A safety throttle emergency braking control system and method based on artificial intelligence

Through the safety throttle emergency braking control system based on artificial intelligence, the kmeans algorithm is used to judge abnormal vehicle attribute data and generate and withdraw brake signals, which solves the problem of novice drivers accidentally stepping on the accelerator as brakes, and improves judgment accuracy and safety , reducing the occurrence of traffic accidents.

CN118439042BActive Publication Date: 2024-11-01JIANGSU TONGLIN ELECTRIC CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410559465.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-08
Publication Date
2024-11-01
Estimated Expiration
2044-05-08

AI Technical Summary

Technical Problem

In an emergency, novice drivers may mistakenly step on the accelerator as a brake, resulting in traffic accidents. It is difficult for the prior art to accurately judge such misoperation.

Method used

The safety throttle emergency braking control system based on artificial intelligence is adopted. By obtaining vehicle attribute data, using the kmeans algorithm to cluster to determine whether there is any abnormality, generate and withdraw braking signals, ensuring timely braking in an emergency situation to reduce the risk of accidents.

Benefits of technology

It improves the accuracy of judging the situation where novice drivers accidentally step on the accelerator, reduces the incidence of traffic accidents, has a simple structure, a small number of hardware, and a low probability of failure.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118439042B_ABST
    Figure CN118439042B_ABST
Patent Text Reader

Abstract

The invention discloses a safe throttle emergency brake control system and method based on artificial intelligence, which relates to the technical field of throttle emergency brake control, and comprises: acquiring attribute data of a vehicle; normalizing the attribute data of the vehicle, clustering by a kmeans algorithm, and judging whether the attribute data of the current vehicle is abnormal; determining whether a brake signal is needed according to the result; judging whether the accelerator is mistakenly stepped on according to the change value of the throttle opening, so as to improve the accuracy of the judgment; controlling the throttle opening and the brake opening by using the output signal of a logic controller, so as to reduce the occurrence of faults; making the judgment more accurate by a double judgment method; and having a small amount of hardware and a low probability of faults.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of throttle emergency brake control, and in particular to a safe throttle emergency brake control system and method based on artificial intelligence. Background Art

[0002] With the development of my country's economy and the improvement of people's living standards, the number of cars owned has continued to rise. As a result, the number of novice drivers has also increased, and traffic accidents caused by driver misoperation also occur from time to time. Due to their lack of experience, novice drivers may make operational errors in emergency situations, such as accidentally stepping on the accelerator when they need to slow down or stop. This misoperation usually occurs under nervous or panic emotions, especially during emergency braking or avoidance. Since the accelerator and brake pedals are located adjacent to each other, novice drivers may not be able to accurately judge which is the accelerator and which is the brake in a nervous state, resulting in stepping on the wrong pedal. Therefore, how to accurately judge the situation where the driver mistakenly operates the accelerator as the brake has become a problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a safety throttle emergency brake control system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0004] In one aspect of the present invention, a safety throttle emergency braking control method based on artificial intelligence is provided, comprising:

[0005] S1-1, obtaining attribute data of the vehicle;

[0006] S1-2, normalize the attribute data of the vehicle, perform clustering using the kmeans algorithm, and determine whether the attribute data of the current vehicle is abnormal;

[0007] S1-3, if the current vehicle attribute data is abnormal, a braking signal is generated; if there is no abnormality, no braking signal is generated; in case of an emergency, the danger caused by braking is usually less than the danger caused by not braking. Therefore, when the vehicle attribute data is abnormal, a braking signal is generated, and whether the braking signal needs to be withdrawn is determined based on the subsequent judgment results. When the module fails, the generated braking signal can reduce the risk caused by the abnormal vehicle attribute data and reduce the harm caused by the module failure;

[0008] After the braking signal is generated, it is determined whether the current vehicle needs to be braked. If so, the braking signal is maintained; if not, the vehicle braking signal is withdrawn.

