Vehicle emergency braking method, device and equipment and storage medium

By obtaining and filtering obstacle information and identifying driving scenarios and obstacle types, accurate brake stops for low-speed emergency braking are achieved, solving the problems of unreliable stopping distance and high false triggering rate, and improving the accuracy of emergency braking and efficiency.

CN119078819APending Publication Date: 2024-12-06VOYAH AUTOMOBILE TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411402655.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-09
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The stopping distance of low-speed emergency braking cannot be guaranteed, the error trigger rate is high, the existing technology structure is complex and resource consumption is large.

Method used

By obtaining obstacle information and bicycle information, multiple screenings are performed to determine target obstacles, and emergency braking decisions are made based on the driving scenarios and types of target obstacles, and errors and calculations are reduced using the hierarchical structure of pre-screening and final screening. redundancy.

Benefits of technology

有效筛选出高置信度的障碍物目标,降低误差发生的概率,保证不同场景下的刹停距离,提高紧急制动的准确性和效率。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078819A_ABST
    Figure CN119078819A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle emergency braking method, device and equipment and a storage medium, and relates to the technical field of vehicle control, and the method comprises the steps that obstacle information and vehicle information are obtained, and effective obstacles are obtained according to the obstacle information and the vehicle information; performing multiple times of screening according to the effective obstacle target to obtain a target obstacle; identifying a driving scene of the target obstacle, and obtaining a scene time threshold value of the target obstacle based on the driving scene; vehicle emergency braking is carried out according to the scene time threshold value of the target obstacle, the obstacle type and the obstacle confidence coefficient; according to the method, barriers are screened by using a hierarchical structure of pre-screening, final screening and scene processing, so that the barriers can be effectively screened out, barrier targets which are high in confidence and related to a vehicle can be reserved, the probability of error occurrence is reduced, the targets after pre-screening are further subjected to multi-layer screening, the calculation redundancy is reduced, and the calculation efficiency is improved. Scene processing is added, so that the braking distance of various types of obstacles in different scenes is effectively ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle emergency braking method, device, equipment and storage medium. Background Art

[0002] In recent years, the complexity of low-speed emergency braking application scenarios has increased and the types of obstacles have increased. At low speeds and close distances, emergency braking of various obstacles needs to be completed. The current screening method has complex structure, high resource consumption, and the braking distance of low-speed emergency braking cannot be guaranteed, and the false trigger rate is high.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a vehicle emergency braking method, device, equipment and storage medium, aiming to solve the current technical problems of low-speed emergency braking that the stopping distance cannot be guaranteed and the false triggering rate is high.

[0005] To achieve the above objectives, the present application proposes a vehicle emergency braking method, the vehicle emergency braking method comprising:

[0006] Obtaining obstacle information and vehicle information, and obtaining effective obstacles according to the obstacle information and vehicle information;

[0007] Perform multiple screenings based on the effective obstacles to obtain target obstacles;

[0008] Identifying a driving scene of the target obstacle, and obtaining a scene time threshold of the target obstacle based on the driving scene;

[0009] The vehicle emergency braking is performed according to the scene time threshold of the target obstacle, the obstacle type and the obstacle confidence.

[0010] In one embodiment, the obtaining of obstacle information and vehicle information, and obtaining a valid obstacle according to the obstacle information and vehicle information, includes:

[0011] Obtain obstacle information and vehicle information;

[0012] Obtaining vehicle heading and slope information according to the vehicle information, optimizing the size of the vehicle model according to the vehicle heading and the slope information, and obtaining a vehicle reference model;

[0013] Performing four-corner optimization on the ego-vehicle reference model to obtain an ego-vehicle model;

[0014] The trajectory coordinates of the vehicle are obtained by performing trajectory prediction according to the vehicle model, and effective obstacles are obtained according to the trajectory coordinates and the obstacle information.

[0015] In one embodiment, the step of performing multiple screenings based on the effective obstacles to obtain the target obstacles includes:

[0016] Based on the trajectory prediction time of the ego vehicle, the fastest collision time and the shortest relative distance between each obstacle and the ego vehicle are obtained;

[0017] The importance of each obstacle is obtained according to the fastest collision time and the shortest relative distance of each obstacle;

[0018] Perform preliminary screening according to the fastest collision moment, the shortest relative distance and the importance to obtain an initial obstacle;

[0019] The initial obstacles are screened again according to the fastest collision time, confidence, collision type and importance to obtain target obstacles.

[0020] In one embodiment, the initial obstacle is obtained by preliminary screening according to the fastest collision time, the shortest relative distance and the importance, including:

[0021] Obtain a reference array based on the fastest collision moment, the shortest relative distance and the importance of each obstacle;

[0022] Obtaining the number of obstacles whose fastest collision time is less than N seconds from the reference array;

[0023] A screening strategy is determined according to the number of obstacles, and initial obstacles are obtained based on the screening strategy.

