An automatic braking system and method for turning at an intersection based on vehicle speed

Abstract

The present invention provides an automatic braking method for turning at an intersection based on vehicle speed. By calculating the time to collision (TTC) in segments based on the decoupled vehicle speed in the transverse and longitudinal directions and combining with the method of engineering calibration, the function of emergency braking of the vehicle at the intersection is realized. The present invention calculates the transverse and longitudinal TTCs through a method of transverse and longitudinal decoupling based on segmented interpolation of the relative vehicle speed; when the calculated transverse and longitudinal TTCs are within the TTC threshold range representing the collision risk calibrated, it indicates a collision risk. Through simple motion analysis, the present invention combines one-dimensional parameter constraints for scenario screening, and then selects relatively accurate risk boundary points through the method of engineering calibration. For the scenarios within the boundary points, smoothing is performed through segmented interpolation based on different relative speeds; that is, it simplifies the algorithm model, reduces the software load, and can increase the accuracy through the method of experimental calibration. The present invention has low requirements for the hardware and software loads and has portability.

Description

Technical Field

[0001] The present invention belongs to the technical field of automotive braking, and particularly relates to an automatic braking system and method for turning at an intersection based on vehicle speed. Background Art

[0002] The intersection scenario is a complex traffic scenario covering motor vehicles, non-motor vehicles, and pedestrians, and is also a section prone to traffic accidents. When the vehicle turns at an intersection, if there is a risk of collision with an oncoming vehicle, emergency braking is used to avoid or reduce the collision. In existing implementation solutions, it is often chosen to predict the driving trajectories of the vehicle itself and the target vehicle, and judge the collision risk by whether the trajectory regions of the two overlap.

[0003] For the calculation of the collision risk, a prior art method is to represent the sizes of the two vehicles as two circles according to the widths of the vehicle itself and the target vehicle. Two straight lines in contact with the intersection are obtained from the two circles. The sum of the diameters of the two circles is set as the boundary not only with respect to the contact points of the two straight lines but also with respect to the center point of the width of the front surface of the host vehicle. When the angle of the motion vector of the host vehicle satisfies the boundary condition, it is determined that there is a possibility of collision between the two vehicles. This technical solution uses a geometric mathematical model. Therefore, for the risk judgment, a high degree of fit between the model and the actual vehicle size and motion trend is required, and the modeling error in the modeling process will directly affect the judgment of the actual vehicle collision risk. Moreover, this solution only simply uses the geometric judgment method, lacking the estimation of the attitude motion trends of the host vehicle and the target vehicle, and this will also have a great impact on the judgment of the actual collision risk.

[0004] Another prior art method calculates the dangerous area of the target vehicle based on parameters such as the shape and speed of the target vehicle detected by the host vehicle. Then, the actual trajectory points of the host vehicle are used for fitting to estimate the trajectory of the vehicle in the next 2 seconds. When the estimated trajectory falls into the dangerous area, it indicates that there is a collision risk between the two vehicles. This solution has a clear mathematical basis it proposed. When implementing the solution on the vehicle, the actual vehicle effect can be analyzed from top to bottom. The mathematical method for judging the collision risk proposed by this solution calculates the dangerous area and the host vehicle estimation separately, without considering the influence of time factors. The host vehicle and the target vehicle must proceed synchronously in the time series. Judging the risk by whether the estimated trajectory of the host vehicle falls into the dangerous area according to this method, it is possible that when the estimated trajectory falls into the dangerous area, the target vehicle has already driven away or the host vehicle has already driven away from the dangerous area before the target vehicle approaches. This solution requires processing historical trajectory points in code implementation, and at the same time uses the method of region intersection, increasing the complexity of software implementation. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an automatic braking system and method for turning at an intersection based on vehicle speed for emergency braking of a vehicle at an intersection.

