Vehicle braking method, device and equipment

Abstract

The invention provides a vehicle braking method, device and equipment, and the method comprises the steps: for each moment, obtaining a first physical coordinate of a moving object at the moment, and obtaining a second physical coordinate of a target vehicle at the moment; determining a first expansion area of the moving object based on the first physical coordinate, and determining a second expansion area of the target vehicle based on the second physical coordinate; if it is determined that the collision risk exists between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, pre-braking is conducted on the target vehicle in a pre-braking time interval, and pre-braking comprises brake pre-filling and / or speed reduction; if it is determined that the moving object is the obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, comfortable braking is conducted on the target vehicle. According to the technical scheme, good driving experience is brought to a driver.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a vehicle braking method, device and equipment. Background Art

[0002] Autonomous driving refers to the use of artificial intelligence, sensors and other technologies to enable vehicles to complete driving tasks autonomously without human intervention. Autonomous driving relies on a variety of sensors, such as lidar, cameras and radar, to perceive the surrounding environment in real time and make decisions through complex algorithms.

[0003] For moving objects such as pedestrians, motor vehicles and non-motor vehicles, the movement trajectory of the moving objects is difficult to predict, that is, the moving objects may suddenly cut into the travel area during the vehicle's driving process. Based on this, during the vehicle's automatic driving process, if the moving objects suddenly cut into the travel area during the vehicle's driving process, it will cause the vehicle to brake suddenly (i.e., cause the vehicle to brake suddenly), thus giving the driver a poor driving experience. Summary of the invention

[0004] The present application provides a vehicle braking method, which is applied to a target vehicle, and the method comprises:

[0005] For each moment, a first physical coordinate of the moving object at the moment is obtained, and a second physical coordinate of the target vehicle at the moment is obtained; wherein the moving object is located in a traveling area during the traveling of the target vehicle; a first expansion area of ​​the moving object is determined based on the first physical coordinate, and a second expansion area of ​​the target vehicle is determined based on the second physical coordinate;

[0006] If it is determined that there is a risk of collision between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, pre-braking the target vehicle in a pre-braking time interval, wherein the pre-braking includes brake pre-filling and / or deceleration; wherein the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment;

[0007] If the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, comfort braking is performed on the target vehicle; when comfort braking is performed on the target vehicle, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

[0008] The present application provides a vehicle braking device, applied to a target vehicle, the device comprising:

[0009] A processing module, configured to obtain, for each moment, a first physical coordinate of the moving object at the moment, and a second physical coordinate of the target vehicle at the moment; wherein the moving object is located in a traveling area during the traveling of the target vehicle; determine a first expansion area of ​​the moving object based on the first physical coordinate, and determine a second expansion area of ​​the target vehicle based on the second physical coordinate;

[0010] a pre-braking module, configured to pre-brake the target vehicle in a pre-braking time interval if it is determined based on a first expansion area at a first moment and a second expansion area at a first moment that there is a risk of collision between the target vehicle and the moving object, wherein the pre-braking includes brake pre-filling and / or deceleration; the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment;

[0011] A comfort braking module is used to perform comfort braking on the target vehicle if the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment; when performing comfort braking, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

[0012] The present application provides a vehicle device, comprising: a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor; the processor is used to execute the machine-executable instructions to implement the above-mentioned example vehicle braking method.

[0013] The present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the vehicle braking method of the above example is implemented.

[0014] The present application provides a machine-readable storage medium, which stores machine-executable instructions that can be executed by a processor; wherein the processor is used to execute the machine-executable instructions, and the vehicle braking method of the above example is implemented when the machine-executable instructions are executed.

[0015] It can be seen from the above technical solutions that in the embodiment of the present application, when there is a risk of collision between the target vehicle and the moving object (i.e. the moving object may interfere with the moving trajectory of the target vehicle, but has not yet affected the target vehicle), the target vehicle is pre-braked in advance, and the pre-braking is imperceptible to the driver (i.e. the driver will not perceive the pre-braking process). When the moving object is an obstacle to the target vehicle (i.e. the moving object is locked as an obstacle, and the moving object has already affected the target vehicle), since pre-braking has been performed in advance (such as the vehicle speed has been reduced), the target vehicle can be comfortably braked, that is, the deceleration of the target vehicle is not greater than the maximum braking deceleration, so that the vehicle speed can be slowly reduced (i.e. a comfortable brake stop) without causing emergency braking of the vehicle (i.e. emergency braking of the vehicle), thereby giving the driver a better driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flow chart of a vehicle braking method in one embodiment of the present application;

[0017] Figure 2 is a schematic flow chart of a vehicle braking method in one embodiment of the present application;

[0018] Figure 3 is a flowchart of a moving object recall process in one embodiment of the present application;

[0019] Figure 4 is a schematic diagram of a first expansion region in one embodiment of the present application;

[0020] Figure 5 is a schematic diagram of interference between the first expansion area and the second expansion area in one embodiment of the present application;

[0021] Fig. 6A is a schematic diagram of a low-speed emergency braking scenario in automatic parking in one embodiment of the present application;

[0022] Figure 6B is a schematic diagram of a high-speed emergency braking scenario in adaptive cruise control in one embodiment of the present application;

[0023] Figure 7 is a schematic structural diagram of a vehicle braking device in one embodiment of the present application;

[0024] Figure 8 It is a hardware structure diagram of a vehicle device in one embodiment of the present application. DETAILED DESCRIPTION

[0025] In the embodiment of the present application, a vehicle braking method is proposed, which is applied to a target vehicle, see Figure 1 FIG. 1 is a flow chart of the vehicle braking method, which may include:

[0026] Step 101: for each moment, obtain a first physical coordinate of a moving object at that moment, and obtain a second physical coordinate of a target vehicle at that moment; wherein the moving object may be located in a traveling area of ​​the target vehicle during its travel; determine a first expansion area of ​​the moving object based on the first physical coordinate, and determine a second expansion area of ​​the target vehicle based on the second physical coordinate.

[0027] Step 102: If it is determined that there is a risk of collision between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, pre-braking the target vehicle is performed in a pre-braking time interval, and the pre-braking may include brake pre-filling and / or deceleration; wherein the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment.

[0028] Step 103: If the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, comfort braking is performed on the target vehicle; for example, when comfort braking is performed on the target vehicle, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

[0029] Exemplarily, obtaining the first physical coordinates of the moving object at this moment may include, but is not limited to: determining the coordinate prediction error of the moving object at this moment based on the measured physical coordinates of the moving object at this moment, the measured physical coordinates of the moving object at the moment before this moment, the acceleration of the moving object at the previous moment, and the interval duration between this moment and the previous moment; determining the acceleration prediction error based on the coordinate prediction error and the interval duration; determining the first physical coordinates of the moving object at this moment based on the measured physical coordinates of the moving object at this moment, the acceleration prediction error and the interval duration.

[0030] Exemplarily, the following formula may be used to determine the coordinate prediction error of the moving object at this moment: The acceleration prediction error can be determined using the following formula: The following formula can be used to determine the first physical coordinates of the moving object at this moment: Among them, x t and t represents the measured physical coordinates of the moving object at that moment, x t-1 and t-1 Represents the measured physical coordinates of the moving object at the previous moment, a x-1 and a y-1 represents the acceleration of the moving object at the previous moment, T represents the interval duration, and represents the coordinate prediction error, and represents the acceleration prediction error, and represents the first physical coordinate; e -(n-3) represents the error parameter, n represents the number of time intervals between this moment and the first moment, and the first moment is the moment when the moving object is first located in the traveling area during the driving process of the target vehicle.

[0031] Exemplarily, obtaining the second physical coordinates of the target vehicle at that moment may include, but is not limited to: determining the maximum braking deceleration of the target vehicle at that moment based on the corresponding acceleration of the target vehicle and the maximum braking deceleration of the target vehicle at the previous moment; determining the second physical coordinates of the target vehicle at that moment based on the physical coordinates of the target vehicle at the previous moment, the maximum braking deceleration of the target vehicle at that moment, the time length corresponding to that moment, and the angle corresponding to the target vehicle at that moment.

