Method and device for selecting activation target of automatic emergency braking, and storage medium

Abstract

The application relates to an automatic emergency braking activation target selection method and device and a storage medium. The method comprises: performing dynamic and static classification processing on a target object perceived by a self vehicle, if a moving target is found in the dynamic and static classification processing, and obtaining a moving target parameter of the moving target; wherein the moving target parameter comprises at least one of a lane where the moving target is located, a moving speed and a moving direction. The method determines a first moving target which has coincidence with a to-be-traveled trajectory of the self vehicle from the found moving target, determines a first static target which has coincidence with the to-be-traveled trajectory of the self vehicle from the found static target, selects a target with the minimum collision time from the first moving target and the first static target as an activation target of automatic emergency braking, avoids false triggering, selects a target which needs to be triggered by AEB, and improves the accuracy of the activation target selection.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle auxiliary technology, in particular to an activation target selection method and device of automatic emergency braking and a storage medium. BACKGROUND

[0002] At present, with the development of China's economy, cars have become the mainstream transportation tool for every family. With the increase of the total amount of family car maintenance in the country, more and more vehicles are driving on the road. When a driver drives a vehicle configured with an automatic emergency braking (hereinafter also referred to as AEB) function on the road, if the driver is distracted, looks down at the mobile phone or looks at the navigation, etc., resulting in the AEB of the ego vehicle needing to be activated, which target of multiple targets should be selected as the braking target, while ensuring that the AEB function cannot be triggered mistakenly when the driver is driving normally, because once the AEB is mistakenly braked, especially in complex traffic flow with many people and many vehicles on urban roads, it is likely to cause a rear-end collision accident due to the failure of the rear vehicle to brake in time. For example, when the driver feels that the vehicle in front of the ego vehicle is driving too slowly and wants to overtake, the driver will press the accelerator. At this time, if the AEB system cannot correctly identify the overtaking intention of the driver, it is likely to select the vehicle in front as the target of the AEB function triggering, which will cause a mistaken braking, causing a very bad driving experience for the driver, and also likely to cause a rear-end collision accident due to the failure of the rear vehicle to brake in time, endangering the safety of the driver. Therefore, how to select the activation target when the AEB function needs to be activated in an emergency situation has become a problem to be solved. SUMMARY

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides an activation target selection method and device of automatic emergency braking and a storage medium.

[0004] In a first aspect, the present application provides an activation target selection method of automatic emergency braking, the method comprising:

[0005] performing dynamic and static classification processing on a target object perceived by the ego vehicle;

[0006] if a moving target is found in the dynamic and static classification processing, obtaining a moving target parameter of the moving target; wherein the moving target parameter comprises at least one of a lane where the moving target is located, a moving speed and a moving direction of the moving target;

[0007] determining a first moving target of the moving targets that has a coincidence with a to-be-traveled trajectory of the ego vehicle according to the moving target parameter of the moving target;

[0008] If a stationary target is found in the moving and static classification processing, a first stationary target is determined from the stationary targets, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle;

[0009] An activated target with the minimum collision time is selected from the first moving target and / or the first stationary target, so that the ego vehicle activates automatic emergency braking according to the activated target.

[0010] Optionally, determining the first stationary target from the stationary targets, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle, comprises:

[0011] The following steps are repeatedly performed until there is only one same stationary target in the intersection of the first target group and the second target group: obtaining a first target group in a first time frame, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle; wherein the first target group includes at least one stationary target; obtaining a second target group in a second time frame after the first time frame, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle; wherein the second target group includes at least one stationary target;

[0012] The intersection of the first target group and the second target group is taken as the first stationary target.

[0013] Optionally, the moving target parameter at least includes a lane where the moving target is located and a moving direction of the moving target; and determining the first moving target from the moving targets, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle, comprises:

[0014] Obtaining a current lane where the ego vehicle is located;

[0015] Dividing the moving target into an in-lane target and an out-lane target based on the current lane and the lane where the moving target is located;

[0016] Dividing the out-lane target into an out-lane cross target and an out-lane longitudinal moving target according to the moving direction;

[0017] Dividing the in-lane target into an in-lane cross target and an in-lane longitudinal moving target according to the moving direction;

[0018] Determining the first moving target from the out-lane cross target, the out-lane longitudinal moving target, the in-lane cross target, and the in-lane longitudinal moving target, which has an overlapping trajectory with the to-be-traveled trajectory of the ego vehicle.

[0019] Optionally, the motion target parameter further comprises a moving speed of the motion target; determining the first motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, from the cross-lane target, the longitudinal motion target outside the lane, the cross-lane target inside the lane, and the longitudinal motion target inside the lane, comprises:

[0020] acquiring an ego speed and a steering angle of the ego vehicle;

[0021] determining a second motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, according to the moving speed of the cross-lane target, the moving direction of the cross-lane target, the ego speed, and the steering angle;

[0022] determining a third motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, according to the moving speed of the longitudinal motion target outside the lane, the moving direction of the longitudinal motion target outside the lane, the ego speed, and the steering angle;

[0023] determining a fourth motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, according to the moving speed of the cross-lane target, the moving direction of the cross-lane target, the ego speed, and the steering angle;

[0024] determining a fifth motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, according to the moving speed of the longitudinal motion target inside the lane, the moving direction of the longitudinal motion target inside the lane, the ego speed, and the steering angle;

[0025] taking the second motion target, the third motion target, the fourth motion target, and the fifth motion target as the first motion target.