[0006] The technical solution adopted by the present invention to solve the above technical problem is: an automatic braking system for turning at an intersection based on vehicle speed, including a calibration observation management module, a perception information processing module, a state machine management module or a scenario screening module, a risk calculation module, and a control signal mapping module connected in sequence according to the signal flow direction; the state machine management module and the scenario screening module are respectively connected between the perception information processing module and the risk calculation module; the calibration observation management module is used to define variables that need to be set as adjustable as calibration quantities and define internal variables that need to be observed in real time as observation quantities; the perception information processing module is used to preprocess the target-related signals output by on-vehicle sensors; the state machine management module is used to classify and judge the self-vehicle state-related signals provided by on-vehicle sensors according to the states that cause the function to enter including failure, prohibition, or normal enabling, and reserve expandable states; the state machine management module is also used to output the system state signal state and the function enabling signal enable as the state driving signals for subsequent risk calculation; the scenario screening module is used to streamline the function triggering range by restricting a series of parameters of the self-vehicle and the target vehicle, including self-vehicle state screening and target screening; the scenario screening module also adjusts the calibration parameters to enable the triggering scenario required for the function and reduce false triggering of other scenarios; the risk calculation module is used to judge whether there is a collision risk between the self-vehicle and the target vehicle; the control signal mapping module is used to send a calibratable deceleration clb_DecSet according to the result of whether there is a collision risk judged by the risk calculation module, cooperate with the response logic of the reducer of the vehicle model to send the deceleration interaction signal required to complete braking, and map the deceleration interaction signal to the in-vehicle bus control instruction to realize the automatic braking of the self-vehicle.

[0007] According to the above solution, the on-vehicle sensors include a front camera, a front millimeter-wave radar, and a front corner radar.

[0008] According to the above solution, the preprocessing performed by the perception information processing module includes classification packetization and unit unification.

[0009] According to the above solution, the self-vehicle state-related signals include vehicle speed, yaw rate, and steering wheel angle; the expandable states include an inhibition state and an initialization state.

[0010] According to the above solution, the self-vehicle state screening includes: restricting the vehicle speed range of the self-vehicle driving at a low speed at the intersection to 5 - 30 km / h; restricting the steering wheel angle of the self-vehicle turning left to a certain calibratable positive number clb_w; limiting the steering wheel rotation speed of the self-vehicle to a certain calibratable value clb_dw, which is used to distinguish the intensity of the driver's intention to control the vehicle.

[0011] Object screening includes: restricting the longitudinal speed of the object to a calibratable value clb_obj_vx to filter out scenarios where the object is stationary or has other custom vehicle speeds; restricting the longitudinal distance of the object relative to the host vehicle to a calibratable value clb_obj_londis to filter out inaccurate detection of the object by the sensor at relatively long distances; restricting the lateral distance of the object relative to the host vehicle to a calibratable value clb_obj_latdis to reduce false triggers at relatively long distances; restricting the type of the target vehicle to a calibratable value clb_obj_type to customize the type of object for which the selectable function can trigger braking.

[0012] Object risk priority determination is used to divide the urgency of multiple objects detected by the sensor according to the lateral and longitudinal distances and lateral and longitudinal speeds, and select the most urgent object as the target object for subsequent processing.

[0013] According to the above solution, the risk calculation module includes a speed grading module, a lateral and longitudinal TTC calculation module, and a risk judgment module connected to the output ends of these two modules respectively.