[0009] In step S1-2, the determination of whether the attribute data of the current vehicle is abnormal further includes the following steps:

[0010] S2-1, the vehicle attribute data includes throttle opening, throttle opening change value and vehicle speed; according to the slope of the road section where the vehicle is located, the kmeans distance operation is performed on the vehicle attribute data under the same slope; the slope conditions include uphill, downhill and flat road;

[0011] S2-2, based on the kmeans clustering results, obtain the cluster center and clusters, as well as the maximum distance between the vehicle attribute data in each cluster and the cluster center , the value range of i is a positive integer between [1, n], and n is the number of clusters;

[0012] S2-3, calculate the distance between the current vehicle attribute data and each cluster center , if for all cases within the value range of i, Are greater than , then the attribute data of the current vehicle is abnormal; otherwise, the attribute data of the current vehicle is normal.

[0013] Use historical data to cluster in advance to get the cluster center and the farthest distance In actual use, you only need to calculate the distance between the current vehicle attribute data and the cluster center to determine whether the current vehicle attribute data is a favorable point, that is, whether there is an anomaly; it can speed up the inspection of vehicle attribute data and improve the response speed of the system.

[0014] In step S1-3, the following steps are also included:

[0015] S3-1, determine whether the opening degree of the vehicle brake is 0; if not, no braking signal needs to be generated, and the process goes to step S3-4; if yes, the process goes to step S3-2 and continues the analysis;

[0016] When the brake opening is not 0, it means that the driver did not mistake the accelerator for the brake, but the driver's current driving style is quite different from the previous driving style, so there is no need to generate a brake signal. The vehicle attribute data can increase the clustering data set and improve the clustering effect.

[0017] S3-2, find the cluster center closest to the current vehicle attribute data, compare the throttle opening of the cluster center data with the throttle opening of the current vehicle, if the throttle opening of the current vehicle is less than or equal to the throttle opening of the cluster center data, there is no need to generate a braking signal, and go to step S3-4; if it is greater, go to step S3-3; when the throttle opening of the current vehicle is less than or equal to the throttle opening of the cluster center data, the current vehicle's driving speed will be lower than the normal driving speed, which can indicate that the current driver has not panicked and stepped on the accelerator as the brake or the current driver is in a panic before stepping on the accelerator as the brake; when the driver mistakenly steps on the accelerator as the brake, the throttle opening will be greater than the throttle opening of the cluster center data, and it can be detected by judging the vehicle attribute data at any time, and no braking signal can be generated here.

[0018] S3-3, determine whether the throttle opening change value is too large, if so, maintain the generated brake signal and end; if not, enter step S3-4;

[0019] S3-4, withdraw the generated braking signal, the current vehicle does not need to brake, and the process ends.

[0020] In step S3-3, the step of determining whether the throttle opening change value is too large further includes the following steps:

[0021] S4-1, with v, k and dk representing the current vehicle speed, throttle opening and throttle opening change value, , and Indicates the cluster center closest to the current vehicle attribute data The vehicle speed, throttle opening and throttle opening change value; at the cluster center In the cluster where the vehicle is located, the vehicle speed, throttle opening and throttle opening change value in the vehicle attribute data are taken to form data points, and the data point with the smallest difference from the current vehicle's speed, throttle opening and throttle opening change value is found ( ), the difference is calculated as , , and is the cluster center The vehicle speed, throttle opening and throttle opening change value in the cluster where j is a positive integer;

[0022] S4-2, obtain cluster center Vehicle attribute data and cluster center in the cluster The longest distance , adjust the current vehicle speed and throttle from v and k to and , calculate the current vehicle attribute data and cluster center again The distance E between , if E is less than or equal to , then the throttle opening change value is judged to be not too large, and the process ends; if E is greater than , then the critical value of dk is calculated according to the following formula :

[0023] = ;

[0024] Get dk with If dk and If the difference between dk and If the difference is greater than the threshold, it is judged that the throttle opening change is too large.

