Vehicle trunk control method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a vehicle trunk control method and device, equipment and a storage medium. According to the technical scheme, firstly, the type of an obstacle within the preset distance range of the trunk of the vehicle is detected, then, the target opening area of the trunk is calculated according to the size parameters of the trunk, and the target risk level of the obstacle is determined according to the type of the obstacle and the target opening area; and finally, controlling the trunk of the vehicle according to a target strategy corresponding to the target risk level of the obstacle. According to the control method of the vehicle trunk, the target risk level of the obstacle is determined based on the type of the obstacle and the target opening area, and then the trunk is intelligently controlled according to the corresponding target strategy, so that the safety and the driving experience can be effectively improved, the trunk opening process can be intelligently managed, and the driving safety is improved. Human intervention and misoperation are reduced, the accuracy of obstacle avoidance when the trunk is controlled to be opened is improved, and then the performance and the service life of the vehicle are optimized.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of vehicles, and relate to, but are not limited to, a control method, device, equipment and storage medium for a vehicle trunk. Background Art

[0002] With the popularization of new energy vehicles, the intelligent functions of vehicles are constantly enriched. However, when opening the trunk in a narrow space, there is often a risk of collision with walls or ceilings, resulting in vehicle damage or inconvenience in use.

[0003] Existing vehicle safety systems mostly focus on driving safety or parking assistance, and lack an effective solution for the safety of trunk opening. Therefore, how to improve the accuracy of obstacle avoidance when controlling the trunk to open is an urgent problem to be solved. Summary of the Invention

[0004] The control method, device, equipment and storage medium for a vehicle trunk provided by the embodiments of the present application can improve the accuracy of obstacle avoidance when controlling the trunk to open. The control method, device, equipment and storage medium for a vehicle trunk provided by the embodiments of the present application are implemented as follows:

[0005] The control method for a vehicle trunk provided by the embodiments of the present application is applied to a vehicle, and the method includes:

[0006] Detect the type of obstacles within a preset distance range of the trunk of the vehicle;

[0007] Calculate the target opening area of the trunk according to the size parameters of the trunk;

[0008] Determine the target risk level of the obstacle according to the type of the obstacle and the target opening area;

[0009] Control the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, and different risk levels correspond to different strategies.

[0010] In some embodiments, the calculating the target opening area of the trunk according to the size parameters of the trunk includes:

[0011] Calculate the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located.

[0012] In some embodiments, the calculating the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located includes:

[0013] Calculate the initial opening area of the trunk according to the size parameters;

[0014] Modify the initial opening area according to the inclination angle of the ground where the vehicle is located to obtain the target opening area.

[0015] In some embodiments, determining the target risk level of the obstacle according to the type of the obstacle and the target opening area includes:

[0016] Determine the state information of the obstacle according to the type of the obstacle, where the state information is used to indicate the distance between the obstacle and the trunk and / or the motion state of the obstacle;

[0017] Determine the risk level of the obstacle according to the state information of the obstacle and the target opening area.

[0018] In some embodiments, determining the risk level of the obstacle according to the state information of the obstacle and the target opening area includes:

[0019] According to the state information of the obstacle and the target opening area, when the obstacle meets the target preset condition during the opening of the trunk along the target opening area, determine that the risk level corresponding to the target preset condition is the target risk level, and different preset conditions correspond to different risk levels.

[0020] In some embodiments, different risk levels correspond to different response durations. Controlling the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle includes:

[0021] Control the trunk of the vehicle according to the target strategy within the target response duration corresponding to the target risk level.

[0022] In some embodiments, the vehicle includes a camera module. Detecting the type of the obstacle within a preset distance range of the trunk of the vehicle includes:

[0023] Obtain the obstacle within the preset distance range of the trunk of the vehicle through the camera module to obtain an obstacle depth map;

[0024] Based on the obstacle depth map, perform type recognition on the obstacles within the preset distance range to determine the type of the obstacles within the preset distance range.

