deceleration correction methods for intelligent driving vehicles described in the present invention.

[0014] The present invention has the following positive effects: This invention constructs a polynomial for the total deceleration of a vehicle to calculate its total deceleration, and then optimizes the total deceleration using an improved fox optimization algorithm. Simultaneously, a preset threshold is set. If the optimized total deceleration exceeds the preset threshold, the vehicle's comfort requirements are not met; if the optimized total deceleration is less than the preset threshold, the vehicle's comfort requirements are met. The total deceleration value is output. This not only corrects the acceleration and deceleration of intelligent driving vehicles, controlling the deviation between target and requested values ​​for more precise control, but also monitors the entire deceleration process in real time, improving vehicle safety and passenger experience. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram illustrating the process of constructing the polynomial of the total vehicle deceleration according to the present invention; Figure 3 This is a flowchart illustrating the improved fox optimization algorithm of the present invention; Figure 4 This is a schematic diagram of the system framework of the present invention. Detailed Implementation

[0016] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0017] Example 1: As Figure 1 As shown, a method for correcting deceleration in an intelligent driving vehicle includes: M1. When the vehicle is driving on the road, the vehicle's deceleration data is obtained in real time based on the on-board deceleration sensor, the vehicle's speed data is obtained in real time based on the on-board speed sensor, and the vehicle's wheel speed data is obtained in real time based on the on-board wheel speed meter. M2. Based on the vehicle's speed data, wheel speed data, and deceleration data, construct a total deceleration polynomial for the vehicle, calculate the total deceleration of the vehicle, and obtain the total deceleration data of the vehicle. M3. Based on the total deceleration data of the vehicle and combined with the deceleration request data of the vehicle, the improved fox optimization algorithm is used to optimize the total deceleration of the vehicle to obtain the optimized total deceleration data of the vehicle. M4. Based on the optimized total deceleration data of the vehicle, set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle's comfort requirements are not met, and return to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle's comfort requirements are met, and output the vehicle's total deceleration value.

[0018] In this embodiment, as Figure 2 As shown, in step M2, the construction of the vehicle's total deceleration polynomial and the calculation of the vehicle's total deceleration include: M21. Based on the vehicle's speed data, wheel speed data, and deceleration data, perform data preprocessing to obtain preprocessed vehicle speed, wheel speed, and deceleration data. M22. Based on the preprocessed vehicle speed and wheel speed data, construct the vehicle's average deceleration function a. 平 and wheel deceleration function a 轮 , , , Among them, v t+Δt Let v be the preprocessed speed of the vehicle at time t+Δt. t Let be the preprocessed vehicle speed at time t. The preprocessed wheel speed at time t+Δt. Given the preprocessed wheel speed at time t, the average deceleration and wheel deceleration of the vehicle are calculated to obtain the data information of the average deceleration and wheel deceleration of the vehicle. M23. Based on the data of the vehicle's average deceleration and wheel deceleration, and combined with the data of the vehicle's total deceleration, construct the vehicle's total deceleration polynomial a. 总 , a_total = w1 * a 平 +w2*a轮 +w3*a1, Among them, w1, w2 and w3 are weighting coefficients, and a1 is the vehicle deceleration data. The total deceleration of the vehicle is calculated to obtain the total deceleration data of the vehicle.

[0019] In this embodiment, the constraints on the weighting coefficients w1, w2, and w3 are as follows: w1+w2+w3=1.

[0020] In this embodiment, the data preprocessing includes data cleaning and data standardization. The data cleaning removes outliers from the data, and the data standardization standardizes the units in the data.

[0021] In this embodiment, as Figure 3 As shown, in step M3, optimizing the total deceleration of the vehicle using the improved fox optimization algorithm includes: M31. Based on the data information of the total deceleration of the vehicle and the data information of the vehicle's deceleration request value, the fox population is initialized to determine the population parameters and the maximum number of iterations L, and the data information of the initialized fox population is obtained. M32. Based on the data information of the initialized fox population, it is necessary to find the new location of the fox. To find the new location, the optimal location is found by measuring the time required for sound to travel between the fox and its prey. In step M33, the fox randomly searches based on the best location found, obtains the optimal solution, substitutes the optimal solution into step M32, and iterates until the maximum number of iterations L is reached, optimizing the total deceleration of the vehicle and obtaining the optimized data information of the total deceleration of the vehicle.

[0022] In this embodiment, the optimal location found by measuring the time required for sound to travel between the fox and its prey is determined by setting a preset range value based on the time required for sound to travel between the fox and its prey. If the time required for sound to travel between the fox and its prey is within the preset range value, it is considered the optimal location; otherwise, it is rejected.

[0023] In this embodiment, three typical scenarios were selected for the real vehicle test: Scenario 1: Gentle braking on an urban expressway (initial speed 80km / h → 0) The original sensor deceleration a average deviation was +0.12g, and the Jerk peak was 4.32m / s². 3 After correction by this invention, the steady-state error of a is reduced to +0.018g, and the Jerk peak value is 2.17m / s. 3The passenger subjective comfort rating rose from 5.4 to 8.9 (out of 10).