[0025] The cluster that contains the cluster center closest to the current vehicle attribute data is the cluster that the current vehicle attribute data is most likely to belong to, and the data in the cluster is closest to the pattern of the current vehicle attribute data. When a novice driver encounters an emergency, he may accidentally step on the accelerator, which will produce a large accelerator opening change value. Therefore, the accelerator opening change value can be used to determine whether the novice driver accidentally stepped on the accelerator. In order to determine whether the abnormality of the current vehicle attribute data is caused by the accelerator opening change value, it is necessary to normalize the vehicle speed and accelerator opening, and then calculate the current vehicle attribute data and the cluster center again. If the vehicle speed and throttle opening are normalized, the current vehicle attribute data and the cluster center The distance is less than or equal to , it means that the abnormality of the current vehicle attribute data is caused by the vehicle speed or throttle opening, which has nothing to do with the throttle opening change value, so the braking signal needs to be withdrawn at this time; after normalization, the current vehicle attribute data and the cluster center The distance is still greater than , it indicates that the abnormality of the current vehicle attribute data is caused by the change in the throttle opening value, and further analysis is needed; Find the data point closest to the current vehicle attribute data in the cluster to normalize the vehicle speed and throttle opening of the current vehicle attribute data;

[0026] When the throttle opening is reduced to After normalization, the current vehicle attribute data and cluster center The distance is equal to , the current vehicle attribute data is no longer abnormal data. is the throttle opening change value under normal conditions; when dk and The difference between is less than or equal to the threshold, which means that dk and There is no significant difference between them, so dk is also regarded as the throttle opening change value under normal circumstances, and the braking signal is withdrawn; when dk is equal to The difference between is greater than the threshold, then dk and There is a significant difference between them, dk is abnormal data and needs to be braked; the threshold can be obtained by using the 3 sigma rule, and the cluster center The standard deviation of the throttle opening change value is calculated from the data in the clusters of , and dk is judged to be an abnormal value; however, the error between dk and the mean is not calculated at this time, but the error between dk and the mean. When the error between dk and the mean is less than the threshold, dk can be determined to be a normal value; and it is only necessary to ensure that dk is within the critical value. When the error between them is less than the threshold, it can also be determined that dk is a normal value.

[0027] The threshold is determined by the following steps:

[0028] At the cluster center In the cluster where the vehicle is located, the standard deviation σ of the throttle opening change value in all vehicle attribute data is calculated, and the threshold is N×σ, where N is a positive number less than or equal to 3.

[0029] The final values ​​of the vehicle brake signal and throttle signal are obtained through the following steps:

[0030] The logic controller determines whether the vehicle needs braking based on the current vehicle attribute data. If braking is not required, the logic controller outputs a 100% throttle opening signal. If braking is required, the logic controller outputs a 0% throttle opening signal.

[0031] The logic controller and the driver's signal applied to the throttle are minimized to generate the final value of the throttle signal to control the vehicle;

[0032] The throttle opening signal output by the logic controller is inverted and then taken to be the maximum value with the signal applied by the driver to the brake to generate the final value of the vehicle braking signal.

[0033] When the logic controller outputs a 100% throttle opening signal, the inverter outputs a 0% braking signal; when the logic controller outputs a 0% throttle opening signal, the inverter outputs a braking signal greater than 0, and a corresponding braking signal can be generated according to the current vehicle speed.

[0034] When the vehicle is running normally, the logic controller outputs a 100% throttle opening signal, which is minimized by the control signal applied by the driver to the throttle to obtain the final value of the throttle signal. Therefore, the final value of the throttle signal is the control signal applied by the driver to the throttle. After passing through the inverter, the 100% throttle opening signal is converted into a 0% brake opening signal, which is maximized by the brake signal applied by the driver to obtain the final value of the brake signal. Therefore, the final value of the brake signal is the control signal applied by the driver to the brake.