[0024] In one embodiment, the re-screening of the initial obstacles according to the fastest collision time, confidence, collision type, and importance to obtain the target obstacle includes:

[0025] Arrange the initial obstacles from small to large based on the fastest collision moment to obtain a target sequence;

[0026] Obtaining the number of obstacles with the fastest collision time less than n based on the target sequence;

[0027] When the number of obstacles is 0 or the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is less than n, the first m initial obstacles in the target sequence are used as target obstacles;

[0028] When the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is greater than or equal to n, the initial obstacles are screened according to the confidence, collision type and importance to obtain a target obstacle.

[0029] In one embodiment, the identifying the driving scene of the target obstacle and obtaining the scene time threshold of the target obstacle based on the driving scene includes:

[0030] Obtaining an obstacle area according to the coordinates of the target obstacle, and obtaining a driving scene according to the driving scene in the vehicle information and the obstacle area;

[0031] Based on the preset scenario collision time table, the collision time corresponding to the vehicle speed, the vehicle heading angle and the obstacle type in the driving scenario is obtained;

[0032] The sum of the multiple collision times is used as the scene time threshold.

[0033] In one embodiment, performing emergency braking of the vehicle according to the scene time threshold, obstacle type, and obstacle confidence of the target obstacle includes:

[0034] When the scene time threshold is less than or equal to the minimum collision time threshold, the obstacle type is a fused obstacle, and the obstacle confidence is greater than or equal to the confidence threshold, emergency braking of the vehicle is controlled.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle emergency braking device, the vehicle emergency braking device comprising:

[0036] An information acquisition module, used to acquire obstacle information and vehicle information, and obtain effective obstacles according to the obstacle information and vehicle information;

[0037] An obstacle screening module, used for performing multiple screenings based on the valid obstacles to obtain target obstacles;

[0038] The obstacle screening module is further used to identify the driving scene of the target obstacle and obtain the scene time threshold of the target obstacle based on the driving scene;

[0039] The emergency braking module is used to perform emergency braking of the vehicle according to the scene time threshold, obstacle type and obstacle confidence of the target obstacle.

[0040] In addition, to achieve the above objectives, the present application also proposes a vehicle emergency braking device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle emergency braking method described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle emergency braking method described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle emergency braking method described above are implemented.

[0043] One or more technical solutions proposed in this application have at least the following technical effects: BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the vehicle emergency braking method of the present application;

[0047] Figure 2 A schematic diagram of an optimized vehicle model provided in Embodiment 1 of the vehicle emergency braking method of the present application;

[0048] Figure 3 A schematic diagram of a complete process of vehicle emergency braking provided in Embodiment 1 of the vehicle emergency braking method of the present application;

[0049] Figure 4 A schematic diagram of a flow chart provided for the second embodiment of the vehicle emergency braking method of the present application;

[0050] Figure 5 This is a schematic diagram of the module structure of the vehicle emergency brake device according to an embodiment of the present application;

[0051] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the vehicle emergency braking method in the embodiment of the present application. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the embodiment of the present application is: obtaining obstacle information and vehicle information, and obtaining effective obstacles based on the obstacle information and vehicle information; performing multiple screenings based on effective obstacle targets to obtain target obstacles; identifying the driving scene of the target obstacle, and obtaining the scene time threshold of the target obstacle based on the driving scene; and performing vehicle emergency braking based on the scene time threshold of the target obstacle, the obstacle type, and the obstacle confidence.

[0055] In this embodiment, for the convenience of description, the following description is made by taking the identification of the vehicle emergency brake equipment as the execution subject.

[0056] Due to the increase in the complexity of low-speed emergency braking application scenarios and the increase in the types of obstacles in recent years, emergency braking of various obstacles needs to be completed at low speeds and close distances. The current screening method has complex structure, high resource consumption, and the braking distance of low-speed emergency braking cannot be guaranteed, and the false trigger rate is high.

[0057] The present application provides a solution, which can effectively screen out obstacles by utilizing a hierarchical structure of pre-screening, final screening, and scene processing to screen obstacles, retain obstacle targets with high confidence and related to the vehicle, reduce the probability of error occurrence, perform further multi-layer screening on the pre-screened targets, reduce calculation redundancy, and increase scene processing to effectively ensure the braking distance of various types of obstacles in different scenarios.