[0026] Optionally, determining the second motion target, which has a trajectory overlap with the to-be-traveled trajectory of the ego vehicle, according to the moving speed of the cross-lane target, the moving direction of the cross-lane target, the ego speed, and the steering angle, comprises:

[0027] if the moving direction of the cross-lane target indicates that the cross-lane target outside the lane is a cross-lane target outside the lane turning into a straight-line target, discarding the cross-lane target outside the lane;

[0028] if the moving direction of the cross-lane target indicates that the cross-lane target outside the lane is not a cross-lane target outside the lane turning into a straight-line target, judging whether the cross-lane target outside the lane has a trajectory overlap with the ego vehicle according to the moving speed of the cross-lane target, the moving direction of the cross-lane target, the ego speed, and the steering angle;

[0029] if the off-lane crossing target has no trajectory overlap with the ego vehicle, discarding the off-lane crossing target;

[0030] if the off-lane crossing target has trajectory overlap with the ego vehicle, taking the off-lane crossing target as the second moving target.

[0031] Optionally, determining a third moving target having trajectory overlap with a trajectory to be traveled by the ego vehicle according to a moving speed of the off-lane longitudinal moving target, a moving direction of the off-lane longitudinal moving target, the ego vehicle speed and the steering angle, comprises:

[0032] if the moving direction of the off-lane longitudinal moving target indicates that the off-lane longitudinal moving target has no lateral moving trend, discarding the off-lane longitudinal moving target;

[0033] if the moving direction of the off-lane longitudinal moving target indicates that the off-lane longitudinal moving target has lateral moving trend, judging whether the off-lane longitudinal moving target has trajectory overlap with the ego vehicle according to the moving speed of the off-lane longitudinal moving target, the moving direction of the off-lane longitudinal moving target, the ego vehicle speed and the steering angle;

[0034] if the off-lane longitudinal moving target has no trajectory overlap with the ego vehicle, discarding the off-lane longitudinal moving target;

[0035] if the off-lane longitudinal moving target has trajectory overlap with the ego vehicle, taking the off-lane longitudinal moving target as the third moving target.

[0036] Optionally, determining a fourth moving target having trajectory overlap with a trajectory to be traveled by the ego vehicle according to a moving speed of the in-lane crossing target, a moving direction of the in-lane crossing target, the ego vehicle speed and the steering angle, comprises:

[0037] judging whether the in-lane crossing target has trajectory overlap with the ego vehicle according to the moving speed of the in-lane crossing target, the moving direction of the in-lane crossing target, the ego vehicle speed and the steering angle;

[0038] if the in-lane crossing target has no trajectory overlap with the ego vehicle, discarding the in-lane crossing target;

[0039] if the in-lane crossing target has trajectory overlap with the ego vehicle, taking the in-lane crossing target as the fourth moving target.

[0040] Optionally, the fifth moving target overlapped with the to-be-traveled trajectory of the ego vehicle is determined according to the moving speed of the longitudinal moving target in the lane, the moving direction of the longitudinal moving target in the lane, the ego vehicle speed and the steering angle, including:

[0041] If the moving speed of the longitudinal moving target in the lane is greater than or equal to the ego vehicle speed, the longitudinal moving target in the lane is discarded.

[0042] If the moving speed of the longitudinal moving target in the lane is less than the ego vehicle speed, whether the longitudinal moving target in the lane is overlapped with the trajectory of the ego vehicle is determined according to the moving speed of the longitudinal moving target in the lane, the moving direction of the longitudinal moving target in the lane, the ego vehicle speed and the steering angle.

[0043] If the longitudinal moving target in the lane is not overlapped with the trajectory of the ego vehicle, the longitudinal moving target in the lane is discarded.

[0044] If the longitudinal moving target in the lane is overlapped with the trajectory of the ego vehicle, the longitudinal moving target in the lane is taken as the fifth moving target.

[0045] Optionally, the activated target with the minimum collision time is selected from the first moving target and / or the first stationary target, so that the ego vehicle activates the automatic emergency braking according to the activated target, including:

[0046] The first collision time of the first moving target and the ego vehicle is obtained.

[0047] The second collision time of the first stationary target and the ego vehicle is obtained.

[0048] The target collision time with the minimum time is determined from the second collision time and the first collision time.

[0049] The target corresponding to the target collision time is taken as the activated target.

[0050] The ego vehicle is controlled to activate the automatic emergency braking according to the activated target.

[0051] In a second aspect, the present application provides an activated target selection device for automatic emergency braking, the device comprising:

[0052] A dynamic and static classification module is configured to perform dynamic and static classification processing on the target object perceived by the ego vehicle.

[0053] The acquisition module is configured to acquire a moving target parameter of the moving target if the moving target is found in the dynamic-static classification processing, wherein the moving target parameter comprises at least one of a lane where the moving target is located, a moving speed and a moving direction.

[0054] The first determination module is configured to determine a first moving target that overlaps with a to-be-traveled trajectory of the ego vehicle from the moving targets according to the moving target parameter of the moving target.

[0055] The second determination module is configured to determine a first stationary target that overlaps with the to-be-traveled trajectory of the ego vehicle from the stationary targets if the stationary target is found in the dynamic-static classification processing.

[0056] The target selection module is configured to select an activated target with a minimum collision time from the first moving target and / or the first stationary target, so that the ego vehicle activates an automatic emergency brake according to the activated target.