[0032] The following formula can be used to determine the maximum braking deceleration of the target vehicle at this moment: The second physical coordinate of the target vehicle at this moment is determined using the following formula: in, Indicates the maximum braking deceleration of the target vehicle at the previous moment, represents the maximum braking deceleration of the target vehicle at that moment, a ′ k represents the jerk; k represents the pre-configured jerk level, and a ′ k is the jerk corresponding to the jerk level; and represents the physical coordinates of the target vehicle at the previous moment, and represents the second physical coordinate, t represents the time length, θ v Indicates an angle.

[0033] Exemplarily, determining that there is a collision risk between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment may include but is not limited to: determining a first degree of overlap at the first moment based on the first expansion area at the first moment and the second expansion area at the first moment, and if the first degree of overlap is greater than a preset first threshold, determining that there is a collision risk between the target vehicle and the moving object; determining that the moving object is an obstacle to the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment includes: determining a second degree of overlap at the second moment based on the first expansion area at the second moment and the second expansion area at the second moment, and if the second degree of overlap is greater than a preset second threshold, determining that the moving object is an obstacle to the target vehicle; wherein the preset second threshold is greater than or equal to the preset first threshold.

[0034] Exemplarily, determining the first degree of overlap at the first moment based on the first expansion region at the first moment and the second expansion region at the first moment may include, but is not limited to: the first degree of overlap may be determined using the following formula: represents the lateral overlap size of the first expansion area and the second expansion area, and the lateral overlap size is determined by the following formula: It represents the longitudinal overlap size of the first expansion area and the second expansion area, and the longitudinal overlap size is determined by the following formula: IOU represents the first degree of overlap, w o represents half of the lateral dimension of the first expansion region, h o represents half of the longitudinal dimension of the first expansion region, w v represents half of the lateral dimension of the second expansion region, h v represents half of the longitudinal dimension of the second expansion region; and represents the center point coordinates of the first expansion area, which are the first physical coordinates. and It represents the center point coordinates of the second expansion area, and the center point coordinates are second physical coordinates.

[0035] Exemplary: if it is determined based on the first expansion area at the second moment and the second expansion area at the second moment that the moving object is not an obstacle to the target vehicle, the pre-braking of the target vehicle is released; wherein, releasing the pre-braking includes releasing the brake pre-filling and / or accelerating; the vehicle braking method is applied to a low-speed emergency braking scenario in automatic parking, or the vehicle braking method is applied to a high-speed emergency braking scenario in adaptive cruise control.

[0036] For example, when the moving object is located in the traveling area of ​​the target vehicle during its driving process, the moving object may be located in the front area of ​​the target vehicle during its driving process, or in the rear area of ​​the target vehicle during its driving process. For example, for the low-speed emergency braking scenario in automatic parking, the target vehicle may be driving in reverse at a low speed, so the moving object is located in the rear area of ​​the target vehicle during its driving process. For the high-speed emergency braking scenario in adaptive cruise control, the target vehicle may be driving forward at a high speed, so the moving object is located in the front area of ​​the target vehicle during its driving process. Of course, the above are just two examples of application scenarios, and the above vehicle braking method can be used in any driving process of the target vehicle.

[0037] It can be seen from the above technical solutions that in the embodiment of the present application, when there is a risk of collision between the target vehicle and the moving object (i.e. the moving object may interfere with the moving trajectory of the target vehicle, but has not yet affected the target vehicle), the target vehicle is pre-braked in advance, and the pre-braking is imperceptible to the driver (i.e. the driver will not perceive the pre-braking process). When the moving object is an obstacle to the target vehicle (i.e. the moving object is locked as an obstacle, and the moving object has already affected the target vehicle), since pre-braking has been performed in advance (such as the vehicle speed has been reduced), the target vehicle can be comfortably braked, that is, the deceleration of the target vehicle is not greater than the maximum braking deceleration, so that the vehicle speed can be slowly reduced (i.e. a comfortable brake stop) without causing emergency braking of the vehicle (i.e. emergency braking of the vehicle), thereby giving the driver a better driving experience.

[0038] The above technical solutions of the embodiments of the present application are described below in combination with specific application scenarios.

[0039] For moving objects such as pedestrians, motor vehicles and non-motor vehicles, the movement trajectory of the moving objects is difficult to predict, that is, the moving objects may suddenly cut into the travel area during the vehicle's driving process. Based on this, during the vehicle's automatic driving process, if the moving objects suddenly cut into the travel area during the vehicle's driving process, it will cause the vehicle to brake suddenly (i.e., cause the vehicle to brake suddenly), thus giving the driver a poor driving experience.

[0040] In view of the above findings, a vehicle braking method is proposed in the embodiment of the present application. By adopting a pre-braking strategy, when a moving object may interfere with the motion trajectory of the vehicle, the vehicle is pre-braked in advance. The pre-braking is not felt by the driver, but the vehicle speed will slowly decrease. On this basis, after locking the obstacle, since the vehicle speed has been reduced, the vehicle speed can be slowly reduced (i.e., a comfortable brake stop is performed), which will not cause emergency braking of the vehicle, thereby giving the driver a better driving experience.

[0041] In the embodiment of the present application, a vehicle braking method is proposed, which can be applied to a target vehicle, the target vehicle can include a vehicle-mounted terminal device, and the method can be applied to the vehicle-mounted terminal device of the target vehicle. The vehicle-mounted terminal device can support an intelligent driving system for realizing intelligent driving (autonomous driving) of the target vehicle.

[0042] For example, the target vehicle may be a vehicle equipped with an intelligent driving system (such as an ordinary vehicle equipped with an intelligent driving system or an automatic parking system, the intelligent driving system is used to assist the driver in completing the vehicle positioning). Alternatively, the target vehicle may also be a vehicle equipped with an autonomous unmanned driving system (i.e., a vehicle that does not require a driver to drive, the autonomous unmanned driving system completes the vehicle positioning alone), for example, a robot, a logistics vehicle, or an unmanned passenger vehicle, and there is no restriction on the type of the target vehicle.

[0043] See also Figure 2 As shown, it is a flow chart of the vehicle braking method, which may include processes such as moving object recall, pre-braking, moving object locking, comfort braking, and moving object release.

[0044] For the moving object, the moving object may be an object located in the traveling area (such as the front area or the rear area) of the target vehicle during the driving process, that is, during the driving process of the target vehicle, the target vehicle may collide with the moving object, and the moving object may interfere with the moving trajectory of the target vehicle. For example, the moving object may be a pedestrian, a motor vehicle, a non-motor vehicle, etc. There is no restriction on the type of the moving object, and it may be any moving object.

[0045] For the moving object recall process, it is necessary to detect whether there is a collision risk between the moving object and the target vehicle. If there is a collision risk between the moving object and the target vehicle, a pre-braking process can be executed. If there is no collision risk between the moving object and the target vehicle, a moving object release process can be executed.

[0046] For the moving object locking process, it is necessary to detect whether the moving object is an obstacle to the target vehicle. If the moving object is an obstacle to the target vehicle (lock the moving object as an obstacle), the comfort braking process can be executed. If the moving object is not an obstacle to the target vehicle, the moving object release process can be executed.

[0047] For the moving object release, the moving object may be released, a pre-braking process is not performed based on the moving object, and a comfort braking process is not performed based on the moving object, and the moving object recall process is repeated.

[0048] The following describes the moving object recall process, pre-braking process, moving object locking process, comfort braking process, moving object release process, etc. in the embodiments of the present application in combination with specific application scenarios.

[0049] First, for the moving object recall process, it is necessary to detect whether there is a collision risk between the moving object and the target vehicle, see Figure 3 FIG. 4 is a flow chart of a moving object recall process, which may include:

[0050] Step 301: for each moment, obtain the first physical coordinates (ie, the coordinates in the world coordinate system) of the moving object at that moment, and the moving object is located in the traveling area of ​​the target vehicle during its driving process.

[0051] For example, when the current moment is moment t1, the first physical coordinates of the moving object at moment t1 are obtained, and when the current moment is moment t2, the first physical coordinates of the moving object at moment t2 are obtained, and so on.

