Automobile rear tail door control method and device, vehicle and storage medium

Abstract

The invention discloses an automobile rear tail door control method and device, an automobile and a storage medium. The method is applied to a vehicle which is provided with a visual sensor. The method comprises the following steps: in an unfolding process of a rear tail gate, acquiring at least one rear tail gate image shot by a visual sensor; based on the at least one rear tail gate image, obtaining feature point parameters of a rear tail gate; acquiring a preset calibration parameter; acquiring motion characteristic parameters of the target obstacle; and based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tail gate, the rear tail gate is controlled to be unfolded on the premise that the safe unfolding condition is met, and the safe unfolding condition means that the rear tail gate does not collide with the target obstacle. According to the technical scheme, the probability that the rear tail door collides with the target obstacle in the unfolding process can be reduced, real-time obstacle avoidance of the rear tail door in the unfolding process is achieved, and the unfolding safety of the rear tail door is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a control method, device, vehicle and storage medium for a rear tailgate of an automobile. Background Art

[0002] At present, more and more vehicles are equipped with hatchback tailgates. Such tailgates need to occupy a large space when unfolded and are prone to scratches when unfolded in a small space. Therefore, it is necessary to design corresponding obstacle avoidance solutions.

[0003] In the related art, the vehicle uses a rear tailgate camera or a reversing radar to identify obstacles that have a certain probability of colliding with the rear tailgate and predict the movement state of the obstacle. In addition, the rear tailgate is provided with a Hall system, which detects the unfolding angle of the rear tailgate and controls the rear tailgate to stop unfolding before it collides with the obstacle. The Hall system includes a Hall sensor and a magnet. The Hall sensor determines the unfolding angle of the rear tailgate by measuring the relevant parameters of the magnetic field generated by the magnet.

[0004] However, when there is metal in the tailgate area of ​​the vehicle, the measurement results of the Hall system will be disturbed, and the tailgate is prone to scratching against obstacles. Summary of the invention

[0005] The present application proposes a control method, device, vehicle and storage medium for a rear tailgate of an automobile.

[0006] In a first aspect, an embodiment of the present application provides a method for controlling a rear tailgate of a vehicle, which is applied to a vehicle, wherein the vehicle is provided with a visual sensor; the method comprises: acquiring at least one rear tailgate image taken by the visual sensor; acquiring feature point parameters of the rear tailgate based on the at least one rear tailgate image; acquiring preset calibration parameters, wherein the preset calibration parameters characterize the relationship between the feature point parameters of the rear tailgate and the deployment angle of the rear tailgate; acquiring motion feature parameters of a target obstacle, wherein the target obstacle is an obstacle within a specified range determined based on the deployment path of the rear tailgate; and controlling the rear tailgate to deploy under the premise of satisfying a safe deployment condition based on the motion feature parameters of the target obstacle, the preset calibration parameters and the feature point parameters of the rear tailgate. The safe deployment condition refers to the rear tailgate not colliding with the target obstacle.

[0007] In a second aspect, an embodiment of the present application provides a control device for a rear tailgate of a car, the device comprising: an image acquisition module, used to acquire at least one rear tailgate image taken by a visual sensor; a feature extraction module, used to acquire feature point parameters of the rear tailgate based on at least one rear tailgate image; a first acquisition module, used to acquire preset calibration parameters, the preset calibration parameters characterizing the relationship between the feature point parameters of the rear tailgate and the deployment angle of the rear tailgate; a second acquisition module, used to acquire motion feature parameters of a target obstacle, the target obstacle being an obstacle within a specified range determined based on the deployment path of the rear tailgate; a rear tailgate control module, used to control the rear tailgate to deploy under the premise of satisfying a safe deployment condition based on the motion feature parameters of the target obstacle, the preset calibration parameters and the feature point parameters of the rear tailgate, the safe deployment condition being that the rear tailgate does not collide with the target obstacle.

[0008] In a third aspect, an embodiment of the present application provides a vehicle, comprising: a visual sensor; one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the method of the first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that computer program instructions are stored in the computer-readable storage medium, and the computer program instructions can be called by a processor to execute the method of the first aspect.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when instructions in the computer program product are executed, is used to implement the method of the first aspect.

[0011] Compared with the prior art, the technical solution provided in the embodiment of the present application obtains the motion characteristic parameters of the target obstacle and the preset calibration parameters during the deployment of the rear tailgate by the vehicle, and captures the rear tailgate image in real time to obtain the feature point parameters of the rear tailgate. The rear tailgate is controlled to be deployed under the condition of meeting the safety deployment conditions through the preset calibration parameters, the feature point parameters of the rear tailgate and the motion characteristic parameters of the target obstacle. Compared with the technical solution provided by the related art, the situation in which the deployment angle measurement result of the rear tailgate is disturbed when there is metal in the rear tailgate area can be avoided, so that the probability of the rear tailgate colliding with the target obstacle during the deployment process is greatly reduced, and the real-time obstacle avoidance of the rear tailgate during the deployment process is achieved, thereby improving the deployment safety of the rear tailgate. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 It is a schematic diagram of the implementation environment provided by the embodiment of the present application.

[0014] Figure 2 This is a flow chart of a method for controlling a rear tailgate of a vehicle provided by an embodiment of the present application.

[0015] Figure 3 This is a flow chart of a method for controlling a rear tailgate of a vehicle provided in another embodiment of the present application.

[0016] Figure 4 yes Figure 3 A schematic diagram of a process for determining a target angle according to an embodiment.

[0017] Figure 5 It is a flowchart of a process for determining preset calibration parameters provided by an embodiment of the present application.

[0018] Figure 6 This is a block diagram of a control device for a car tailgate provided by an embodiment of the present application.