[0025] In some embodiments, the number of the obstacles is multiple. Determining the target risk level of the obstacle according to the type of the obstacle and the target opening area includes:

[0026] Determine the risk level of each obstacle among the multiple obstacles according to the type of each obstacle and the target opening area of the trunk.

[0027] Determine the highest risk level among the risk levels of the multiple obstacles as the target risk level.

[0028] In some embodiments, the type of the obstacle includes any one of a moving object, a static object, a ground depression or a water accumulation type.

[0029] In some embodiments, the target strategy includes any one of the following strategies: a strategy for indicating normal opening of the trunk, a strategy for indicating reducing the opening speed of the trunk, a strategy for indicating keeping the current opening state of the trunk unchanged, and a strategy for indicating closing the trunk.

[0030] In some embodiments, before controlling the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, the method further includes:

[0031] Determine the target strategy corresponding to the target risk level of the obstacle according to a preset correspondence relationship, where the preset correspondence relationship is used to indicate the correspondence relationship between multiple risk levels of the obstacle and multiple strategies, the multiple risk levels include the target risk level, and the multiple strategies include the target strategy.

[0032] The control device for the trunk of a vehicle provided by an embodiment of the present application is applied to a vehicle, and the device includes:

[0033] A detection module, configured to detect the type of an obstacle within a preset distance range of the trunk of the vehicle;

[0034] A calculation module, configured to calculate the target opening area of the trunk according to the size parameters of the trunk;

[0035] A determination module, configured to determine the target risk level of the obstacle according to the type of the obstacle and the target opening area;

[0036] A control module, configured to control the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, and different risk levels correspond to different strategies.

[0037] The computer device provided by an embodiment of the present application includes a memory and a processor, the memory stores a computer program that can run on the processor, and when the processor executes the program, it implements the control method for the trunk of the vehicle described in the embodiment of the present application.

[0038] The computer-readable storage medium provided by the embodiments of the present application stores a computer program, and when the computer program is executed by a processor, the control method of the vehicle trunk provided by the embodiments of the present application is implemented.

[0039] The computer program product provided by the embodiments of the present application includes a computer program, and when the computer program is executed by a processor, the control method of the vehicle trunk provided by the embodiments of the present application is implemented.

[0040] In the control method, device, equipment and storage medium of the vehicle trunk provided by the embodiments of the present application, first, the type of obstacles within a preset distance range of the vehicle trunk is detected, then, according to the size parameters of the trunk, the target opening area of the trunk is calculated, and according to the type of obstacles and the target opening area, the target risk level of the obstacles is determined. Finally, according to the target strategy corresponding to the target risk level of the obstacles, the vehicle trunk is controlled. In the control method of the vehicle trunk of the present application, the target risk level of the obstacles is determined based on the type of obstacles and the target opening area, and then the trunk is intelligently controlled according to the corresponding target strategy, which can not only effectively improve safety and driving experience, but also intelligently manage the trunk opening process, reduce human intervention and misoperation, improve the accuracy of obstacle avoidance when controlling the trunk to open, and further optimize the vehicle performance and service life, so as to solve the technical problems proposed in the background art. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings here are incorporated into the specification and form a part of this specification. These drawings show embodiments consistent with the present application and are used together with the specification to explain the technical solutions of the present application.