[0058] It can be seen from the above embodiments that the present application discloses a vehicle emergency braking method, device, equipment and storage medium, which relates to the field of vehicle control technology, and discloses: obtaining obstacle information and self-vehicle information, and obtaining effective obstacles according to the obstacle information and self-vehicle information; performing multiple screenings according to effective obstacle targets to obtain target obstacles; identifying the driving scene of the target obstacle, and obtaining the scene time threshold of the target obstacle based on the driving scene; performing vehicle emergency braking according to the scene time threshold of the target obstacle, the obstacle type and the obstacle confidence; the method screens obstacles by using a hierarchical structure of pre-screening, final screening and scene processing, so as to effectively screen out obstacles, retain obstacle targets with high confidence and related to the self-vehicle, reduce the probability of error occurrence, perform further multi-layer screening on the pre-screened targets, reduce calculation redundancy, and increase scene processing to effectively ensure the braking distance of various types of obstacles in different scenarios.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a vehicle emergency brake device, etc. The following takes the vehicle emergency brake device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the embodiment of the present application provides a vehicle emergency braking method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle emergency braking method of the present application.

[0061] In this embodiment, the vehicle emergency braking method includes steps S10 to S40:

[0062] Step S10, obtaining obstacle information and vehicle information, and obtaining effective obstacles according to the obstacle information and vehicle information.

[0063] It is understandable that a valid obstacle may be an obstacle that is judged to be likely to collide with the ego vehicle based on obstacle information and ego vehicle information.

[0064] It should be understood that the screening process of low-speed emergency braking is pre-screened according to the vehicle's motion trajectory and obstacle confidence information, mainly to screen effective obstacles and reduce the probability of false triggering.

[0065] It is understandable that the obstacle information may include the position coordinates of the obstacle, the speed and driving direction of the obstacle, etc.; the vehicle information may include the position, driving direction, speed, acceleration and inclination angle of the vehicle, etc.;

[0066] In a feasible implementation, step S10 may include steps A11 to A14:

[0067] Step A11, obtaining obstacle information and vehicle information.

[0068] It is understandable that the information related to the vehicle can be directly obtained through the information such as the vehicle speed, the vehicle position, the vehicle acceleration, the vehicle steering angle, etc.; the information such as the relative distance, relative speed, relative driving direction between the vehicle and the obstacle can be obtained through image acquisition, thereby obtaining the obstacle information.

[0069] Step A12, obtaining vehicle heading and slope information according to the vehicle information, optimizing the size of the vehicle model according to the vehicle heading and the slope information, and obtaining a vehicle reference model.

[0070] It should be noted that the vehicle heading can be obtained based on the vehicle information. The gyroscope can measure the angular velocity of the vehicle, and the rotation angle of the vehicle can be obtained through integration operation, and then the vehicle heading can be calculated; or the magnetometer can measure the changes in the earth's magnetic field, and these data can be used to determine the direction of the vehicle relative to the geographic North Pole, that is, the heading; or the global positioning system can provide vehicle location information. Through continuous position point calculation, the vehicle's moving direction, that is, the heading, can be obtained.

[0071] It should be noted that the slope information obtained from the vehicle information can be obtained by using an inclination sensor to measure the vehicle's tilt angle on the vertical axis, thereby obtaining the vehicle's slope; or an accelerometer can measure the vehicle's acceleration in all directions, and by analyzing these data, the vehicle's tilt angle in different directions can be calculated, thereby obtaining the slope; or by combining a high-precision map and the vehicle's current position, the elevation data on the map can be used to estimate the slope of the vehicle. Alternatively, a combined navigation system can also be used to estimate the slope, especially when the GNSS signal is poor, INS can provide short-term slope information.

[0072] It should be noted that the size of the ego vehicle model is optimized according to the vehicle heading and the slope information, and the ego vehicle reference model can be obtained by dividing the scene into four major scenes: straight flat ground, straight ramp, turning flat ground and turning slope according to the vehicle heading and slope information. For each scene, the size of the left and right vehicles must be expanded or contracted accordingly. The purpose of doing this is mainly to prevent obstacles that are not under the driving trajectory of the ego vehicle from being screened in and causing misbraking.

[0073] Step A13, performing four-corner optimization on the ego vehicle reference model to obtain an ego vehicle model.

[0074] It should be noted that the ego vehicle model is defined first, and the ego vehicle is simplified into an octagon. The four-corner optimization can be to regard the vehicle as a rectangle first, and calculate the coordinates of the four corner points (ABCD) through trajectory prediction of the ego vehicle coordinates and heading angle information. However, in fact, the four corners of the car are arcs, and it is not accurate to define the ego vehicle model with a rectangle. Therefore, the four corners are cut off to obtain an octagonal ego vehicle model (abcdefgh), and the coordinates of each corner point are calculated for subsequent collision judgment calculations. The optimized ego vehicle model can be referred to Figure 2 In the figure, A, B, C, and D are the coordinate points of the four corners of the ego-vehicle model before optimization, and a, b, c, d, e, f, g, and h are the four angle coordinates of the four corners of the ego-vehicle model after optimization.