[0019] Figure 7 It is a structural block diagram of a vehicle provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0021] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0022] Please refer to Figure 1, which shows a schematic diagram of an implementation environment provided by an embodiment of the present application. The implementation environment includes a vehicle 100. The vehicle 100 includes a rear tailgate control system. The rear tailgate control system includes a rear tailgate controller, a rear tailgate actuator electrically connected to the rear tailgate controller, and a rear tailgate transmission-connected to the rear tailgate actuator. The rear tailgate actuator can be a motor. The rear tailgate is also called a trunk door, which is used to open or close the trunk, which is a space set at the rear of the vehicle for storing items.

[0023] In an embodiment of the present application, during the deployment of the rear tailgate, the rear tailgate controller obtains motion characteristic parameters of the target obstacle and preset calibration parameters, and captures the rear tailgate image in real time to obtain feature point parameters of the rear tailgate. Through the preset calibration parameters, the feature point parameters of the rear tailgate and the motion characteristic parameters of the target obstacle, the rear tailgate is controlled to be deployed when the safety deployment conditions are met, so that the probability of the rear tailgate colliding with the target obstacle during the deployment is greatly reduced, thereby achieving real-time obstacle avoidance of the rear tailgate during the deployment process and improving the deployment safety of the rear tailgate.

[0024] In this embodiment, the vehicle 100 is provided with a visual sensor, such as a camera. The visual sensor can capture images of the rear tailgate being unfolded to any angle, such as an image of the rear tailgate being completely closed, and an image of the rear tailgate being completely unfolded. The installation position of the visual sensor can be set based on experiments or experience, for example, the visual sensor can be installed at the shark fin position of the vehicle or at the top of the rear windshield.

[0025] In some embodiments, the visual sensor is rotatably mounted on the vehicle 100. Specifically, the visual sensor can rotate back and forth along the deployment direction of the rear tailgate to obtain a better viewing angle.

[0026] In this embodiment, when the vehicle 100 captures an image including the rear tailgate, it can determine the characteristic point parameters of the rear tailgate (such as the pixel coordinates of the characteristic point of the rear tailgate) based on the image, and determine the unfolding angle of the rear tailgate based on the preset calibration parameters and the characteristic point parameters of the rear tailgate. The characteristic point can be a characteristic point on the contour of the rear tailgate (such as the vertex of the frame of the rear tailgate) or a characteristic point on the handle of the rear tailgate. The preset calibration parameters are used to indicate the relationship between the characteristic point parameters of the rear tailgate and the unfolding angle of the rear tailgate.

[0027] In other embodiments, the vehicle 100 is further provided with an angle detection device, which can be used to measure the unfolding angle of the rear tailgate. The angle detection device can be a Hall system. Optionally, the Hall system includes a Hall sensor and a magnet, the magnet is installed near the frame of the rear tailgate away from the rotating shaft, and the Hall sensor is installed near the rotating shaft. When the rear tailgate is unfolded, the Hall sensor can detect the parameter information (such as direction, intensity, etc.) of the magnetic field generated by the magnet, and the above-mentioned parameter information of the magnetic field can be used to determine the unfolding angle of the rear tailgate. Optionally, the rear tailgate includes an electric strut connected to the rear tailgate actuator, and the rear tailgate actuator drives the electric strut to extend and retract, thereby realizing the unfolding and closing of the rear tailgate. At this time, the Hall sensor can detect the rotation speed of the rear tailgate actuator. The rotation speed of the rear tailgate actuator and the initial state of the rear tailgate can be used to determine the unfolding angle of the rear tailgate.

[0028] In some embodiments, the vehicle 100 is further provided with a radar component, which is used to detect the movement information and state information of the obstacle, such as the shape, current position, speed, etc. of the obstacle. The radar component includes a laser radar, an ultrasonic radar, a millimeter wave radar, etc.

[0029] Please refer to Figure 2 , which shows a flow chart of a method for controlling a rear tailgate of a vehicle provided by an embodiment of the present application. The method includes the following process.

[0030] S201, obtaining at least one rear tailgate image captured by a visual sensor.

[0031] When the rear tailgate has different deployment angles, the rear tailgate region is located at different positions in the images captured by the visual sensor, so the rear tailgate deployment angle can be estimated through the images captured by the visual sensor. In this embodiment, during the rear tailgate deployment process, the vehicle periodically captures rear tailgate images through the visual sensor to facilitate estimation of the rear tailgate deployment angle. The rear tailgate image capture period is set based on experiments or experience, for example, 1 second.

[0032] In some embodiments, when the vehicle is controlling the unfolding of the tailgate, it detects whether there is a target obstacle. If so, the process starts from S201; if not, the process ends.

[0033] The target obstacle is an obstacle within the specified range determined based on the deployment path of the rear tailgate. During the deployment process of the rear tailgate, the target obstacle has a certain probability of colliding with the rear tailgate. The distance between any position point within the specified range determined based on the deployment path of the rear tailgate and the deployment path of the rear tailgate is less than or equal to a first distance threshold, for example, the first distance threshold is 10 cm. The target obstacle is within the specified range determined based on the deployment path of the rear tailgate, which means that at least a portion of the target obstacle is within the above-mentioned specified range, and the target obstacle does not need to be completely within the above-mentioned specified range.

[0034] In some embodiments, the vehicle detects whether there is a target obstacle based on the rear tailgate image. Specifically, the vehicle identifies whether there is an obstacle in the rear tailgate image. When the obstacle is identified in the rear tailgate image, the spatial position information of the obstacle is determined based on the pixel coordinates of the obstacle feature points. If the spatial position information of the obstacle is within the above-specified range, the obstacle is the target obstacle. If the spatial position information of the obstacle is not within the above-specified range, the obstacle is not the target obstacle. In other embodiments, the vehicle can detect whether there is a target obstacle through a radar component (laser radar, ultrasonic radar, millimeter wave radar, etc.).

[0035] If there is no obstacle within the specified range determined based on the rear tailgate deployment path, the rear tailgate can be directly deployed to the maximum angle without monitoring the deployment angle, thereby saving processing resources of the rear tailgate controller in the vehicle. In addition, during the deployment of the rear tailgate, the target obstacle detection step is also performed periodically, thereby avoiding the collision between the dynamic obstacle and the rear tailgate when the rear tailgate is deployed, and improving the safety of the rear tailgate deployment.