[0057] In a third aspect, the present application provides an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus.

[0058] The memory is configured to store a computer program.

[0059] The processor is configured to execute the program stored on the memory, and implement the steps of the automatic emergency brake activated target selection method of any one of the embodiments of the first aspect.

[0060] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the automatic emergency brake activated target selection method of any one of the embodiments of the first aspect.

[0061] The present application has the following beneficial effects:

[0062] The method provided by the embodiment of the present application performs dynamic and static classification processing on the target object perceived by the ego vehicle; if a moving target is found in the dynamic and static classification processing, a moving target parameter of the moving target is acquired; wherein the moving target parameter comprises at least one of a lane where the moving target is located, a moving speed and a moving direction; according to the moving target parameter of the moving target, a first moving target that has an overlap with a to-be-traveled trajectory of the ego vehicle is determined; if a static target is found in the dynamic and static classification processing, a first static target that has an overlap with the to-be-traveled trajectory of the ego vehicle is determined from the static target; and an active target with the minimum collision time is selected from the first moving target and / or the first static target, so that the ego vehicle activates automatic emergency braking according to the active target. The method determines a first moving target that has an overlap with a to-be-traveled trajectory of the ego vehicle from a moving target found by performing dynamic and static classification processing on a target object other than the ego vehicle, determines a first static target that has an overlap with the to-be-traveled trajectory of the ego vehicle from a static target found, and then selects a target with the minimum collision time from the first moving target and the first static target as an active target of automatic emergency braking, thereby avoiding false triggering, screening out a target that needs to be triggered by AEB, and improving the accuracy of selection of the active target. BRIEF DESCRIPTION OF DRAWINGS

[0063] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced here. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0065] Figure 1 A system architecture diagram of an automatic emergency braking active target selection method provided by an embodiment of the present application;

[0066] Figure 2 A flowchart of an automatic emergency braking active target selection method provided by an embodiment of the present application;

[0067] Figure 3 A flowchart of an automatic emergency braking active target selection method provided by another embodiment of the present application;

[0068] Figure 4 A structural diagram of an automatic emergency braking active target selection device provided by an embodiment of the present application;

[0069] Figure 5 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0070] The embodiments of the present application will be described in detail with reference to the drawings and preferred embodiments, and other advantages and effects of the present application can be easily understood by those skilled in the art from the contents disclosed in the present specification. The present application can also be implemented or applied in other different specific embodiments, and various modifications or changes can be made to the details of the present specification based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0071] The first embodiment of the present application provides an activation target selection method of automatic emergency braking, which can be applied to a system architecture as shown in the figure, which can include a vehicle 101, and can also include a vehicle 101 and a server 102, and when including the vehicle 101 and the server 102, the vehicle 101 and the server 102 establish a communication connection. Figure 1

[0072] The method can be applied to the vehicle 101 or the server 102 in the system architecture, wherein the type of the vehicle 101 is not limited, such as a fuel car, a pure electric car, a hybrid car or a fuel cell car, etc., the vehicle 101 applying the method can be referred to as a target vehicle, and the server 102 can be a local server, a cloud server, or a server cluster.

[0073] Next, based on the system architecture, the activation target selection method of the automatic emergency braking is described in detail, as shown in the figure. Figure 2 The activation target selection method of the automatic emergency braking comprises:

[0074] Step 201, performing dynamic and static classification processing on the target object perceived by the ego vehicle.

[0075] The ego vehicle can perceive the target object outside the vehicle through devices such as laser radar, millimeter wave radar and visual camera, and the target object can be a surrounding vehicle, a pedestrian, a guardrail, a road edge, a water mark, a power pole, etc., without limitation. By comparing the same target object at different time frames, the target object can be dynamically and statically classified and processed to find moving targets and stationary targets. Of course, only moving targets can be found, or only stationary targets can be found, without limitation. The type and number found during dynamic and static classification processing are used as the criterion. For example, vehicles, pedestrians, electric bicycles, bicycles, etc. on the road are moving targets found in dynamic and static classification processing, and road edges, guardrails, signal lights, water marks, power poles, etc. are stationary targets found in dynamic and static classification processing.​

[0076] In step 202, if a moving target is found in the moving and static classification processing, a moving target parameter of the moving target is acquired; wherein the moving target parameter comprises at least one of a lane where the moving target is located, a moving speed and a moving direction.

[0077] For a moving target such as a car, an electric bicycle, a pedestrian, etc., a moving target parameter of the moving target can be acquired, the moving target parameter can be one or more of a moving speed, a moving direction and a lane where the moving target is located, of course, it can also include a lateral width, a longitudinal width and a height of the moving target, etc., without limitation. For a vehicle, the moving direction can be a target heading angle of the vehicle.

[0078] In step 203, according to the moving target parameter of the moving target, a first moving target which has coincidence with a to-be-traveled trajectory of the ego vehicle is determined.

[0079] In one embodiment, the moving target parameter at least comprises a lane where the moving target is located and a moving direction of the moving target; according to the moving target parameter of the moving target, the first moving target which has coincidence with the to-be-traveled trajectory of the ego vehicle is determined, comprising:

[0080] Acquiring a current lane where the ego vehicle is located;

[0081] Based on the current lane and the lane where the moving target is located, the moving target is divided into an in-lane target and an out-lane target;

[0082] The out-lane target is divided into an out-lane crossing target and an out-lane longitudinal moving target according to the moving direction;

[0083] The in-lane target is divided into an in-lane crossing target and an in-lane longitudinal moving target according to the moving direction;

[0084] The first moving target which has coincidence with the to-be-traveled trajectory of the ego vehicle is determined from the out-lane crossing target, the out-lane longitudinal moving target, the in-lane crossing target and the in-lane longitudinal moving target.

