Rear automatic emergency braking method and system based on millimeter wave radar

Abstract

The invention discloses a rear automatic emergency braking method and system based on a millimeter wave radar, and the method comprises the steps: delimiting an alarm region and a potential collision region according to the information of a vehicle, and setting an emergency braking condition flag bit of the vehicle; traversing all the target vehicles and evaluating the risk levels of all the target vehicles according to the vehicle information of all the target vehicles, the alarm area and the potential collision area; dividing an alarm area into a left alarm area and a right alarm area by taking the vehicle as a reference point, and respectively obtaining nearest neighbor targets and secondary neighbor targets in the left alarm area and the right alarm area according to the vehicle position and the target vehicle positions of all target vehicles; according to the emergency braking condition flag bit of the vehicle and the risk levels of all the target vehicles, whether the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area have collision risks or not is judged; and if the collision risk exists, alarming and braking are carried out based on an alarm braking logic algorithm.

Description

Technical Field

[0001] This application relates to the field of automotive engineering and advanced driver assistance technologies, and more particularly, to a rear automatic emergency braking method and system based on millimeter-wave radar. Background Art

[0002] In the development of autonomous driving and advanced driver assistance systems (ADAS), the rear autonomous emergency braking system (RAEB) has become one of the key technologies to improve vehicle safety. The main purpose of the RAEB system is to actively apply emergency braking to prevent the vehicle from colliding with an oncoming vehicle when the driver fails to notice an oncoming vehicle from the rear side during reverse driving and there is a risk of collision between the oncoming vehicle and the host vehicle. At the same time, the driver is reminded to abort the previous action and take over the vehicle as soon as possible. The RAEB system does not make other decisions on behalf of the driver after active braking. That is, the main function of the RAEB system is to automatically activate braking when a rear collision risk is detected to reduce or avoid accidents. Currently, most traditional RAEB systems rely on cameras or lidar (laser detection and ranging) for obstacle detection. However, the performance of these traditional sensors often deteriorates significantly under adverse weather conditions (such as rain, fog, snow) or in environments with poor lighting, resulting in poor performance and affecting their detection effectiveness and system reliability. In addition, lidar systems are usually costly, and cameras are limited by image processing technology and may misidentify or miss identifying obstacles in complex traffic environments. Summary of the Invention

[0003] This application provides a rear automatic emergency braking method and system based on millimeter-wave radar, which can effectively identify and track high-speed moving vehicles under adverse weather conditions and also maintain a high level of vigilance and accuracy in complex traffic situations.

[0004] The specific technical solutions are as follows:

[0005] In a first aspect, an embodiment of this application provides a rear automatic emergency braking method based on millimeter-wave radar, including:

[0006] Obtaining the radar data of oncoming vehicles at the rear side of the host vehicle using a rear corner millimeter-wave radar, and processing the oncoming vehicle radar data based on a signal processing algorithm and a target clustering and tracking algorithm to calculate the vehicle information of all target vehicles; wherein, the vehicle information includes the target vehicle position, target speed, and target heading information;

[0007] Define an alarm area and a potential collision area based on the vehicle information of the host vehicle, and set the flag bit of the emergency braking condition of the host vehicle; wherein, the vehicle information of the host vehicle includes vehicle model, current vehicle condition, host vehicle position, and host vehicle heading information, and the flag bit of the emergency braking condition of the host vehicle is valid or invalid;

[0008] Based on the vehicle information of all target vehicles, the alarm area, and the potential collision area, traverse all target vehicles and evaluate the risk levels of all target vehicles;

[0009] Taking the host vehicle as a reference point, divide the alarm area into an alarm left area and an alarm right area. According to the vehicle position and the target vehicle positions of all target vehicles, respectively obtain the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area, and determine whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area based on the flag bit of the emergency braking condition of the host vehicle and the risk levels of all target vehicles;

[0010] If there is a collision risk, alarm and brake based on the alarm braking logic algorithm.

[0011] In some embodiments of the present application, the defining the alarm area and the potential collision area based on the vehicle information of the host vehicle and setting the flag bit of the emergency braking condition of the host vehicle specifically includes:

[0012] Define the alarm area and the potential collision area according to the vehicle model; wherein, the potential collision area is located in the middle of the alarm area in the X-axis direction, and the X-axis direction is perpendicular to the body of the host vehicle;

[0013] Judge whether the current vehicle speed of the host vehicle is within the preset expected speed range of the Rear Automatic Emergency Braking (RAEB) function, and at the same time judge whether the current gear of the host vehicle is the expected gear of the RAEB system function. If the current vehicle speed of the host vehicle is within the preset expected speed range and the current gear of the host vehicle is the expected gear, set the flag bit of the emergency braking condition of the host vehicle to be valid, otherwise set it to be invalid.

[0014] In some embodiments of the present application, the evaluating the risk levels of all target vehicles specifically includes:

[0015] Judge whether the target vehicle to be evaluated is within the alarm area, judge whether the target vehicle speed of the target vehicle is greater than the preset collision risk speed threshold, and at the same time judge whether the target vehicle will cross the potential collision area or be located within the potential collision area within the collision risk time threshold;

[0016] If the target vehicle is within the alarm area, and the target speed of the target vehicle is greater than the preset collision risk speed threshold, and at the same time the target vehicle will pass through or be located within the potential collision area within the collision risk time threshold, then the risk level of the target vehicle is rated as 1; otherwise, the risk level of the target vehicle is rated as 0.

