EBA deceleration request method and system based on vision and automobile

Abstract

The invention discloses a vision-based EBA deceleration request method, which comprises the following steps: S1, after detecting that a longitudinal collision risk exists between a vehicle and a target vehicle, starting to periodically predict a longitudinal driving track TH of the vehicle and a longitudinal driving track TG of the target vehicle; s2, detecting whether the longitudinal driving track TH of the vehicle in the current prediction period is overlapped with the longitudinal driving track TG of the target vehicle in the current period or not, and if the detection result is yes, determining the deceleration increment requested by the current prediction period based on the relative vehicle speed during collision; and S3, after it is detected that the driver of the vehicle intends to brake, the vehicle executes the deceleration action based on the sum of the deceleration increments requested in the current and previous prediction periods. According to the method, collision detection is achieved by periodically predicting the longitudinal driving track TH of the vehicle and the longitudinal driving track TG of the target vehicle, when the collision risk is detected, the speed reduction request calibrated based on the real vehicle is calculated to adjust the speed of the vehicle, and the collision risk of the two vehicles is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle assisted driving, and more specifically, the present invention relates to a vision-based EBA deceleration request method, system and automobile. Background Art

[0002] ADAS assisted driving technology can use the front camera to identify the target vehicle and output the kinematic relationship between the vehicle and the target vehicle, thereby analyzing the risk of collision with the target vehicle. When a collision risk is detected, it will issue relevant prompts to the driver. Even if the driver steps on the brake pedal, the risk of collision may still exist.

[0003] The existing technology is based on a front-mounted monocular camera to identify the target vehicle in the lane and obtain the longitudinal distance, speed, acceleration and other information of the target vehicle. Since the obtained target vehicle information is different from the actual information of the target vehicle, when the current required deceleration of the vehicle is calculated by simply relying on a formula - that is, the relative speed divided by the collision time (TTC) to calculate the required deceleration of the vehicle, there will be a deviation from the actual target deceleration required by the vehicle.

[0004] If the result is larger than the required target deceleration, it will cause a false trigger, that is, the driver could have avoided the risk of collision by braking himself, but mistakenly requested excessive deceleration, causing the driver to complain; if the result is smaller than the required target deceleration, there may be a risk of collision between the vehicle and the target vehicle ahead. Summary of the invention

[0005] The present invention provides a vision-based EBA deceleration request method, aiming to improve the above-mentioned problem.

[0006] The present invention is implemented as follows: a vision-based EBA deceleration request method, the method comprising the following steps:

[0007] S1. After detecting the longitudinal collision risk between the vehicle and the target vehicle, the longitudinal trajectory of the vehicle is periodically predicted. H The longitudinal trajectory T of the target vehicle G ;

[0008] S2. Detect the longitudinal driving trajectory T of the vehicle in the current prediction cycle H The longitudinal trajectory T of the target vehicle in this cycle G whether there is overlap, and if so, determining the deceleration increment requested for the current prediction period based on the relative vehicle speed at the time of the collision;

[0009] S3. After detecting that the driver of the vehicle has the intention to brake, the vehicle performs a deceleration action based on the sum of the deceleration increments requested in the current and previous prediction cycles.

[0010] Furthermore, if the longitudinal trajectory T of the vehicle in the current prediction period is H The longitudinal trajectory T of the target vehicle in this cycle G If there is no overlap, the deceleration increment for the next prediction period is determined based on the minimum longitudinal distance of the host vehicle relative to the target vehicle in the current prediction period.

[0011] Furthermore, the longitudinal trajectory T of the vehicle in each prediction cycle H , the longitudinal trajectory of the target vehicle T G The specific method of obtaining is as follows:

[0012] The prediction step length N within the prediction cycle is set, and the longitudinal driving distances of the vehicle and the target vehicle within each prediction step are gradually predicted to form the longitudinal driving trajectories of the vehicle and the target vehicle.