[0085] In this embodiment, the devices such as laser radar, millimeter wave radar and visual camera can collect the lane where each moving target is located and the current lane where the ego vehicle is located, so that the moving targets can be divided into in-lane targets and out-lane targets in combination with the lane where the ego vehicle is located and the lane where the moving targets are located. Further, the out-lane targets can be divided into out-lane crossing targets and out-lane longitudinal moving targets according to the moving direction of the moving targets, and the in-lane targets can be divided into in-lane crossing targets and in-lane longitudinal moving targets, so that the first moving target which coincides with the to-be-traveled trajectory of the ego vehicle can be determined from the out-lane crossing targets, the out-lane longitudinal moving targets, the in-lane crossing targets and the in-lane longitudinal moving targets. The first moving target can be one or multiple, without limitation.

[0086] The moving target parameter can further include the moving speed of the moving target.

[0087] For the out-lane crossing target, determining the first moving target which coincides with the to-be-traveled trajectory of the ego vehicle from the out-lane crossing targets, the out-lane longitudinal moving targets, the in-lane crossing targets and the in-lane longitudinal moving targets includes: obtaining the ego speed and the steering angle of the ego vehicle; determining the second moving target which coincides with the to-be-traveled trajectory of the ego vehicle according to the moving speed of the out-lane crossing target, the moving direction of the out-lane crossing target, the ego speed and the steering angle; determining the third moving target which coincides with the to-be-traveled trajectory of the ego vehicle according to the moving speed of the out-lane longitudinal moving target, the moving direction of the out-lane longitudinal moving target, the ego speed and the steering angle; determining the fourth moving target which coincides with the to-be-traveled trajectory of the ego vehicle according to the moving speed of the in-lane crossing target, the moving direction of the in-lane crossing target, the ego speed and the steering angle; determining the fifth moving target which coincides with the to-be-traveled trajectory of the ego vehicle according to the moving speed of the in-lane longitudinal moving target, the moving direction of the in-lane longitudinal moving target, the ego speed and the steering angle; and taking the second moving target, the third moving target, the fourth moving target and the fifth moving target as the first moving target.

[0088] In this embodiment, the second moving target, the third moving target, the fourth moving target and the fifth moving target which coincide with the to-be-traveled trajectory of the ego vehicle can be respectively determined by the ego speed of the ego vehicle and the steering angle of the ego vehicle in combination with the moving direction and the moving speed of different moving targets, and the second moving target, the third moving target, the fourth moving target and the fifth moving target are taken as the first moving target. By screening different targets at different levels, the activation target which really needs to activate AEB can be screened from the target objects, so as to avoid the situation of false triggering.

[0089] Next, in a specific embodiment, in combination with Figure 3, respectively, the target selection algorithm for determining whether the to-be-traveled trajectory of the lane-out crossing target and the to-be-traveled trajectory of the ego vehicle coincide is described in detail, Figure 3 The flowchart of the target selection method for automatic emergency braking is shown.

[0090] For the lane-out crossing target, according to the moving speed of the lane-out crossing target, the moving direction of the lane-out crossing target, the ego vehicle speed and the steering angle, the second moving target that coincides with the to-be-traveled trajectory of the ego vehicle is determined, including: if the moving direction of the lane-out crossing target indicates that the lane-out crossing target is a lane-out crossing turning and straight target, the lane-out crossing target is discarded; if the moving direction of the lane-out crossing target indicates that the lane-out crossing target is not a lane-out crossing turning and straight target, whether the lane-out crossing target coincides with the to-be-traveled trajectory of the ego vehicle is determined according to the moving speed of the lane-out crossing target, the moving direction of the lane-out crossing target, the ego vehicle speed and the steering angle; if the lane-out crossing target does not coincide with the to-be-traveled trajectory of the ego vehicle, the lane-out crossing target is discarded; if the lane-out crossing target coincides with the to-be-traveled trajectory of the ego vehicle, the lane-out crossing target is taken as the second moving target.

[0091] In this embodiment, first, all the targets outside the vehicle perceived by the laser radar, millimeter wave radar, visual camera and other devices are divided into moving targets and static targets, the moving targets are further divided into lane-in targets and lane-out targets, the lane-out targets are divided into lane-out crossing targets and lane-out longitudinal moving targets, the lane-in targets are divided into lane-in crossing targets and lane-in longitudinal moving targets, and the static targets are divided into lane-out targets and lane-in targets.

[0092] For the lane-out crossing target, the heading angle judgment is performed in the visual image domain, to determine whether the lane-out crossing target is a crossing turning and straight target, if it is a crossing turning and straight target, there is no collision risk with the ego vehicle (i.e. the ego vehicle), then the lane-out crossing target is discarded; if it is not a crossing turning and straight target, it is only a simple crossing target, then whether the trajectories will overlap at a certain time in the future is calculated according to the ego vehicle speed and the moving speed of the lane-out crossing target, if there is no overlap, the lane-out crossing target is also discarded; if the lane-out crossing target has trajectory overlap with the ego vehicle in the future, the target is kept as the second moving target and passed to the subsequent process for further screening.