[0017] In some embodiments of the present application, the alarm area is divided into an alarm left area and an alarm right area with the vehicle itself as the reference point. According to the vehicle position and the target vehicle positions of all target vehicles, the nearest neighbor target and the next-nearest neighbor target within the alarm left area and the alarm right area are respectively obtained, which specifically includes:

[0018] Set the vehicle position as the origin of the X-axis. With the origin of the X-axis as the boundary, divide the alarm area into the alarm left area and the alarm right area. Traverse all target vehicles within the alarm area, and respectively determine the target vehicles corresponding to the nearest and the next-nearest in the X-axis direction within the alarm left area and the alarm right area according to the target vehicle positions of all target vehicles. Define the target vehicle corresponding to the nearest in the X-axis direction as the nearest neighbor target, and define the target vehicle corresponding to the next-nearest in the X-axis direction as the next-nearest neighbor target.

[0019] In some embodiments of the present application, judging whether there is a collision risk for the nearest neighbor target and the next-nearest neighbor target within the alarm left area and the alarm right area according to the emergency braking condition flag bit of the vehicle itself and the risk levels of all target vehicles specifically includes:

[0020] According to the emergency braking condition flag bit of the vehicle itself and the risk levels of all target vehicles, judge whether the emergency braking condition flag bit of the vehicle itself is valid, and respectively judge whether the risk levels of the nearest neighbor target and the next-nearest neighbor target within the alarm left area and the alarm right area are 1. If the emergency braking condition flag bit of the vehicle itself is valid, and there is a nearest neighbor target or a next-nearest neighbor target with a risk level of 1, then it is determined that there is a collision risk; otherwise, it is determined that there is no collision risk.

[0021] In some embodiments of the present application, alarming and braking based on the alarm braking logic algorithm specifically includes:

[0022] For the nearest neighbor target or the next-nearest neighbor target with a collision risk, the radar generates a corresponding alarm signal and sends the alarm signal to the rear automatic emergency braking system RAEB, and the RAEB system alarms according to the alarm signal;

[0023] Based on the body signals of the vehicle, it is determined whether the driver has taken over the vehicle. If the driver has taken over the vehicle, the RAEB system exits the alarm and enters the first cooling time. Otherwise, the radar sends a braking signal to the Electronic Stability Control (ESC) system and receives the response feedback from the ESC system.

[0024] When the ESC system does not respond, it is determined whether the response time of the ESC system exceeds a preset response time threshold. If the response time of the ESC system does not exceed the preset response time threshold, the radar continues to send the braking signal to the ESC system. Otherwise, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the second cooling time.

[0025] When the radar receives the normal response feedback from the ESC system, it starts to record the braking time and synchronously updates the judgment of the current vehicle condition of the vehicle. If the vehicle automatically brakes from the moving state to the stationary state during the braking process, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the third cooling time. If the vehicle has been in the moving state during the braking process, it is determined whether the braking time exceeds a preset braking time threshold. If the braking time does not exceed the preset braking time threshold, the radar continues to send the braking signal to the ESC system. If the braking time exceeds the preset braking time threshold, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the fourth cooling time.

[0026] In some embodiments of the present application, the determination of whether the driver has taken over the vehicle based on the body signals of the vehicle specifically includes:

[0027] Based on the body signals of the vehicle, it is determined whether the brake pedal or the accelerator pedal of the vehicle is actively depressed by the driver. If the brake pedal or the accelerator pedal is actively depressed by the driver and the pedal travel is greater than a preset takeover judgment threshold, it is determined that the driver has taken over the vehicle. Otherwise, it is determined that the driver has not taken over the vehicle.

[0028] In some embodiments of the present application, the first cooling time, the second cooling time, the third cooling time, and the fourth cooling time are all set according to the minimum interval time between two active brakings defined by the actuator of the ESC system; and / or, the preset response time threshold and the preset braking time threshold are both set according to the vehicle model.

[0029] In some embodiments of the present application, the signal processing algorithm includes ADC mixing processing, Fourier transform algorithm, and velocity deblurring processing algorithm; the target clustering and tracking algorithm includes Kalman filtering algorithm and DBSCAN algorithm.