[0052] For example, based on the sensor data of the target vehicle (such as data collected by radar, data collected by camera, etc.), the first physical coordinates of the moving object in the world coordinate system are obtained, and there is no restriction on this process.

[0053] In one possible implementation, the perception detection error is taken into account, that is, when the first physical coordinates of the moving object in the world coordinate system are obtained based on the sensor data, the first physical coordinates may have deviations. Therefore, for each moment (the moment t is used as an example in the following explanation, that is, the current moment is the moment t), the following steps can also be used to obtain the first physical coordinates of the moving object at the moment t.

[0054] Step S11, determine the coordinate prediction error of the moving object at time t based on the measured physical coordinates of the moving object at time t, the measured physical coordinates of the moving object at the previous time t-1, the acceleration of the moving object at the previous time t-1, and the interval between time t and the previous time t-1.

[0055] For example, based on the sensor data of the target vehicle at time t (such as data collected by radar, data collected by camera, etc.), the physical coordinates of the moving object in the world coordinate system can be obtained, and the physical coordinates are called the measured physical coordinates of the moving object at time t, recorded as measured physical coordinates (x t ,y t ), x t Indicates the horizontal coordinate of the measured physical coordinate, y t The ordinate represents the measured physical coordinate. Based on the sensor data of the target vehicle at the previous time t-1, the physical coordinate of the moving object in the world coordinate system can be obtained. This physical coordinate is called the measured physical coordinate of the moving object at the previous time t-1, and is recorded as the measured physical coordinate (x t-1 ,y t-1 ), x t-1Indicates the horizontal coordinate of the measured physical coordinate, y t-1 The vertical coordinate representing the physical coordinate of the measurement.

[0056] At the previous moment t-1, the acceleration of the moving object can be obtained, that is, the acceleration of the moving object at the previous moment t-1, recorded as acceleration (a x-1 , a y-1 ). x-1 represents the lateral acceleration in the acceleration at the previous moment t-1, a y-1 Indicates the longitudinal acceleration in the acceleration at the previous time t-1.

[0057] When the current moment is moment t, the interval duration between moment t and the previous moment t-1, that is, the difference between moment t and the previous moment t-1, can be determined, and the interval duration is recorded as interval duration T.

[0058] In step S11, the measured physical coordinates (x t ,y t ), the measured physical coordinates of the moving object at the previous time t-1 (x t-1 ,y t-1 ), the acceleration of the moving object at the previous moment t-1 (a x-1 , a y-1 ) and the interval time T determine the coordinate prediction error of the moving object at time t, and the coordinate prediction error at time t is recorded as the coordinate prediction error The lateral coordinate prediction error represents the coordinate prediction error, The longitudinal coordinate prediction error represents the coordinate prediction error.

[0059] For example, although the motion trajectory of a moving object (such as a moving pedestrian, motor vehicle, and non-motor vehicle, etc.) is difficult to predict, the motion trajectory conforms to the following kinematic model: in a short period of time, the acceleration of the moving object will not change suddenly; in a short period of time, the angular acceleration of the moving object will not change suddenly. Based on this, when the motion trajectory conforms to the above kinematic model, the calculation formulas for the acceleration and angular acceleration of the moving object can be shown in formula (1).

[0060]

[0061] In formula (1), a x and a y represents the acceleration of the moving object at time t, a θ represents the angular acceleration of the moving object at time t, x t and t represents the physical coordinates of the moving object at time t, x t-1 andt-1 represents the physical coordinates of the moving object at time t-1, θ t represents the direction of the moving object at time t, θ t-1 represents the direction of the moving object at time t-1, and T represents the interval between time t and time t-1.

[0062] Based on the calculation formula of acceleration and angular acceleration, the physical coordinates at time t can be predicted based on the data at time t-1, which is called the predicted physical coordinates at time t. The physical coordinates at time t can be actually measured based on the sensor data of the target vehicle at time t, which is called the measured physical coordinates at time t. The difference between the measured physical coordinates at time t and the predicted physical coordinates at time t can be used as the coordinate prediction error at time t.

[0063] See formula (2), which is an example of calculating the coordinate prediction error at time t.

[0064]

[0065] In formula (2), and represents the coordinate prediction error at time t, represents the direction prediction error at time t, x t and t represents the measured physical coordinates at time t, θ t Indicates the measurement direction at time t.

[0066] and represents the predicted physical coordinates at time t, which are the physical coordinates at time t predicted based on the data at time t-1. represents the predicted direction at time t, which is the direction at time t predicted based on the data at time t-1. For example, x t-1 and t-1 represents the measured physical coordinates at time t-1, θ t-1 Indicates the measurement direction at time t-1. x-1 and a y-1 represents the acceleration at time t-1, a θ-1 represents the angular acceleration at time t-1, and T represents the interval between time t and time t-1.

[0067] From formula (2), it can be seen that the measured physical coordinates (x t ,y t ), the measured physical coordinates at time t-1 (x t-1 ,y t-1 ), the acceleration at time t-1 (a x-1 , a y-1) and the interval length T, determine the coordinate prediction error of the moving object at time t

[0068] Ideally, the coordinate prediction error is close to 0, but due to the perception detection error, it will lead to coordinate prediction error It is not close to 0, which depends on the relative position and angle between the moving object and the target vehicle. Based on the perception characteristics, the closer the distance between the moving object and the target vehicle, the more accurate the perception detection and the smaller the coordinate prediction error. The closer to 0.

[0069] Step S12: determine the acceleration prediction error of the moving object at time t based on the coordinate prediction error of the moving object at time t and the interval duration T (the interval duration between time t and the previous time t-1).

[0070] For example, based on the coordinate prediction error of the moving object at time t and the interval time T, the acceleration prediction error of the moving object at time t can be determined, and the acceleration prediction error is recorded as The lateral acceleration prediction error represents the acceleration prediction error, The longitudinal acceleration prediction error represents the acceleration prediction error. Referring to formula (3), this is an example of calculating the acceleration prediction error at time t.

[0071]

[0072] In formula (3), and represents the acceleration prediction error, represents the angular acceleration prediction error, represents the coordinate prediction error, represents the direction prediction error, and T represents the interval time. From formula (3), it can be seen that the coordinate prediction error at the known time t is The acceleration prediction error (i.e., the acceleration of the prediction error) and the angular acceleration prediction error (i.e., the angular acceleration of the prediction error) can be calculated.

[0073] Step S13: Determine the first physical coordinates of the moving object at time t based on the measured physical coordinates of the moving object at time t, the acceleration prediction error at time t, and the interval duration T.

[0074] For example, the measured physical coordinates (x t ,y t ), the acceleration prediction error of the moving object at time t and the interval time T, determine the first physical coordinate of the moving object at time t, and mark the first physical coordinate at time t as the first physical coordinate For example, A lateral physical coordinate of the first physical coordinate may be represented, The longitudinal physical coordinate of the first physical coordinate can be represented as: Referring to formula (4), it is an example of calculating the first physical coordinate at time t.

[0075]

[0076] In formula (4), and represents the first physical coordinate of the moving object at time t, represents the direction of the moving object at time t, x t and t represents the measured physical coordinates of the moving object at time t, θ t Represents the measured direction of the moving object at time t. and represents the acceleration prediction error, represents the angular acceleration prediction error, and T represents the interval time. In addition, e -(n-3) represents the error parameter, n represents the number of time intervals between time t and the first time, and the first time is the time when the moving object is first located in the traveling area during the driving process of the target vehicle. In formula (4), n can be greater than or equal to 3. Obviously, the larger the value of n, the smaller the error parameter, that is, The smaller the proportion of The closer to x t .

[0077] It can be seen from formula (4) that the measured physical coordinates and error data at time t are fused to obtain the first physical coordinates at time t. The first physical coordinates are fused physical coordinates. Compared with the measured physical coordinates, the first physical coordinates are more accurate and can reflect the real physical coordinates of the moving object. As the distance between the target vehicle and the moving object approaches, the acceleration prediction error ( and ) tends to 0, the angular acceleration prediction error As the target vehicle approaches the moving object, the physical coordinate gradually transitions from trusting the predicted result to trusting the actual detection result.