[0036] In some embodiments, after receiving the rear tailgate opening request, the vehicle executes S201. The rear tailgate opening request is used to request to open the rear tailgate. The user can trigger the rear tailgate opening request by triggering the rear tailgate control control in the smart key of the vehicle, or by triggering the rear tailgate control control in the center control panel of the vehicle.

[0037] Furthermore, after the vehicle obtains the tailgate opening request, it detects whether the vehicle is in the driving state. If so, it does not respond to the tailgate opening request to avoid the potential safety hazard caused by opening the tailgate while the vehicle is driving. If not, execution starts from S201. In addition, when the vehicle determines that the vehicle is not in the driving state, it can also detect whether the body electrical system in the vehicle is in a dormant state. If it is not in a dormant state, it is necessary to wake up the body electrical system first, and then execute S201. It should be noted that in the embodiment of the present application, the vehicle only wakes up the designated functional modules involved in the embodiment of the present application. The above-mentioned designated functional modules include visual sensors, tailgate controllers, etc. In this way, on the one hand, the wake-up time can be reduced, and on the other hand, the energy consumption of the vehicle can be saved.

[0038] In some other embodiments, the vehicle executes S201 when the tailgate is being deployed.

[0039] S202: Determine feature point parameters of the tailgate based on at least one tailgate image.

[0040] The feature point parameters of the rear tailgate are used to describe the position of the feature point of the rear tailgate in the rear tailgate image. When the installation position of the visual sensor on the vehicle is fixed, the feature point parameters of the rear tailgate can be used to estimate the deployment angle of the rear tailgate. Optionally, the feature point parameters of the rear tailgate are pixel coordinates of the feature point of the rear tailgate. The feature point of the rear tailgate can be a feature point on the contour of the rear tailgate (such as the vertex of the rear tailgate frame), or a feature point on the handle of the rear tailgate, which is not limited in the embodiment of the present application.

[0041] The algorithms used by the vehicle to extract feature points from the tailgate image include but are not limited to: Scale-invariant features transform (SIFT) algorithm, Speeded Up Robust Features (SURF) algorithm, Histogram of Oriented Gradient (HOG) algorithm, Difference of Gaussian (DOG) algorithm, etc., and the embodiments of the present application do not limit this.

[0042] S203, obtaining preset calibration parameters.

[0043] The preset calibration parameters are used to describe the relationship between the characteristic point parameters of the rear tailgate and the unfolding angle of the rear tailgate. The vehicle directly reads the above preset calibration parameters from the local. The determination process of the preset calibration parameters will be described in the following embodiment.

[0044] In some embodiments, the preset calibration parameters are coefficients of a target relationship, which is a mathematical formula describing the relationship between the characteristic point parameters of the rear tailgate and the deployment angle of the rear tailgate. The following calculation formula exemplifies a target relationship.

[0045] θ hall =f(u,v)=a0+a1u+a2v+a3u 2 +a4uv+a5v 2 +…….

[0046] Among them, θ hall is the unfolding angle of the rear tailgate, (u, v) is the pixel coordinates of the feature point of the rear tailgate, and a0, a1, a2, a3, a4, and a5 are preset calibration parameters.

[0047] In some other embodiments, the preset calibration parameters are the mapping relationship between the characteristic point parameters of the rear tailgate and the unfolding angle of the rear tailgate, as shown in Table 1 below, which exemplarily shows a mapping point relationship.

[0048]

[0049] Table-1

[0050] S204: Acquire motion characteristic parameters of the target obstacle.

[0051] The motion characteristic parameters of the target obstacle include the spatial position information, speed, etc. of the target obstacle. The process of acquiring the motion characteristic parameters of the target obstacle will be described in the following embodiments.

[0052] S205 , based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tailgate, controlling the rear tailgate to be deployed under the premise that a safe deployment condition is met.

[0053] The safe deployment condition means that the rear tailgate does not collide with the target obstacle. Optionally, the vehicle determines the maximum deployment angle at which the rear tailgate does not collide with the target obstacle based on the motion characteristic parameters of the target obstacle, and monitors the deployment angle of the tailgate based on the preset calibration parameters and the characteristic point parameters of the rear tailgate, so that the rear tailgate can be deployed under the premise of meeting the safe deployment condition. In this way, the rear tailgate can avoid obstacles in real time during the deployment process, thereby improving the deployment safety of the rear tailgate.

[0054] In summary, the technical solution provided in the embodiment of the present application obtains the motion characteristic parameters of the target obstacle and the preset calibration parameters during the deployment of the rear tailgate by the vehicle, and captures the rear tailgate image in real time to obtain the feature point parameters of the rear tailgate. The rear tailgate is controlled to be deployed under the condition of meeting the safety deployment conditions through the preset calibration parameters, the feature point parameters of the rear tailgate and the motion characteristic parameters of the target obstacle. Compared with the technical solution provided by the related art, the situation in which the deployment angle measurement result of the rear tailgate is disturbed when there is metal in the rear tailgate area can be avoided, so that the probability of the rear tailgate colliding with the target obstacle during the deployment process is greatly reduced, the real-time obstacle avoidance of the rear tailgate during the deployment process is achieved, and the deployment safety of the rear tailgate is improved.

[0055] Please refer to Figure 3 , which shows a flow chart of a method for controlling a rear tailgate of a vehicle according to another embodiment of the present application. The method includes the following process. In this embodiment, S205 can be replaced by S305-S308.

[0056] S301, obtaining at least one rear tailgate image taken by a visual sensor.

[0057] S302: Acquire feature point parameters of the rear tailgate based on at least one rear tailgate image.

[0058] S303, obtaining preset calibration parameters.

[0059] The preset calibration parameters represent the mapping relationship between the characteristic point parameters of the tailgate and the deployment angle.

[0060] S304: Obtain motion characteristic parameters of the target obstacle.

[0061] The target obstacle is an obstacle within a specified range determined based on the deployment path of the rear tailgate.