[0075] Step A13, performing trajectory prediction according to the vehicle model to obtain the vehicle trajectory coordinates, and obtaining effective obstacles according to the trajectory coordinates and the obstacle information.

[0076] It is understandable that after the four-corner optimization of the ego vehicle model, the coordinate point response corresponding to the trajectory coordinates of the ego vehicle changes. In simple terms, the ego vehicle model is more accurate, avoiding inaccurate collision judgments caused by the four corners of the vehicle body.

[0077] It should be understood that, in a specific implementation, trajectory prediction is performed based on the vehicle model to obtain the vehicle trajectory coordinates, and obtaining the effective obstacle based on the trajectory coordinates and the obstacle information can be based on the meaning of vector cross product to determine whether the obstacle is located inside the vehicle. If it is inside, it means that the obstacle collides with the obstacle at this moment.

[0078] In this implementation, pre-screening is performed through the vehicle's motion trajectory and obstacle confidence information, mainly to screen effective obstacles and reduce the probability of false triggering.

[0079] The above are only feasible implementations of step S10 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S10.

[0080] Step S20, performing multiple screenings based on the effective obstacles to obtain target obstacles.

[0081] It is understandable that performing multiple screenings based on the effective obstacles may include screening the effective obstacles twice.

[0082] It should be noted that the first of the two screenings can be based on obstacle information and the distance and collision time between the obstacle and the vehicle to obtain 10 preliminary selected obstacles. The number of preliminary selected obstacles is predetermined and can also be adjusted according to actual conditions. This embodiment does not limit this.

[0083] Furthermore, secondary screening is performed based on the collision time, confidence, collision type, and collision scene of the initially selected obstacles to obtain the final target obstacle.

[0084] Step S30: identifying a driving scene of the target obstacle, and obtaining a scene time threshold of the target obstacle based on the driving scene.

[0085] It is understandable that the driving scenario for identifying the target obstacle can be 12 scenarios composed of four major scenarios: straight flat ground, straight ramp, turning flat ground and turning slope, which are divided into four scenarios according to the location of the obstacle and the vehicle heading and slope information.

[0086] It should be understood that different driving conditions will be encountered when driving due to different scenarios, and there are time thresholds corresponding to each scenario, and collision judgment is performed based on the scenario time threshold.

[0087] In a feasible implementation, step S30 may include steps A31 to A33:

[0088] Step A31, obtaining an obstacle area according to the coordinates of the target obstacle, and obtaining a driving scene according to the driving scene in the vehicle information and the obstacle area.

[0089] It is understandable that the coordinate of the target obstacle may be the Y coordinate of the target obstacle in the world coordinate system, and the area where the obstacle is located is divided into three areas: left, middle and right based on the Y coordinate of the obstacle.

[0090] It should be understood that the driving scenes in the vehicle information are divided into four major scenes: straight flat ground, straight ramp, turning flat ground and turning slope according to the vehicle heading and slope information.

[0091] It should be noted that the driving scenarios include 12 scenarios, each of which corresponds to an obstacle area. There are four types of driving scenarios, and each of which corresponds to three areas.

[0092] Step A32, based on the preset scenario collision time table, obtain the collision time corresponding to the vehicle speed, the vehicle heading angle and the obstacle type in the driving scenario.

[0093] It should be noted that the closest collision time based on vehicle speed, the closest collision time based on vehicle heading angle, and the closest collision time based on obstacle type in various scenarios are pre-calibrated.

[0094] It is understandable that there are three collision times for each scenario based on the calibration.

[0095] Step A33: taking the sum of the multiple collision times as the scene time threshold.

[0096] It is understandable that the three collision times in each scene are added together to obtain the sum of the collision times, and the sum of the collision times is used as the scene time threshold of the scene.

[0097] In this embodiment, by adding a scene processing module, the braking distance of various types of obstacles in different scenarios can be effectively guaranteed. At the same time, the scene time threshold in each scene is considered, and emergency braking judgment is made based on the scene time threshold, which can perform emergency braking more accurately.

[0098] The above are only feasible implementations of step S30 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S30.

[0099] Step S40: performing emergency braking of the vehicle according to the scene time threshold, obstacle type and obstacle confidence of the target obstacle.

[0100] It is understandable that when the scene time threshold is less than or equal to the minimum collision time threshold, the obstacle type is a fused obstacle, and the obstacle confidence is greater than or equal to the confidence threshold, the vehicle is controlled to perform emergency braking.