[0013] Furthermore, the acceleration a of the target vehicle at the initial moment of the prediction period is G [0] is the acceleration a of the target vehicle during the prediction period G , to obtain the longitudinal trajectory T of the target vehicle in the prediction period G .

[0014] Furthermore, the acceleration of the vehicle a H The specific method for determining is as follows:

[0015] Calculate reaction time T R Corresponding forecast period In the first m prediction cycles, let the vehicle acceleration be equal to the acceleration a at the beginning of the prediction cycle. H [0]; After m+1 prediction cycles, the vehicle acceleration changes linearly. The longitudinal acceleration a of the vehicle in the j+1 prediction cycle is H,j+1 =a H,j +DecRate*T C , where DecRate is the linear rate of change of acceleration caused by braking, a H,j is the longitudinal acceleration of the vehicle in the jth prediction cycle, and detects the longitudinal acceleration a H,j+1 Is it greater than the acceleration threshold? If the test result is yes, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration threshold. If the test result is no, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration a. H,j+1 .

[0016] Furthermore, in the longitudinal driving trajectory T G There is a longitudinal distance greater than the longitudinal driving trajectory T in the array H If the corresponding longitudinal distance in the array is equal to the target vehicle, it is determined that there is a risk of collision between the vehicle and the target vehicle.

[0017] Furthermore, the method for determining the deceleration increment based on the relative vehicle speed at the time of collision is as follows:

[0018] Based on the relative vehicle speed-deceleration increment table, the deceleration increment corresponding to the relative vehicle speed is found. The formation process of the relative vehicle speed-deceleration increment table is as follows:

[0019] Simulate the collision of two vehicles at various relative vehicle speeds based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative vehicle speed;

[0020] Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative vehicle speed, and ultimately form a relative vehicle speed-deceleration increment table.

[0021] Furthermore, the method for determining the deceleration increment based on the minimum longitudinal distance is as follows:

[0022] The speed increment corresponding to the current minimum longitudinal distance is found based on the minimum longitudinal distance-deceleration increment table; the formation process of the minimum longitudinal distance-deceleration increment table is as follows:

[0023] Simulate the collision of two vehicles at various relative longitudinal distances based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative longitudinal distance;

[0024] Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative longitudinal distance, and ultimately form a minimum longitudinal distance-deceleration increment table.

[0025] The present invention is implemented as follows: a vision-based EBA deceleration request system, the system comprising:

[0026] The monocular camera installed at the front end of the vehicle collects the current image in front of the vehicle and sends it to the processor of the brake assist system EBA. The processor determines the deceleration increment requested when the vehicle has the intention to brake based on the above-mentioned vision-based EBA deceleration request method.

[0027] The present invention is implemented in a vehicle, wherein the vision-based EBA deceleration request system as described above is integrated into the vehicle.

[0028] The present invention periodically predicts the longitudinal trajectory T of the vehicle. H The longitudinal trajectory T of the target vehicle GTo implement collision detection, when a collision risk is detected, the vehicle speed is adjusted based on the deceleration increment calibrated by the actual vehicle to reduce the risk of collision between the two vehicles. In addition, even if it is detected that there is no collision risk between the two vehicles, the vehicle speed is adjusted based on the minimum longitudinal distance between the two vehicles to further reduce the risk of collision between the two vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A flow chart of a vision-based EBA deceleration request method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The specific implementation modes of the present invention are further explained in detail below by describing the embodiments with reference to the accompanying drawings, so as to help those skilled in the art to have a more complete, accurate and in-depth understanding of the inventive concept and technical solution of the present invention.