[0014] A method for calculating the collision risk of an automatic braking system for turning at an intersection based on vehicle speed includes the following steps:

[0015] Select a calibratable clb_boundary relative speed including the minimum relative speed clb_RelVelMin and the maximum relative speed clb_RelVelMax, as well as the lateral TTC threshold clb_TTCLat and longitudinal TTC threshold clb_TTCLon corresponding to the minimum relative speed clb_RelVelMin, and the lateral TTC threshold clb_TTCLatHigh and longitudinal TTC threshold clb_TTCLonHigh corresponding to the maximum relative speed clb_RelVelMax;

[0016] Set experimental groups for scenarios of the calibratable clb_boundary relative speed respectively, and calculate the lateral collision time LatTTC and longitudinal collision time LonTTC of the vehicle in real time;

[0017] Adjust the corresponding lateral TTC threshold and longitudinal TTC threshold according to whether the actual vehicle collides and whether the braking effect is good;

[0018] According to the determined boundaries clb_TTCLat, clb_TTCLon, clb_TTCLatHigh, and clb_TTCLonHigh, use the method of linear interpolation to determine the corresponding lateral TTC threshold and longitudinal TTC threshold for scenarios between the clb_boundary relative speeds.

[0019] Further, when performing "separately setting test groups for scenarios with calibratable clb boundary relative speeds and calculating the vehicle's lateral time to collision LatTTC and longitudinal time to collision LonTTC in real time", for the minimum relative speed scenario,

[0020] If LatTTC <= clb_TTCLat and LonTTC <= clb_TTCLon, trigger the vehicle's braking;

[0021] If LatTTC <= clb_TTCLat and LonTTC > clb_TTCLon, increase clb_TTCLon by the calibration step clb_step1;

[0022] If LatTTC > clb_TTCLat and LonTTC <= clb_TTCLon, increase clb_TTCLat by the calibration step clb_step1;

[0023] If LatTTC > clb_TTCLat and LonTTC > clb_TTCLon, increase both clb_TTCLat and clb_TTCLon by the calibration step clb_step1 and start the judgment again;

[0024] When performing a fast rough adjustment, set the initial value of the calibration step clb_step1 to 0.3.

[0025] Further, when performing "adjusting the corresponding lateral TTC threshold and longitudinal TTC threshold according to whether the real vehicle collides and whether the braking effect is good", if the longitudinal distance between the two vehicles after braking is greater than the clb_distance X threshold range and the lateral distance is greater than the clb_distance Y threshold range, it is judged that the braking is too early; otherwise, it is judged that the braking is too late;

[0026] If the braking is too early, decrease clb_TTCLat and clb_TTCLon, and perform "separately setting test groups for scenarios with calibratable clb boundary relative speeds and calculating the vehicle's lateral time to collision LatTTC and longitudinal time to collision LonTTC in real time";

[0027] If the braking is too late, increase clb_TTCLat and clb_TTCLon, and perform "separately setting test groups for scenarios with calibratable clb boundary relative speeds and calculating the vehicle's lateral time to collision LatTTC and longitudinal time to collision LonTTC in real time";

[0028] Set the step size for increasing and decreasing to the calibration quantity clb_step2; the initial value of the calibration quantity clb_step2 is set to 0.1 and will be modified according to the effect and experience later.

[0029] Furthermore, for the maximum relative speed scenario, replace clb_TTCLat with clb_TTCLatHigh and clb_TTCLon with clb_TTCLonHigh, and execute "Set up test groups for the scenarios of the calibratable clb_ boundary relative speed respectively, and calculate the lateral time to collision LatTTC and the longitudinal time to collision LonTTC of the vehicle in real time" and "Adjust the corresponding lateral TTC threshold and longitudinal TTC threshold according to whether the real vehicle collides and whether the braking effect is good", and select the better lateral TTC threshold clb_TTCLatHigh and longitudinal TTC threshold clb_TTCLonHigh.

[0030] The beneficial effects of the present invention are as follows:

[0031] 1. An automatic braking system and method for turning at an intersection based on vehicle speed according to the present invention calculates TTC in segments based on the vehicle speed with transverse and longitudinal decoupling, and combines the method of engineering calibration to realize the function of emergency braking of the vehicle at the intersection.

[0032] 2. The present invention is a technical method for triggering emergency braking during the turning process. Through the processing of simple one-dimensional data, the transverse and longitudinal TTC are calculated in a transverse and longitudinal decoupling manner by interpolating based on the relative vehicle speed in segments; when the calculated transverse and longitudinal TTC are within the calibrated TTC threshold range representing the collision risk, it indicates that there is a collision risk.