[0101] In the specific implementation, the ttc (last collision time), type, confidence, etc. of the five screened obstacles are judged to see whether they meet the braking conditions. If one of them meets the conditions, the braking is performed. When one of the last five obstacles meets the following conditions at the same time: a. ttc is less than or equal to 1.5s; b. the obstacle type is a fusion obstacle (such as a person, a two-wheeled vehicle, a car, a trash can, a wall, a warning column, a ground lock, a stone pier, etc.); c. the confidence of the obstacle is 70; then the braking is performed.

[0102] It should be noted that the complete process of vehicle emergency braking can be referred to Figure 3 , the figure includes four steps: pre-screening, fine screening, scene time threshold calculation and emergency braking judgment; among them, pre-screening is to screen out n effective obstacle targets based on vehicle motion information and obstacle confidence; fine screening is to screen out the final 5 targets required from n obstacles, specifically, the TTC and dist of n obstacles are calculated and added to the obstacle information, the obstacle information is sorted according to TTC and dist, the index is obtained, and it is sorted into array A, 10 obstacles with ttc less than 5s are taken out, and then the last 5 obstacle targets are taken out according to ttc, confidence, scene division and other conditions; scene time threshold calculation is to look up the table according to vehicle speed, scene, and obstacle type in each scene to get the ttc threshold, and take the sum of the three as the scene time threshold; emergency braking judgment is that if one or more of the 5 obstacles meet the braking conditions, braking needs to be executed.

[0103] This embodiment provides a vehicle emergency braking method, which can effectively screen out obstacles by using a hierarchical structure of pre-screening, final screening and scene processing to screen obstacles, retain obstacle targets with high confidence and related to the vehicle, reduce the probability of error occurrence, perform further multi-layer screening on the pre-screened targets, reduce calculation redundancy, and increase scene processing to effectively ensure the braking distance of various types of obstacles in different scenarios.

[0104] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , step S20, the vehicle emergency braking method further includes steps S21 to S24:

[0105] Step S21, based on the trajectory prediction time of the vehicle, the fastest collision time and the shortest relative distance between each obstacle and the vehicle are obtained.

[0106] It should be noted that the relative position and relative speed of the ego vehicle and the obstacle can be obtained based on the ego vehicle information and obstacle information; the speed and acceleration of the ego vehicle and the obstacle are used to predict the future trajectory.

[0107] Furthermore, the encounter time (i.e., the fastest collision time) is obtained according to the relative distance and relative speed between the vehicle and the obstacle.

[0108] Furthermore, the shortest relative distance is the shortest distance between the vehicle and the obstacle, which can also be directly understood as the relative distance.

[0109] In the specific implementation, n obstacle information is received, and the obstacles make collision judgments and calculate boundary distances with the vehicle at the predicted moments of the motion trajectories of the respective vehicles (m cycles), thereby calculating the fastest collision time (ttc) and the shortest distance (dist) with the vehicle.

[0110] Step S22, obtaining the importance of each obstacle according to the fastest collision time and the shortest relative distance of each obstacle.

[0111] It is understandable that the two types of information, ttc and dist, are added to their respective obstacle sequences to form a complete obstacle information sequence for subsequent screening.

[0112] It should be noted that all obstacles are sorted according to TTC and Dist to obtain an "index", which indicates the importance or urgency of each obstacle.

[0113] Step S23, performing preliminary screening according to the fastest collision time, the shortest relative distance and the importance to obtain an initial obstacle.

[0114] In a feasible implementation, step S23 may include steps A231 to A233:

[0115] Step A231, obtaining a reference array based on the fastest collision moment, the shortest relative distance and the importance of each obstacle.

[0116] It should be noted that TTC, Dist and index are organized into an array A of n rows and 3 columns, and arranged in descending order of TTC to obtain a new array B. Array B can be understood as a reference array.

[0117] Step A232, obtaining the number of obstacles whose fastest collision time is less than N seconds from the reference array.

[0118] It should be noted that N is 5 in this embodiment, that is, the number of obstacles with the fastest collision time less than 5 seconds obtained from the reference array can also be adjusted according to actual conditions, which is not limited in this embodiment.

[0119] Step A233: determining a screening strategy according to the number of obstacles, and obtaining initial obstacles based on the screening strategy.

[0120] It should be noted that different screening strategies can be determined for the number of obstacles, and the screening strategy is based on the reference array for screening.

[0121] It should be emphasized that if k is less than 10, then in addition to the obstacles with TTC less than 5 seconds, the first 10-k obstacles are sorted in descending order from the obstacles with TTC greater than 5 seconds; if k is equal to 10, the indexes of these 10 obstacles are directly output; if k is greater than 10, further processing is required: if the TTCs of the 10th and 11th obstacles are different, the indexes of the first 10 obstacles are directly output; if the TTCs of the 10th and 11th obstacles are the same, find the number h of obstacles with the same TTC as the 10th obstacle, and then take the first 10-h obstacles from these obstacles with the same TTC in descending order.