[0093] For the out-of-lane longitudinal motion target, according to the moving speed of the out-of-lane longitudinal motion target, the moving direction of the out-of-lane longitudinal motion target, the self vehicle speed and the steering angle, a third motion target which has a track overlap with the to-be-traveled track of the self vehicle is determined, including: if the moving direction of the out-of-lane longitudinal motion target represents that the out-of-lane longitudinal motion target has no lateral motion trend, the out-of-lane longitudinal motion target is discarded; if the moving direction of the out-of-lane longitudinal motion target represents that the out-of-lane longitudinal motion target has a lateral motion trend, whether the out-of-lane longitudinal motion target has a track overlap with the self vehicle is judged according to the moving speed of the out-of-lane longitudinal motion target, the moving direction of the out-of-lane longitudinal motion target, the self vehicle speed and the steering angle; if the out-of-lane longitudinal motion target has no track overlap with the self vehicle, the out-of-lane longitudinal motion target is discarded; if the out-of-lane longitudinal motion target has a track overlap with the self vehicle, the out-of-lane longitudinal motion target is taken as the third motion target.

[0094] In the embodiment, for the out-of-lane longitudinal motion target, whether the out-of-lane longitudinal motion target has a steering angle, such as whether the moving direction has a lateral motion trend, is judged. If there is no lateral motion trend, the out-of-lane longitudinal motion target and the self vehicle will not be in the same lane, and there is no collision risk, so the out-of-lane longitudinal motion target is discarded. If the out-of-lane longitudinal motion target has a lateral motion trend, whether the out-of-lane longitudinal motion target and the self vehicle have a track overlap at a future time under the steering angle and the moving speed is further judged. If there is no overlap, that is, there is no collision risk, the out-of-lane longitudinal motion target is discarded. If there is an overlap, the out-of-lane longitudinal motion target is taken as the third motion target. Of course, whether the self vehicle has a steering angle can be judged first. If there is no steering angle, the self vehicle and the target have no collision risk, and the target is discarded. If the self vehicle has a steering angle, but under the steering angle and the vehicle speed, the target also has no track overlap with the self vehicle, the target also has no collision risk with the self vehicle, and the target is discarded. If the self vehicle and the target have a collision risk under the steering angle and the vehicle speed, the target is retained as the third motion target and is transmitted to the subsequent process for further screening.

[0095] For the in-lane crossing target, according to the moving speed of the in-lane crossing target, the moving direction of the in-lane crossing target, the self vehicle speed and the steering angle, a fourth motion target which has a track overlap with the to-be-traveled track of the self vehicle is determined, including: whether the in-lane crossing target has a track overlap with the self vehicle is judged according to the moving speed of the in-lane crossing target, the moving direction of the in-lane crossing target, the self vehicle speed and the steering angle; if the in-lane crossing target has no track overlap with the self vehicle, the in-lane crossing target is discarded; if the in-lane crossing target has a track overlap with the self vehicle, the in-lane crossing target is taken as the fourth motion target.

[0096] In this embodiment, for the target crossing in the lane, if the target has crossed away from the movement track of the ego vehicle at a certain time in the future at the current speed of the ego vehicle, the target has no collision risk, the target is discarded, if there is an overlap at a certain time with the track of the ego vehicle, it means that there is a collision risk with the ego vehicle, the target is retained as the fourth moving target and is passed to the subsequent process for further screening.

[0097] For the longitudinal moving target in the lane, the fifth moving target which has an overlap with the to-be-traveled track of the ego vehicle is determined according to the moving speed of the longitudinal moving target in the lane, the moving direction of the longitudinal moving target in the lane, the ego vehicle speed and the steering angle, including: if the moving speed of the longitudinal moving target in the lane is greater than or equal to the ego vehicle speed, the longitudinal moving target in the lane is discarded; if the moving speed of the longitudinal moving target in the lane is less than the ego vehicle speed, whether the longitudinal moving target in the lane has an overlap with the ego vehicle is judged according to the moving speed of the longitudinal moving target in the lane, the moving direction of the longitudinal moving target in the lane, the ego vehicle speed and the steering angle; if the longitudinal moving target in the lane has no overlap with the ego vehicle, the longitudinal moving target in the lane is discarded; if the longitudinal moving target in the lane has an overlap with the ego vehicle, the longitudinal moving target in the lane is taken as the fifth moving target.

[0098] In this embodiment, for the longitudinal moving target in the lane, it is first judged whether the longitudinal moving target in the lane has a longitudinal speed as the ego vehicle, if the moving speed of the longitudinal moving target in the lane is greater than or equal to the ego vehicle speed, the longitudinal moving target in the lane has no collision risk and is discarded; if the moving speed of the longitudinal moving target in the lane is less than the ego vehicle speed, it is further judged whether the ego vehicle has a steering angle, if the ego vehicle has no steering angle, the ego vehicle has a collision risk with the longitudinal moving target in the lane, the longitudinal moving target in the lane is retained as the fifth moving target; if the ego vehicle has a steering angle and has no track overlap with the target at the steering angle and the ego vehicle speed, the longitudinal moving target in the lane has no collision risk with the ego vehicle and is discarded; if the ego vehicle has a collision risk with the longitudinal moving target in the lane at the steering angle and the ego vehicle speed, the longitudinal moving target in the lane is retained as the fifth moving target and is passed to the subsequent process for further screening.