[0033] 3. The present invention is not completely based on a mathematical model and is completely carried out based on a preset mathematical model. Instead, through simple motion analysis, combined with one-dimensional parameter limitations (such as factors such as the speed of the vehicle itself and the steering angle), the scenarios are screened, and then more accurate risk boundary points are selected through the method of engineering calibration. For the scenarios within the boundary points, smoothing is performed by interpolating in segments based on different relative speeds. This simplifies the algorithm model, reduces the software load, and can increase the accuracy through the method of experimental calibration.

[0034] 4. The present invention has low requirements for hardware and can be realized only with a camera, a front radar, and a front corner radar; it has a low software load and a low software calculation example, and will not cause problems such as the controller crashing or overflowing due to high-load operation; it has portability. The present invention extracts many parameters as adjustable calibration quantities, and when changing to different vehicle models, only the vehicle configurations and calibration parameters of different vehicles need to be adapted and modified. Description of the Drawings

[0035] Figure 1 It is a scenario diagram of an embodiment of the present invention.

[0036] Figure 2 It is a principle block diagram of an embodiment of the present invention.

[0037] Figure 3 This is the flowchart of an embodiment of the present invention. Detailed implementation manners

[0038] The present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners.

[0039] Refer to Figure 1 In Embodiment 1 of the present invention, the scenario is that the host vehicle turns left at an intersection and there is a risk of collision with an oncoming vehicle going straight ahead on the left.

[0040] The principle block diagram of the present invention is as Figure 2 shown. The embodiments of the present invention include the following modules:

[0041] Calibration and Observation Management Module. This module is used to define variables that need to be set as adjustable as calibration quantities, and define internal variables that need to be observable in real time as observable quantities. It can be applied to various parts of the software module to realize the real-time adjustability and observability of internal variables.

[0042] Perception Information Processing Module. By preprocessing the target object-related signals output by vehicle-mounted sensors, including front cameras, front millimeter-wave radars, and front corner radars, etc., such as classifying and grouping packets and unifying units, it is convenient for subsequent modules to use.

[0043] State Machine Management Module. Through the vehicle's own sensor-provided self-vehicle state-related signals, including vehicle speed, yaw rate, steering wheel angle, etc., it classifies and judges according to states that will cause the function to enter a fault state, a prohibited state, or a normal enabling state, etc., and reserves expandable states such as suppression state, initialization state, etc. This module outputs the system state signal state and the function enabling signal enable as the state drive signals for subsequent risk calculation.

[0044] Scenario Screening Module. This module realizes the refinement of the function trigger range by restricting a series of parameters of the host vehicle and the target vehicle. By adjusting the calibration parameters of this module, the function can be made to achieve, for example, Figure 1The triggered scenarios shown are considered, and false triggering in other scenarios is minimized. Self-vehicle state screening: The speed range of the self-vehicle is restricted to 5 - 30 km / h to comply with the traffic rule that vehicles should drive at a low speed at intersections; the steering wheel angle of the self-vehicle is restricted to a certain calibratable positive value clb_w to meet the scenario where the self-vehicle turns left; the rotational speed of the self-vehicle's steering wheel is limited to a certain calibratable value clb_dw to distinguish to a certain extent the intensity of the driver's intention to control the vehicle by himself. Target object screening: The longitudinal speed of the target object is restricted to a certain calibratable value clb_obj_vx to filter out scenarios where the target object is stationary or has other custom vehicle speeds; the longitudinal distance of the target object relative to the self-vehicle is restricted to a certain calibratable value clb_obj_londis to filter out inaccurate detection of the target object by the sensor at a relatively long distance; the lateral distance of the target object relative to the self-vehicle is restricted to a certain calibratable value clb_obj_latdis to reduce false triggering at a relatively long distance; the type of the target vehicle is restricted to a certain calibratable value clb_obj_type to customize the type of target object for which the braking function can be triggered; the risk priority of the target object is delimited. Multiple target objects detected by the sensor are classified according to the lateral and longitudinal distances and lateral and longitudinal speeds, and the most urgent target object is selected as the target object for subsequent processing.