[0035] When the vehicle needs to brake, the logic controller outputs a 0% throttle opening signal, forcing the final value of the throttle signal to be 0; at the same time, it is converted into a braking signal greater than 0 after passing through the inverter. If the driver does not step on the brake, the final braking signal is the braking signal output by the inverter; if the driver steps on the brake, the final braking signal is the larger value between the two braking signals.

[0036] In another aspect of the present invention, there is provided an artificial intelligence-based safety throttle emergency braking control system, comprising: a vehicle attribute data acquisition module, a vehicle driving section judgment module, a vehicle attribute data storage module, a logic control module and a vehicle attribute data clustering module; the output end of the vehicle attribute data acquisition module is interconnected with the input end of the vehicle attribute data storage module to obtain attribute data during vehicle driving; the output end of the vehicle driving section judgment module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module to judge the slope of the road section where the vehicle is located, and the slope includes uphill, downhill and flat road; the output end of the vehicle attribute data storage module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module to store attribute data during vehicle driving; the logic control module generates the final value of the vehicle braking signal and the throttle signal based on the current vehicle attribute data and the clustering result of the vehicle attribute data clustering module; the output end of the vehicle attribute data clustering module is interconnected with the input end of the logic control module to judge whether the current vehicle attribute data is abnormal through the kmeans clustering algorithm.

[0037] The vehicle driving section judgment module also includes a sensor unit, a dynamic model unit and a data fusion unit. The sensor unit is used to obtain three-dimensional motion information of the vehicle. The data fusion unit is used to fuse the information obtained by the sensor unit. The dynamic model unit estimates the slope of the road section where the vehicle is located through the vehicle's dynamic model based on the fused three-dimensional motion information of the vehicle.

[0038] The logic control module also includes a logic controller, an inverter, a maximum value unit and a minimum value unit; the logic controller is used to output a throttle signal, the output of the logic controller is connected to one end of the minimum value unit input, and the output of the logic controller is connected to one end of the maximum value unit input after passing through the inverter; the other end of the minimum value unit input is the signal applied by the driver to the throttle of the vehicle, and the other end of the maximum value unit input is the signal applied by the driver to the brake of the vehicle; the output of the maximum value unit is the final value of the vehicle braking signal, and the output of the minimum value unit is the final value of the vehicle throttle signal.

[0039] The vehicle attribute data clustering module performs kmeans clustering on the periodic historical vehicle attribute data, and obtains the cluster center and cluster clusters according to the kmeans clustering results; when the vehicle is driving, it is judged whether the attribute data of the current vehicle is abnormal according to the distance between the vehicle attribute data and the cluster center. Compared with the prior art, the beneficial effects achieved by the present invention are as follows: when a novice encounters an emergency, he may mistakenly step on the accelerator in panic. During normal acceleration, the accelerator increases slowly and evenly, while the accidental stepping on the accelerator is short and has great force and amplitude. Judging whether the accidental stepping on the accelerator occurs based on the change in the accelerator opening can improve the accuracy of the judgment; the accelerator opening and the brake opening are controlled by the output signal of the logic controller to achieve the effect that the accelerator opening and the brake opening will not be greater than 0 at the same time, which can reduce the occurrence of faults; through the dual judgment method, the judgment of the accidental stepping on the accelerator is increased to make the judgment more accurate; a braking signal is generated when an abnormal situation is judged for the first time, and when a problem occurs in the subsequent judgment, the vehicle can also be braked, which can reduce the incidence of traffic accidents; it can be implemented with only a logic controller, with a simple structure, easy implementation, a small amount of hardware, and a low probability of failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 It is a structural schematic diagram of a safety throttle emergency brake control system based on artificial intelligence according to an embodiment of the present invention;