[0030] In a second aspect, an embodiment of the present application provides a rear automatic emergency braking system based on a millimeter-wave radar, including:

[0031] A radar data collection and processing module, configured to obtain oncoming vehicle radar data at the rear side of the vehicle using a rear corner millimeter-wave radar, and perform data processing on the oncoming vehicle radar data based on a signal processing algorithm and a target clustering and tracking algorithm to calculate vehicle information of all target vehicles; wherein, the vehicle information includes target vehicle position, target speed, and target heading information;

[0032] A region division and braking marking module, configured to delimit an alarm region and a potential collision region according to vehicle information of the vehicle itself, and set an emergency braking condition flag of the vehicle itself; wherein, the vehicle information of the vehicle itself includes vehicle model, current vehicle condition, vehicle position, and vehicle heading information of the vehicle itself, and the emergency braking condition flag of the vehicle itself is valid or invalid;

[0033] A risk level assessment module, configured to traverse all target vehicles and assess the risk levels of all target vehicles according to the vehicle information of all target vehicles and the alarm region and the potential collision region;

[0034] A collision risk determination module, configured to divide the alarm region into an alarm left region and an alarm right region with the vehicle itself as a reference point, respectively obtain the nearest neighbor target and the second nearest neighbor target in the alarm left region and the alarm right region according to the vehicle position and the target vehicle positions of all target vehicles, and determine whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target in the alarm left region and the alarm right region according to the emergency braking condition flag of the vehicle itself and the risk levels of all target vehicles;

[0035] An alarm and braking module, configured to perform alarm and braking based on an alarm braking logic algorithm when there is a collision risk.

[0036] The beneficial effects of the embodiment of the present application are as follows:

[0037] The rear automatic emergency braking method uses a millimeter-wave radar, which has all-weather performance, is not affected by rain, snow, and light changes, can ensure that the RAEB system can work stably and effectively in various environments, and the millimeter-wave radar has a lower cost, is easy to be deployed on a large scale, and has high cost-effectiveness. At the same time, the millimeter-wave radar has a fast response speed and a fast data processing speed, can respond to emergencies immediately, and improve the braking efficiency. In addition, the rear automatic emergency braking method can quickly judge the approaching speed and distance of oncoming vehicles at the rear side by real-time analysis of millimeter-wave radar signals. When detecting a potential collision risk, it automatically activates emergency braking, greatly improving the vehicle's defensive ability and riding safety, and providing a new algorithm for autonomous driving and advanced driver assistance systems to cope with changing driving environments and improve overall traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a schematic flowchart of a rear automatic emergency braking method based on a millimeter-wave radar provided by an embodiment of the present application;

[0040] Figure 2 It is a schematic diagram of the RAEB system function scenario applied to a rear automatic emergency braking method based on a millimeter-wave radar provided by an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of the alarm area and potential collision area in the RAEB system applied to a rear automatic emergency braking method based on a millimeter-wave radar provided by an embodiment of the present application;

[0042] Figure 4 It is a schematic diagram of the alarm braking logic algorithm in a rear automatic emergency braking method based on a millimeter-wave radar provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic block diagram of the composition of a rear automatic emergency braking system based on a millimeter-wave radar provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0045] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The terms "including" and "having" and any variations thereof in the embodiments of the present application and the drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0046] The embodiment of the present application discloses a rear automatic emergency braking method based on millimeter wave radar, which uses millimeter wave radar to measure the distance and speed of vehicles or obstacles coming from the rear and rear side with high precision, and can effectively identify and track high-speed moving vehicles under severe weather conditions, and can also maintain a high degree of alertness and accuracy in complex traffic conditions. The following are detailed descriptions.

[0047] In the embodiment of the present application, the rear automatic emergency braking method mainly includes three steps: data collection, data processing and decision making, among which decision making is the core step of the method.

[0048] Data collection: Use rear-angle millimeter-wave radar to collect radar data of vehicles coming from behind and to the side of the vehicle (including point cloud data, target detection information, environmental perception information, and object feature information);

[0049] Data processing: Through signal processing algorithms and target clustering tracking algorithms, the location, speed and heading information of the target vehicle are further confirmed;

[0050] Decision making: Based on the vehicle information of the own vehicle and the target vehicle, determine whether the target vehicle has a collision risk, and issue an alarm and brake based on the alarm braking logic algorithm.

[0051] Figure 1 A rear automatic emergency braking method based on millimeter wave radar according to an embodiment of the present application is shown. Figure 1 As shown, the detailed steps of the rear automatic emergency braking method are introduced, such as Figure 1 As shown, it includes the following steps:

[0052] Step S110: Use the rear-angle millimeter-wave radar to obtain the radar data of the vehicles behind and to the side of the vehicle, and process the radar data of the vehicles based on the signal processing algorithm and the target clustering tracking algorithm to calculate the vehicle information of all target vehicles.

[0053] The vehicle information includes the target vehicle position, target speed and target heading information.

[0054] In some embodiments, the signal processing algorithm includes analog-to-digital converter (ADC) mixing processing, Fourier transform algorithm and velocity defuzzification processing algorithm; and the target clustering tracking algorithm includes a Kalman filter algorithm and a density-based spatial clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN).

[0055] It should be noted that this method is carried out for each frame in the subsequent decision-making process, that is, a frame of radar target data is obtained, including the position (X, Y) of the target vehicle, the lateral speed (Vx), and the longitudinal speed (Vy). The static / dynamic state and heading information of the target vehicle are judged, and based on this, the collision risk is determined. When it is determined that there is a collision risk, an alarm and braking are carried out based on the alarm braking logic algorithm to avoid the risk. When it is determined that there is no collision risk in the current frame, the judgment of the next frame is entered.

[0056] Step S120: Delimit the alarm area and the potential collision area according to the vehicle information of the host vehicle, and set the emergency braking condition flag of the host vehicle.