[0062] In some embodiments, the vehicle takes multiple obstacle images of the target obstacle through a visual sensor, and then performs image recognition on each obstacle image to determine the characteristic point parameters of the target obstacle in each obstacle image. The characteristic point parameters of the target obstacle can be the pixel coordinates of the center point of the target obstacle, or the pixel coordinates of the characteristic point in the target obstacle that is closest to the deployment path of the rear tailgate. In this way, the vehicle determines the characteristic point parameters of the target obstacle at different times based on multiple obstacle images, and realizes pixel-level tracking of the target obstacle. Exemplarily, the characteristic point parameters of the target obstacle at time t are (u, v).

[0063] In other possible embodiments, the vehicle obtains the motion characteristic parameters of the target obstacle through a radar component. The radar component may be a laser radar, an ultrasonic radar, a millimeter wave radar, and the like.

[0064] S305: Determine a target angle based on the motion characteristic parameters of the target obstacle.

[0065] The target angle refers to the maximum deployment angle of the tailgate when the tailgate does not collide with the target obstacle.

[0066] In some embodiments, the vehicle predicts the movement trajectory of the target obstacle based on the motion characteristic parameters of the target obstacle; determines the target position based on the movement trajectory of the target obstacle and the deployment speed of the tailgate; and determines the target angle based on the target position.

[0067] Optionally, the vehicle performs fitting based on the first coordinate in the characteristic point parameters of the target obstacle to obtain the following first relationship: t =a u t 2 +b u t+c u The above first relational expression is used to describe the relationship between the first coordinate and time in the characteristic point parameters of the target obstacle. u , b u 、c u are the coefficients to be solved.

[0068] Optionally, the vehicle performs fitting based on the second coordinate in the characteristic point parameters of the target obstacle to obtain the following second relationship: t =a v t 2 +b v t+c v The second relational expression is used to describe the relationship between the first coordinate and time in the characteristic point parameters of the target obstacle. v , b v 、c v are the coefficients to be solved.

[0069] The vehicle can obtain four obstacle images, and then perform image recognition respectively to obtain the feature point parameters of the target obstacle in the four images. Based on the above first relationship and the first coordinate of the feature point parameters of the target obstacle in the four images, the following calculation formula can be obtained:

[0070]

[0071] Based on the above calculation formula, we can solve a u , b u 、c u .

[0072] Based on the above second relational expression and the second coordinate of the feature point parameters of the target obstacle in the four images, the following calculation formula can be obtained:

[0073]

[0074] Based on the above calculation formula, we can solve a v , b v 、c v .

[0075] Thus, the first relation u t =a u t 2 +b u t+c u And the second relation v t =a v t 2 +b v t+c v The motion trajectory of the target obstacle is formed, based on which the characteristic point parameters of the target obstacle after time t can be estimated. For example, taking time t+n as an example, the first coordinate in the characteristic point parameters of the target obstacle is represented by u t+n =a u (t+n) 2 +b u (t+n)+c u ; The second coordinate in the characteristic point parameter of the target obstacle is expressed as v t+n =a v (t+n) 2 +b v (t+n)+c v .

[0076] Afterwards, the vehicle transforms the predicted feature point parameters of the target obstacle into the real coordinate system. The visual sensor is a monocular camera, and the imaging relationship of the monocular camera can be expressed as the following first calculation formula: s*[u,v,1] ^ T=K*[R|t]*[x,y,z,1] ^ T.

[0077] Among them, K is the intrinsic parameter matrix of the monocular camera, R is the rotation matrix, T is the translation vector, s represents the scale factor, (u, v) is the pixel coordinate of the feature point, and (x, y, z) is the spatial position coordinate corresponding to the feature point.

[0078] According to the homography constraint and the imaging relationship of the monocular camera, the following second calculation formula can be determined: [x / z, y / z, 1] ^ T = H*[u,v,1]^T, where H = K*[R|t] is the homography matrix.

[0079] Substituting the pixel coordinates (u, v) of the tailgate feature point and its first-order derivatives (u', v'), (u", v") into the above relationship, the corresponding spatial position information, as well as the speed and acceleration of the target obstacle at the spatial position coordinates can be determined.

[0080] The target position refers to the predicted position where the target obstacle collides with the rear tailgate. After predicting the spatial position information of the target obstacle at each moment, the vehicle determines the spatial position information of the rear tailgate at each moment based on the initial state and deployment speed of the rear tailgate, and then calculates the distance information between the target obstacle and the rear tailgate at each moment. If the distance information is less than the second distance threshold, it is considered that the target obstacle collides with the rear tailgate at that moment, and the spatial position information of the target obstacle at that moment is also the target position. The second distance threshold is set based on experiments or experience, for example, the second distance threshold is 1 cm. The second distance threshold is less than the first distance threshold.

[0081] Finally, the vehicle determines the angle between the first straight line and the second straight line as the target angle, wherein the first straight line is a straight line passing through the target position and a vertical point of the target position on the rotating axis of the rear tailgate, and the second straight line is a straight line passing through the visual sensor and the above vertical point.

[0082] Combined with reference Figure 4 , the vehicle predicts that the collision position of the obstacle 420 and the vehicle is point B, the vertical point of the target position on the rotation axis of the tailgate 430 is point A, the first straight line is AB, the second straight line is the extension line AE between the visual sensor 410 and point A, and the target angle is ∠BAE.

[0083] In some embodiments, when the target angle is less than a predetermined angle threshold, the vehicle sends a first reminder message. The first reminder message is used to remind the user that the deployable angle of the tailgate is too small, which is not conducive to the user to store and retrieve items from the trunk. The owner can drive the vehicle away from the current position according to the first reminder message to facilitate the deployment of the tailgate.

[0084] The predetermined angle threshold is set based on experiments or experience, for example, the predetermined angle threshold is 20°. The first reminder information may be a voice message broadcast by the vehicle, or may be sent by the vehicle to a related mobile device, and the related mobile device may be used to remind the user. The above-mentioned related mobile device may be a mobile device that establishes a wireless communication connection with the vehicle, and the above-mentioned wireless communication connection may be a Bluetooth connection. The related mobile device may be a smart phone, a Bluetooth headset, and the like.