[0042] Figure 1 It is a schematic flowchart of the implementation of the control method of the vehicle trunk provided by an embodiment of the present application;

[0043] Figure 2 It is a schematic flowchart of the implementation of the control method of the vehicle trunk provided by another embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the size parameters of the vehicle trunk provided by an embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the dynamic envelope line of the opening trajectory of the trunk provided by an embodiment of the present application;

[0046] Figure 5 It is a schematic flowchart of the implementation of the control method of the vehicle trunk provided by another embodiment of the present application;

[0047] Figure 6 It is a schematic structural diagram of the control device of the vehicle trunk provided by an embodiment of the present application;

[0048] Figure 7 Structural schematic diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will further describe the specific technical solutions of the present application in detail with reference to the accompanying drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not intended to limit the scope of the present application.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0051] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0052] It should be noted that the terms "first / second / third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0053] With the popularization of new energy vehicles, the intelligent functions of vehicles are constantly enriched. Automobiles are closely related to people's daily travel. In cities where parking spaces are becoming increasingly limited, parking brings many troubles to many drivers, such as too small a safety distance between vehicles, and other obstacles in the opening area of openable parts such as the trunk. This brings inconvenience to the normal opening of the doors and the trunk, and may even cause potential hazards such as the trunk being hit.

[0054] In the current related technologies, for the obstacle avoidance scheme for opening openable parts such as the trunk, mainly monocular Time of Flight (TOF) camera module detection technology or radar detection technology, etc. are adopted. The monocular TOF camera module detection technology uses the TOF camera module to obtain the position of the openable area of the trunk and detect whether there are obstacles. However, the TOF camera module detection technology cannot obtain three-dimensional space information and is difficult to identify low obstacles such as pets and children's toys. Therefore, the accuracy of the detected obstacles is not high; the radar detection technology has some blind spots. For example, when the trunk is opened on a step, since it is not in the radar detection area, there is also a risk of being hit during opening.

[0055] Therefore, how to improve the accuracy of obstacle avoidance when controlling the opening of the trunk is an urgent problem to be solved.

[0056] In view of this, an embodiment of the present application provides a control method for a vehicle trunk. The method is applied to a vehicle and specifically includes: detecting the type of an obstacle within a preset distance range of the vehicle trunk, then calculating a target opening area of the trunk according to the size parameters of the trunk, determining a target risk level of the obstacle according to the type of the obstacle and the target opening area, and finally controlling the vehicle trunk according to a target strategy corresponding to the target risk level of the obstacle. In the control method of the vehicle trunk of the present application, the target risk level of the obstacle is determined based on the type of the obstacle and the target opening area, and then the trunk is intelligently controlled according to the corresponding target strategy, which can not only effectively improve safety and driving experience, but also intelligently manage the trunk opening process, reduce human intervention and misoperation, improve the accuracy of obstacle avoidance when controlling the trunk to open, and further optimize the vehicle performance and lifespan.

[0057] In order to make the purpose and technical solution of the present application more clear and intuitive, the control method, device, equipment and storage medium for a vehicle trunk provided by the embodiments of the present application will be described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] Please refer to Figure 1 , which is a schematic flowchart of the implementation of the control method for a vehicle trunk provided by an embodiment of the present application. As Figure 1 shown, the method may include the following steps 101 to 104:

[0059] Step 101, detecting the type of an obstacle within a preset distance range of the vehicle trunk.

[0060] In some embodiments, multiple sensors or cameras may be installed around the area of the vehicle trunk. For example, multiple ultrasonic sensors are installed to detect the distance of an approaching object from the trunk. A radar sensor is installed to detect obstacles within a wider range, especially for objects of different materials, such as metals, plastics, fabrics, etc., and can provide more distance information. A camera is installed to capture image data around the trunk, and image recognition algorithms, such as deep learning models, are used to identify the type and shape of the obstacle. For example, objects such as vehicles, walls, and pedestrians are identified. An infrared sensor is installed to detect heat sources or temperature differences, which is particularly suitable for detecting obstacles in poor light conditions, such as obstacles at night or in a dim environment. The specific type of sensor or camera installed is not limited in the present application.

[0061] It should be noted that usually when the user triggers the trunk opening instruction, multiple sensors or cameras installed at the rear of the vehicle start to work to collect information about obstacles behind the trunk.

[0062] In some embodiments, the data of all sensors are collected and processed by the central processing unit of the vehicle, and the information from different sensors is integrated through data fusion technology to provide accurate obstacle detection information.