[0078] Exemplarily, when the moving object is located in the traveling area of ​​the target vehicle during its driving process for the first time, that is, the moving object is detected for the first time based on the sensor data of the target vehicle, the current moment is taken as the first moment corresponding to the moving object, recorded as moment t1. Then, each time the moving object is detected based on the sensor data of the target vehicle, the number of moment intervals is increased by 1, and the initial value of the number of moment intervals is 1. For example, when the moving object is detected for the second time based on the sensor data of the target vehicle, the current moment is recorded as moment t2, and the number of moment intervals between moment t2 and the first moment t1 is 1, that is, the value of n is 1. When the moving object is detected for the third time based on the sensor data of the target vehicle, the current moment is recorded as moment t3, and the number of moment intervals between moment t3 and the first moment t1 is 2, that is, the value of n is 2, and so on.

[0079] For each moment, when the moving object is detected based on the sensor data of the target vehicle, the number of time intervals between this moment and the first moment t1, that is, the value of n, can be known, so that the error parameter e can be calculated. -(n-3) , and then use formula (4) to determine the first physical coordinate of the moving object at time t.

[0080] Exemplarily, each time the moving object is detected based on the sensor data of the target vehicle, the number of time intervals can be increased by 1, or, if the distance between the moving object and the target vehicle becomes closer, the number of time intervals can be increased by 1, and if the distance between the moving object and the target vehicle becomes farther, the number of time intervals can be kept unchanged.

[0081] For example, a moving object is detected for the first time based on the sensor data of the target vehicle. The first moment is recorded as moment t1. The moment t1 corresponds to the distance d1, and the distance d1 represents the distance between the moving object and the target vehicle.

[0082] When the moving object is detected for the second time based on the sensor data of the target vehicle, if the distance between the moving object and the target vehicle is less than the distance d1, the current moment is recorded as the moment t2, and the number of time intervals is 1, and the moment t2 corresponds to the distance d2. If the distance between the moving object and the target vehicle is not less than the distance d1, the data of the current moment is not counted, that is, the current moment is not recorded as the moment t2, and the number of time intervals is kept as 0.

[0083] When the moving object is detected for the third time based on the sensor data of the target vehicle, if the time t2 and the distance d2 have been recorded, if the distance between the moving object and the target vehicle is less than the distance d2, the current time is recorded as time t3, and the number of time intervals is 2, and the time t3 corresponds to the distance d3. If the time t2 and the distance d2 are not recorded, if the distance between the moving object and the target vehicle is less than the distance d1, the current time is recorded as time t2, and the number of time intervals is 1, and the time t2 corresponds to the distance d2. By analogy, each time the moving object is detected based on the sensor data of the target vehicle, the number of time intervals is increased by 1 only when the distance between the moving object and the target vehicle becomes closer. In this way, the number of time intervals n represents the amount by which the moving object is close to the target vehicle.

[0084] For example, the distance between the moving object and the target vehicle can be calculated using the following formula: d t represents the distance, x t and t Represents the first physical coordinate of the moving object at time t.

[0085] Step S14: Determine the speed of the moving object at time t based on the first physical coordinate of the moving object at time t, the first physical coordinate of the moving object at the previous time t-1, and the interval time T. For example, see formula (5), which is an example of calculating the speed of the moving object at time t.

[0086]

[0087] In formula (5), v x and v y represents the speed of the moving object at time t, and represents the first physical coordinate of the moving object at time t, and represents the first physical coordinate of the moving object at the previous moment t-1, and T represents the interval between the moment t and the previous moment t-1.

[0088] At this point, the first physical coordinate (x o ,y o ), The velocity v of the moving object at time t o , v o = {v x ,v y}, the angle θ of the moving object at time t o ,

[0089] At this point, step 301 is completed, and the first physical coordinates of the moving object at each moment are obtained.

[0090] Step 302: For each moment, obtain the second physical coordinates of the target vehicle at that moment.

[0091] For example, when the current moment is time t1, the second physical coordinates of the target vehicle at time t1 are obtained, and when the current moment is time t2, the second physical coordinates of the target vehicle at time t2 are obtained, and so on.

[0092] In a possible implementation, for each moment (hereinafter, moment t is used as an example for explanation, that is, the current moment is moment t), the following steps may be used to obtain the second physical coordinates of the target vehicle at moment t.

[0093] Step S21, obtaining the jerk corresponding to the target vehicle.

[0094] For example, since different users have different perceptions of the rate of change of acceleration (i.e., jerk), in order to minimize the discomfort caused by collision braking to users, different jerk levels are supported. For example, jerk level 1, jerk level 2, and jerk level 3 are supported, and jerk a can be configured for jerk level 1. ′ k1 , configure jerk a for jerk level 2 ′ k2 , configure jerk a for jerk level 3 ′ k3 . Acceleration a ′ k1 , acceleration a ′ k2 and acceleration a ′ k3 It can be configured based on experience, and there is no limitation on the configuration method of this acceleration in this embodiment.

[0095] The user can pre-configure the jerk level on the target vehicle, such as jerk level 1, jerk level 2, or jerk level 3, and then query the above configuration to obtain the jerk corresponding to the pre-configured jerk level. For example, if the user pre-configures the jerk level 1 on the target vehicle, by querying the above configuration, the jerk corresponding to the jerk level 1 can be obtained. ′ k1 .

[0096] Step S22: Determine the maximum braking deceleration of the target vehicle at time t based on the jerk corresponding to the target vehicle and the maximum braking deceleration of the target vehicle at time t-1 before time t.

[0097] For example, the maximum braking deceleration of the target vehicle at time t can be determined using the following formula (6):

[0098]

[0099] In formula (6), represents the maximum braking deceleration of the target vehicle at time t, represents the maximum braking deceleration of the target vehicle at the previous moment t-1. For example, the maximum braking deceleration at the first moment is a fixed empirical value. In the subsequent process, the maximum braking deceleration is iteratively calculated using formula (6). ′ k represents the jerk corresponding to the target vehicle, and k represents the pre-configured jerk level.

[0100] From formula (6), we can see that when we get the acceleration a corresponding to the target vehicle, ′ k Afterwards, the maximum braking deceleration at different times can be obtained Obviously, by adopting the variable deceleration mode, that is, the maximum braking deceleration at different times It can not only shorten the braking distance to the maximum extent, but also ensure the braking comfort of different users and improve the user's driving experience.

[0101] In formula (6), the maximum braking deceleration at time t can be expressed as Differentiate into lateral maximum braking deceleration and maximum longitudinal braking deceleration Based on this, when calculating the maximum lateral braking deceleration hour, is the maximum lateral braking deceleration at time t-1, a ′ k It is the lateral jerk corresponding to the jerk level (i.e., the lateral jerk and longitudinal jerk need to be configured separately for each jerk level).

[0102] In addition, when calculating the maximum longitudinal braking deceleration hour, is the maximum longitudinal braking deceleration at time t-1, a ′ k is the longitudinal jerk corresponding to the jerk level.

[0103] Step S23, based on the physical coordinates of the target vehicle at the previous time t-1, the maximum braking deceleration of the target vehicle at time t, the time length corresponding to time t and the angle corresponding to the target vehicle at time t, determine the second physical coordinates of the target vehicle at time t (i.e., the coordinates in the world coordinate system).

[0104] For example, the second physical coordinate at time t can be determined using the following formula (7):

[0105]

[0106] In formula (7), and represents the second physical coordinate of the target vehicle at time t, represents the horizontal physical coordinate of the second physical coordinate, A longitudinal physical coordinate representing the second physical coordinate.

[0107] and represents the physical coordinates of the target vehicle at the previous time t-1, represents the horizontal physical coordinate, Represents the longitudinal physical coordinate. The physical coordinate at the first moment can be a fixed value (such as 0). In the subsequent process, the physical coordinate of the target vehicle at each moment is iteratively calculated using formula (7).