[0085] S306: Determine the deployment angle of the rear tailgate based on the preset calibration parameters and the characteristic point parameters of the rear tailgate.

[0086] In some embodiments, the preset calibration parameters are coefficients of a target relational expression, and the target relational expression is used to describe the relationship between the unfolding angle of the rear tailgate and the characteristic point parameters of the rear tailgate. At this time, S306 is specifically implemented as follows: determining the target relational expression based on the preset calibration parameters; and determining the unfolding angle of the rear tailgate based on the target relational expression and the characteristic point parameters of the rear tailgate.

[0087] The vehicle substitutes the characteristic point parameters of the rear tailgate into the above target relationship to obtain the rear tailgate expansion angle. There are usually multiple rear tailgate characteristic points, and accordingly, there are also multiple rear tailgate expansion angles determined by the vehicle. At this time, the vehicle performs mean filtering or median filtering on the multiple rear tailgate expansion angles determined to obtain the final rear tailgate expansion angle. Please refer to Figure 4 , ∠CAE is the deployment angle of the rear tailgate 430.

[0088] S307 , when the difference between the deployment angle of the rear tailgate and the target angle is less than or equal to a predetermined difference, controlling the rear tailgate to stop deploying.

[0089] The unfolding angle of the rear tailgate is smaller than the target angle. The predetermined difference is set based on experiments or experience, for example, the predetermined difference is 2°.

[0090] In some embodiments, the vehicle also sends a second reminder message when the difference between the deployment angle of the rear tailgate and the target angle is less than or equal to a predetermined difference, and the second reminder message is used to remind the rear tailgate to stop deploying. The implementation form of the second reminder message can refer to the implementation form of the first reminder message, and will not be repeated here.

[0091] S308, when the difference between the deployment angle of the rear tailgate and the target angle is greater than a predetermined difference, controlling the rear tailgate to continue to be deployed until the difference between the deployment angle of the rear tailgate and the target angle is less than or equal to the predetermined difference.

[0092] When the difference between the unfolding angle of the rear tailgate and the target angle is greater than the predetermined difference, the vehicle controls the rear tailgate to continue to unfold, and repeatedly executes S301-S303 and S305 to achieve real-time monitoring of the unfolding angle of the rear tailgate.

[0093] In summary, according to the technical solution provided by the embodiment of the present application, the vehicle obtains the motion characteristic parameters of the target obstacle to determine the maximum deployment angle of the rear tailgate without colliding with the target obstacle, and captures the rear tailgate image in real time to obtain the characteristic point parameters of the rear tailgate, and monitors the deployment angle of the rear tailgate in real time through the predetermined preset calibration parameters and the characteristic point parameters of the rear tailgate, and when the difference between the deployment angle of the rear tailgate and the above-mentioned maximum deployment angle is less than or equal to the predetermined difference, the rear tailgate is controlled to stop deploying in time, so that the probability of the rear tailgate colliding with the target obstacle during the deployment process is greatly reduced, thereby realizing real-time obstacle avoidance of the rear tailgate during the deployment process and improving the deployment safety of the rear tailgate.

[0094] Please refer to Figure 5 , which shows a flow chart of a process for obtaining preset calibration parameters provided by an embodiment of the present application. The process includes the following steps.

[0095] S501, controlling the rear tailgate to unfold to a plurality of specified angles.

[0096] The vehicle controls the rear tailgate to gradually unfold at a predetermined step length until the rear tailgate unfolds to the maximum angle. The predetermined step length can be set based on experiments or experience, such as 1 degree. The number of designated angles is the ratio of the maximum angle to the predetermined step length. For example, if the maximum unfolding angle of the rear tailgate is 113 degrees and the predetermined step length is 1 degree, the number of designated angles is 113.

[0097] S502, after the tailgate is unfolded to each specified angle, a calibration image is captured by a visual sensor.

[0098] After the rear tailgate is unfolded to each specified angle, it pauses for a preset time, during which the visual sensor captures the calibration image. The preset time is set based on experiments or experience, and the embodiment of the present application does not limit this.

[0099] S503, extracting feature point parameters of the tailgate from the calibration image.

[0100] The feature point parameters of the rear tailgate may be the pixel coordinates of the feature point of the rear tailgate. The feature point of the rear tailgate may be a feature point on the contour of the rear tailgate (such as a vertex on the rear tailgate frame), or a feature point on the rear door handle, which is not limited in the present embodiment of the application. The extraction process of the feature point parameters of the rear tailgate may refer to step S203, which will not be described in detail here.

[0101] For example, based on the i-th frame image, the vehicle can extract the pixel coordinates of K rear tailgate feature points. The pixel coordinates of one rear tailgate feature point can be expressed as (u ik , v ik ), where k ranges from 0 to K-1.

[0102] S504, performing fitting based on each designated angle and the characteristic point parameters corresponding to the designated angle to obtain a target relationship equation.

[0103] The feature point parameters corresponding to the specified angle refer to the feature point parameters extracted from the calibration image corresponding to the specified angle.

[0104] The vehicle performs polynomial fitting on the specified angle and the characteristic point parameters corresponding to each specified angle. The polynomial fitting method includes but is not limited to: least square method, Lagrange interpolation method, Newton interpolation method, gradient descent method. In the embodiment of the present application, only the least square method is used as an example for explanation.

[0105] The polynomial to be fitted is expressed as: θ hall =f(u,v)=a0+a1u+a2v+a3u 2 +a4uv+a5v 2 +…….

[0106] The goal of polynomial fitting by least squares method can be expressed as follows: minsum((f(u ik , v ik )-θ hall_i ) 2 ). Wherein, i ranges from 1 to N, and N is the total number of calibration images. That is, the goal of polynomial fitting by least squares method is to solve a set of coefficients a0, a1, a2, a3, a4, a5 so that the sum of the squares of the differences between the predicted values ​​of the polynomial under all feature point parameters and the specified angle is minimized. The above polynomial fitting method can reduce the storage pressure of the vehicle.