[0045] The risk calculation module, the flowchart is as Figure 3 shown. Let the lateral TTC (time to collision) be the lateral distance of the target object relative to the self-vehicle divided by the absolute value of the lateral speed of the target object relative to the self-vehicle; the longitudinal TTC is the longitudinal distance of the target object relative to the self-vehicle divided by the absolute value of the longitudinal speed of the target object relative to the self-vehicle.

[0046] a) First, select the calibratable clb_boundary relative speed and its corresponding boundary lateral and longitudinal TTC thresholds. The minimum relative speed clb_RelVelMin corresponds to the lateral and longitudinal TTC thresholds clb_TTCLat and clb_TTCLon respectively, and the maximum relative speed clb_RelVelMax corresponds to the lateral and longitudinal TTC thresholds clb_TTCLatHigh and clb_TTCLonHigh respectively;

[0047] b) Set up a test group for the scenario of the relative speed between two boundaries, and calculate the longitudinal and lateral TTC (LatTTC, LonTTC) of the vehicle in real time. For the scenario of the minimum relative speed, if LatTTC <= clb_TTCLat and LonTTC <= clb_TTCLon, the vehicle's own braking will be triggered. If LatTTC <= clb_TTCLat and LonTTC > clb_TTCLon, then clb_TTCLon will be increased by the calibratable step clb_step1. If LatTTC > clb_TTCLat and LonTTC <= clb_TTCLon, then clb_TTCLat will be increased by the calibratable step clb_step1. If LatTTC > clb_TTCLat and LonTTC > clb_TTCLon, then both clb_TTCLat and clb_TTCLon will be increased by the calibratable step clb_step1 and step b) will be repeated. The initial setting of clb_step1 is 0.3, which is a relatively fast action for rough adjustment;

[0048] c) Adjust the corresponding longitudinal and lateral thresholds according to whether the real vehicle collides and whether the braking effect is good. If the braking is early (judged according to whether the longitudinal and lateral distances between the two vehicles after braking are greater than the clb_distance X\Y threshold range), then reduce clb_TTCLat and clb_TTCLon, and return to step b). If the braking is late, then increase clb_TTCLat and clb_TTCLon, and return to step b). The step size for increasing or decreasing can be set as the calibrated quantity clb_step2, and the default can be set to 0.1. Subsequently, it can be modified according to the effect and experience to improve the efficiency;

[0049] d) Repeat steps b) and c) to select the optimal longitudinal and lateral TTC thresholds clb_TTCLatHigh and clb_TTCLonHigh for the scenario of the maximum relative speed. In b) and c), replace clb_TTCLat with clb_TTCLatHigh and clb_TTCLon with clb_TTCLonHigh;

[0050] e) According to the determined boundaries clb_TTCLat, clb_TTCLon, clb_TTCLatHigh, and clb_TTCLonHigh, use the method of linear interpolation to determine the corresponding longitudinal and lateral TTC thresholds for the scenarios between the boundary relative speeds clb_RelVelMin and clb_RelVelMax.

[0051] Control signal mapping module. Based on whether there is a collision risk determined by the risk calculation module, the control signal mapping module sends a calibratable deceleration clb_DecSet, and cooperates with the response logic of the reducer of a specific vehicle model to send an interaction signal of the deceleration required to complete braking, mapping the internal software deceleration request signal to a vehicle bus control instruction to achieve automatic braking of the host vehicle.

[0052] In Embodiment 2 of the present invention, the scenario is that the host vehicle turns right at an intersection and there is a collision risk with an oncoming vehicle going straight ahead on the right side in front. The processing process is the same as that of Embodiment 1.