[0057] Among them, the vehicle information of the host vehicle includes the vehicle model, the current vehicle condition, the position of the host vehicle, and the heading information of the host vehicle. The current vehicle condition includes the motion state information such as the speed, acceleration, and driving direction of the host vehicle, and the static state; the emergency braking condition flag of the host vehicle is valid or invalid.

[0058] In some embodiments, the alarm area and the potential collision area are delimited according to the vehicle model, that is, the alarm area and the potential collision area are mainly delimited according to the requirements of different vehicle models, and generally, the minimum area required to meet the regulations of the Car Assessment Programme (CAP) is default. As Figure 2 and Figure 3 shown, the potential collision area is located in the middle of the alarm area in the X-axis direction. Further, the potential collision area has the same width as the alarm area in the Y-axis direction. Among them, in this application, the X-axis direction is the direction perpendicular to the body of the host vehicle, and the Y-axis direction is the direction parallel to the body of the host vehicle. However, it should be noted that the perpendicularity in this application is not absolute perpendicularity and can be 90°±10°. Similarly, the parallelism is not absolute parallelism and can be 180°±10°.

[0059] In some other embodiments, it is determined whether the current vehicle speed of the host vehicle is within the preset expected speed range of the RAEB system function, and at the same time, it is determined whether the current gear of the host vehicle is the expected gear of the RAEB system function. If the current vehicle speed of the host vehicle is within the preset expected speed range and the current gear of the host vehicle is the expected gear, the emergency braking condition flag of the host vehicle is set to valid; otherwise, it is set to invalid. That is, it is determined whether the vehicle body of the host vehicle meets the following two conditions: 1. Whether the current vehicle speed is within the preset expected speed range of the RAEB system function; 2. Whether the current gear is the expected gear of the RAEB system function. When both conditions are met, the emergency braking condition flag of the host vehicle is set to valid; when any one of the conditions is not met, the emergency braking condition flag of the host vehicle is set to invalid. Among them, the preset expected speed range of the RAEB system function needs to cover the speed requirements of the European New Car Assessment Programme (E-NCAP) and the China New Car Assessment Program (C-NCAP) regulations, and the expected gear of the RAEB system function is the R gear.

[0060] Step S130: According to the vehicle information of all target vehicles, as well as the alarm area and the potential collision area, traverse all target vehicles and evaluate the risk levels of all target vehicles.

[0061] Among them, the risk level of the target vehicle is 1 or 0.

[0062] In some embodiments, it is determined whether the evaluated target vehicle is within the warning area, whether the target vehicle speed of the target vehicle is greater than the preset collision risk speed threshold, and whether the target vehicle will pass through or be located within the potential collision area within the collision risk time threshold; if the target vehicle is within the warning area, the target vehicle speed of the target vehicle is greater than the preset collision risk speed threshold, and the target vehicle will pass through or be located within the potential collision area within the collision risk time threshold, the risk level of the target vehicle is rated as 1, otherwise the risk level of the target vehicle is rated as 0. That is, all target vehicles are traversed to determine whether the vehicle information of the target vehicle meets the following three conditions: 1. The target vehicle is within the warning area; 2. The target vehicle speed is greater than the preset collision risk speed threshold; 3. The target vehicle will pass through or be located within the potential collision area within the collision risk time threshold. If the above three conditions are met simultaneously, it is considered that there is a collision risk for this target vehicle (risk level is 1), and if any one of the conditions is not met, it is considered that there is no collision risk (risk level is 0). Among them, the preset collision risk speed threshold and the collision risk time threshold can be set according to the vehicle model. Further, they can also be set according to the vehicle model and the specific scenario to meet the vehicle model performance of specific vehicles and different scenario requirements. However, it should be noted that the set preset collision risk speed threshold and collision risk time threshold need to ensure that the final braking effect of the algorithm meets the test requirements of the CAP regulations.

[0063] Step S140: Divide the warning area into a warning left area and a warning right area with the vehicle itself as the reference point. According to the vehicle position and the target vehicle positions of all target vehicles, obtain the nearest neighbor target and the second nearest neighbor target within the warning left area and the warning right area respectively, and determine whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target within the warning left area and the warning right area according to the emergency braking condition flag of the vehicle itself and the risk levels of all target vehicles.

[0064] In some embodiments, the vehicle position is set as the origin of the X-axis. Taking the origin of the X-axis as the boundary, the warning area is divided into a left warning area and a right warning area. All target vehicles located within the warning area are traversed. According to the target vehicle positions of all target vehicles, the target vehicles corresponding to the closest and the second closest distances from the origin of the X-axis in the X-axis direction within the left warning area and the right warning area are respectively determined. The target vehicle corresponding to the closest distance from the origin of the X-axis in the X-axis direction is defined as the closest neighbor target, and the target vehicle corresponding to the second closest distance from the origin of the X-axis in the X-axis direction is defined as the second closest neighbor target. That is, taking X = 0 as the boundary, all target vehicles are divided into two areas for warning judgment. All target vehicles located within the warning area are traversed, and the closest neighbor target (ClosestIn-PathVehicle, CIPV) and the second closest neighbor target (Secondary ClosestIn-Path Vehicle, SCIPV) on the left and right sides are respectively found through the target vehicle positions (X, Y) of the target vehicles.