[0108] Indicates the maximum braking deceleration of the target vehicle at time t. When calculating the second physical coordinate at time t, the same maximum braking deceleration can be used See formula (7). Alternatively, when calculating the second physical coordinate at time t, the same maximum braking deceleration can also be used. For example, when calculating the lateral physical coordinate of the second physical coordinate When the maximum braking deceleration in formula (7) is Can be replaced by the maximum lateral braking deceleration Similarly, when calculating the longitudinal physical coordinate of the second physical coordinate When the maximum braking deceleration in formula (7) is Can be replaced by the maximum longitudinal braking deceleration

[0109] t represents the time length (the time length corresponding to the moment t), that is, the time length between the moment t and the first moment, and the first moment is the moment when the moving object is first located in the traveling area during the driving process of the target vehicle.

[0110] θ v Represents the angle (also called direction) of the target vehicle at time t.

[0111] At this point, step 302 is completed, and the second physical coordinates of the target vehicle at each moment are obtained.

[0112] Step 303: For each moment, determine a first expansion area (also called a target area) of the moving object at that moment based on the first physical coordinates of the moving object at that moment, and determine a second expansion area (also called a vehicle area) of the target vehicle at that moment based on the second physical coordinates of the target vehicle at that moment.

[0113] For example, a first expansion region is obtained by performing an expansion operation with the first physical coordinate as the center. The first expansion region may be a rectangular region, a circular region, or a region of other shapes, and there is no limitation on this. For example, the first expansion region is a rectangular region. Figure 4 , which is a schematic diagram of the first expansion area.

[0114] With the first physical coordinate (x o ,y o ) as the center, in the horizontal direction, the length of the expansion to the left is w o , expand to the right by a length w o , in the longitudinal direction, the upward expansion length h o , downward expansion length h o , and get the first expansion region. Obviously, w o represents half of the lateral dimension of the first expansion region, h o represents half of the longitudinal dimension of the first expansion region. In addition, the first expansion region can be denoted as (x o ,y o ,w o ,h o ).

[0115] Take time t as an example to illustrate. Assume that the first physical coordinate of the moving object at time t is Then the first expansion area of ​​the moving object at time t can be recorded as

[0116] About the expansion size w o ,h o , can be configured based on experience, or the actual detected size can be used. The same expansion size w can be configured for different types of moving objects (such as pedestrians, motor vehicles, non-motor vehicles, etc.) o ,h o , you can also configure different expansion sizes w for different types of moving objects o ,h o .

[0117] For example, the second expansion area is obtained by performing an expansion operation with the second physical coordinate as the center. The second expansion area can be a rectangular area, a circular area, or an area of ​​other shapes, which is not limited. The second expansion area is taken as an example as a rectangular area. v ,y v ) as the center, in the horizontal direction, the length of the expansion to the left is w v , expand to the right by a length w v , in the longitudinal direction, the upward expansion length h v , downward expansion length h v , and the second expansion region is obtained. Obviously, w v represents half of the lateral dimension of the second expansion region, h v The second expansion area can be denoted as (x v ,y v ,w v ,h v ). Take time t as an example to illustrate, assuming that the second physical coordinate of the target vehicle at time t is Then the second expansion area of ​​the target vehicle at time t can be recorded as

[0118] About the expansion size w v ,h v , can be configured based on experience, or the actual detected size can be used. For example, the expansion size w can be configured based on the actual size of the target vehicle. v ,h v .

[0119] Step 304: Determine whether there is a collision risk between the target vehicle and the moving object based on the first expansion area at the first moment (the first moment is the current moment) and the second expansion area at the first moment.

[0120] When the current moment is moment t2, the first moment is moment t2, and whether there is a collision risk between the target vehicle and the moving object is determined based on the first expansion area at moment t2 and the second expansion area at moment t2. When the current moment is moment t3, the first moment is moment t3, and whether there is a collision risk between the target vehicle and the moving object is determined based on the first expansion area at moment t3 and the second expansion area at moment t3. By analogy, for each moment, when the current moment is the moment, it is taken as the first moment, and whether there is a collision risk between the target vehicle and the moving object is determined based on the first expansion area at the first moment and the second expansion area at the first moment.

[0121] Exemplarily, a first degree of overlap at the first moment can be determined based on the first expansion area at the first moment and the second expansion area at the first moment, and if the first degree of overlap is greater than a preset first threshold (the preset first threshold can be configured based on experience), it is determined that there is a collision risk between the target vehicle and the moving object. If the first degree of overlap is not greater than the preset first threshold, it is determined that there is no collision risk between the target vehicle and the moving object.

[0122] For example, the first overlap degree may be IOU (Intersection over Union), and the first overlap degree may be determined by the following formula (8). Of course, formula (8) is only an example and is not limited thereto, as long as the first overlap degree can be determined based on the first dilated area and the second dilated area.

[0123]

[0124] In formula (8), The lateral overlap size between the first expansion region and the second expansion region can be expressed as: The longitudinal overlap size between the first expansion area and the second expansion area can be expressed as:

[0125] IOU can represent the first degree of overlap, w o It can represent half of the lateral dimension of the first expansion region, h o It can represent half of the longitudinal dimension of the first expansion area, w v It can represent half of the lateral dimension of the second expansion region, h v can represent half of the longitudinal dimension of the second expansion region, and may represent the center point coordinates of the first expansion region, and the center point coordinates may be first physical coordinates, and The center point coordinates of the second expansion area may be represented by , and the center point coordinates may be second physical coordinates.

[0126] For example, see Figure 5 , which is a schematic diagram of interference between the first expansion region and the second expansion region. When there is an overlapping area between the first expansion region and the second expansion region, a first overlapping degree between the first expansion region and the second expansion region can be calculated, that is, the first overlapping degree is determined based on the area of ​​the interference region.

[0127] After obtaining the first overlap degree, if the first overlap degree is greater than the preset first threshold value e (e is the judgment threshold), it means that there is interference between the target vehicle and the moving object, that is, it is determined that there is a collision risk between the target vehicle and the moving object. Therefore, the result of the moving object recall is that there is a collision risk, and pre-braking is prepared. In summary, if it is determined that there is a collision risk between the target vehicle and the moving object, the pre-braking process can be executed.

[0128] After obtaining the first degree of overlap, if the first degree of overlap is not greater than the preset first threshold value e, it means that there is no interference between the target vehicle and the moving object, that is, it is determined that there is no collision risk between the target vehicle and the moving object. Therefore, the result of the moving object recall is that there is no collision risk and the moving object can be released. Releasing the moving object means that the moving object is not used as the risk control target of the target vehicle, and there is no need to execute the pre-braking process and the comfort braking process. In summary, if it is determined that there is no collision risk between the target vehicle and the moving object, the moving object release process can be executed, and then the moving object recall process is returned. At the next time t+1, take the next time t+1 as the current time, and repeat. Figure 3 The process shown.

[0129] In a possible implementation, there may be multiple moving objects for the target vehicle, and the first overlap between the target vehicle and each moving object needs to be calculated. If any first overlap is greater than a preset first threshold, it is determined that there is a collision risk between the target vehicle and the moving object, and a pre-braking process needs to be performed. If all first overlaps are not greater than the preset first threshold, it is determined that there is no collision risk between the target vehicle and the moving object, and a moving object release process needs to be performed, and then the moving object recall process is returned.

[0130] Alternatively, the maximum first overlap degree may be selected from all first overlap degrees, and if the maximum first overlap degree is greater than a preset first threshold, it is determined that there is a collision risk between the target vehicle and the moving object, and a pre-braking process needs to be performed. If the maximum first overlap degree is not greater than the preset first threshold, it is determined that there is no collision risk between the target vehicle and the moving object, and a moving object release process needs to be performed, and then the moving object recall process is returned.

[0131] Second, for the pre-braking process, if it is determined that there is a risk of collision between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, then the pre-braking process needs to be performed. For example, the target vehicle can be pre-braked during the pre-braking time interval.

[0132] For example, the pre-braking time t can be pre-configured pp , pre-braking time t ppIt can be configured based on experience. If the current moment is the first moment, and it is known that there is a risk of collision between the target vehicle and the moving object, then the start moment of the pre-braking time interval is the first moment, the end moment of the pre-braking time interval is the second moment, and the interval between the second moment and the first moment is the pre-braking time length t pp , that is, the second moment is the first moment + t pp In this way, the pre-braking time t pp Within t, the pre-braking of the target vehicle is completed, that is, based on the first moment, the pre-braking time t is increased. pp , complete the pre-braking of the target vehicle.