[0031] Figure 1 The flowchart of the vision-based EBA deceleration request method provided by the embodiment of the present invention specifically includes the following steps:

[0032] S1. After detecting the longitudinal collision risk between the vehicle and the target vehicle, the longitudinal trajectory of the vehicle is periodically predicted. H The longitudinal trajectory T of the target vehicle G ;

[0033] In the embodiment of the present invention, the target vehicle is the other vehicle closest to the vehicle in front of the vehicle in the lane, and the lane where the vehicle is located is the lane. When the collision time between the vehicle and the target vehicle is detected to be less than the set threshold value, it is determined that there is a longitudinal collision risk between the vehicle and the target vehicle. From the moment when the longitudinal collision risk between the vehicle and the target vehicle is detected, the longitudinal driving trajectory of the vehicle T is periodically predicted. H The longitudinal trajectory T of the target vehicle G , the longitudinal trajectory of the vehicle in each prediction cycle T H , the longitudinal trajectory of the target vehicle T G The specific method of obtaining is as follows:

[0034] The prediction step length N within the prediction cycle is set, and the longitudinal driving distances of the vehicle and the target vehicle within each prediction step are gradually predicted to form the longitudinal driving trajectories of the vehicle and the target vehicle.

[0035] The longitudinal direction in the embodiment of the present invention is the driving direction of the vehicle. The origin of the vehicle coordinate system of the vehicle at the initial moment of the prediction period is taken as the origin of the longitudinal driving distance. The longitudinal driving distance of the vehicle at the initial moment of the prediction period is 0. The longitudinal driving distance of the target vehicle at the initial moment of the prediction period is the longitudinal distance Relative_distance between the current vehicle and the target vehicle, which is expressed as follows:

[0036] T H [0] = 0;

[0037] T G [0] = Relative_distance;

[0038] Use T G [i] represents the longitudinal travel distance of the target vehicle at the i-th prediction step, i ranges from 0 to N, and the acceleration a of the target vehicle at the initial moment of the prediction cycle is G [0] is the acceleration of the target vehicle during the prediction period, T G The calculation formula of [i] is as follows:

[0039] T G [i] = T G [i-1]+1 / 2*(v G [i]+v G [i-1])*T C ;

[0040] v G [i] = v G [i-1]+a G [i-1]*T C ;

[0041] a G [i-1] = a G [i-2] = a G [0];

[0042] Among them, T G [i-1] The longitudinal distance travelled by the target vehicle at the i-1th prediction step, v G [i]、v G [i-1] represents the longitudinal speed of the target vehicle at the i-th prediction step and the i-1-th prediction step, respectively. C is the duration of the prediction cycle, a G [i-1], a G [i-2] represents the longitudinal acceleration of the target vehicle at the i-1th prediction step and the i-2th prediction step, respectively. G [0] represents the longitudinal acceleration of the target vehicle at the initial moment of the prediction period, a G [0], vG [0] is obtained by analyzing the image in front of the vehicle captured by the monocular camera at the front of the vehicle.

[0043] Use T H [i] represents the longitudinal travel distance of the vehicle at the i-th prediction step. The method for obtaining the longitudinal travel distance of the vehicle at the i-th prediction step is as follows:

[0044] There is a driver reaction time T between detecting the longitudinal collision risk between the vehicle and the target vehicle and the driver pressing the brake pedal. R , calculate the reaction time T R Corresponding forecast period In the first m prediction cycles, let the vehicle acceleration be equal to the acceleration a at the beginning of the prediction cycle. H [0]; After m+1 prediction cycles, the vehicle acceleration changes linearly. The longitudinal acceleration a of the vehicle in the j+1 prediction cycle is H,j+1 =a H,j +DecRate*T C , where DecRate is the linear rate of change of acceleration caused by braking, a H,j is the longitudinal acceleration of the vehicle in the jth prediction cycle, and detects the longitudinal acceleration a H,j+1 Is it greater than the acceleration threshold? If the test result is yes, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration threshold. If the test result is no, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration a. H,j+1 The longitudinal travel distance T of the vehicle at the i-th prediction step H The calculation principle of [i] is the same as above and will not be repeated here. The acceleration a of the vehicle at the initial moment of the prediction cycle is H [0], speed v H [0] is read from the vehicle in real time.

