Target selection method and device for adaptive cruise control system (ACC)

Abstract

The invention relates to a target selection method for an adaptive cruise control system (ACC), and the method comprises the steps: selecting a first target and a second target which are located in a lane and in front of a vehicle from a plurality of targets, and enabling the second target to be in front of the first target; predicting the motion states of the first target, the second target and the vehicle after a certain time; and determining a proper car following target from the first target and the second target based on the motion state. The invention further relates to target selection equipment of the ACC, a computer readable storage medium and an ADAS (Advanced Driving Assistance System).

Description

Technical Field

[0001] The present application relates to the control field of an adaptive cruise control system ACC, and more specifically, to a target selection method and device for an adaptive cruise control system ACC, a computer-readable storage medium, and an advanced driver assistance system ADAS. Background Art

[0002] As the main basic component of the advanced driver assistance system ADAS, the main purpose of the adaptive cruise control system ACC is to be able to select the moving vehicle in front of the vehicle as the primary target (also called the "target vehicle"), and to control the longitudinal motion state and following distance of the vehicle in real time and comfortably according to the motion state of the primary target.

[0003] At present, most ACC products will select the vehicle closest to the vehicle in the lane as the target vehicle when activated, and send its kinematic properties to the vehicle motion control module VMC. VMC can calculate the appropriate acceleration to control the vehicle to follow the target vehicle at an appropriate distance. However, selecting the closest vehicle in the lane to calculate the target acceleration is not suitable for some special scenarios. For example, when the vehicle is following a stationary car (or a slow-moving vehicle), if a two-wheeled vehicle in the lane overtakes the vehicle, the adaptive cruise control system ACC will switch the main target to the two-wheeled vehicle. Since the speed of the two-wheeled vehicle is higher than that of the vehicle, the vehicle motion control module VMC plans a positive acceleration, causing the vehicle to accelerate forward. When the two-wheeled vehicle overtakes the stationary vehicle (or slow-moving vehicle) in front, the system will switch the main target to the stationary vehicle (or slow-moving vehicle) again. At this time, since the distance between the vehicle and the stationary vehicle (or slow-moving vehicle) is too close, it is impossible to stop, which may eventually lead to a rear-end collision. Summary of the invention

[0004] According to one aspect of the present application, a target selection method for an adaptive cruise control system ACC is provided, the method comprising: selecting a first target and a second target located in a lane and in front of a vehicle from a plurality of targets, wherein the second target is in front of the first target; predicting the motion state of the first target, the second target and the vehicle after a certain period of time; and determining a suitable following target from the first target and the second target based on the motion state.

[0005] As a supplement or alternative to the above solution, the above method may further include: before selecting the first target and the second target from the multiple targets, filtering all targets detected by the sensor to obtain the multiple targets.

[0006] As a supplement or alternative to the above solution, in the above method, the first target and the second target are two targets located in front of the vehicle and closest to the vehicle.

[0007] As a supplement or alternative to the above-mentioned scheme, in the above-mentioned method, predicting the motion state of the first target, the second target and the vehicle after a certain time includes: predicting the position, speed and acceleration of the first target, the second target and the vehicle after the first time; and predicting the position, speed and acceleration of the first target, the second target and the vehicle after the second time, wherein the second time is greater than the first time.

[0008] As a supplement or alternative to the above solution, in the above method, the first time is 1s and the second time is 3s.

[0009] As a supplement or alternative to the above-mentioned scheme, in the above-mentioned method, based on the motion state, determining a suitable following target from the first target and the second target includes: calculating a first safety distance based on the speed of the vehicle after the first time; calculating a second safety distance based on the speed of the vehicle after the second time; and when the sum of the longitudinal distance coordinates of the front bumper of the vehicle after the first time and the first safety distance is less than the longitudinal distance coordinates of the rear bumper of the first target after the first time, the longitudinal distance coordinates of the front bumper of the first target after the second time are greater than the longitudinal distance coordinates of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinates of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinates of the rear bumper of the second target after the second time, determining the second target as the following target of the vehicle; otherwise, taking the first target as the following target of the vehicle.