[0107] S505, determining the coefficients of the target relationship as preset calibration parameters.

[0108] Exemplarily, the vehicle determines (a0, a1, a2, a3, a4, a5) as preset calibration parameters and saves them locally.

[0109] In this embodiment, a mapping relationship between the feature point parameters of the rear tailgate and the unfolding angle of the rear tailgate can be established through the above steps S501-S505. The vehicle subsequently extracts the feature point parameters of the rear tailgate from the image taken by the visual sensor to determine the unfolding angle of the rear tailgate, thereby realizing angle measurement based on the visual sensor.

[0110] To summarize, the technical solution provided in the embodiment of the present application obtains calibration images of the visual sensor at multiple specified angles and extracts corresponding feature point parameters, determines preset calibration parameters based on the specified angles and the corresponding feature point parameters, and subsequently the vehicle extracts feature point parameters from the images taken by the visual sensor, determines the expansion angle of the tailgate based on the extracted feature point parameters and the preset calibration parameters, thereby realizing real-time monitoring of the expansion angle of the tailgate.

[0111] In some embodiments, when the visual sensor is rotatably mounted on the vehicle, the preset calibration parameters are calibrated when the mounting angle of the visual sensor is a reference angle, and the reference angle may be a maximum angle or a minimum angle at which the visual sensor rotates in the deployment direction of the rear tailgate. When the reference angle is the maximum angle at which the visual sensor rotates in the deployment direction of the rear tailgate, the visual sensor cannot continue to rotate in the deployment direction of the rear tailgate; when the reference angle is the minimum angle at which the visual sensor rotates in the deployment direction of the rear tailgate, the visual sensor cannot continue to rotate in the opposite direction of the deployment direction of the rear tailgate.

[0112] In this embodiment, the vehicle can obtain the difference between the current installation angle of the visual sensor and the reference angle, and determine the angle compensation value based on the above difference and the preset mapping relationship. After obtaining the expansion angle of the rear tailgate through S306, the sum of the expansion angle of the rear tailgate and the angle compensation value is used as the actual expansion angle of the rear tailgate, and the rear tailgate is controlled to continue to expand or stop expanding based on the difference between the actual expansion angle of the rear tailgate and the target angle. The preset mapping relationship is a mapping relationship between different differences between the current installation angle of the visual sensor and the reference angle and different angle compensation values. The process of obtaining the preset mapping relationship may include: for each installation angle of the visual sensor, respectively obtaining multiple frames of images

[0113] In this way, when the visual sensor is rotatably mounted on the vehicle, the vehicle can avoid repeating the calibration process multiple times, saving processing resources of the vehicle controller.

[0114] In some embodiments, when a vehicle is equipped with a Hall system, the vehicle first detects whether the Hall system is in a failed state when the tailgate is being deployed. If the Hall system is in a failed state, the process starts with the step of acquiring at least one image of the tailgate taken by a visual sensor. If the Hall system is not in a failed state, the tailgate is controlled to be deployed when the safety deployment conditions are met based on the output result of the Hall system and the motion characteristic parameters of the target obstacle.

[0115] Optionally, the vehicle can obtain the number of electrical signals output by the Hall system per unit time. If the number of electrical signals is less than the first number or greater than the second number, it means that the Hall system is in a failed state. If the number of electrical signals is greater than or equal to the first number and less than or equal to the second number, it means that the Hall system is not in a failed state. The first number is less than the second number. The values ​​of the first number and the second number are set based on experiments or experience, and the embodiments of the present application do not limit this.

[0116] Optionally, the vehicle can also obtain the period of the electrical signal output by the Hall signal, and determine the electrical signal with a period less than the first period or greater than the second period as an abnormal electrical signal. If the number of abnormal electrical signals is greater than a preset number, it means that the Hall system is in a failed state. If the number of abnormal electrical signals is less than or equal to the preset number, it means that the Hall system is not in a failed state. The first period is less than the second period. The values ​​of the first period, the second period, and the preset number are set according to actual experience, and the embodiments of the present application do not limit this.

[0117] In addition, based on the output result of the Hall system and the motion characteristic parameters of the target obstacle, controlling the rear tailgate to unfold when the safety unfolding conditions are met is specifically implemented as follows: determining the unfolding angle of the rear tailgate based on the output result of the Hall system, determining the target angle based on the motion characteristic parameters of the target obstacle, and when the difference between the unfolding angle of the rear tailgate and the target angle is less than or equal to a predetermined difference, controlling the rear tailgate to stop unfolding, wherein the target angle is greater than the unfolding angle of the rear tailgate; when the difference between the unfolding angle of the rear tailgate and the target angle is greater than the predetermined difference, controlling the rear tailgate to continue unfolding until the difference between the unfolding angle of the rear tailgate and the target angle is less than or equal to the predetermined difference.

[0118] In other possible implementation forms, the above Figure 2 S203-S205 in the embodiment can be replaced by: processing the feature point parameters of the tailgate through a pre-trained angle prediction model to obtain the deployment angle of the tailgate, and based on the motion feature parameters of the target obstacle and the deployment angle of the tailgate, controlling the tailgate to deploy when the safety deployment conditions are met.

[0119] The pre-trained angle prediction model is obtained by training the neural network model through multiple sets of training feature point parameters, and each set of training feature point parameters in the multiple sets of training feature point parameters corresponds to a calibration angle. The process of obtaining the training feature point parameters can be referred to S501-S503, which will not be repeated here. The neural network model can be a random forest model, a support vector machine model, etc. The training process of the angle prediction model can automatically mine the complex mapping relationship between features and angles, and compared with the generation process of the target relationship in the above embodiment, the interpolation and generalization capabilities are stronger.