[0133] Exemplarily, pre-braking may include but is not limited to brake pre-filling and / or deceleration. Of course, brake pre-filling and deceleration are just two examples of pre-braking, and there is no limitation on the implementation of pre-braking.

[0134] In a possible implementation, the target vehicle may be pre-filled with brakes during the pre-braking time interval, and the pre-filling with brakes may also be referred to as pressure building. Alternatively, the target vehicle may be decelerated during the pre-braking time interval, or the target vehicle may be pre-filled with brakes and decelerated during the pre-braking time interval.

[0135] Pre-filling the brakes of the target vehicle means: the purpose of pre-filling the brakes is to achieve a faster braking response. For the braking system, there is a gap between the friction pad and the brake disc to prevent the friction pad from wearing out prematurely. In emergency braking, the existence of this gap will affect the entire braking distance. Pre-filling the brakes will prepare for emergency situations by eliminating the gap between the friction pad and the brake disc in advance, but without applying braking force, so that the braking system can respond to the braking request more quickly, thereby saving the vehicle's braking response time.

[0136] Slowing down the target vehicle means that a reference speed can be pre-configured, and the reference speed can be relatively small, such as 60km / h, 50km / h, etc. During the pre-braking time interval, the speed of the target vehicle is reduced to the reference speed without feeling, thereby further alleviating the discomfort caused by subsequent braking.

[0137] Third, for the moving object locking process, it is necessary to detect whether the moving object is an obstacle of the target vehicle, that is, whether to lock the moving object as an obstacle. For example, after the pre-braking process is completed within the pre-braking time interval, the end time of the pre-braking time interval is the second time, and whether the moving object is an obstacle of the target vehicle is determined based on the first expansion area at the second time and the second expansion area at the second time.

[0138] For example, when the current moment is the second moment, the first expansion area of ​​the moving object at the second moment and the second expansion area of ​​the target vehicle at the second moment may be obtained, referring to steps 301 to 303, and then it is determined whether the moving object is an obstacle of the target vehicle based on the first expansion area and the second expansion area.

[0139] Exemplarily, the second degree of overlap at the second moment can be determined based on the first expansion area at the second moment and the second expansion area at the second moment, and if the second degree of overlap is greater than a preset second threshold (the preset second threshold can be configured based on experience), the moving object is determined to be an obstacle to the target vehicle. If the second degree of overlap is not greater than the preset second threshold, it is determined that the moving object is not an obstacle to the target vehicle.

[0140] For example, the second overlap degree may be an IOU, and the second overlap degree may be determined by using the above formula (8), by updating the first expansion region at the first moment to the first expansion region at the second moment, and by updating the second expansion region at the first moment to the second expansion region at the second moment, which will not be repeated here.

[0141] After obtaining the second overlap, if the second overlap is greater than the preset second threshold E (E is the obstacle interference threshold, and the preset second threshold E can be greater than the preset first threshold e, so that the second overlap is greater than the preset second threshold E only when the moving object is closer to the target vehicle, avoiding the mistaken locking of the moving object as an obstacle), it means that the target vehicle and the moving object will collide, that is, the moving object is determined to be an obstacle of the target vehicle. Therefore, the result of locking the moving object is that there is an obstacle, and comfort braking is prepared. In summary, if the moving object is determined to be an obstacle of the target vehicle, the comfort braking process is executed.

[0142] After obtaining the second degree of overlap, if the second degree of overlap is not greater than the preset second threshold value E, it means that the target vehicle and the moving object will not collide, that is, it is determined that the moving object is not an obstacle to the target vehicle. Therefore, the result of locking the moving object is that there is no obstacle and the moving object can be released. For example, releasing the moving object means not using the moving object as a wind control target for the target vehicle, and there is no need to perform a comfort braking process. In summary, if it is determined that the moving object is not an obstacle to the target vehicle, that is, the obstacle cannot be locked, the moving object release process can be executed, and then the moving object recall process is returned. At the next time t+1, the next time t+1 is used as the current time, and repeated. Figure 3 The process shown.

[0143] Since the target vehicle has been pre-braked, the pre-braking can also be released when executing the moving object release process, that is, the pre-braking of the target vehicle can be released. The release of the pre-braking may include but is not limited to the release of the brake pre-filling and / or the acceleration. For example, if the target vehicle is braked pre-filled in the pre-braking time interval, the brake pre-filling of the target vehicle is released, that is, the gap between the friction plate and the brake disc is restored, and there is no restriction on this process. Alternatively, if the target vehicle is decelerated in the pre-braking time interval, the target vehicle is accelerated, that is, the speed of the target vehicle is slowly increased. Alternatively, if the target vehicle is braked pre-filled and decelerated in the pre-braking time interval, the brake pre-filling and acceleration of the target vehicle are released.

[0144] Alternatively, when executing the moving object release process, the pre-brake can also be released. For example, the driver can take over the vehicle and release the pre-brake to avoid false triggering and affect the driver's driving experience.

[0145] In a possible implementation, there may be multiple moving objects for the target vehicle, and the second overlap between the target vehicle and each moving object needs to be calculated. If any second overlap is greater than a preset second threshold, the moving object is determined to be an obstacle to the target vehicle, and the comfort braking process needs to be performed. If all second overlaps are not greater than the preset second threshold, it is determined that the moving object is not an obstacle to the target vehicle, and the moving object release process needs to be performed, and then the moving object recall process is returned.

[0146] Alternatively, the maximum second overlap degree may be selected from all second overlap degrees. If the maximum second overlap degree is greater than a preset second threshold value, it is determined that the moving object is an obstacle to the target vehicle, and the comfort braking process needs to be performed. If the maximum second overlap degree is not greater than the preset second threshold value, it is determined that the moving object is not an obstacle to the target vehicle, and the moving object release process needs to be performed, and then the moving object recall process is returned.

[0147] Fourth, for the comfort braking process, if the moving object is determined to be an obstacle to the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, then the comfort braking process needs to be executed. For example, starting from the second moment, the target vehicle can be comfortably braked.

[0148] Exemplarily, when the target vehicle is comfortably braked, the deceleration of the target vehicle is not greater than the maximum braking deceleration. For example, the deceleration of the target vehicle is controlled based on the maximum braking deceleration so that the deceleration of the target vehicle is not greater than the maximum braking deceleration, thereby achieving comfortable braking.

[0149] The maximum braking deceleration of the target vehicle can also be adjusted dynamically. For example, the maximum braking deceleration of the target vehicle at the current moment can be determined based on the jerk corresponding to the target vehicle and the maximum braking deceleration of the target vehicle at the previous moment. For example, during the driving process of the target vehicle, the maximum braking deceleration can be dynamically adjusted using formula (6).

[0150] In a possible implementation, the vehicle braking method can be applied to a low-speed emergency braking scenario in automatic parking, or the vehicle braking method can be applied to a high-speed emergency braking scenario in adaptive cruise control. Of course, the above are just two examples, and the application scenarios of the vehicle braking method are not limited.

[0151] Application scenario 1: Low-speed emergency braking scenario in automatic parking.

[0152] In the automatic parking scenario, the target vehicle cruises at a low speed, that is, controls the target vehicle to travel at a low speed and parks the target vehicle in the parking space. During the low-speed driving of the target vehicle, if there is an obstacle (moving object) in the moving path of the target vehicle, the driver cannot intervene in time, resulting in a collision risk.

[0153] See also Fig. 6A The figure shows a schematic diagram of a low-speed emergency braking scenario in automatic parking. During the driving process of the target vehicle, if it is determined that there is a collision risk based on the first expansion area at the first moment and the second expansion area at the first moment, the target vehicle is pre-braked from the first moment and the pre-braking of the target vehicle is completed at the second moment, so as to take the brake pre-filling operation for the vehicle in advance to save the vehicle braking response time, or reduce the vehicle speed to a speed that can be comfortably stopped in advance. The position corresponding to the first moment is the pre-braking start position, and the position corresponding to the second moment is the pre-braking end position and the braking start position.