[0010] As a supplement or alternative to the above scheme, in the above method, the first safety distance is calculated according to the following formula: Safety_distance1=v1*Timegap+braking_distance, wherein Safety_distance1 represents the first safety distance, v1 represents the speed of the vehicle after the first time, Timegap is a preset parameter, and braking_distance represents the following stop distance; and the second safety distance is calculated according to the following formula: Safety_distance2=v2*Timegap+braking_distance, wherein Safety_distance2 represents the second safety distance, and v2 represents the speed of the vehicle after the second time.

[0011] According to another aspect of the present application, a target selection device of an adaptive cruise control system ACC is provided, the device comprising: a selection device for selecting a first target and a second target located in a lane and in front of a vehicle from a plurality of targets, wherein the second target is in front of the first target; a prediction device for predicting the motion state of the first target, the second target and the vehicle after a certain period of time; and a determination device for determining a suitable following target from the first target and the second target based on the motion state.

[0012] As a supplement or alternative to the above scheme, the above device also includes: a preprocessing device, which is used to filter all targets detected by the sensor before the selection device selects the first target and the second target from the multiple targets, so as to obtain the multiple targets.

[0013] As a supplement or replacement for the above solution, in the above device, the first target and the second target are two targets located in front of the vehicle and closest to the vehicle.

[0014] As a supplement or alternative to the above-mentioned scheme, in the above-mentioned device, the prediction device includes: a first prediction unit, used to predict the position, speed and acceleration of the first target, the second target and the vehicle after a first time; and a second prediction unit, used to predict the position, speed and acceleration of the first target, the second target and the vehicle after a second time, wherein the second time is greater than the first time.

[0015] As a supplement or alternative to the above solution, in the above device, the first time is 1s and the second time is 3s.

[0016] As a supplement or replacement for the above-mentioned scheme, in the above-mentioned device, the determination device includes: a first calculation unit, used to calculate the first safety distance based on the speed of the vehicle after the first time; a second calculation unit, used to calculate the second safety distance based on the speed of the vehicle after the second time; and a determination unit, used to determine that the second target is the following target of the vehicle when the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the first time and the first safety distance is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time, the longitudinal distance coordinate of the front bumper of the first target after the second time is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time; otherwise, the first target is used as the following target of the vehicle.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the medium includes instructions, and the instructions execute the above method when executed.

[0018] According to yet another aspect of the present application, an advanced driving assistance system (ADAS) is provided. The advanced driving assistance system (ADAS) includes the target selection device as described above.

[0019] The target selection scheme of the embodiment of the present application is different from the target selection scheme of the prior art. It does not simply take the target closest to the vehicle as the following target (i.e., the main target), but selects the first target and the second target located in the lane and in front of the vehicle from multiple targets, wherein the second target is in front of the first target, and determines the appropriate following target from the first target and the second target based on the predicted first target, the second target, and the motion state of the vehicle after a certain period of time. This target selection scheme can help the ACC system switch to a target vehicle (the first target or the second target) with a higher collision risk and plan deceleration in time in complex traffic scenarios (for example, with more traffic participants), which significantly improves the adaptability of the ACC system to complex scenarios, taking into account both comfort and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects and advantages of the present application will become more fully apparent from the following detailed description in conjunction with the accompanying drawings, wherein the same or similar elements are represented by the same reference numerals.