[0042] Figure 2 is a control flow chart of the throttle signal and brake signal of a vehicle according to an embodiment of the present invention;

[0043] Figure 3 It is a flow chart of determining whether a vehicle needs to brake according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In the embodiments of the present invention, please refer to Figure 1 , a structural schematic diagram of a safety throttle emergency brake control system based on artificial intelligence is provided, comprising: a vehicle attribute data acquisition module, a vehicle driving section judgment module, a vehicle attribute data storage module, a logic control module and a vehicle attribute data clustering module; the output end of the vehicle attribute data acquisition module is interconnected with the input end of the vehicle attribute data storage module to obtain attribute data during vehicle driving; the output end of the vehicle driving section judgment module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module to judge the slope of the road section where the vehicle is located, and the slope includes uphill, downhill and flat road; the output end of the vehicle attribute data storage module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module to store attribute data during vehicle driving; the logic control module generates the final value of the vehicle brake signal and the throttle signal based on the current vehicle attribute data and the clustering result of the vehicle attribute data clustering module; the output end of the vehicle attribute data clustering module is interconnected with the input end of the logic control module to judge whether the current vehicle attribute data is abnormal through the kmeans clustering algorithm.

[0046] The vehicle driving section judgment module also includes a sensor unit, a dynamic model unit and a data fusion unit. The sensor unit is used to obtain three-dimensional motion information of the vehicle. The data fusion unit is used to fuse the information obtained by the sensor unit. The dynamic model unit estimates the slope of the road section where the vehicle is located through the vehicle's dynamic model based on the fused three-dimensional motion information of the vehicle.

[0047] The logic control module also includes a logic controller, an inverter, a maximum value unit and a minimum value unit; the logic controller is used to output a throttle signal, the output of the logic controller is connected to one end of the minimum value unit input, and the output of the logic controller is connected to one end of the maximum value unit input after passing through the inverter; the other end of the minimum value unit input is the signal applied by the driver to the throttle of the vehicle, and the other end of the maximum value unit input is the signal applied by the driver to the brake of the vehicle; the output of the maximum value unit is the final value of the vehicle braking signal, and the output of the minimum value unit is the final value of the vehicle throttle signal.

[0048] The vehicle attribute data clustering module performs kmeans clustering on the periodic historical vehicle attribute data, and obtains the cluster center and cluster clusters according to the kmeans clustering results; when the vehicle is driving, it is judged whether the attribute data of the current vehicle is abnormal according to the distance between the vehicle attribute data and the cluster center.

[0049] In an embodiment of the present invention, a safety throttle emergency braking control method based on artificial intelligence is provided, comprising:

[0050] S1-1, obtaining attribute data of the vehicle.

[0051] S1-2, normalize the attribute data of the vehicle, perform clustering using the kmeans algorithm, and determine whether the attribute data of the current vehicle is abnormal;

[0052] The process includes the following steps S2-1 to S2-3:

[0053] S2-1, the vehicle attribute data includes throttle opening, throttle opening change value and vehicle driving speed; according to the slope of the road section where the vehicle is located, the kmeans distance operation is performed on the vehicle attribute data under the same slope; the slope conditions include uphill, downhill and flat road; the patterns between the driving speed and the throttle opening under different slope conditions are different, and the data of different slope conditions are distinguished and then clustered, which can improve the accuracy of clustering; only the three conditions of uphill, downhill and flat road need to be identified, and there is no need to obtain specific slope data;

[0054] S2-2, perform kmeans clustering on the historical vehicle attribute data of uphill, downhill and flat roads respectively. According to the kmeans clustering results, obtain the cluster center and clusters, as well as the farthest distance between the vehicle attribute data in each cluster and the cluster center , the value range of i is a positive integer between [1, n], and n is the number of clusters;

[0055] S2-3, determine the slope of the road section where the vehicle is currently located. If the vehicle is on an uphill section, calculate the distance between the current vehicle attribute data and each cluster center from the clustering results of the uphill section. , if for all cases within the value range of i, Are greater than , then the attribute data of the current vehicle is abnormal; otherwise, the attribute data of the current vehicle is normal.