[0065] Specifically, in this rear automatic emergency braking method, the selection methods for CIPV and SCIPV are as follows:

[0066] A. Taking X = 0 as the boundary, the area behind the vehicle is divided into a left rear area and a right rear area, and the selection of CIPV and SCIPV is performed for the two areas respectively;

[0067] B. All target vehicles within the left rear area are traversed to find the two target vehicles closest to the Y-axis. The closest target vehicle is the left rear CIPV, and the second closest target vehicle is the left rear SCIPV. At the same time, all target vehicles within the right rear area are traversed to find the two target vehicles closest to the Y-axis. The closest target vehicle is the right rear CIPV, and the second closest target vehicle is the right rear SCIPV.

[0068] It should be noted that in the algorithm of this application, the risk levels of all target vehicles are first evaluated to obtain the risk levels, and then CIPV and SCIPV are selected. The subsequent processing is directly carried out according to the evaluated risk levels. At the same time, the above step B is repeated for each frame, and CIPV and SCIPV are continuously updated, so as to cope with the situation where CIPV and SCIPV may switch at any time on the actual road by judging the risk levels of each target vehicle in advance.

[0069] In some other embodiments, according to the emergency braking condition flag of the host vehicle and the risk levels of all target vehicles, it is determined whether the emergency braking condition flag of the host vehicle is valid, and it is respectively determined whether the risk levels of the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area are 1. If the emergency braking condition flag of the host vehicle is valid and there is a nearest neighbor target or a second nearest neighbor target with a risk level of 1, it is determined that there is a collision risk; otherwise, it is determined that there is no collision risk. That is, it is determined whether the position of the emergency braking condition flag of the host vehicle is valid, and at the same time, it is determined whether there is a collision risk between the CIPV and the SCIPV (i.e., the risk level is 1). If the position of the emergency braking condition flag of the host vehicle is valid and there is at least one target with a risk level of 1, it is determined that there is a collision risk in the current frame of radar target data, and it enters step S150 from step S140; otherwise, there is no collision risk, and it enters the next frame judgment, entering step S110 from step S140.

[0070] Step S150: Alarm and brake based on the alarm braking logic algorithm.

[0071] In some embodiments, for the nearest neighbor target or the second nearest neighbor target with a collision risk, the radar generates a corresponding alarm signal and sends the alarm signal to the Rear Automatic Emergency Braking system (RAEB), and the RAEB system alarms according to the alarm signal.

[0072] According to the body signal of the host vehicle, it is determined whether the driver has taken over the vehicle. If the driver has taken over the vehicle, the radar does not send a braking signal, cancels the RAEB alarm signal, and the RAEB system exits the alarm and enters the first cooling time; otherwise, the radar sends a braking signal to the Electronic Stability Control (ESC) system and receives the response feedback of the ESC system. In the specific implementation process, the radar determines whether the driver has noticed the collision risk and actively taken over by whether the brake pedal and the accelerator pedal are depressed and the travel exceeds the threshold. Specifically, according to the body signal of the host vehicle, it is determined whether the brake pedal or the accelerator pedal of the host vehicle is actively depressed by the driver. If the brake pedal or the accelerator pedal is actively depressed by the driver (including the cases where the brake pedal and the accelerator pedal are depressed separately and simultaneously), and the pedal travel is greater than the preset takeover judgment threshold, that is, a direct intervention has been made on the motion state of the vehicle, it is determined that the driver has taken over the vehicle; otherwise, it is determined that the driver has not taken over the vehicle. Among them, the preset takeover judgment threshold can be set according to the vehicle model to adapt to the performance of different specific vehicle models.

[0073] When the ESC system fails to respond, it is determined whether the response time of the ESC system exceeds a preset response time threshold. If the response time of the ESC system does not exceed the preset response time threshold, the radar continues to send a braking signal to the ESC system; otherwise, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the second cooling time.

[0074] When the radar receives a normal response feedback from the ESC system, it starts to record the braking time and synchronously updates the judgment of the current vehicle condition of the vehicle. If the vehicle automatically brakes from the moving state to the stationary state during the braking process, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the third cooling time. If the vehicle is in the moving state all the time during the braking process (that is, it never enters the stationary state), the braking time is continuously monitored to determine whether the braking time exceeds a preset braking time threshold. If the braking time does not exceed the preset braking time threshold, the radar continues to send a braking signal to the ESC system; if the braking time exceeds the preset braking time threshold, regardless of whether the vehicle is stationary or not, the radar stops sending the braking signal, and the RAEB system exits the alarm and enters the fourth cooling time.

[0075] Further, before determining whether the driver has taken over the vehicle, the rear automatic emergency braking method first determines whether the RAEB system is in the cooling state. If it is in the cooling state, the radar continues to send an alarm signal to the collision target; otherwise, it further determines whether the driver has taken over the vehicle.