[0021] Figure 1 A schematic flow chart of a target selection method of an adaptive cruise control system ACC according to an embodiment of the present application is shown;

[0022] Figure 2 A schematic diagram of the structure of a target selection device of an adaptive cruise control system ACC according to an embodiment of the present application is shown;

[0023] Figure 3 A diagram showing an implementation scenario of a target selection scheme of an adaptive cruise control system ACC according to an embodiment of the present application; and

[0024] Figure 4 A schematic flow chart of a target selection method for an adaptive cruise control system ACC according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] Hereinafter, a target selection scheme of an adaptive cruise control system ACC according to various exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0026] Figure 1FIG. 1 is a flow chart of a target selection method 1000 for an adaptive cruise control system ACC according to an embodiment of the present application. Figure 1 As shown, the target selection method 1000 includes:

[0027] In step S110, a first target and a second target located in the lane and in front of the vehicle are selected from a plurality of targets, wherein the second target is in front of the first target;

[0028] In step S120, predicting the motion state of the first target, the second target and the vehicle after a certain period of time; and

[0029] In step S130, based on the motion state, a suitable following target is determined from the first target and the second target.

[0030] In the context of this application, the term "adaptive cruise control system ACC" is also referred to as an adaptive cruise control function, which sends instructions to the actuator according to the driving status (e.g., distance and speed) of the target vehicle in front and the vehicle itself, thereby deciding whether to accelerate or decelerate, or exit cruise. In some embodiments, when there is a risk of collision, the adaptive cruise control system ACC will prompt the driver and take active braking intervention. Moreover, when the distance to the vehicle in front is too small, the adaptive cruise control system ACC can appropriately brake the wheels by cooperating with the anti-lock braking system, etc., so as to always maintain a safe distance from the vehicle in front. In general, the adaptive cruise control system ACC can reduce the driver's driving fatigue to a certain extent.

[0031] In the context of this application, the term "target selection" refers to the selection of a following target (primary target) by the adaptive cruise control system ACC. In one embodiment, after the adaptive cruise control system ACC selects a following target, the adaptive cruise control system ACC sends the kinematic properties (e.g., position, speed, acceleration, etc.) of the following target to the vehicle motion control module VMC, so that the vehicle motion control module VMC can calculate an appropriate acceleration based on the kinematic properties of the following target to control the vehicle.

[0032] In step S110, a first target and a second target located in the lane and in front of the vehicle are selected from multiple targets, wherein the second target is in front of the first target. As described in the background technology section, in existing schemes, a (single) target that is closest to the vehicle (e.g., the closest longitudinal distance) is usually selected from multiple targets as a following target. However, in an embodiment of the present application, as described in step S110, two different targets, namely the first target and the second target, are selected from multiple targets, and the second target is in front of the first target.

[0033] It should be noted that the second target being located in front of the first target is only intended to indicate that the second target is further away from the vehicle relative to the first target. In one embodiment, the second target is located directly in front of the first target. In another embodiment, the second target is located in front of the first target, but both the first target and the second target are located in the lane (also referred to as the "own lane" or "own lane") where the vehicle is located. In one embodiment, the first target and the second target are the two targets located in front of the vehicle and closest to the vehicle (longitudinal distance).

[0034] In step S120, the motion state of the first target, the second target and the host vehicle after a certain period of time is predicted. Here, the term "motion state" refers to the kinematic properties of the first target, the second target and the host vehicle after a certain period of time, which can be helpful for target selection. In one embodiment, the motion state includes: (in the host vehicle coordinate system) position (longitudinal position), velocity (longitudinal velocity) and acceleration (longitudinal acceleration) after a certain period of time.

[0035] In one embodiment, step S120 includes: predicting the position p1, speed v1 and acceleration a1 of the first target, the second target and the vehicle after the first time t1; and predicting the position p2, speed v2 and acceleration a2 of the first target, the second target and the vehicle after the second time t2, wherein the second time t2 is greater than the first time t1. In one embodiment, the first time is 1s and the second time is 3s. That is, the motion states (position, speed and acceleration) of the first target, the second target and the vehicle after 1 second and 3 seconds are predicted respectively.

[0036] Next, in step S130, based on the motion state predicted in step S120, a suitable following target is determined from the first target and the second target. In other words, the following target is determined by selecting one of the first target and the second target.