[0120] The training process of the angle prediction model includes: inputting multiple sets of training feature point parameters into the initial neural network model in sequence, outputting the predicted angle from the neural network model, comparing the relative error between the predicted angle and the calibrated angle, adjusting the parameters in the initial neural network model using the back propagation algorithm and the relative error, and repeating the above steps until the conditions for stopping iteration are met. The conditions for stopping iteration include: the relative error is less than the preset error threshold; or / and the number of iterations is greater than the preset number of iterations.

[0121] Please refer to Figure 6 , which shows a structural block diagram of a control device for a car tailgate provided by an embodiment of the present application. The device comprises: an image acquisition module 610, a feature extraction module 620, a first acquisition module 630, a second acquisition module 640, and a rear tailgate control module 650.

[0122] The image acquisition module 610 is used to acquire at least one image of the rear tailgate taken by the visual sensor during the unfolding process of the rear tailgate.

[0123] The feature extraction module 620 is used to obtain feature point parameters of the rear tailgate based on at least one rear tailgate image.

[0124] The first acquisition module 630 is used to acquire preset calibration parameters, where the preset calibration parameters represent the relationship between the characteristic point parameters of the rear tailgate and the deployment angle of the rear tailgate.

[0125] The second acquisition module 640 is used to acquire motion characteristic parameters of a target obstacle, where the target obstacle is an obstacle within a specified range determined based on the deployment path of the rear tailgate.

[0126] The rear tailgate control module 650 is used to control the rear tailgate to unfold under the premise of satisfying a safe unfolding condition based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tailgate, wherein the safe unfolding condition means that the rear tailgate does not collide with the target obstacle.

[0127] In some embodiments, the tailgate control module 650 is used to determine a target angle based on motion characteristic parameters of a target obstacle, where the target angle refers to the maximum deployment angle of the tailgate when the tailgate does not collide with the target obstacle; determine the deployment angle of the tailgate based on preset calibration parameters and characteristic point parameters of the tailgate; control the tailgate to stop deploying when the difference between the deployment angle of the tailgate and the target angle is less than or equal to a predetermined difference, wherein the target angle is greater than the deployment angle of the tailgate; control the tailgate to continue deploying when the difference between the deployment angle of the tailgate and the target angle is greater than a predetermined difference, until the difference between the deployment angle of the tailgate and the target angle is less than or equal to the predetermined difference.

[0128] In some embodiments, the preset calibration parameters are coefficients of a target relationship equation, which is used to describe the relationship between the deployment angle of the rear tailgate and the characteristic point parameters of the rear tailgate; the rear tailgate control module 650 is used to determine the target relationship equation based on the preset calibration parameters; and determine the deployment angle of the rear tailgate based on the target relationship equation and the characteristic point parameters of the rear tailgate.

[0129] In some embodiments, the tailgate control module 650 is used to predict the movement trajectory of the target obstacle based on the motion characteristic parameters of the target obstacle; determine the target position based on the movement trajectory of the target obstacle and the deployment speed of the tailgate, where the target position refers to the predicted position where the target obstacle collides with the tailgate; and determine the target angle based on the target position.

[0130] In some embodiments, the device further includes: a calibration module (not shown in the figure). The calibration module is used to control the rear tailgate to unfold to multiple specified angles; after the rear tailgate unfolds to each specified angle, a calibration image is captured by a visual sensor; feature point parameters of the rear tailgate are extracted from the calibration image; based on each specified angle, the feature point parameters corresponding to the specified angle are fitted to obtain a target relationship, and the feature point parameters corresponding to the specified angle refer to the feature point parameters extracted from the calibration image corresponding to the specified angle; and the coefficients of the target relationship are determined as preset calibration parameters.

[0131] In some embodiments, the device further includes: a first detection module (not shown in the figure). The first detection module is used to detect whether the Hall system is in a failed state. The image acquisition module is used to start the execution from the step of acquiring at least one rear tailgate image taken by the visual sensor when the Hall system is in a failed state. The rear tailgate control module 650 is also used to control the rear tailgate to be unfolded to a target angle based on the output result of the Hall system and the motion characteristic parameters of the target obstacle when the Hall system is not in a failed state.

[0132] In some embodiments, the device further includes: a second detection module (not shown in the figure). The second detection module is used to detect whether there is a target obstacle during the unfolding process of the rear tailgate. The image acquisition module 610 is used to start execution by acquiring at least one rear tailgate image taken by the visual sensor when the target obstacle is detected.

[0133] In summary, the technical solution provided in the embodiment of the present application obtains the motion characteristic parameters of the target obstacle and the preset calibration parameters during the deployment of the rear tailgate by the vehicle, and captures the rear tailgate image in real time to obtain the feature point parameters of the rear tailgate. The rear tailgate is controlled to be deployed under the condition of meeting the safety deployment conditions through the preset calibration parameters, the feature point parameters of the rear tailgate and the motion characteristic parameters of the target obstacle. Compared with the technical solution provided by the related art, the situation in which the deployment angle measurement result of the rear tailgate is disturbed when there is metal in the rear tailgate area can be avoided, so that the probability of the rear tailgate colliding with the target obstacle during the deployment process is greatly reduced, the real-time obstacle avoidance of the rear tailgate during the deployment process is achieved, and the deployment safety of the rear tailgate is improved.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0135] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0136] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0137] See also Figure 7 , which shows that the embodiment of the present application further provides a vehicle 700, which includes: one or more processors 710, a memory 720, and one or more applications. Among them, the one or more applications are stored in the memory 720 and are configured to be executed by the one or more processors 710, and the one or more applications are configured to execute the method described in the above embodiment.

[0138] The processor 710 may include one or more processing cores. The processor 710 uses various interfaces and lines to connect various parts of the entire battery management system, and executes various functions and processes data of the battery management system by running or executing instructions, programs, code sets or instruction sets stored in the memory 720, and calling data stored in the memory 720. Optionally, the processor 710 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 710 can integrate one or more combinations of a central processing unit 710 (CPU), a graphics processing unit 710 (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 710, but may be implemented separately through a communication chip.