[0122] In a specific implementation, n obstacles are sorted and screened according to their ttc and dist to obtain an index, ttc, dist, and index are organized into an n*3 array A and arranged in descending order according to ttc to obtain an array B, 10 obstacles with ttc less than 5s are taken out and arranged according to the index: if the number of obstacles with ttc less than 5s is k, when k<10, the ttc greater than 5s is arranged in descending order, and the first 10-k indexes are taken out and supplemented in the order of ttc; when k=10, the index of the sorted array is output as the filtered index; when k>10, if the tenth element and the eleventh array in array B are not equal, the first 10 index columns of array B are output; if the tenth element and the eleventh array in array B are equal, the number h that is not equal to the tenth element is obtained, the array equal to the tenth element in the array is taken out and arranged in descending order to obtain the first 10-h indexes to supplement it.

[0123] In this implementation, by calculating TTC (Time To Collision) and Dist (distance), obstacles that are most likely to cause collisions are placed in front, and priority is given to obstacles that pose an immediate threat to the vehicle, so that necessary risk avoidance measures can be taken in advance; at the same time, by screening out the most relevant obstacles, unnecessary calculations are reduced, thereby reducing the processor load, allowing the system to run more efficiently.

[0124] The above are only feasible implementations of step S23 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S23.

[0125] Step S24: the initial obstacles are screened again according to the fastest collision time, confidence, collision type and importance to obtain target obstacles.

[0126] In a feasible implementation, step S24 may include steps A241 to A243:

[0127] Step A241, arranging the initial obstacles from small to large based on the fastest collision time to obtain a target sequence, and obtaining the number of obstacles whose fastest collision time is less than n based on the target sequence.

[0128] It should be noted that n can be 5 or other values, can be adjusted according to actual conditions, and can be the same as N or different.

[0129] Step A242: When the number of obstacles is 0 or the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is less than n, the first m initial obstacles in the target sequence are used as target obstacles.

[0130] It should be noted that the number of obstacles being 0 can be understood as if the number of obstacles with TTC less than 5 seconds among 10 obstacles is 0, and the first 5 obstacles are directly taken as the final result.

[0131] It should be noted that this embodiment is described with m being 5, and m may also be adjusted, which is not limited in this embodiment.

[0132] It should be noted that the fastest collision time of the mth initial obstacle in the target sequence is less than n, which can be understood as if the TTC of the fifth obstacle is less than 5 seconds, the first five obstacles are directly taken as the final result.

[0133] In the specific implementation, the 10 obstacles screened in the previous step are further screened, and the indexes of the 5 obstacles that need to be output are finally obtained by screening according to ttc, confidence, type, scene division, etc. If the number of obstacles with ttc less than 5s among the 10 obstacles is equal to 0, the first 5 obstacles are directly taken as the index output after screening.

[0134] Step A243, when the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is greater than or equal to n, the initial obstacles are screened according to the confidence, collision type and importance to obtain the target obstacle.

[0135] It should be understood that the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is greater than or equal to n, which can be understood as the TTC of the fifth obstacle is greater than 5 seconds.

[0136] It should be noted that the initial obstacles are screened according to the confidence, collision type and importance, and the target obstacles can be obtained by organizing the confidence, type, index and priority (pri) into an array C with 10 rows and 4 columns; obstacles with a TTC greater than 5 seconds are extracted from array C to form a new array D; array D is arranged in descending order according to the priority (pri) to obtain array E; the indices of the first 10-k obstacles with a TTC less than 5 seconds are taken from array C, and the indices of the first 5-(10-k) obstacles in array E are added as the final indices of the 5 obstacles.

[0137] In the specific implementation, if the number of obstacles with ttc less than 5s among 10 obstacles is greater than 0, when the ttc of the fifth obstacle is less than 5s, the first five obstacles are directly taken as the filtered index output; when the ttc of the fifth obstacle is greater than 5s, the confidence, type, index and pri (priority) are sorted into a 10*4 array C, and obstacles with ttc greater than 5s are taken out to form a new array D, and array E is obtained by descending order according to the pri column in array D. The first 10-k indices with ttc less than 5s in array C and the first 5-(10-k) indices in E are taken as the filtered index output. In this way, the last 5 obstacle targets can be filtered out according to the index, which can reduce the redundancy of calculation.