[0037] In one embodiment, step S130 specifically includes: calculating a first safety distance based on the speed of the vehicle after the first time; calculating a second safety distance based on the speed of the vehicle after the second time; and determining the second target as the following target of the vehicle when the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the first time and the first safety distance is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time, the longitudinal distance coordinate of the front bumper of the first target after the second time is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time; otherwise, the first target is used as the following target of the vehicle. In short, the second target is used as the following target when the following three conditions are met:

[0038] (1) After a first time (e.g., 1 second), the sum of the longitudinal distance coordinate of the front bumper of the own vehicle and the first safety distance is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time;

[0039] (2) after a second time (e.g., 3 seconds), the longitudinal distance coordinate of the front bumper of the first target is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time; and

[0040] (3) After a second time (eg, 3 seconds), the sum of the longitudinal distance coordinate of the front bumper of the host vehicle and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time.

[0041] In this embodiment, if any of the above three conditions is not satisfied, the first target is used as the following target.

[0042] In one or more embodiments, the safety distance may be determined based on the speed of the vehicle. For example, the first safety distance may be calculated according to the following formula:

[0043] Safety_distance1=v1*Timegap+braking_distance,

[0044] Wherein, Safety_distance1 represents the first safety distance, v1 represents the (longitudinal) speed of the vehicle after the first time (e.g., 1 second), Timegap is a preset parameter (e.g., settable by the driver), and braking_distance represents the stopping distance (i.e., the distance between the ACC system and the target vehicle after stopping the target vehicle). In one embodiment, Timegap is set to multiple gears (e.g., four), and the value range of this parameter can be about 0.4s to 1.2s. In one embodiment, the stopping distance is a calibrable value, e.g., about 1 to 3m.

[0045] Similarly, the second safety distance can be calculated according to the following formula:

[0046] Safety_distance2=v2*Timegap+braking_distance,

[0047] Wherein, Safety_distance2 represents the second safety distance, and v2 represents the (longitudinal) speed of the vehicle after the second time (eg, 3 seconds). In addition, the meanings of Timegap and braking_distance in the above formula are the same as those in the first safety distance calculation formula, and are not repeated here.

[0048] In one embodiment, although Figure 1 Not shown in the figure, the target selection method 1000 may further include: before step S110, filtering all targets detected by the sensor (for example, filtering all detected targets according to attributes such as existence probability, obstacle probability, object type, driving task, etc.), so as to obtain the multiple targets. That is, in the context of this application, the term "multiple targets" refers to potential candidates for the final vehicle following target, rather than any target detected by the detection sensor (such as a camera, millimeter wave radar, etc.).

[0049] The target selection method 1000 of the adaptive cruise control system ACC is particularly suitable for complex road scenes. Figure 3 , which shows an implementation scenario diagram of a target selection scheme of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 3As shown, the vehicle 310 is traveling in the left lane, and the vehicle 330 located in the front may be stationary or slow-moving for some reason, while the vehicle 320 located in front of the vehicle suddenly cuts out (switches to the adjacent lane). In one embodiment of the present application, the adaptive cruise control system ACC of the vehicle 310 takes both the vehicles 320 and 330 located in front into consideration when selecting a following target, and selects a suitable following target (e.g., selects a vehicle with a high probability of collision as the following target) based on their motion states to avoid collision, rather than simply selecting a vehicle in the lane that is closest to the vehicle.

[0050] Figure 4 FIG. 2 shows a flow chart of a target selection method of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 4 As shown, in step S410, the whole process starts; in step S415, the targets in front of the vehicle (including various traffic participants, such as cars, two-wheeled vehicles, pedestrians, etc.) are filtered, and two targets in the lane and closest to the longitudinal distance of the vehicle are selected and recorded as PO0 and PO1; in step S420, the motion states of the vehicle, PO0 and PO1 are predicted to obtain their positions, speeds and accelerations after 1 second and 3 seconds respectively; in step S425, the safety distance is calculated according to the speed of the vehicle; then, in step S430, it is determined whether the sum of the longitudinal distance coordinate dx of the front end (such as the front bumper) of the vehicle after 1 second and the safety distance is less than the longitudinal distance coordinate dx of the rear end (such as the rear bumper) of PO0 after 1 second; if so, continue to execute step S440, otherwise execute step S435 and determine the following target as PO0.