[0099] It should be understood that in the process of determining the second moving target, the third moving target, the fourth moving target and the fifth moving target, there can be no second moving target, third moving target, fourth moving target or fifth moving target meeting the conditions, for example, only the second moving target and the third moving target meeting the conditions exist, at this time, the first moving target can be determined according to the second moving target and the third moving target.

[0100] Step 204, if a stationary target is found in the dynamic and static classification processing, a first stationary target is determined from the stationary targets which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle.

[0101] In one embodiment, the first stationary target is determined from the stationary targets which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle, including: repeatedly performing the following steps until there is only one same stationary target in the intersection of the first target group and the second target group: obtaining a first target group which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle in a first time frame; wherein the first target group includes at least one stationary target; obtaining a second target group which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle in a second time frame after the first time frame; wherein the second target group includes at least one stationary target. The intersection of the first target group and the second target group is taken as the first stationary target.

[0102] In the embodiment, the stationary targets can be divided into lane-out targets and lane-in targets, and a delay judgment is performed on the lane-out targets and the lane-in targets, that is, in the first time frame, a first target group which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle is determined from all the stationary targets, and then in the second time frame after the first time frame, a second target group which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle is determined from all the stationary targets, until there is only one same stationary target in the intersection of the first target group and the second target group, and the stationary target is taken as the first stationary target. The first stationary target is on the trajectory of the ego vehicle and has the shortest longitudinal distance from the front bumper of the ego vehicle.

[0103] Step 205, selecting an activated target with the minimum collision time from the first moving target and / or the first stationary target, so that the ego vehicle activates the automatic emergency braking according to the activated target.

[0104] The method determines a first moving target which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle from the moving targets found by performing the dynamic and static classification processing on the target objects other than the ego vehicle, determines a first stationary target which has a coincident trajectory with the to-be-traveled trajectory of the ego vehicle from the stationary targets found, and selects a target with the minimum collision time from the first moving target and the first stationary target as the activated target of the automatic emergency braking, thereby avoiding false triggering and screening out the target which the AEB truly needs to trigger, and improving the accuracy of the selection of the activated target.

[0105] In one embodiment, the activated target with the minimum time to collision is selected from the first moving target and / or the first stationary target to activate the automatic emergency braking of the ego vehicle according to the activated target, including: obtaining a first time to collision of the first moving target with the ego vehicle; obtaining a second time to collision of the first stationary target with the ego vehicle; determining a target time to collision with the minimum time from the second time to collision and the first time to collision; taking the target corresponding to the target time to collision as the activated target; and controlling the ego vehicle to activate the automatic emergency braking according to the activated target.

[0106] In the embodiment, the time to collision (TTC) is calculated for the previously screened first moving target (which can include the second moving target, the third moving target, the fourth moving target and the fifth moving target) and the first stationary target with the ego vehicle, i.e., the first time to collision of the first moving target with the ego vehicle and the second time to collision of the first stationary target with the ego vehicle are calculated respectively, one first moving target corresponds to one first time to collision, if there are multiple first moving targets, there are also multiple first times to collision, and the second time to collision is the same. From all the times to collision, the target with the minimum time to collision is selected, which is the most dangerous target screened out, i.e., the activated target. The activated target is output to the AEB function module to control the ego vehicle to activate the AEB function, so as to screen out the target that the AEB really needs to trigger while avoiding false triggering, thereby improving the accuracy of the selection of the activated target.

[0107] Based on the same technical concept, the second embodiment of the present application provides an activated target selection device for automatic emergency braking, as shown in Figure 4 , the device comprises:

[0108] The dynamic and static classification module 401 is configured to perform dynamic and static classification processing on the target object perceived by the ego vehicle.

[0109] The acquisition module 402 is configured to, if a moving target is found in the dynamic and static classification processing, acquire a moving target parameter of the moving target; wherein the moving target parameter includes at least one of a lane where the moving target is located, a moving speed and a moving direction.

[0110] The first determination module 403 is configured to determine, according to the moving target parameter of the moving target, a first moving target that has an overlapping trajectory with the ego vehicle to be driven in the moving target.

[0111] The second determination module 404 is configured to, if a stationary target is found in the dynamic and static classification processing, determine a first stationary target that has an overlapping trajectory with the ego vehicle to be driven in the stationary target.

[0112] The target selection module 405 is configured to select an activated target with the minimum collision time from the first moving target and / or the first stationary target, so that the automatic emergency brake of the ego vehicle is activated according to the activated target.

[0113] The device determines the first moving target having the overlapping trajectory with the ego vehicle from the moving targets and the first stationary target having the overlapping trajectory with the ego vehicle from the stationary targets, and selects the target with the minimum collision time from the first moving target and the first stationary target as the activated target of the automatic emergency brake, so as to avoid false triggering and select the target that needs to be triggered by the AEB, and improve the accuracy of the selection of the activated target.

[0114] As shown in Figure 5 The third embodiment of the present application provides an electronic device, which comprises a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112 and the memory 113 are in communication with each other through the communication bus 114,

[0115] The memory 113 is configured to store a computer program.

[0116] In an embodiment, the processor 111 is configured to execute the program stored in the memory 113, so as to implement the method for selecting the activated target of the automatic emergency brake according to any one of the preceding method embodiments.

[0117] The memory and the processor in the electronic device are in communication through the communication bus and the communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus and a control bus, etc.

[0118] The memory can include a Random Access Memory (RAM) and a non-volatile memory such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the processor.