[0138] In this implementation, by giving priority to obstacles with a TTC (Time To Collision) of less than 5 seconds, these obstacles can be quickly identified and handled, thereby improving driving safety. Further consideration is given to multiple factors such as confidence, type, priority, etc., and not just relying on a single indicator (such as TTC), but rather comprehensively considering various factors to assess the risk level of obstacles. At the same time, when the number of obstacles with a TTC of less than 5 seconds is less than 5, the strategy is automatically adjusted to select the most urgent obstacles from the remaining obstacles to supplement them. Reasonable decisions can be made in different scenarios, and unnecessary computing burden can be reduced based on the screening of target obstacles, thereby ensuring that the system can operate efficiently.

[0139] The above are only feasible implementations of step S24 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S24.

[0140] This embodiment provides a vehicle emergency braking method, which, through a multi-level screening mechanism for target obstacles, can ensure that the most pressing obstacles can be quickly and accurately identified and processed when facing a complex traffic environment, thereby improving driving safety and system reliability; at the same time, a smaller amount of obstacle collision assessment data can reduce unnecessary computing burden and ensure that the system can operate efficiently.

[0141] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the vehicle emergency braking method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0142] This application also provides a vehicle emergency brake device, please refer to Figure 5 , the vehicle emergency braking device comprises:

[0143] The information acquisition module 10 is used to acquire obstacle information and vehicle information, and obtain effective obstacles according to the obstacle information and vehicle information;

[0144] The obstacle screening module 20 is used to perform multiple screenings based on the effective obstacles to obtain target obstacles;

[0145] The obstacle screening module 20 is further used to identify the driving scene of the target obstacle and obtain the scene time threshold of the target obstacle based on the driving scene;

[0146] The emergency braking module 30 is used to perform emergency braking of the vehicle according to the scene time threshold, obstacle type and obstacle confidence of the target obstacle.

[0147] The vehicle emergency braking device provided by the present application adopts the vehicle emergency braking method in the above-mentioned embodiment, which can solve the technical problems that the braking distance of low-speed emergency braking cannot be guaranteed and the false triggering rate is high. Compared with the prior art, the beneficial effects of the vehicle emergency braking device provided by the present application are the same as the beneficial effects of the vehicle emergency braking method provided by the above-mentioned embodiment, and the other technical features of the vehicle emergency braking device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0148] The present application provides a vehicle emergency braking device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle emergency braking method in the above-mentioned embodiment one.

[0149] Reference below Figure 6, which shows a schematic diagram of the structure of a vehicle emergency braking device suitable for implementing an embodiment of the present application. The vehicle emergency braking device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The vehicle emergency braking device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0150] like Figure 6 As shown, the vehicle emergency brake device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle emergency brake device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle emergency brake device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a vehicle emergency brake device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0151] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0152] The vehicle emergency braking device provided by the present application adopts the vehicle emergency braking method in the above embodiment, which can solve the technical problems that the stopping distance of low-speed emergency braking cannot be guaranteed and the false triggering rate is high. Compared with the prior art, the beneficial effects of the vehicle emergency braking device provided by the present application are the same as the beneficial effects of the vehicle emergency braking method provided by the above embodiment, and the other technical features of the vehicle emergency braking device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0153] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0154] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0155] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle emergency braking method in the above-mentioned embodiment.

[0156] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0157] The computer-readable storage medium may be included in the vehicle emergency brake device; or may exist independently without being assembled into the vehicle emergency brake device.

[0158] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle emergency braking device, the vehicle emergency braking device: obtains obstacle information and vehicle information, and obtains effective obstacles according to the obstacle information and vehicle information; performs multiple screenings according to effective obstacle targets to obtain target obstacles; identifies the driving scene of the target obstacle, and obtains the scene time threshold of the target obstacle based on the driving scene; performs vehicle emergency braking according to the scene time threshold of the target obstacle, the obstacle type, and the obstacle confidence.

[0159] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0160] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0161] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0162] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle emergency braking method, and can solve the technical problems that the braking distance of low-speed emergency braking cannot be guaranteed and the false triggering rate is high. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the vehicle emergency braking method provided by the above-mentioned embodiment, and will not be repeated here.

[0163] The present application also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the vehicle emergency braking method as described above are implemented.

[0164] The computer program product provided by the present application can solve the technical problems that the stopping distance of low-speed emergency braking cannot be guaranteed and the false triggering rate is high. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle emergency braking method provided by the above embodiment, which will not be elaborated here.

[0165] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle emergency braking method, It is characterized in that The vehicle emergency braking method comprises: Obtaining obstacle information and vehicle information, and obtaining effective obstacles according to the obstacle information and vehicle information; Perform multiple screenings based on the effective obstacles to obtain target obstacles; Identifying a driving scene of the target obstacle, and obtaining a scene time threshold of the target obstacle based on the driving scene; The vehicle emergency braking is performed according to the scene time threshold of the target obstacle, the obstacle type and the obstacle confidence.