[0051] In step S440, determine whether the longitudinal distance coordinate dx of the front end (e.g., front bumper) of PO0 after 3 seconds is greater than the longitudinal distance coordinate dx of the rear end (e.g., rear bumper) of PO1 after 3 seconds; if so, continue to step S450, otherwise execute step S445 and determine the following vehicle target as PO0.

[0052] In step S450, determine whether the sum of the longitudinal distance coordinate dx of the front end (e.g., front bumper) of the vehicle after 3s and the safety distance is greater than the longitudinal distance coordinate dx of the rear end (e.g., rear bumper) of PO1 after 3s; if so, continue to step S460, otherwise execute step S455 and determine the following vehicle target as PO0.

[0053] In step S460, the following target is switched to PO1 (for example, the following target is PO0 by default); and finally, the whole process ends in step S465.

[0054] It should be noted that in the aforementioned embodiments, we describe the target (directly or implicitly) as a vehicle, for example, the target includes the front bumper, the rear bumper, etc., but those skilled in the art will understand that the target may also be other traffic participants, including motorcycles, bicycles, pedestrians, etc., not limited to vehicles.

[0055] The target selection method 1000 of the adaptive cruise control system ACC in the above embodiment can significantly improve the adaptability of the ACC system to complex scenarios, while taking into account both comfort and safety.

[0056] In addition, it is easy for a person skilled in the art to understand that the target selection method 1000 provided in the above one or more embodiments of the present application can be implemented by a computer program. For example, the computer program is included in a computer program product, and when the computer program is executed by a processor, the target selection method 1000 of one or more embodiments of the present application is implemented. For another example, when a computer-readable storage medium (such as a USB flash drive) storing the computer program is connected to a computer, the target selection method 1000 of one or more embodiments of the present application can be executed by running the computer program.

[0057] refer to Figure 2 , Figure 2 FIG. 2 shows a schematic diagram of a target selection device 2000 of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 2 As shown, the target selection device 2000 includes a selection device 210, a prediction device 220 and a determination device 230. The selection device 210 is used to select a first target and a second target located in the lane and in front of the vehicle from a plurality of targets, wherein the second target is in front of the first target; the prediction device 220 is used to predict the motion state of the first target, the second target and the vehicle after a certain period of time; and the determination device 230 is used to determine a suitable following target from the first target and the second target based on the motion state.

[0058] In the context of this application, the term "adaptive cruise control system ACC" is also referred to as an adaptive cruise control function, which sends instructions to the actuator according to the driving status (e.g., distance and speed) of the target vehicle in front and the vehicle itself, thereby deciding whether to accelerate or decelerate, or exit cruise. In some embodiments, when there is a risk of collision, the adaptive cruise control system ACC will prompt the driver and take active braking intervention. Moreover, when the distance to the vehicle in front is too small, the adaptive cruise control system ACC can appropriately brake the wheels by cooperating with the anti-lock braking system, etc., so as to always maintain a safe distance from the vehicle in front. In general, the adaptive cruise control system ACC can reduce the driver's driving fatigue to a certain extent.

[0059] In the context of this application, the term "target selection" refers to the selection of a following target (primary target) by the adaptive cruise control system ACC. In one embodiment, after the adaptive cruise control system ACC selects a following target, the adaptive cruise control system ACC sends the kinematic properties (e.g., position, speed, acceleration, etc.) of the following target to the vehicle motion control module VMC, so that the vehicle motion control module VMC can calculate an appropriate acceleration based on the kinematic properties of the following target to control the vehicle.