[0053] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0054] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made according to the principles and design ideas disclosed by the present invention are within the protection scope of the present invention.

Claims

1. An automatic braking collision risk calculation method for intersection turning based on vehicle speed, characterized in that: It includes the following steps: Select a calibratable clb_boundary relative speed including the minimum relative speed clb_RelVelMin and the maximum relative speed clb_RelVelMax, as well as the lateral TTC threshold clb_TTCLat and the longitudinal TTC threshold clb_TTCLon corresponding to the minimum relative speed clb_RelVelMin, and the lateral TTC threshold clb_TTCLatHigh and the longitudinal TTC threshold clb_TTCLonHigh corresponding to the maximum relative speed clb_RelVelMax; Respectively set test groups for the scenarios of the calibratable clb_boundary relative speed, and calculate the lateral collision time LatTTC and the longitudinal collision time LonTTC of the vehicle in real time; for the minimum relative speed scenario, If LatTTC <= clb_TTCLat and LonTTC <= clb_TTCLon, then trigger the braking of the host vehicle; If LatTTC <= clb_TTCLat and LonTTC > clb_TTCLon, then increase clb_TTCLon by the calibration step clb_step1 and start the judgment again; If LatTTC > clb_TTCLat and LonTTC <= clb_TTCLon, then increase clb_TTCLat by the calibration step clb_step1 and start the judgment again; If LatTTC > clb_TTCLat and LonTTC > clb_TTCLon, then increase clb_TTCLat and clb_TTCLon simultaneously by the calibration step clb_step1 and start the judgment again; When making a relatively fast rough adjustment, set the initial value of the calibration step clb_step1 to 0.3; Adjust the corresponding lateral TTC threshold and longitudinal TTC threshold according to whether the actual vehicle collides and whether the braking effect is good; if the longitudinal distance between the two vehicles after braking is greater than the clb_distance X threshold range and the lateral distance is greater than the clb_distance Y threshold range, it is judged that the braking is too early; otherwise, it is judged that the braking is too late; If the braking is too early, then decrease clb_TTCLat and clb_TTCLon, and execute "respectively set test groups for the scenarios of the calibratable clb_boundary relative speed, and calculate the lateral collision time LatTTC and the longitudinal collision time LonTTC of the vehicle in real time"; If the braking is too late, then increase clb_TTCLat and clb_TTCLon, and execute "respectively set test groups for the scenarios of the calibratable clb_boundary relative speed, and calculate the lateral collision time LatTTC and the longitudinal collision time LonTTC of the vehicle in real time"; Set the step size of increase and decrease as the calibrated quantity clb_step2; set the initial value of the calibrated quantity clb_step2 to 0.1, and modify it according to the effect and experience later; According to the determined boundaries clb_TTCLat, clb_TTCLon, clb_TTCLatHigh, and clb_TTCLonHigh, the corresponding lateral TTC threshold and longitudinal TTC threshold are determined by using the method of linear interpolation for the scenarios between the clb_boundary relative speeds.

2. The automatic braking collision risk calculation method for intersection turning based on vehicle speed according to claim 1, wherein: For the maximum relative speed scenario, replace clb_TTCLat with clb_TTCLatHigh and clb_TTCLon with clb_TTCLonHigh, and execute "Set test groups for the scenarios of the calibratable clb_boundary relative speeds respectively, and calculate the lateral collision time LatTTC and longitudinal collision time LonTTC of the vehicle in real time" and "Adjust the corresponding lateral TTC threshold and longitudinal TTC threshold according to whether the real vehicle collides and whether the braking effect is good", and select the better lateral TTC threshold clb_TTCLatHigh and longitudinal TTC threshold clb_TTCLonHigh.