[0076] In this application, the RAEB system defaults that one braking can avoid risks and the driver will actively avoid risks after receiving the reminder information. By setting each cooling time, it is prevented that the RAEB system has another false braking after the current risk is avoided. Further, the first cooling time, the second cooling time, the third cooling time, and the fourth cooling time can all be set according to the minimum interval time of two active brakings limited by the actuator of the ESC system to ensure that the driver can actively respond to the risk environment during each cooling time; and / or, the preset response time threshold and the preset braking time threshold are both set according to the vehicle model, that is, the specific values can be set according to the performance of the specific vehicle model. Because the functional algorithm of the RAEB system in this application will judge that the collision risk has disappeared and exit the braking after the alarm braking, it is necessary to ensure that the collision risk has been avoided when the braking time is greater than this preset braking time threshold. At the same time, the RAEB system should not keep braking forever, so it is necessary to judge a larger braking time threshold, and it is determined according to the braking effect of the vehicle and experience that this braking time threshold fully meets the braking time required for the vehicle to avoid risks. In addition, the braking of the RAEB system needs to be responded by the vehicle body actuator, and the response may be delayed. Therefore, according to the radar emission cycle and the vehicle body message cycle, a preset response time threshold is required, that is, this preset response time threshold meets the response time required by the actuator when the vehicle body system is normal.

[0077] In a specific implementation process, such as Figure 4 shown, the alarm braking logic algorithm is described in detail:

[0078] Step S151: The radar emits an alarm signal to the collision target.

[0079] Step S152: Determine whether the RAEB system is in a cooling state.

[0080] After step S151, determine whether the RAEB system is in a cooling state. If so, return from step S152 to step S151; otherwise, proceed from step S152 to step S153.

[0081] Step S153: Determine whether the driver has taken over the vehicle.

[0082] Determine whether the driver has taken over the vehicle. If so, return from step S153 to step S154; otherwise, proceed from step S153 to step S155.

[0083] Step S154: Exit the alarm and enter the cooling state.

[0084] Step S155: The radar sends a braking signal.

[0085] Step S156: Determine whether the ESC system responds to the braking.

[0086] After step S155, determine whether the ESC system responds to the braking. If so, proceed from step S156 to step S157; otherwise, proceed from step S156 to step S158.

[0087] Step S157: Record the braking time, and synchronously update the current vehicle condition of the vehicle itself, and determine whether the vehicle itself brakes to a stop.

[0088] Determine whether the vehicle itself brakes to a stop. If so, proceed from step S157 to step S159; otherwise, return from step S157 to step S1510.

[0089] Step S158: Determine whether the non-response time exceeds the preset response time threshold.

[0090] Determine whether the non-response time exceeds the preset response time threshold. If so, proceed from step S158 to step S1511; otherwise, return from step S158 to step S155.

[0091] Step S159: Determine whether the stationary time exceeds the preset stationary time threshold.

[0092] Determine whether the stationary time exceeds a preset stationary time threshold. If so, proceed from step S159 to step S1511; otherwise, return from step S159 to step S155.

[0093] Step S1510: Determine whether the braking time exceeds a preset braking time threshold.

[0094] Determine whether the braking time exceeds a preset braking time threshold. If so, proceed from step S1510 to step S1511; otherwise, return from step S1510 to step S155.

[0095] Step S1511: Exit braking and enter the cooling state.

[0096] Corresponding to the above method embodiments, an embodiment of the present application also provides a rear automatic emergency braking system based on a millimeter-wave radar, which is used to execute the steps of the rear automatic emergency braking method based on a millimeter-wave radar in the above embodiments. As Figure 5 shown, the rear automatic emergency braking system 200 based on a millimeter-wave radar includes: a radar data collection and processing module 210, a region division and braking marking module 220, a risk level assessment module 230, a collision risk determination module 240, and an alarm and braking module 250.

[0097] Specifically, the radar data collection and processing module 210 is used to obtain the oncoming vehicle radar data at the rear side of the vehicle using the rear corner millimeter-wave radar, and perform data processing on the oncoming vehicle radar data based on a signal processing algorithm and a target clustering and tracking algorithm to calculate the vehicle information of all target vehicles. Among them, the vehicle information includes the target vehicle position, target speed, and target heading information.

[0098] The region division and braking marking module 220 is used to delimit an alarm region and a potential collision region according to the vehicle information of the vehicle itself, and set an emergency braking condition flag bit for the vehicle itself. Among them, the vehicle information of the vehicle itself includes the vehicle model, the current vehicle condition, the vehicle position of the vehicle itself, and the heading information of the vehicle itself, and the emergency braking condition flag bit for the vehicle itself is valid or invalid.

[0099] The risk level assessment module 230 is used to traverse all target vehicles and evaluate the risk levels of all target vehicles according to the vehicle information of all target vehicles and the alarm region and potential collision region.

[0100] The collision risk determination module 240 is used to divide the alarm region into an alarm left region and an alarm right region with the vehicle itself as a reference point, respectively obtain the nearest neighbor target and the second nearest neighbor target in the alarm left region and the alarm right region according to the vehicle position and the target vehicle positions of all target vehicles, and determine whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target in the alarm left region and the alarm right region according to the emergency braking condition flag bit of the vehicle itself and the risk levels of all target vehicles.

[0101] The alarm and braking module 250 is used to give an alarm and apply braking based on the alarm braking logic algorithm when there is a collision risk.