[0060] The selection device 210 is configured to select a first target and a second target located in the lane and in front of the vehicle from a plurality of targets, wherein the second target is in front of the first target. In the existing scheme, a (single) target closest to the vehicle (e.g., the shortest longitudinal distance) is usually selected from the plurality of targets as the following target. However, unlike the existing scheme, in the embodiment of the present application, the selection device 210 is configured to select two different targets from the plurality of targets, namely the first target and the second target, and the second target is in front of the first target.

[0061] It should be noted that the second target being located in front of the first target is only intended to indicate that the second target is further away from the vehicle relative to the first target. In one embodiment, the second target is located directly in front of the first target. In another embodiment, the second target is located in front of the first target, but both the first target and the second target are located in the lane (also referred to as the "own lane" or "own lane") where the vehicle is located. In one embodiment, the first target and the second target are the two targets located in front of the vehicle and closest to the vehicle (longitudinal distance).

[0062] The prediction device 220 is configured to predict the motion state of the first target, the second target and the host vehicle after a certain period of time. Here, the term "motion state" refers to the kinematic properties of the first target, the second target and the host vehicle after a certain period of time, which can be helpful for target selection. In one embodiment, the motion state includes: (in the host vehicle coordinate system) the position (longitudinal position), speed (longitudinal speed) and acceleration (longitudinal acceleration) after a certain period of time.

[0063] In one embodiment, the prediction device 220 includes: a first prediction unit for predicting the position p1, speed v1 and acceleration a1 of the first target, the second target and the vehicle after a first time t1; and a second prediction unit for predicting the position p2, speed v2 and acceleration a2 of the first target, the second target and the vehicle after a second time t2, wherein the second time t2 is greater than the first time t1. In one embodiment, the first time is 1s and the second time is 3s. That is, the prediction device 220 predicts the motion state (position, speed and acceleration) of the first target, the second target and the vehicle after 1 second and 3 seconds, respectively.

[0064] The determining device 230 is configured to determine a suitable following target from the first target and the second target based on the motion state predicted by the predicting device 220. That is, the following target is determined by selecting one of the first target and the second target.

[0065] In one embodiment, the determination device 230 specifically includes: a first calculation unit, used to calculate the first safety distance based on the speed of the vehicle after the first time; a second calculation unit, used to calculate the second safety distance based on the speed of the vehicle after the second time; and a determination unit, used to determine the second target as the following target of the vehicle when the sum of the longitudinal distance coordinates of the front bumper of the vehicle after the first time and the first safety distance is less than the longitudinal distance coordinates of the rear bumper of the first target after the first time, the longitudinal distance coordinates of the front bumper of the first target after the second time is greater than the longitudinal distance coordinates of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinates of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinates of the rear bumper of the second target after the second time; otherwise, the first target is used as the following target of the vehicle. In short, when the following three conditions are met, the determination device 230 (or the determination unit) uses the second target as the following target:

[0066] (1) After a first time (e.g., 1 second), the sum of the longitudinal distance coordinate of the front bumper of the own vehicle and the first safety distance is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time;

[0067] (2) after a second time (e.g., 3 seconds), the longitudinal distance coordinate of the front bumper of the first target is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time; and

[0068] (3) After a second time (eg, 3 seconds), the sum of the longitudinal distance coordinate of the front bumper of the host vehicle and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time.

[0069] In this embodiment, if any of the above three conditions is not satisfied, the determination device 230 (or determination unit) takes the first target as the following target.

[0070] In one or more embodiments, the safety distance may be determined based on the speed of the vehicle. For example, the first safety distance may be calculated according to the following formula:

[0071] Safety_distance1=v1*Timegap+braking_distance,

[0072] Wherein, Safety_distance1 represents the first safety distance, v1 represents the (longitudinal) speed of the vehicle after the first time (e.g., 1 second), Timegap is a preset parameter (e.g., settable by the driver), and braking_distance represents the stopping distance (i.e., the distance between the ACC system and the target vehicle after stopping the target vehicle). In one embodiment, Timegap is set to multiple gears (e.g., four), and the value range of this parameter can be about 0.4s to 1.2s. In one embodiment, the stopping distance is a calibrable value, e.g., about 1 to 3m.