[0045] S2. Detect the longitudinal driving trajectory T of the vehicle in the current prediction cycle H The longitudinal trajectory T of the target vehicle in this cycle G whether there is overlap, and if so, determining the deceleration increment requested for the current prediction period based on the relative vehicle speed at the time of the collision;

[0046] In the embodiment of the present invention, if the longitudinal driving trajectory T of the vehicle in the current prediction period H The longitudinal trajectory T of the target vehicle in this cycle G There is overlap, that is, the longitudinal trajectory T G There is a longitudinal distance greater than the longitudinal driving trajectory T in the array HIf the longitudinal distance in the array corresponds to the vehicle, there is a risk of collision between the vehicle and the target vehicle. The relative speed between the vehicle and the target vehicle at the time of trajectory overlap is calculated. The deceleration increment corresponding to the relative speed is found based on the relative speed-deceleration increment table. The formation process of the relative speed-deceleration increment table is as follows:

[0047] Simulate the collision of two vehicles at various relative vehicle speeds based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative vehicle speed;

[0048] Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative vehicle speed, and ultimately form a relative vehicle speed-deceleration increment table.

[0049] S3. After detecting that the driver of the vehicle has the intention to brake, the vehicle performs a deceleration action based on the sum of the deceleration increments requested in the current and previous prediction cycles.

[0050] In the embodiment of the present invention, if the longitudinal driving trajectory T of the vehicle in the current prediction period H The longitudinal trajectory T of the target vehicle in this cycle G If there is no overlap, the deceleration request increment for the current cycle is determined based on the minimum longitudinal distance of the host vehicle relative to the target vehicle in the current prediction cycle.

[0051] In the embodiment of the present invention, the speed increment corresponding to the current minimum longitudinal distance is searched based on the minimum longitudinal distance-deceleration increment table. The formation process of the minimum longitudinal distance-deceleration increment table is as follows:

[0052] Simulate the collision of two vehicles at various relative longitudinal distances based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative longitudinal distance;

[0053] Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative longitudinal distance, and ultimately form a minimum longitudinal distance-deceleration increment table.

[0054] The present invention periodically predicts the longitudinal trajectory T of the vehicle. H The longitudinal trajectory T of the target vehicle G To implement collision risk detection, when a collision risk is detected, the deceleration request based on the actual vehicle calibrated is calculated to adjust the vehicle speed and reduce the risk of collision between the two vehicles. In addition, even if it is detected that there is no collision risk between the two vehicles, the deceleration request is adjusted based on the minimum longitudinal distance between the two vehicles to avoid braking too far.

[0055] The present invention also provides a vision-based EBA deceleration request system, the system comprising:

[0056] The monocular camera installed at the front end of the vehicle collects the current image in front of the vehicle and sends it to the processor of the brake assist system EBA. The processor determines the deceleration increment requested when the vehicle has the intention to brake based on the above-mentioned vision-based EBA deceleration request method.

[0057] The present invention also provides a car, on which the above-mentioned vision-based EBA deceleration request system is integrated, wherein a monocular camera is integrated into the front windshield.

[0058] The present invention has been described exemplarily. Obviously, the specific implementation of the present invention is not limited to the above-mentioned method. As long as various non-substantial improvements are made using the method concept and technical solution of the present invention, or the concept and technical solution of the present invention are directly applied to other occasions without improvement, they are all within the protection scope of the present invention.

Claims

1. A vision-based EBA deceleration request method, characterized in that: The method comprises the following steps: S1. After detecting the longitudinal collision risk between the vehicle and the target vehicle, the longitudinal trajectory of the vehicle is periodically predicted. H The longitudinal trajectory T of the target vehicle G ; S2. Detect the longitudinal driving trajectory T of the vehicle in the current prediction cycle H The longitudinal trajectory T of the target vehicle in this cycle G whether there is overlap, and if so, determining the deceleration increment requested for the current prediction period based on the relative vehicle speed at the time of the collision; S3. After detecting that the driver of the vehicle has the intention to brake, the vehicle performs a deceleration action based on the sum of the deceleration increments requested in the current and previous prediction cycles.