[0154] If it is determined based on the first expansion area at the second moment and the second expansion area at the second moment that an obstacle exists, that is, when the obstacle is locked, comfort braking is performed to stop the vehicle to avoid the risk of collision. Fig. 6A As shown, even when comfort braking is performed, the brake stop position is located in front of the target collision position.

[0155] Application scenario 2: High-speed emergency braking scenario in adaptive cruise control.

[0156] In the adaptive cruise control scenario, the target vehicle cruises at high speed, that is, controls the target vehicle to travel at high speed. During the high-speed driving of the target vehicle, the motion state of the vehicle in front changes all the time. When there is a vehicle cutting into the target vehicle's path, the driver cannot intervene in time, resulting in a collision risk.

[0157] See also Figure 6B The figure shows a schematic diagram of a high-speed emergency braking scenario in adaptive cruise control. During the driving process of the target vehicle, if a collision risk is determined based on the first expansion area at the first moment and the second expansion area at the first moment, the target vehicle is pre-braked from the first moment and the pre-braking of the target vehicle is completed at the second moment, so that the vehicle is pre-braked in advance to save the vehicle's braking response time, or the vehicle speed is reduced to a comfortable braking speed in advance. The position corresponding to the first moment is the pre-braking start position, and the position corresponding to the second moment is the pre-braking end position and the braking start position.

[0158] If it is determined based on the first expansion area at the second moment and the second expansion area at the second moment that there is an obstacle (i.e., the vehicle ahead is an obstacle), comfort braking is performed to stop the vehicle to avoid the risk of collision. Figure 6B As shown, even when comfort braking is performed, the brake stop position is located in front of the target collision position.

[0159] When the vehicle ahead accelerates and leaves, the collision risk is eliminated, and the lock on the vehicle ahead is released. When the vehicle ahead continues to slow down, the collision risk is confirmed, and the target vehicle is braked comfortably to avoid collision.

[0160] In a possible implementation manner, all data involved in this embodiment (such as all data on the target vehicle) are acquired and used only with the knowledge and authorization of the relevant users.

[0161] It can be seen from the above technical solutions that in the embodiment of the present application, when there is a risk of collision between the target vehicle and the moving object, the target vehicle is pre-braked in advance, and the pre-braking is imperceptible to the driver (that is, the driver will not perceive the pre-braking process), that is, when it is detected that the driving direction may collide with an obstacle, pre-braking is performed in advance to reduce the vehicle speed. When the moving object is an obstacle to the target vehicle (that is, the moving object is locked as an obstacle, and the moving object has already affected the target vehicle), since pre-braking has been performed in advance (such as the vehicle speed has been reduced), the target vehicle can be comfortably braked, that is, the deceleration of the target vehicle is not greater than the maximum braking deceleration, so that after locking the obstacle, a comfortable brake is performed to avoid sudden braking and accidental touch. In this way, the vehicle speed can be slowly reduced (that is, a comfortable brake is performed), and emergency braking of the vehicle will not be caused (that is, sudden braking of the vehicle), thereby giving the driver a better driving experience.

[0162] Based on the same application concept as the above method, a vehicle braking device is proposed in the embodiment of the present application and applied to the target vehicle, see Figure 7 FIG. 1 is a schematic diagram of the structure of the device, wherein the device comprises:

[0163] The processing module 71 is used to obtain, for each moment, a first physical coordinate of the moving object at that moment, and obtain a second physical coordinate of the target vehicle at that moment; wherein the moving object is located in a traveling area during the traveling of the target vehicle; determine a first expansion area of ​​the moving object based on the first physical coordinate, and determine a second expansion area of ​​the target vehicle based on the second physical coordinate;

[0164] a pre-braking module 72, configured to pre-brake the target vehicle in a pre-braking time interval if it is determined based on the first expansion area at the first moment and the second expansion area at the first moment that there is a risk of collision between the target vehicle and the moving object, wherein the pre-braking includes brake pre-filling and / or deceleration; the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment;

[0165] The comfort braking module 73 is used to perform comfort braking on the target vehicle if the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment; when performing comfort braking, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

[0166] Exemplarily, when the processing module 71 obtains the first physical coordinate of the moving object at the moment, it is specifically used to: determine the coordinate prediction error of the moving object at the moment based on the measured physical coordinate of the moving object at the moment, the measured physical coordinate of the moving object at the moment before the moment, the acceleration of the moving object at the moment before, and the interval between the moment and the moment before;

[0167] Determining an acceleration prediction error based on the coordinate prediction error and the interval duration;

[0168] Based on the measured physical coordinates of the moving object at the moment, the acceleration prediction error and the interval duration, the first physical coordinates of the moving object at the moment are determined.

[0169] Exemplarily, the processing module 71 uses the following formula to determine the coordinate prediction error of the moving object at this moment:

[0170] The processing module 71 uses the following formula to determine the acceleration prediction error:

[0171] The processing module 71 uses the following formula to determine the first physical coordinate of the moving object at this moment:

[0172]

[0173] Among them, xt and t represents the measured physical coordinates of the moving object at that moment, x t-1 and t-1 represents the measured physical coordinates of the moving object at the previous moment, a x-1 and a y-1 represents the acceleration of the moving object at the previous moment, T represents the duration of the interval, and represents the coordinate prediction error, and represents the acceleration prediction error, and represents the first physical coordinate;

[0174] Among them, e -(n-3) represents an error parameter, n represents the number of time intervals between this moment and the first moment, and the first moment is the moment when the moving object is first located in the traveling area during the driving process of the target vehicle.

[0175] Exemplarily, the processing module 71 acquires the second physical coordinate of the target vehicle at the moment, and is specifically used to: determine the maximum braking deceleration of the target vehicle at the moment based on the jerk corresponding to the target vehicle and the maximum braking deceleration of the target vehicle at the moment before the moment;

[0176] Based on the physical coordinates of the target vehicle at the previous moment, the maximum braking deceleration of the target vehicle at this moment, the time length corresponding to this moment and the angle corresponding to the target vehicle at this moment, the second physical coordinates of the target vehicle at this moment are determined.

[0177] Exemplarily, the processing module 71 uses the following formula to determine the maximum braking deceleration of the target vehicle at this moment: The processing module 71 uses the following formula to determine the second physical coordinates of the target vehicle at this moment: represents the maximum braking deceleration of the target vehicle at the previous moment, represents the maximum braking deceleration of the target vehicle at that moment, a ′ k represents the jerk; wherein k represents the pre-configured jerk level, and a ′ k is the jerk corresponding to the jerk level; and represents the physical coordinates of the target vehicle at the previous moment, and represents the second physical coordinate, t represents the time length, θ v represents the angle.

[0178] Exemplarily, when the pre-braking module 72 determines that there is a risk of collision between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, it is specifically used to: determine a first degree of overlap at the first moment based on the first expansion area at the first moment and the second expansion area at the first moment, if the first degree of overlap is greater than a preset first threshold, it is determined that there is a risk of collision between the target vehicle and the moving object; when the comfort braking module 73 determines that the moving object is an obstacle to the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, it is specifically used to: determine a second degree of overlap at the second moment based on the first expansion area at the second moment and the second expansion area at the second moment, if the second degree of overlap is greater than a preset second threshold, it is determined that the moving object is an obstacle to the target vehicle; wherein the preset second threshold is greater than or equal to the preset first threshold.

[0179] Exemplarily, the pre-braking module 72 determines the first overlap at the first moment based on the first expansion area at the first moment and the second expansion area at the first moment, specifically for:

[0180] The first overlap degree is determined by the following formula:

[0181] in, represents the lateral overlap size between the first expansion area and the second expansion area, and the lateral overlap size is determined by the following formula:

[0182] in, represents the longitudinal overlap size of the first expansion area and the second expansion area, and the longitudinal overlap size is determined by the following formula:

[0183] Wherein, IOU represents the first overlap, w o represents half of the lateral dimension of the first expansion region, h o represents half of the longitudinal dimension of the first expansion region, w v represents half of the lateral dimension of the second expansion region, h v represents half of the longitudinal dimension of said second expansion region; and represents the center point coordinates of the first expansion area, and the center point coordinates are the first physical coordinates, and represents the center point coordinates of the second expansion area, and the center point coordinates are the second physical coordinates.