[0073] Similarly, the second safety distance can be calculated according to the following formula:

[0074] Safety_distance2=v2*Timegap+braking_distance,

[0075] Wherein, Safety_distance2 represents the second safety distance, and v2 represents the (longitudinal) speed of the vehicle after the second time (eg, 3 seconds). In addition, the meanings of Timegap and braking_distance in the above formula are the same as those in the first safety distance calculation formula, and are not repeated here.

[0076] In one embodiment, although Figure 2 Not shown, the target selection device 2000 may further include: a pre-processing device for filtering all targets detected by the sensor before the selection device 210 selects the first target and the second target from the multiple targets, thereby obtaining the multiple targets. For example, the pre-processing device may filter all detected targets according to attributes such as existence probability, obstacle probability, object type, driving task, etc., thereby obtaining the multiple targets. That is, in the context of the present application, the term "multiple targets" refers to potential candidates for the final following target, rather than any target detected by a detection sensor (such as a camera, millimeter-wave radar, etc.).

[0077] In one embodiment, the target selection device 2000 of the adaptive cruise control system ACC may be integrated into various advanced driving assistance systems ADAS. In one embodiment, the advanced driving assistance system ADAS may be installed in a vehicle.

[0078] "Advanced driver assistance system", also known as ADAS or advanced driver assistance system. It uses various sensors installed on the car (such as millimeter wave radar, lidar, single / binocular camera and satellite navigation) to sense the surrounding environment at any time during the car's driving, collect data, identify, detect and track static and dynamic objects, and combine navigation map data to perform systematic calculations and analysis, so as to make the driver aware of possible dangers in advance, effectively increasing the comfort and safety of car driving. In one embodiment, in addition to adaptive cruise control ACC, the advanced driving assistance system may also include a navigation and real-time traffic system TMC, an electronic police system ISA (Intelligent speed adaptation or intelligent speed advice), a vehicle network (Vehicular communication systems), a lane departure warning system LDWS (Lane departure warning system), a collision avoidance or pre-collision system (Collision avoidance system or Precrash system), a night vision system (Night Vision system), an adaptive light control (Adaptive light control), a pedestrian protection system (Pedestrian protection system), an automatic parking system (Automatic parking), traffic sign recognition (Traffic sign recognition), blind spot detection (Blind spot detection), driver fatigue detection (Driver drowsiness detection), a downhill control system (Hill descent control) and an electric vehicle warning sounds (Electric vehicle warning sounds) system, etc.

[0079] In summary, the target selection scheme of the embodiment of the present application is different from the target selection scheme of the prior art. It does not simply take the target closest to the vehicle as the following target (i.e., the main target), but selects the first target and the second target located in the lane and in front of the vehicle from multiple targets, wherein the second target is in front of the first target, and based on the predicted first target, second target and the motion state of the vehicle after a certain period of time, determines the appropriate following target from the first target and the second target. This target selection scheme can help the ACC system switch to a target vehicle (the first target or the second target) with a higher collision risk and plan deceleration in a timely manner in complex traffic scenarios (e.g., with more traffic participants), significantly improving the adaptability of the ACC system to complex scenarios, while taking into account both comfort and safety.

[0080] The above examples mainly illustrate the target selection scheme of the embodiments of the present application. Although only some of the embodiments of the present application are described, it should be understood by those skilled in the art that the present application can be implemented in many other forms without departing from its subject matter and scope. Therefore, the examples and embodiments shown are considered to be illustrative rather than restrictive, and the present application may cover various modifications and substitutions without departing from the spirit and scope of the present application as defined in the claims.

Claims

1. A target selection method for an adaptive cruise control system ACC, characterized in that: The method comprises: Selecting a first target and a second target located in the lane and in front of the vehicle from a plurality of targets, wherein the second target is in front of the first target; Predicting the motion states of the first target, the second target, and the vehicle after a certain period of time; and Based on the motion state, a suitable following target is determined from the first target and the second target.