[0024] Scenario 2: Deceleration on a highway ramp in rainy weather (initial speed 100km / h → 40km / h, μ≈0.4) The traditional method underestimates the slip ratio by 0.23g, resulting in a 5.7m increase in braking distance. The present invention uses dynamic compensation of the Δa(t) term to compress the error of a to -0.031g, and the braking distance error is <0.8m (compliant with GB / T 39901-2021 requirements).

[0025] Scenario 3: Continuous downhill slope in mountainous area (slope -5% to -8%, lasting 12 minutes) Traditional PID control exhibits periodic oscillations (period ≈ 8.3s), with a Jerk standard deviation of 1.92m / s. 3 The present invention updates the IFOA coefficients online every 200ms, successfully suppressing oscillations and reducing the Jerk standard deviation to 0.43m / s. 3 The thermal decay compensation response time is shortened by 62%.

[0026] Example 2: Based on the deceleration correction method for intelligent driving vehicles in Example 1, the present invention will be further explained and described below.

[0027] like Figure 1 As shown, a method for correcting deceleration in an intelligent driving vehicle includes: M1. When the vehicle is driving on the road, the vehicle's deceleration data is obtained in real time based on the on-board deceleration sensor, the vehicle's speed data is obtained in real time based on the on-board speed sensor, and the vehicle's wheel speed data is obtained in real time based on the on-board wheel speed meter. M2. Based on the vehicle's speed data, wheel speed data, and deceleration data, construct a total deceleration polynomial for the vehicle, calculate the total deceleration of the vehicle, and obtain the total deceleration data of the vehicle. M3. Based on the total deceleration data of the vehicle and combined with the deceleration request data of the vehicle, the improved fox optimization algorithm is used to optimize the total deceleration of the vehicle to obtain the optimized total deceleration data of the vehicle. M4. Based on the optimized total deceleration data of the vehicle, set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle's comfort requirements are not met, and return to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle's comfort requirements are met, and output the vehicle's total deceleration value.

[0028] In this embodiment, as Figure 4As shown, the present invention provides a deceleration correction system for intelligent driving vehicles, used to implement the aforementioned deceleration correction method for intelligent driving vehicles, the system comprising: The data acquisition module is used to acquire real-time data on the vehicle's deceleration based on the onboard deceleration sensor, real-time data on the vehicle's speed based on the onboard speed sensor, and real-time data on the vehicle's wheel rotation speed based on the onboard wheel speed meter. The vehicle total deceleration calculation module is connected to the data acquisition module and is used to construct the vehicle total deceleration polynomial, calculate the vehicle total deceleration, and obtain the vehicle total deceleration data information. The vehicle total deceleration optimization module is connected to the vehicle total deceleration calculation module and is used to optimize the vehicle's total deceleration using an improved fox optimization algorithm to obtain the optimized vehicle total deceleration data. The vehicle comfort threshold module is connected to the vehicle total deceleration optimization module and is used to set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle comfort requirements are not met, and the process returns to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle comfort requirements are met, and the total deceleration value of the vehicle is output.

[0029] In this embodiment, the system further includes a human-computer interaction module connected to the vehicle comfort threshold module, used to display the total deceleration data of the vehicle in real time.

[0030] In this embodiment, the system further includes a voice broadcast module connected to the vehicle comfort threshold module, used to announce that the vehicle is about to decelerate and remind passengers to sit properly.

[0031] In this embodiment, the present invention has been integrated into a car manufacturer's intelligent driving domain controller software V2.3.1 and deployed in its flagship model. Actual user data shows: The AEB false trigger rate decreased by 73.5% (from 0.87 times / 10,000 km to 0.23 times / 10,000 km). The ACC following-car comfort NPS (Net Promoter Score) improved by 31 percentage points (from -12% to +19%). The overall vehicle braking energy recovery efficiency is improved by 4.2%, which corresponds to an increase of approximately 6.8km in CLTC range.

[0032] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the deceleration correction methods for intelligent driving vehicles described herein.

[0033] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0034] In summary, this invention not only corrects the acceleration and deceleration of intelligent driving vehicles and controls the deviation between target and requested values ​​to achieve more precise control, but also monitors the entire deceleration process in real time, thereby improving vehicle driving safety and passenger riding experience.