[0102] It should be noted that the rear automatic emergency braking system based on millimeter-wave radar provided in the embodiments of the present application, because it is based on the same concept as the embodiments of the rear automatic emergency braking method based on millimeter-wave radar of the present application, the technical effects brought by it are the same as those of the embodiments of the rear automatic emergency braking method based on millimeter-wave radar of the present application. For specific content, reference can be made to the description in the embodiments of the rear automatic emergency braking method based on millimeter-wave radar of the present application, and details will not be repeated here.

[0103] Those of ordinary skill in the art can realize that the modules and algorithm steps of each embodiment described in combination with the embodiments disclosed in the present application can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but this implementation should not be considered to exceed the scope of the present application.

[0104] In summary, the present application discloses a rear automatic emergency braking method and system based on millimeter-wave radar. By real-time analysis of millimeter-wave radar signals, the approaching speed and distance of vehicles coming from the rear side can be quickly judged. When a potential collision risk is detected, emergency braking is automatically activated, greatly improving the vehicle's defensive ability and riding safety, and providing a new algorithm for autonomous driving and advanced driver assistance systems to cope with the changing driving environment and enhance overall traffic safety.

[0105] Those of ordinary skill in the art can understand that the drawings are only schematic diagrams of an embodiment, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0106] Those of ordinary skill in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be correspondingly changed to be located in one or more devices different from this embodiment. The modules in the above embodiments can be combined into one module, or further split into multiple sub-modules.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic emergency braking method for the rear based on a millimeter-wave radar, characterized in that, Including: Obtaining the radar data of oncoming vehicles at the rear side of the host vehicle by using the rear corner millimeter-wave radar, and processing the oncoming vehicle radar data based on a signal processing algorithm and a target clustering and tracking algorithm to calculate the vehicle information of all target vehicles; wherein, the vehicle information includes the target vehicle position, the target speed, and the target heading information; Defining an alarm area and a potential collision area according to the host vehicle information, and setting the emergency braking condition flag of the host vehicle; wherein, the host vehicle information includes the vehicle model, the current vehicle condition, the host vehicle position, and the host vehicle heading information, and the emergency braking condition flag of the host vehicle is valid or invalid; Traversing all target vehicles and evaluating the risk levels of all target vehicles according to the vehicle information of all target vehicles and the alarm area and the potential collision area; Dividing the alarm area into an alarm left area and an alarm right area with the host vehicle as a reference point, respectively obtaining the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area according to the vehicle position and the target vehicle positions of all target vehicles, and judging whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target in the alarm left area and the alarm right area according to the emergency braking condition flag of the host vehicle and the risk levels of all target vehicles; If there is a collision risk, then alarm and brake based on the alarm braking logic algorithm.

2. The rear automatic emergency braking method based on millimeter wave radar according to claim 1, wherein The defining the alarm area and the potential collision area according to the host vehicle information, and setting the emergency braking condition flag of the host vehicle specifically includes: Defining the alarm area and the potential collision area according to the vehicle model; wherein, the potential collision area is located in the middle of the alarm area in the X-axis direction, and the X-axis direction is perpendicular to the body of the host vehicle; Judging whether the current vehicle speed of the host vehicle is within the preset expected speed range of the rear automatic emergency braking system (RAEB) function, and at the same time judging whether the current gear of the host vehicle is the expected gear of the RAEB system function. If the current vehicle speed of the host vehicle is within the preset expected speed range and the current gear of the host vehicle is the expected gear, then set the emergency braking condition flag of the host vehicle to be valid, otherwise set it to be invalid.

3. The rear automatic emergency braking method based on millimeter wave radar according to claim 1, characterized in that The evaluating the risk levels of all target vehicles specifically includes: Judging whether the target vehicle to be evaluated is within the alarm area, judging whether the target speed of the target vehicle is greater than the preset collision risk speed threshold, and at the same time judging whether the target vehicle will cross the potential collision area or be located within the potential collision area within the collision risk time threshold; If the target vehicle is within the alarm area, the target speed of the target vehicle is greater than the preset collision risk speed threshold, and the target vehicle will cross the potential collision area or be located within the potential collision area within the collision risk time threshold, then evaluate the risk level of the target vehicle as 1, otherwise evaluate the risk level of the target vehicle as 0.

4. The method for rear automatic emergency braking based on millimeter-wave radar according to claim 3, wherein Taking the vehicle itself as a reference point, the warning area is divided into a left warning area and a right warning area. According to the vehicle position and the target vehicle positions of all target vehicles, the nearest neighbor target and the second-nearest neighbor target within the left warning area and the right warning area are respectively obtained, which specifically includes: Setting the vehicle position as the origin of the X-axis. Taking the origin of the X-axis as the boundary, the warning area is divided into the left warning area and the right warning area. All target vehicles located within the warning area are traversed. According to the target vehicle positions of all target vehicles, the target vehicles corresponding to the nearest and the second-nearest in the X-axis direction within the left warning area and the right warning area are respectively determined. The target vehicle corresponding to the nearest in the X-axis direction is defined as the nearest neighbor target, and the target vehicle corresponding to the second-nearest in the X-axis direction is defined as the second-nearest neighbor target.