2. The vehicle emergency braking method according to claim 1, It is characterized in that The obtaining of obstacle information and vehicle information, and obtaining effective obstacles according to the obstacle information and vehicle information, includes: Obtain obstacle information and vehicle information; Obtaining vehicle heading and slope information according to the vehicle information, optimizing the size of the vehicle model according to the vehicle heading and the slope information, and obtaining a vehicle reference model; Performing four-corner optimization on the ego-vehicle reference model to obtain an ego-vehicle model; The trajectory coordinates of the vehicle are obtained by performing trajectory prediction according to the vehicle model, and effective obstacles are obtained according to the trajectory coordinates and the obstacle information.

3. The vehicle emergency braking method according to claim 1, It is characterized in that The step of performing multiple screenings according to the effective obstacles to obtain target obstacles includes: Based on the trajectory prediction time of the ego vehicle, the fastest collision time and the shortest relative distance between each obstacle and the ego vehicle are obtained; The importance of each obstacle is obtained according to the fastest collision time and the shortest relative distance of each obstacle; Perform preliminary screening according to the fastest collision moment, the shortest relative distance and the importance to obtain an initial obstacle; The initial obstacles are screened again according to the fastest collision time, confidence, collision type and importance to obtain target obstacles.

4. The vehicle emergency braking method according to claim 3, It is characterized in that The initial obstacle is obtained by preliminary screening according to the fastest collision time, the shortest relative distance and the importance, including: Obtain a reference array based on the fastest collision moment, the shortest relative distance and the importance of each obstacle; Obtaining the number of obstacles whose fastest collision time is less than N seconds from the reference array; A screening strategy is determined according to the number of obstacles, and initial obstacles are obtained based on the screening strategy.

5. The vehicle emergency braking method according to claim 3, It is characterized in that The initial obstacle is screened again according to the fastest collision time, confidence, collision type and importance to obtain a target obstacle, including: Arrange the initial obstacles from small to large based on the fastest collision time to obtain a target sequence, and obtain the number of obstacles whose fastest collision time is less than n based on the target sequence; When the number of obstacles is 0 or the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is less than n, the first m initial obstacles in the target sequence are used as target obstacles; When the number of obstacles is not 0 and the fastest collision time of the mth initial obstacle in the target sequence is greater than or equal to n, the initial obstacles are screened according to the confidence, collision type and importance to obtain a target obstacle.

6. The vehicle emergency braking method according to any one of claims 1 to 5, It is characterized in that The step of identifying the driving scene of the target obstacle and obtaining a scene time threshold of the target obstacle based on the driving scene includes: Obtaining an obstacle area according to the coordinates of the target obstacle, and obtaining a driving scene according to the driving scene in the vehicle information and the obstacle area; Based on the preset scenario collision time table, the collision time corresponding to the vehicle speed, the vehicle heading angle and the obstacle type in the driving scenario is obtained; The sum of the multiple collision times is used as the scene time threshold.

7. The vehicle emergency braking method according to any one of claims 1 to 5, It is characterized in that The performing vehicle emergency braking according to the scene time threshold, obstacle type and obstacle confidence of the target obstacle includes: When the scene time threshold is less than or equal to the minimum collision time threshold, the obstacle type is a fused obstacle, and the obstacle confidence is greater than or equal to the confidence threshold, emergency braking of the vehicle is controlled.

8. A vehicle emergency brake device, It is characterized in that The vehicle emergency brake device comprises: An information acquisition module, used to acquire obstacle information and vehicle information, and obtain effective obstacles according to the obstacle information and vehicle information; An obstacle screening module, used for performing multiple screenings based on the valid obstacles to obtain target obstacles; The obstacle screening module is further used to identify the driving scene of the target obstacle and obtain the scene time threshold of the target obstacle based on the driving scene; The emergency braking module is used to perform emergency braking of the vehicle according to the scene time threshold, obstacle type and obstacle confidence of the target obstacle.

9. A vehicle emergency braking device, It is characterized in that The device comprises: a memory, a processor, and a vehicle emergency braking program stored in the memory and executable on the processor, wherein the vehicle emergency braking program is configured to implement the vehicle emergency braking method according to any one of claims 1 to 7.

10. A storage medium, It is characterized in that The storage medium stores a vehicle emergency braking program, and when the vehicle emergency braking program is executed by the processor, the vehicle emergency braking method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Control method for reducing false triggering of automatic emergency brake system

    CN119568086A

  • Vehicle emergency braking method and device, vehicle, storage medium and program product

    CN120942297A