2. The method of claim 1, further comprising: Before selecting the first target and the second target from the plurality of targets, all targets detected by the sensor are filtered to obtain the plurality of targets.

3. The method of claim 1, wherein: The first target and the second target are two targets located in front of the vehicle and closest to the vehicle.

4. The method of claim 1, wherein: Predicting the motion state of the first target, the second target, and the vehicle after a certain period of time includes: Predicting the position, speed and acceleration of the first target, the second target and the vehicle after a first time; and Predict the position, velocity, and acceleration of the first target, the second target, and the vehicle after a second time, wherein the second time is greater than the first time.

5. The method of claim 4, wherein: The first time is 1 s and the second time is 3 s.

6. The method according to claim 4 or 5, wherein: Determining a suitable following target from the first target and the second target based on the motion state includes: Calculating a first safety distance based on the speed of the vehicle after the first time; Calculating a second safety distance based on the speed of the vehicle after the second time; and When the sum of the longitudinal distance coordinate of the front bumper of the vehicle and the first safety distance after the first time is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time, the longitudinal distance coordinate of the front bumper of the first target after the second time is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time, the second target is determined as the following target of the vehicle; otherwise, the first target is taken as the following target of the vehicle.

7. The method of claim 6, wherein: The first safety distance is calculated according to the following formula: Safety_distance1=v1*Timegap+braking_distance, Wherein, Safety_distance1 represents the first safety distance, v1 represents the speed of the vehicle after the first time, Timegap is a preset parameter, and braking_distance represents the following stopping distance; and The second safety distance is calculated according to the following formula: Safety_distance2=v2*Timegap+braking_distance, Among them, Safety_distance2 represents the second safety distance, and v2 represents the speed of the vehicle after the second time.

8. A target selection device for an adaptive cruise control system ACC, characterized in that: The device comprises: A selection device, for selecting a first target and a second target located in the lane and in front of the vehicle from a plurality of targets, wherein the second target is in front of the first target; A prediction device, used to predict the motion state of the first target, the second target and the vehicle after a certain period of time; and A determining device is used to determine a suitable following target from the first target and the second target based on the motion state.

9. The apparatus of claim 8, further comprising: The preprocessing device is used for filtering all the targets detected by the sensor before the selection device selects the first target and the second target from the multiple targets, so as to obtain the multiple targets.

10. The device of claim 8, wherein: The first target and the second target are two targets located in front of the vehicle and closest to the vehicle.

11. The device of claim 8, wherein: The prediction device comprises: A first prediction unit, configured to predict the position, speed, and acceleration of the first target, the second target, and the vehicle after a first time; and The second prediction unit is used to predict the position, speed and acceleration of the first target, the second target and the vehicle after a second time, wherein the second time is greater than the first time.

12. The device of claim 11, wherein: The first time is 1 s and the second time is 3 s.

13. The apparatus of claim 11 or 12, wherein: The determining device comprises: A first calculation unit, configured to calculate a first safety distance based on the speed of the vehicle after the first time; A second calculation unit, configured to calculate a second safety distance based on the speed of the vehicle after the second time; and A determination unit is used to determine that the second target is the following target of the vehicle when the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the first time and the first safety distance is less than the longitudinal distance coordinate of the rear bumper of the first target after the first time, the longitudinal distance coordinate of the front bumper of the first target after the second time is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time, and the sum of the longitudinal distance coordinate of the front bumper of the vehicle after the second time and the second safety distance is greater than the longitudinal distance coordinate of the rear bumper of the second target after the second time; otherwise, the first target is used as the following target of the vehicle.

14. A computer-readable storage medium, characterized in that: The medium includes instructions which, when executed, perform the method of any one of claims 1 to 7.

15. An advanced driver assistance system ADAS, characterized in that: The advanced driver assistance system ADAS comprises a target selection device as claimed in any one of claims 8 to 13 .

Images