[0184] Exemplarily, the pre-braking module 72 is further used to release pre-braking of the target vehicle if it is determined based on the first expansion area at the second moment and the second expansion area at the second moment that the moving object is not an obstacle to the target vehicle; the release of pre-braking includes releasing brake pre-filling and / or accelerating.

[0185] Exemplarily, the vehicle braking method is applied to a low-speed emergency braking scenario in automatic parking, or the vehicle braking method is applied to a high-speed emergency braking scenario in adaptive cruise control.

[0186] Based on the same application concept as the above method, a vehicle device is proposed in the embodiment of the present application, see Figure 8 As shown, the vehicle device includes: a processor 81 and a machine-readable storage medium 82, the machine-readable storage medium 82 stores machine-executable instructions that can be executed by the processor 81; the processor 81 is used to execute the machine-executable instructions to implement the vehicle braking method disclosed in the above example of this application.

[0187] Based on the same application concept as the above method, an embodiment of the present application also provides a machine-readable storage medium, on which a number of computer instructions are stored. When the computer instructions are executed by a processor, the vehicle braking method disclosed in the above example of the present application can be implemented.

[0188] The above-mentioned machine-readable storage medium may be any electronic, magnetic, optical or other physical storage device, which may contain or store information, such as executable instructions, data, etc. For example, the machine-readable storage medium may be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk (such as CD, DVD, etc.), or similar storage medium, or a combination thereof.

[0189] Based on the same application concept as the above method, an embodiment of the present application further provides a computer program product, which may include a computer program, wherein when the computer program is executed by a processor, the vehicle braking method disclosed in the above example of the present application is implemented.

[0190] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0191] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A vehicle braking method, characterized in that: Applied to a target vehicle, the method comprises: For each moment, a first physical coordinate of the moving object at the moment is obtained, and a second physical coordinate of the target vehicle at the moment is obtained; wherein the moving object is located in a traveling area during the traveling of the target vehicle; a first expansion area of ​​the moving object is determined based on the first physical coordinate, and a second expansion area of ​​the target vehicle is determined based on the second physical coordinate; If it is determined that there is a risk of collision between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment, pre-braking the target vehicle in a pre-braking time interval, wherein the pre-braking includes brake pre-filling and / or deceleration; wherein the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment; If the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment, comfort braking is performed on the target vehicle; when comfort braking is performed on the target vehicle, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

2. The method according to claim 1, characterized in that The obtaining of the first physical coordinates of the moving object at the moment includes: Determine a coordinate prediction error of the moving object at the moment based on the measured physical coordinates of the moving object at the moment, the measured physical coordinates of the moving object at the moment before the moment, the acceleration of the moving object at the moment before, and the interval between the moment and the moment before; Determining an acceleration prediction error based on the coordinate prediction error and the interval duration; Based on the measured physical coordinates of the moving object at the moment, the acceleration prediction error and the interval duration, the first physical coordinates of the moving object at the moment are determined.

3. The method according to claim 2, characterized in that The following formula is used to determine the coordinate prediction error of the moving object at this moment: The acceleration prediction error is determined using the following formula: The first physical coordinate of the moving object at this moment is determined using the following formula: Among them, x t and t represents the measured physical coordinates of the moving object at that moment, x t-1 and t-1 represents the measured physical coordinates of the moving object at the previous moment, a x-1 and a y-1 represents the acceleration of the moving object at the previous moment, T represents the duration of the interval, and represents the coordinate prediction error, and represents the acceleration prediction error, and represents the first physical coordinate; Among them, e -(n-3) represents an error parameter, n represents the number of time intervals between this moment and the first moment, and the first moment is the moment when the moving object is first located in the traveling area during the driving process of the target vehicle.

4. The method according to claim 1, characterized in that: The obtaining of the second physical coordinates of the target vehicle at the moment includes: Determine the maximum braking deceleration of the target vehicle at the moment based on the jerk corresponding to the target vehicle and the maximum braking deceleration of the target vehicle at the moment before the moment; Based on the physical coordinates of the target vehicle at the previous moment, the maximum braking deceleration of the target vehicle at this moment, the time length corresponding to this moment and the angle corresponding to the target vehicle at this moment, the second physical coordinates of the target vehicle at this moment are determined.

5. The method according to claim 4, characterized in that The maximum braking deceleration of the target vehicle at this moment is determined by the following formula: The second physical coordinate of the target vehicle at this moment is determined using the following formula: in, represents the maximum braking deceleration of the target vehicle at the previous moment, represents the maximum braking deceleration of the target vehicle at that moment, a ′ k represents the jerk; wherein k represents the pre-configured jerk level, and a ′ k is the jerk corresponding to the jerk level; and represents the physical coordinates of the target vehicle at the previous moment, and represents the second physical coordinate, t represents the time length, θ v represents the angle.

6. The method according to claim 1, characterized in that The determining that there is a collision risk between the target vehicle and the moving object based on the first expansion area at the first moment and the second expansion area at the first moment includes: determining a first overlap degree at the first moment based on the first expansion area at the first moment and the second expansion area at the first moment, and if the first overlap degree is greater than a preset first threshold, determining that there is a collision risk between the target vehicle and the moving object; The determining that the moving object is an obstacle to the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment includes: determining a second overlap degree at the second moment based on the first expansion area at the second moment and the second expansion area at the second moment, and determining that the moving object is an obstacle to the target vehicle if the second overlap degree is greater than a preset second threshold; Wherein, the preset second threshold is greater than or equal to the preset first threshold.

7. The method according to claim 6, characterized in that The determining the first degree of overlap at the first moment based on the first expansion region at the first moment and the second expansion region at the first moment includes: The first overlap degree is determined by the following formula: in, represents the lateral overlap size between the first expansion area and the second expansion area, and the lateral overlap size is determined by the following formula: in, represents the longitudinal overlap size of the first expansion area and the second expansion area, and the longitudinal overlap size is determined by the following formula: Wherein, IOU represents the first overlap, w o represents half of the lateral dimension of the first expansion region, h o represents half of the longitudinal dimension of the first expansion region, w v represents half of the lateral dimension of the second expansion region, h v represents half of the longitudinal dimension of said second expansion region; and represents the center point coordinates of the first expansion area, and the center point coordinates are the first physical coordinates, and represents the center point coordinates of the second expansion area, and the center point coordinates are the second physical coordinates.

8. The method according to any one of claims 1 to 7, characterized in that: The method further includes: if it is determined based on the first expansion area at the second moment and the second expansion area at the second moment that the moving object is not an obstacle to the target vehicle, releasing pre-braking of the target vehicle; wherein releasing pre-braking includes releasing brake pre-filling and / or accelerating; The vehicle braking method is applied to a low-speed emergency braking scenario in automatic parking, or the vehicle braking method is applied to a high-speed emergency braking scenario in adaptive cruise control.

9. A vehicle braking device, characterized in that: Applied to a target vehicle, the device comprises: A processing module, configured to obtain, for each moment, a first physical coordinate of the moving object at the moment, and a second physical coordinate of the target vehicle at the moment; wherein the moving object is located in a traveling area during the traveling of the target vehicle; determine a first expansion area of ​​the moving object based on the first physical coordinate, and determine a second expansion area of ​​the target vehicle based on the second physical coordinate; a pre-braking module, configured to pre-brake the target vehicle in a pre-braking time interval if it is determined based on a first expansion area at a first moment and a second expansion area at a first moment that there is a risk of collision between the target vehicle and the moving object, wherein the pre-braking includes brake pre-filling and / or deceleration; the start time of the pre-braking time interval is the first moment, and the end time of the pre-braking time interval is the second moment; A comfort braking module is used to perform comfort braking on the target vehicle if the moving object is determined to be an obstacle of the target vehicle based on the first expansion area at the second moment and the second expansion area at the second moment; when performing comfort braking, the deceleration of the target vehicle is not greater than the maximum braking deceleration.

10. A vehicle device, characterized in that: include: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; The processor is used to execute machine executable instructions to implement the method described in any one of claims 1-8.

Images