[0139] The memory 720 may include a random access memory 720 (RAM) or a read-only memory 720 (Read-Only Memory). The memory 720 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 720 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the various method embodiments described below, etc. The data storage area may also store data created by the vehicle map during use (such as a phone book, audio and video data, chat record data), etc.

[0140] An embodiment of the present application further provides a computer-readable storage medium, in which computer program instructions are stored. The computer program instructions can be called by a processor to execute the method described in the above embodiment.

[0141] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for computer program instructions for executing any method step in the above method. These computer program instructions may be read from or written to one or more computer program products. The computer program instructions may be compressed in an appropriate form.

[0142] The above are only preferred embodiments of the present application, and are not intended to limit the present application in any form. Although the present application has been disclosed as above with preferred embodiments, it is not intended to limit the present application. Any technical personnel in the field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present application. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A method for controlling a rear door of a vehicle, characterized in that: Applied to a vehicle, the vehicle is provided with a visual sensor; the method comprises: Acquire at least one rear tailgate image taken by the visual sensor; Based on at least one of the rear tailgate images, acquiring characteristic point parameters of the rear tailgate; Acquiring a preset calibration parameter, wherein the preset calibration parameter represents a relationship between a characteristic point parameter of the rear tailgate and an unfolding angle of the rear tailgate; acquiring motion characteristic parameters of a target obstacle, wherein the target obstacle is an obstacle within a specified range determined based on a deployment path of the rear tailgate; Based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tailgate, the rear tailgate is controlled to be deployed under the premise of satisfying a safe deployment condition, wherein the safe deployment condition refers to that the rear tailgate does not collide with the target obstacle.

2. The method according to claim 1, characterized in that: The controlling the rear tailgate to be deployed under the premise of satisfying a safe deployment condition based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tailgate includes: determining a target angle based on the motion characteristic parameters of the target obstacle, wherein the target angle refers to a maximum deployment angle of the rear tailgate when the rear tailgate does not collide with the target obstacle; Determining an unfolding angle of the rear tailgate based on the preset calibration parameters and the characteristic point parameters of the rear tailgate; When the difference between the deployment angle of the rear tailgate and the target angle is less than or equal to a predetermined difference, controlling the rear tailgate to stop deploying, wherein the target angle is greater than the deployment angle of the rear tailgate; When the difference between the deployment angle of the rear tailgate and the target angle is greater than a predetermined difference, the rear tailgate is controlled to continue to be deployed until the difference between the deployment angle of the rear tailgate and the target angle is less than or equal to the predetermined difference.

3. The method according to claim 2, characterized in that The preset calibration parameters are coefficients of a target relational expression, and the target relational expression is used to describe the relationship between the deployment angle of the rear tailgate and the characteristic point parameters of the rear tailgate; determining the deployment angle of the rear tailgate based on the preset calibration parameters and the characteristic point parameters of the rear tailgate includes: Determining the target relationship based on the preset calibration parameters; Based on the target relationship expression and the characteristic point parameters of the rear tailgate, an unfolding angle of the rear tailgate is determined.

4. The method according to claim 2, characterized in that: The determining of the target angle based on the motion characteristic parameters of the target obstacle includes: Predicting a motion trajectory of the target obstacle based on motion characteristic parameters of the target obstacle; Determining a target position based on a motion trajectory of the target obstacle and an expansion speed of the rear tailgate, wherein the target position refers to a predicted position where the target obstacle collides with the rear tailgate; Based on the target position, a target angle is determined.

5. The method according to any one of claims 1 to 4, characterized in that: The process of obtaining the preset calibration parameters includes: Controlling the rear tailgate to unfold to a plurality of specified angles; After the rear tailgate is unfolded to each of the specified angles, capturing a calibration image by the visual sensor; Extracting feature point parameters of the rear tailgate from the calibration image; Based on each of the specified angles, fitting is performed with the feature point parameters corresponding to the specified angle to obtain a target relationship, where the feature point parameters corresponding to the specified angle refer to feature point parameters extracted from the calibration image corresponding to the specified angle; The coefficients of the target relationship are determined as the preset calibration parameters.

6. The method according to any one of claims 1 to 4, characterized in that The vehicle is further provided with a Hall system, and the Hall system is used to detect the deployment angle of the rear tailgate. The method further includes: Detecting whether the Hall system is in a failure state; When the Hall system is in the failure state, executing the step of acquiring at least one rear tailgate image taken by the visual sensor; When the Hall system is not in the failure state, the rear tailgate is controlled to be unfolded to a target angle based on an output result of the Hall system and a motion characteristic parameter of a target obstacle.

7. The method according to any one of claims 1 to 4, characterized in that The method further comprises: During the unfolding process of the rear tailgate, detecting whether the target obstacle exists; When the target obstacle is detected, the method starts with acquiring at least one rear tailgate image taken by the visual sensor.

8. A control device for a rear door of an automobile, characterized in that: The device comprises: An image acquisition module, used to acquire at least one rear tailgate image taken by a visual sensor; A feature extraction module, used for acquiring feature point parameters of the rear tailgate based on at least one of the rear tailgate images; A first acquisition module, used to acquire a preset calibration parameter, wherein the preset calibration parameter represents a relationship between a characteristic point parameter of the rear tailgate and an unfolding angle of the rear tailgate; a second acquisition module, configured to acquire motion characteristic parameters of a target obstacle, wherein the target obstacle is an obstacle within a specified range determined based on the deployment path of the rear tailgate; The rear tailgate control module is used to control the rear tailgate to be deployed under the premise of meeting a safe deployment condition based on the motion characteristic parameters of the target obstacle, the preset calibration parameters and the characteristic point parameters of the rear tailgate, wherein the safe deployment condition means that the rear tailgate does not collide with the target obstacle.

9. A vehicle, characterized in that: include: Vision sensors; one or more processors; Memory; One or more applications, wherein one or more of the applications are stored in the memory and configured to be executed by one or more of the processors, and one or more of the applications are configured to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and the computer program instructions can be called by a processor to execute the method according to any one of claims 1 to 7.

Images