[0035] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for correcting deceleration in intelligent driving vehicles, characterized in that, The method includes: M1. When the vehicle is driving on the road, the vehicle's deceleration data is obtained in real time based on the on-board deceleration sensor, the vehicle's speed data is obtained in real time based on the on-board speed sensor, and the vehicle's wheel speed data is obtained in real time based on the on-board wheel speed meter. M2. Based on the vehicle's speed data, wheel speed data, and deceleration data, construct a total deceleration polynomial for the vehicle, calculate the total deceleration of the vehicle, and obtain the total deceleration data of the vehicle. M3. Based on the total deceleration data of the vehicle and combined with the deceleration request data of the vehicle, the improved fox optimization algorithm is used to optimize the total deceleration of the vehicle to obtain the optimized total deceleration data of the vehicle. M4. Based on the optimized total deceleration data of the vehicle, set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle's comfort requirements are not met, and return to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle's comfort requirements are met, and output the total deceleration value of the vehicle. In step M2, constructing the total vehicle deceleration polynomial and calculating the total vehicle deceleration includes: M21. Based on the vehicle's speed data, wheel speed data, and deceleration data, perform data preprocessing to obtain preprocessed vehicle speed, wheel speed, and deceleration data. M22. Based on the preprocessed vehicle speed and wheel speed data, construct the vehicle's average deceleration function a. 平 and wheel deceleration function a 轮 , ， ， Among them, v t+Δt Let v be the preprocessed vehicle speed at time t+Δt. t Let be the preprocessed vehicle speed at time t. The preprocessed wheel speed at time t+Δt. Given the preprocessed wheel speed at time t, the average deceleration and wheel deceleration of the vehicle are calculated to obtain the data information of the average deceleration and wheel deceleration of the vehicle. M23. Based on the data of the vehicle's average deceleration and wheel deceleration, and combined with the data of the vehicle's total deceleration, construct the vehicle's total deceleration polynomial a. 总 , a_total = w1 * a 平 + w2 * a 轮 + w3 * a1, Among them, w1, w2 and w3 are weighting coefficients, a1 is the vehicle deceleration data, the total deceleration of the vehicle is calculated, and the total deceleration data of the vehicle is obtained. In step M3, optimizing the total deceleration of the vehicle using the improved fox optimization algorithm includes: M31. Based on the data information of the total deceleration of the vehicle and the data information of the vehicle's deceleration request value, the fox population is initialized to determine the population parameters and the maximum number of iterations L, and the data information of the initialized fox population is obtained. M32. Based on the data information of the initialized fox population, it is necessary to find the new location of the fox. To find the new location, the optimal location is found by measuring the time required for sound to travel between the fox and its prey. M33. In this stage, the fox randomly searches based on the found optimal location to obtain the optimal solution, and substitutes the optimal solution into step M32, and iterates until the maximum number of iterations L is reached to optimize the total deceleration of the vehicle, obtaining the optimized total deceleration data information of the vehicle; the optimal location found by the time required for sound to travel between the fox and the prey is based on a preset range value set according to the time required for sound to travel between the fox and the prey. If the time required for sound to travel between the fox and the prey is within the preset range value, it is the optimal location; if the time required for sound to travel between the fox and the prey is not within the preset range value, it is discarded.

2. The method for correcting deceleration in intelligent driving vehicles according to claim 1, characterized in that: The constraints on the weighting coefficients w1, w2, and w3 are as follows: w1+w2+w3=1.

3. The method for correcting deceleration in intelligent driving vehicles according to claim 1, characterized in that: The data preprocessing includes data cleaning and data standardization. Data cleaning removes outliers from the data, and data standardization standardizes the units in the data.

4. A deceleration correction system for intelligent driving vehicles, characterized in that, A method for correcting deceleration in an intelligent driving vehicle as described in any one of claims 1-3, characterized in that the system comprises: The data acquisition module is used to acquire real-time data on the vehicle's deceleration based on the onboard deceleration sensor, real-time data on the vehicle's speed based on the onboard speed sensor, and real-time data on the vehicle's wheel rotation speed based on the onboard wheel speed meter. The vehicle total deceleration calculation module is connected to the data acquisition module and is used to construct the vehicle total deceleration polynomial, calculate the vehicle total deceleration, and obtain the vehicle total deceleration data information. The vehicle total deceleration optimization module is connected to the vehicle total deceleration calculation module and is used to optimize the vehicle's total deceleration using an improved fox optimization algorithm to obtain the optimized vehicle total deceleration data. The vehicle comfort threshold module is connected to the vehicle total deceleration optimization module and is used to set a preset threshold. If the optimized total deceleration of the vehicle is greater than the preset threshold, the vehicle comfort requirements are not met, and the process returns to step M3. If the optimized total deceleration of the vehicle is less than the preset threshold, the vehicle comfort requirements are met, and the total deceleration value of the vehicle is output.

5. The deceleration correction system for intelligent driving vehicles according to claim 4, characterized in that, The system also includes a human-computer interaction module connected to the vehicle comfort threshold module, used to display the vehicle's total deceleration data in real time.

6. The deceleration correction system for intelligent driving vehicles according to claim 4, characterized in that, The system also includes a voice broadcast module connected to the vehicle comfort threshold module, used to announce that the vehicle is about to slow down and remind passengers to sit properly.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is programmed or configured to perform the deceleration correction method for an intelligent driving vehicle as described in any one of claims 1 to 3.

Images