5. The rear automatic emergency braking method based on millimeter wave radar according to claim 4, wherein Judging whether there is a collision risk for the nearest neighbor target and the second-nearest neighbor target within the left warning area and the right warning area according to the emergency braking condition flag of the vehicle itself and the risk levels of all target vehicles, which specifically includes: According to the emergency braking condition flag of the vehicle itself and the risk levels of all target vehicles, judging whether the emergency braking condition flag of the vehicle itself is valid, and respectively judging whether the risk levels of the nearest neighbor target and the second-nearest neighbor target within the left warning area and the right warning area are 1. If the emergency braking condition flag of the vehicle itself is valid and there is a nearest neighbor target or a second-nearest neighbor target with a risk level of 1, it is determined that there is a collision risk; otherwise, it is determined that there is no collision risk.

6. The method for rear automatic emergency braking based on millimeter wave radar according to claim 1, wherein, Carrying out warning and braking based on the warning braking logic algorithm, which specifically includes: For the nearest neighbor target or the second-nearest neighbor target with a collision risk, the radar generates a corresponding warning signal and sends the warning signal to the Rear Automatic Emergency Braking system (RAEB). The RAEB system gives an alarm according to the warning signal. According to the body signal of the vehicle itself, judging whether the driver has taken over the vehicle. If the driver has taken over the vehicle, the RAEB system exits the warning and enters the first cooling time; otherwise, the radar sends a braking signal to the Electronic Stability Control system (ESC) and receives the response feedback of the ESC system. When the ESC system does not respond, judging whether the response time of the ESC system exceeds the preset response time threshold. If the response time of the ESC system does not exceed the preset response time threshold, the radar continues to send the braking signal to the ESC system; otherwise, the radar stops sending the braking signal, and the RAEB system exits the warning and enters the second cooling time. When the radar receives the normal response feedback from the ESC system, it starts to record the braking time and synchronously updates the judgment of the current vehicle condition of the vehicle. If the vehicle automatically brakes from the moving state to the stationary state during the braking process, the radar stops sending the braking signal, the RAEB system exits the alarm and enters the third cooling time. If the vehicle remains in the moving state during the braking process, it is judged whether the braking time exceeds the preset braking time threshold. If the braking time does not exceed the preset braking time threshold, the radar continues to send the braking signal to the ESC system. If the braking time exceeds the preset braking time threshold, the radar stops sending the braking signal, the RAEB system exits the alarm and enters the fourth cooling time.

7. The rear automatic emergency braking method based on millimeter-wave radar according to claim 6, characterized in that, Judging whether the driver has taken over the vehicle according to the vehicle body signal of the vehicle, specifically including: According to the vehicle body signal of the vehicle, it is judged whether the brake pedal or the accelerator pedal of the vehicle is actively stepped on by the driver. If the brake pedal or the accelerator pedal is actively stepped on by the driver and the pedal stroke is greater than the preset takeover judgment threshold, it is determined that the driver has taken over the vehicle, otherwise it is determined that the driver has not taken over the vehicle.

8. The rear automatic emergency braking method based on millimeter-wave radar according to claim 6, characterized in that The first cooling time, the second cooling time, the third cooling time and the fourth cooling time are all set according to the minimum interval time of two active brakings defined by the actuator of the ESC system; and / or, the preset response time threshold and the preset braking time threshold are both set according to the vehicle model.

9. The rear automatic emergency braking method based on millimeter-wave radar according to claim 1, wherein The signal processing algorithm includes ADC mixing processing, Fourier transform algorithm and velocity deblurring processing algorithm; the target clustering and tracking algorithm includes Kalman filtering algorithm and DBSCAN algorithm.

10. An automatic emergency braking system for the rear based on a millimeter-wave radar, characterized in that, Including: A radar data collection and processing module, which is used to obtain the oncoming vehicle radar data at the rear side of the vehicle by using the rear corner millimeter wave radar, and perform data processing on the oncoming vehicle radar data based on the signal processing algorithm and the target clustering and tracking algorithm, and calculate the vehicle information of all target vehicles; wherein, the vehicle information includes the target vehicle position, the target speed and the target heading information; A region division and braking marking module, which is used to delimit the alarm region and the potential collision region according to the vehicle information of the vehicle, and set the emergency braking condition flag of the vehicle; wherein, the vehicle information of the vehicle includes the vehicle model, the current vehicle condition, the vehicle position and the vehicle heading information, and the emergency braking condition flag of the vehicle is valid or invalid; A risk level evaluation module, which is used to traverse all target vehicles and evaluate the risk levels of all target vehicles according to the vehicle information of all target vehicles and the alarm region and the potential collision region; The collision risk determination module is used to divide the warning area into a warning left area and a warning right area with the host vehicle as a reference point, respectively obtain the nearest neighbor target and the second nearest neighbor target within the warning left area and the warning right area according to the vehicle position and the target vehicle positions of all target vehicles, and determine whether there is a collision risk for the nearest neighbor target and the second nearest neighbor target within the warning left area and the warning right area according to the emergency braking condition flag of the host vehicle and the risk levels of all target vehicles; The alarm and braking module is used to alarm and brake based on the alarm braking logic algorithm when there is a collision risk.

Images