[0119] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0120] The fourth embodiment of the present application provides a computer readable medium having a non-volatile program code executable by a processor.

[0121] Optionally, in the embodiments of the present application, the computer readable medium is configured to store program code for the processor to execute the above method.

[0122] Optionally, the specific examples in the embodiments can refer to the examples described in the above embodiments, and the embodiments will not be described here again.

[0123] When the embodiments of the present application are implemented, reference can be made to the above various embodiments, and have corresponding technical effects.

[0124] It can be understood that the embodiments described herein can be realized in hardware, software, firmware, middleware, microcode or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units designed to perform the functions described in the embodiments of the present application, or a combination thereof.

[0125] For software implementation, the technologies herein can be implemented by units performing functions herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0126] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software 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 such implementation should not be considered beyond the scope of the present application.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0128] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. In actual implementation, another division mode can be used. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0129] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0130] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0131] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the embodiments. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various media that can store program codes.

[0132] It should be noted that, in the present document, relational terms such as "first" and "second", and the like can be used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0133] The above embodiments are only preferred embodiments of the present application, but the protection scope of the present application is not limited thereto. Any equivalent replacement or transformation made by those skilled in the art based on the present application shall fall within the protection scope of the present application.

Claims

1. A method for selecting an activation target for automatic emergency braking, characterized in that, The method includes: Perform dynamic / static classification processing on target objects perceived by the vehicle itself; If a moving target is detected in the static / dynamic classification process, then the motion target parameters of the moving target are obtained; wherein, the motion target parameters include at least one of the lane in which the moving target is located, its speed, and its direction of movement; Based on the motion target parameters of the moving target, determine the first moving target among the moving targets that overlaps with the trajectory to be traveled by the vehicle itself; If a stationary target is found in the dynamic-static classification process, then a first stationary target that overlaps with the vehicle's trajectory to be driven is determined from the stationary targets. Select the activation target with the shortest collision time from the first moving target and / or the first stationary target, so that the vehicle itself activates automatic emergency braking according to the activation target; The method of identifying a first stationary target from the stationary targets that overlaps with the trajectory to be traveled by the vehicle itself includes: Repeat the following steps until there is only one identical stationary target in the intersection of the first target group and the second target group: Obtain the first target group that overlaps with the vehicle's trajectory in the first time frame; wherein the first target group includes at least one stationary target; Obtain the second target group that overlaps with the vehicle's trajectory in the second time frame after the first time frame; wherein the second target group includes at least one stationary target. The intersection of the first target group and the second target group is taken as the first stationary target; The moving target parameters include at least the lane where the moving target is located and the direction of movement of the moving target; based on the moving target parameters, a first moving target that overlaps with the vehicle's trajectory is determined, including: Get the current lane of your vehicle; Based on the current lane and the lane where the moving target is located, the moving target is divided into targets within the lane and targets outside the lane; The targets outside the lane are divided into targets crossing the lane and targets moving longitudinally outside the lane according to their direction of movement. The targets within the lane are divided into targets moving across the lane and targets moving longitudinally within the lane according to the direction of movement. The first moving target that overlaps with the trajectory of the vehicle to be driven is identified from among the following: the target crossing outside the lane, the longitudinal moving target outside the lane, the target crossing inside the lane, and the longitudinal moving target inside the lane.

2. The method according to claim 1, characterized in that, The moving target parameters also include the moving speed of the moving target; determining the first moving target that overlaps with the vehicle's trajectory among the following: the outward-crossing target, the outward-longitudinal moving target, the inward-crossing target, and the inward-longitudinal moving target, including: Obtain the vehicle's own speed and steering angle; Based on the moving speed of the target crossing the lane, the moving direction of the target crossing the lane, the vehicle's own speed, and the turning angle, a second moving target that overlaps with the vehicle's trajectory is determined. Based on the moving speed of the longitudinal moving target outside the lane, the moving direction of the longitudinal moving target outside the lane, the vehicle's own speed, and the steering angle, a third moving target that overlaps with the vehicle's own trajectory is determined. Based on the moving speed of the target crossing the lane, the moving direction of the target crossing the lane, the vehicle's own speed, and the turning angle, a fourth moving target that overlaps with the vehicle's trajectory is determined. Based on the moving speed of the longitudinal moving target in the lane, the moving direction of the longitudinal moving target in the lane, the vehicle's own speed, and the steering angle, a fifth moving target that overlaps with the vehicle's own driving trajectory is determined. The second moving target, the third moving target, the fourth moving target, and the fifth moving target are designated as the first moving target.

3. The method according to claim 2, characterized in that, Based on the moving speed of the target crossing the lane outside, the moving direction of the target crossing the lane outside, the vehicle's own speed, and the steering angle, a second moving target overlapping with the vehicle's intended trajectory is determined, including: If the movement direction of the target crossing the lane indicates that the target crossing the lane is a target crossing the lane and then turning straight, then the target crossing the lane is discarded. If the direction of movement of the target crossing the lane indicates that the target crossing the lane is not a target crossing the lane and turning straight, then the vehicle's own speed and the turning angle are used to determine whether the target crossing the lane and the vehicle's own trajectory overlap. If the target crossing the lane does not overlap with the trajectory of the vehicle itself, then the target crossing the lane is discarded. If the trajectory of the target crossing the lane overlaps with that of the vehicle itself, then the target crossing the lane is designated as the second moving target.