2. The vision-based EBA deceleration request method according to claim 1, characterized in that: If the longitudinal trajectory of the vehicle in the current prediction cycle is T H The longitudinal trajectory T of the target vehicle in this cycle G If there is no overlap, the deceleration increment for the current cycle is determined based on the minimum longitudinal distance of the host vehicle relative to the target vehicle during the current prediction cycle.

3. The vision-based EBA deceleration request method according to claim 1 or 2, characterized in that: The longitudinal trajectory of the vehicle in each prediction cycle T H , the longitudinal trajectory of the target vehicle T G The specific method of obtaining is as follows: The prediction step length N within the prediction cycle is set, and the longitudinal driving distances of the vehicle and the target vehicle within each prediction step are gradually predicted to form the longitudinal driving trajectories of the vehicle and the target vehicle.

4. The vision-based EBA deceleration request method according to claim 3, characterized in that: The acceleration a of the target vehicle at the initial moment of the prediction cycle G [0] is the acceleration a of the target vehicle during the prediction period G , to obtain the longitudinal trajectory T of the target vehicle in the prediction period G .

5. The vision-based EBA deceleration request method according to claim 3, characterized in that: The acceleration of the vehicle is a H The specific method for determining is as follows: Calculate reaction time T R Corresponding forecast period In the first m prediction cycles, let the vehicle acceleration be equal to the acceleration a at the beginning of the prediction cycle. H [0]; After m+1 prediction cycles, the vehicle acceleration changes linearly. The longitudinal acceleration a of the vehicle in the j+1 prediction cycle is H,j+1 =a H,j +DecRate*T C , where DecRate is the linear rate of change of acceleration caused by braking, a H,j is the longitudinal acceleration of the vehicle in the jth prediction cycle, and detects the longitudinal acceleration a H,j+1 Is it greater than the acceleration threshold? If the test result is yes, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration threshold. If the test result is no, the longitudinal acceleration of the vehicle is taken as the longitudinal acceleration a. H,j+1 .

6. The vision-based EBA deceleration request method according to claim 3, characterized in that: In the longitudinal trajectory T G There is a longitudinal distance greater than the longitudinal driving trajectory T in the array. H If the corresponding longitudinal distance in the array is equal to the target vehicle, it is determined that there is a risk of collision between the vehicle and the target vehicle.

7. The vision-based EBA deceleration request method according to claim 1, characterized in that: The method for determining the deceleration increment based on the relative vehicle speed at the time of the predicted collision is as follows: Based on the relative vehicle speed-deceleration increment table, the deceleration increment corresponding to the relative vehicle speed is found. The formation process of the relative vehicle speed-deceleration increment table is as follows: Simulate the collision of two vehicles at various relative vehicle speeds based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative vehicle speed; Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative vehicle speed, and ultimately form a relative vehicle speed-deceleration increment table.

8. The vision-based EBA deceleration request method according to claim 1, characterized in that: The method for determining the deceleration increment based on the minimum longitudinal distance is as follows: The speed increment corresponding to the current minimum longitudinal distance is found based on the minimum longitudinal distance-deceleration increment table; the formation process of the minimum longitudinal distance-deceleration increment table is as follows: Simulate the collision of two vehicles at various relative longitudinal distances based on the simulation software, and determine the minimum deceleration increment to avoid the collision of the two vehicles as the initial deceleration increment at the relative longitudinal distance; Calibration and testing are carried out under CNCAP standard conditions to optimize the initial deceleration increment at each relative longitudinal distance, and ultimately form a minimum longitudinal distance-deceleration increment table.

9. A vision-based EBA deceleration request system, characterized in that: The system comprises: A monocular camera arranged at the front end of the vehicle respectively collects images in front of the current vehicle and sends them to a processor of the brake assist system EBA. The processor determines the deceleration increment requested when the vehicle has a braking intention based on the vision-based EBA deceleration request method as claimed in any one of claims 1 to 8.

10. An automobile, characterized in that: The vehicle is integrated with the vision-based EBA deceleration request system as claimed in claim 9.

Images