3. A system for the method of calculating the automatic braking collision risk for turning at an intersection based on vehicle speed according to any one of claims 1 to 2, characterized in that: It includes a calibration observation management module, a perception information processing module, a state machine management module or a scenario screening module, a risk calculation module, and a control signal mapping module that are connected in sequence according to the signal flow direction; the state machine management module and the scenario screening module are respectively connected between the perception information processing module and the risk calculation module; The calibration observation management module is used to define the variables that need to be set as adjustable as calibrated quantities and the internal variables that need to be observed in real time as observed quantities; The perception information processing module is used to preprocess the target-related signals output by the vehicle-mounted sensors; The state machine management module is used to classify and judge the self-vehicle state-related signals provided by the vehicle-mounted sensors according to the states that cause the function to enter including failure, prohibition, or normal enabling, and reserve expandable states; the state machine management module is also used to output the system state signal state and the function enabling signal enable as the state driving signals for subsequent risk calculation; The scenario screening module is used to streamline the function trigger range by restricting a series of parameters of the self-vehicle and the target vehicle, including self-vehicle state screening and target screening; the scenario screening module also adjusts the calibration parameters to enable the trigger scenarios required for the function to be realized and reduce the mis-triggering of other scenarios; The risk calculation module is used to judge whether there is a collision risk between the self-vehicle and the target vehicle; The control signal mapping module is used to send the calibratable deceleration clb_DecSet according to the result of whether there is a collision risk judged by the risk calculation module, cooperate with the response logic of the reducer of the vehicle model to send the deceleration interaction signal required for braking, and map the deceleration interaction signal to the in-vehicle bus control instruction to realize the automatic braking of the self-vehicle.

4. The system of a method for calculating the automatic braking collision risk of turning at an intersection based on vehicle speed according to claim 3, characterized in that: The vehicle-mounted sensors include a front camera, a front millimeter-wave radar, and a front corner radar.

5. The system of a vehicle speed-based automatic braking collision risk calculation method for intersection turning according to claim 3, wherein: The preprocessing performed by the perception information processing module includes classification packetization and unit unification.

6. The system of a method for calculating the automatic braking collision risk of turning at an intersection based on vehicle speed according to claim 3, characterized in that: The self-vehicle state-related signals include vehicle speed, yaw rate, and steering wheel angle; The expandable states include an inhibition state and an initialization state.

7. The system of a method for calculating the automatic braking collision risk at an intersection based on vehicle speed according to claim 3, wherein: The self-vehicle state screening includes: Limit the speed range of the host vehicle driving at a low speed at an intersection to 5 - 30 km / h; Limit the steering wheel angle of the host vehicle turning left to a certain calibratable positive number clb_w; Limit the steering wheel rotation speed of the host vehicle to a certain calibratable value clb_dw, which is used to distinguish the intensity of the driver's intention to control the vehicle; Target object screening includes: Limit the longitudinal speed of the target object to a certain calibratable value clb_obj_vx, which is used to filter out scenarios where the target object is stationary or has other custom vehicle speeds; Limit the longitudinal distance between the target object and the host vehicle to a certain calibratable value clb_obj_londis, which is used to filter out the inaccurate detection of the target object by the sensor at a relatively long distance; Limit the lateral distance between the target object and the host vehicle to a certain calibratable value clb_obj_latdis, which is used to reduce false triggers at a relatively long distance; Limit the type of the target vehicle to a certain calibratable value clb_obj_type, which is used to customize the type of target object for which the selectable function can trigger braking; Define the risk priority of the target object, which is used to divide the emergency levels of multiple target objects detected by the sensor according to the lateral and longitudinal distances and lateral and longitudinal speeds, and select the most urgent target object as the target object for subsequent processing.

8. The system of a method for calculating the automatic braking collision risk of turning at an intersection based on vehicle speed according to claim 3, characterized in that: The risk calculation module includes a speed grading module, a lateral and longitudinal TTC calculation module, and a risk judgment module connected to the output ends of these two modules respectively.

Images