[0056] S1-3, if the attribute data of the current vehicle is abnormal, a braking signal is generated; if there is no abnormality, no braking signal is generated;

[0057] After the braking signal is generated, it is determined whether the current vehicle needs to brake. If so, the braking signal is maintained; if not, the vehicle braking signal is withdrawn; specifically, steps S3-1 to S3-4 are included:

[0058] S3-1, determine whether the opening degree of the vehicle brake is 0; if not, no braking signal needs to be generated, and the process goes to step S3-4; if yes, the process goes to step S3-2 and continues the analysis;

[0059] S3-2, find the cluster center closest to the current vehicle attribute data, compare the throttle opening of the cluster center data with the throttle opening of the current vehicle, if the throttle opening of the current vehicle is less than or equal to the throttle opening of the cluster center data, then no braking signal needs to be generated, and the process goes to step S3-4; if it is greater, then the process goes to step S3-3;

[0060] S3-3, determine whether the throttle opening change value is too large, if so, maintain the generated brake signal and end; if not, enter step S3-4;

[0061] Steps S4-1 and S4-2 are used to determine whether the throttle opening change is too large:

[0062] S4-1, with v, k and dk representing the current vehicle speed, throttle opening and throttle opening change value, , and Indicates the cluster center closest to the current vehicle attribute data The vehicle speed, throttle opening and throttle opening change value; at the cluster center In the cluster where the vehicle is located, the vehicle speed, throttle opening and throttle opening change value in the vehicle attribute data are taken to form data points, and the data point with the smallest difference from the current vehicle's speed, throttle opening and throttle opening change value is found ( ), the difference is calculated as , , and is the cluster center The vehicle speed, throttle opening and throttle opening change value in the cluster where j is a positive integer;

[0063] S4-2, obtain cluster center Vehicle attribute data and cluster center in the cluster The longest distance , adjust the current vehicle speed and throttle from v and k to and , calculate the current vehicle attribute data and cluster center again The distance E between , if E is less than or equal to , then the throttle opening change value is judged to be not too large, and the process ends; if E is greater than , then the critical value of dk is calculated according to the following formula :

[0064] = ;

[0065] Get dk with If dk and If the difference between dk and If the difference is greater than the threshold, it is judged that the throttle opening change is too large;

[0066] At the cluster center In the cluster where the vehicle is located, the standard deviation σ of the throttle opening change value in all vehicle attribute data is calculated, then the threshold is N×σ, N is a positive number less than or equal to 3, and N is 1, then the threshold is σ, when dk- When dk- is less than or equal to σ, the logic controller withdraws the braking signal and continues to output a 100% throttle opening signal; When it is greater than σ, the logic controller maintains the braking signal and outputs a braking signal greater than 0; the normal output of the logic control is a 100% throttle opening signal. When an abnormal value appears in the vehicle attribute data, a braking signal is generated, that is, a 0% throttle opening signal is output, and it is determined whether the braking signal needs to be withdrawn; if it needs to be withdrawn, the logic controller restores the 0% throttle opening signal to a 100% throttle opening signal. If it does not need to be withdrawn, the output of the 0% throttle opening signal is maintained.

[0067] S3-4, withdraw the generated braking signal, the current vehicle does not need to brake, and the process ends.

[0068] The final values ​​of the vehicle brake signal and throttle signal are obtained through the following steps:

[0069] The logic controller determines whether the vehicle needs braking based on the current vehicle attribute data. If braking is not required, the logic controller outputs a 100% throttle opening signal. If braking is required, the logic controller outputs a 0% throttle opening signal.