4. The method according to claim 2, characterized in that, Based on the moving speed of the longitudinally moving target outside the lane, the moving direction of the longitudinally moving target outside the lane, the vehicle's own speed, and the steering angle, a third moving target that overlaps with the vehicle's trajectory is determined, including: If the direction of movement of the longitudinally moving target outside the lane indicates that the longitudinally moving target outside the lane has no lateral movement trend, then the longitudinally moving target outside the lane is discarded. If the direction of movement of the longitudinally moving target outside the lane indicates that the longitudinally moving target outside the lane has a lateral movement trend, then based on the speed of movement of the longitudinally moving target outside the lane, the direction of movement of the longitudinally moving target outside the lane, the vehicle's own speed, and the steering angle, it is determined whether the trajectory of the longitudinally moving target outside the lane overlaps with that of the vehicle itself. If the longitudinal moving target outside the lane does not overlap with the trajectory of the vehicle itself, then the longitudinal moving target outside the lane is discarded; If the longitudinal moving target outside the lane overlaps with the trajectory of the vehicle itself, then the longitudinal moving target outside the lane is regarded as the third moving target.

5. The method according to claim 2, characterized in that, Based on the moving speed of the target crossing the lane, the moving direction of the target crossing the lane, the vehicle's own speed, and the steering angle, a fourth moving target overlapping with the vehicle's intended trajectory is determined, including: Based on the moving speed of the target crossing the lane, the moving direction of the target crossing the lane, the vehicle's own speed, and the turning angle, determine whether the trajectory of the target crossing the lane overlaps with that of the vehicle itself. If the target crossing the lane does not overlap with the trajectory of the vehicle itself, then the target crossing the lane is discarded. If the target crossing the lane has a trajectory that overlaps with the vehicle's own trajectory, then the target crossing the lane is considered the fourth moving target.

6. The method according to claim 2, characterized in that, Based on the moving speed of the longitudinally moving target within the lane, the moving direction of the longitudinally moving target within the lane, the vehicle's own speed, and the steering angle, a fifth moving target that overlaps with the vehicle's intended travel trajectory is determined, including: If the speed of the longitudinally moving target in the lane is greater than or equal to the vehicle's own speed, then the longitudinally moving target in the lane is discarded. If the speed of the longitudinally moving target in the lane is less than the vehicle's own speed, then based on the speed of the longitudinally moving target in the lane, the direction of movement of the longitudinally moving target in the lane, the vehicle's own speed, and the steering angle, it is determined whether the trajectory of the longitudinally moving target in the lane overlaps with that of the vehicle. If the longitudinally moving target within the lane does not overlap with the trajectory of the vehicle itself, then the longitudinally moving target within the lane is discarded. If the longitudinal moving target within the lane overlaps with the trajectory of the vehicle itself, then the longitudinal moving target within the lane is designated as the fifth moving target.

7. The method according to claim 1, characterized in that, Selecting the activation target with the shortest collision time from the first moving target and / or the first stationary target, so that the vehicle itself activates automatic emergency braking based on the activation target, includes: Obtain the first collision time between the first moving target and the vehicle itself; Obtain the second collision time between the first stationary target and its own vehicle; Determine the target collision time that is the shortest between the second collision time and the first collision time; The target corresponding to the target collision time is taken as the activated target; The vehicle activates automatic emergency braking according to the activation target.

8. An activation target selection device for automatic emergency braking, characterized in that, The device includes: The static / dynamic classification module is used to perform static / dynamic classification processing on target objects perceived by the vehicle itself; The acquisition module is used to acquire motion target parameters of the moving target if a moving target is detected in the static / dynamic classification process; wherein the motion target parameters include at least one of the lane in which the moving target is located, its speed, and its direction of movement; A first determining module is configured to determine, based on the motion target parameters of the moving targets, a first moving target that overlaps with the vehicle's intended driving trajectory; wherein the motion target parameters include at least the lane where the moving target is located and the direction of movement of the moving target; determining, based on the motion target parameters of the moving targets, the first moving target that overlaps with the vehicle's intended driving trajectory includes: obtaining the current lane where the vehicle is located; classifying the moving targets into in-lane targets and out-of-lane targets based on the current lane and the lane where the moving target is located; classifying the out-of-lane targets into out-of-lane traversing targets and out-of-lane longitudinal moving targets according to the direction of movement; classifying the in-lane targets into in-lane traversing targets and in-lane longitudinal moving targets according to the direction of movement; and determining, among the out-of-lane traversing targets, the out-of-lane longitudinal moving targets, the in-lane traversing targets, and the in-lane longitudinal moving targets, the first moving target that overlaps with the vehicle's intended driving trajectory; The second determining module is configured to, if a stationary target is found in the static / dynamic classification process, determine a first stationary target from the stationary targets that overlaps with the vehicle's intended driving trajectory; wherein determining the first stationary target from the stationary targets that overlaps with the vehicle's intended driving trajectory includes: repeatedly performing the following steps until there is only one identical stationary target in the intersection of the first target group and the second target group: obtaining a first target group that overlaps with the vehicle's intended driving trajectory in a first time frame; wherein the first target group includes at least one stationary target; obtaining a second target group that overlaps with the vehicle's intended driving trajectory in a second time frame after the first time frame; wherein the second target group includes at least one stationary target; and taking the intersection of the first target group and the second target group as the first stationary target; The target selection module is used to select the active target with the shortest collision time from the first moving target and / or the first stationary target, so that the vehicle itself can activate automatic emergency braking based on the active target.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images