[0070] The logic controller and the driver's signal applied to the throttle are minimized to generate the final value of the throttle signal to control the vehicle;

[0071] The throttle opening signal output by the logic controller is inverted and then taken to be the maximum value with the signal applied by the driver to the brake to generate the final value of the vehicle braking signal.

[0072] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0073] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A safety throttle emergency braking control method based on artificial intelligence, characterized in that: The following steps are involved: S1-1, obtaining attribute data of the vehicle; S1-2, normalizing the attribute data of the vehicle, performing clustering by using the kmeans algorithm, and determining whether the attribute data of the current vehicle is abnormal, including steps S2-1 to S2-3; S2-1, the vehicle attribute data includes throttle opening, throttle opening change value and vehicle speed; according to the slope of the road section where the vehicle is located, the kmeans distance operation is performed on the vehicle attribute data under the same slope; the slope conditions include uphill, downhill and flat road; S2-2, based on the kmeans clustering results, obtain the cluster center and clusters, as well as the maximum distance between the vehicle attribute data in each cluster and the cluster center , the value range of i is a positive integer between [1, n], and n is the number of clusters; S2-3, calculate the distance between the current vehicle attribute data and each cluster center , if for all cases within the value range of i, Are greater than , then the attribute data of the current vehicle is abnormal; otherwise, the attribute data of the current vehicle is normal; S1-3, if the attribute data of the current vehicle is abnormal, a braking signal is generated; if there is no abnormality, no braking signal is generated; After the brake signal is generated, it is determined whether the current vehicle needs to be braked. If so, the brake signal is maintained; if not, the vehicle brake signal is withdrawn.

2. The artificial intelligence-based safety throttle emergency brake control method according to claim 1 is characterized in that: Step S1-3 also includes the following steps: S3-1, determine whether the opening degree of the vehicle brake is 0; if not, no braking signal needs to be generated, and the process goes to step S3-4; if so, the process goes to step S3-2 and continues the analysis; S3-2, find the cluster center closest to the current vehicle attribute data, compare the throttle opening of the cluster center data with the throttle opening of the current vehicle, if the throttle opening of the current vehicle is less than or equal to the throttle opening of the cluster center data, then no braking signal needs to be generated, and the process goes to step S3-4; if it is greater, then the process goes to step S3-3; S3-3, determine whether the throttle opening change value is too large, if so, maintain the generated brake signal and end; if not, enter step S3-4; S3-4, withdraw the generated braking signal, the current vehicle does not need to brake, and the process ends.

3. The artificial intelligence-based safety throttle emergency brake control method according to claim 2 is characterized in that: In step S3-3, the step of determining whether the throttle opening change value is too large further includes the following steps: S4-1, with v, k and dk representing the current vehicle speed, throttle opening and throttle opening change value, , and Indicates the cluster center closest to the current vehicle attribute data The vehicle speed, throttle opening and throttle opening change value; at the cluster center In the cluster where the vehicle is located, the vehicle speed, throttle opening and throttle opening change value in the vehicle attribute data are taken to form data points, and the data point with the smallest difference with the current vehicle speed, throttle opening and throttle opening change value is found ( ), the difference is calculated as , , and is the cluster center The vehicle speed, throttle opening and throttle opening change value in the cluster where j is a positive integer; S4-2, obtain cluster center Vehicle attribute data and cluster center in the cluster The longest distance , adjust the current vehicle speed and throttle from v and k to and , calculate the current vehicle attribute data and cluster center again The distance E between , if E is less than or equal to , then the throttle opening change value is judged to be not too large, and the process ends; if E is greater than , then the critical value of dk is calculated according to the following formula : = ; Get dk with If dk and If the difference between dk and If the difference is greater than the threshold, it is judged that the throttle opening change is too large.

4. The artificial intelligence-based safety throttle emergency brake control method according to claim 3 is characterized in that: The threshold is determined by the following steps: At the cluster center In the cluster where the vehicle is located, the standard deviation σ of the throttle opening change value in all vehicle attribute data is calculated, and the threshold is N×σ, where N is a positive number less than or equal to 3.

5. The artificial intelligence-based safety throttle emergency brake control method according to claim 4 is characterized in that: The final values ​​of the vehicle brake signal and throttle signal are obtained through the following steps: The logic controller determines whether the vehicle needs braking based on the current vehicle attribute data. If braking is not required, the logic controller outputs a 100% throttle opening signal. If braking is required, the logic controller outputs a 0% throttle opening signal. The logic controller and the driver's signal applied to the throttle are minimized and the final value of the throttle signal is generated to control the vehicle; The throttle opening signal output by the logic controller is inverted and then taken to be the maximum value with the signal applied by the driver to the brake to generate the final value of the vehicle braking signal.

6. An artificial intelligence-based safety throttle emergency brake control system, using an artificial intelligence-based safety throttle emergency brake control method as described in any one of claims 1-5, characterized in that: include: Vehicle attribute data collection module, vehicle driving section judgment module, vehicle attribute data storage module, logic control module and vehicle attribute data clustering module; The output end of the vehicle attribute data acquisition module is connected to the input end of the vehicle attribute data storage module to obtain the attribute data of the vehicle during driving; The output end of the vehicle driving section judgment module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module, and is used to judge the slope of the road section where the vehicle is located, and the slope includes uphill, downhill and flat road; the output end of the vehicle attribute data storage module is interconnected with the input end of the logic control module and the vehicle attribute data clustering module, and is used to store the attribute data of the vehicle during driving; the logic control module generates the final value of the vehicle brake signal and the throttle signal based on the current vehicle attribute data and the clustering result of the vehicle attribute data clustering module; The output end of the vehicle attribute data clustering module is connected to the input end of the logic control module, and the kmeans clustering algorithm is used to determine whether the current vehicle attribute data is abnormal.

7. The artificial intelligence-based safety throttle emergency brake control system according to claim 6 is characterized in that: The vehicle driving section judgment module also includes a sensor unit, a dynamic model unit and a data fusion unit. The sensor unit is used to obtain three-dimensional motion information of the vehicle. The data fusion unit is used to fuse the information obtained by the sensor unit. The dynamic model unit estimates the slope of the road section where the vehicle is located through the vehicle's dynamic model based on the fused three-dimensional motion information of the vehicle.

8. The artificial intelligence-based safety throttle emergency brake control system according to claim 6 is characterized in that: The logic control module also includes a logic controller, an inverter, a maximum value unit and a minimum value unit; the logic controller is used to output a throttle signal, the output of the logic controller is connected to one end of the minimum value unit input, and the output of the logic controller is connected to one end of the maximum value unit input after passing through the inverter; the other end of the minimum value unit input is the signal applied by the driver to the throttle of the vehicle, and the other end of the maximum value unit input is the signal applied by the driver to the brake of the vehicle; the output of the maximum value unit is the final value of the vehicle braking signal, and the output of the minimum value unit is the final value of the vehicle throttle signal.

9. The artificial intelligence-based safety throttle emergency brake control system according to claim 6 is characterized in that: The vehicle attribute data clustering module performs kmeans clustering on the periodic historical vehicle attribute data, and obtains the cluster center and cluster clusters according to the kmeans clustering results; when the vehicle is driving, it is judged whether the attribute data of the current vehicle is abnormal according to the distance between the vehicle attribute data and the cluster center.

Citation Information

Patent Citations

  • Individualized intelligent accelerator pedal device and control method thereof

    CN108189668A

  • Vehicle accelerator control method, system, vehicle and storage medium

    CN110834537A

  • Accelerator mistaken stepping control method, device and equipment and storage medium

    CN115214596A

  • Intelligent auxiliary teaching system safety early warning and protection function test system and method

    CN116881778A

  • Vehicle pedal erroneous stepping correspondence control device

    JP2021030882A