[0063] Taking the example of a camera installed at the rear of the vehicle, a trained deep learning model, such as a convolutional neural network, can be used to analyze the images obtained by the camera to identify the types of obstacles. For example, they can be classified as static obstacles, dynamic obstacles, as well as ground depressions and puddles. Taking the example of ultrasonic and radar sensors installed at the rear of the vehicle, the ultrasonic and radar sensors can further identify the nature of the obstacles based on the reflection intensity and distance. For example, the reflection characteristics of metal objects are different from those of soft objects, such as human clothing or fabric, and the radar system can use these characteristics to assist in identification.

[0064] Optionally, the preset distance range can be a range from 1 meter to 2 meters from the rear of the vehicle.

[0065] Step 102: Calculate the target opening area of the trunk according to the size parameters of the trunk.

[0066] In some embodiments, the size parameters of the trunk generally include the height (h) of the trunk, the width (w) of the trunk, the length (l) of the trunk, and the opening angle (θ) of the trunk. The trunk height generally refers to the vertical height from the ground to the top of the trunk door. The trunk width generally refers to the horizontal width from one side to the other side of the trunk door. The trunk length generally refers to the length of the trunk door, that is, the distance from the starting point of opening to the end of the trunk door. The opening angle generally refers to the opening angle of the trunk door, which can usually be set to a maximum angle, such as 90 degrees, 120 degrees, etc., and is automatically adjusted according to the vehicle speed, environment, and obstacles.

[0067] In some embodiments, according to the size parameters of the trunk, the opening trajectory envelope of the trunk can be obtained, and then the target opening area of the trunk can be calculated. Assuming the shape of the trunk door is rectangular or oval, the size of the opening area can be estimated by calculating the space volume occupied by the trunk when opening the door.

[0068] Step 103: Determine the target risk level of the obstacle according to the type of the obstacle and the target opening area.

[0069] In some embodiments, it is assumed that the types of obstacles are divided into static obstacles, dynamic obstacles, ground depressions and puddles, etc. Static obstacles such as the walls of a parking lot, other vehicles, fences or other objects, etc. Dynamic obstacles such as pedestrians who may be standing or walking, running kittens or puppies or other moving vehicles, etc.

[0070] In some embodiments, according to the calculation result of the target opening area and in combination with the type of obstacle, the relative position of the current obstacle to the opening area of the trunk door is evaluated, as well as the potential impact of the obstacle on the opening of the trunk. For example, considering the distance between the obstacle and the trunk door, if the obstacle is within the opening path of the trunk door and is relatively close to the door, the risk is higher; if the obstacle is far from the opening area, the impact on the opening is smaller and the risk is lower. If considering the matching degree between the size of the obstacle and the opening of the trunk door, if the obstacle is too large and occupies a relatively large opening space, there may be a collision or obstruction to the opening of the door when opening the door; small obstacles or flexible obstacles, such as pedestrians, may have a smaller impact, but real-time monitoring is required. If considering whether the obstacle is movable, if the obstacle is dynamic, such as a pedestrian or other vehicle, the system will need to consider the movement trajectory and speed of the obstacle to evaluate its impact on the opening of the trunk.

[0071] In a possible implementation manner, by comprehensively considering the type of the current obstacle, the target opening area of the trunk, and the potential impact of the obstacle on the opening of the trunk, the target risk level of the obstacle can be determined. Assuming that the risk levels are divided into low risk, medium risk and high risk, the low-risk level situations may include that the obstacle is far from the trunk door and there is almost no possibility of collision when opening the door, or the obstacle does not affect the opening angle of the trunk door or the smooth opening and closing of the door, or a moving obstacle, such as a pedestrian or vehicle, is far away and has a slow speed and is unlikely to enter the opening area in a short time, etc. The medium-risk level situations may include that the obstacle is relatively close to the trunk door and there is a slight possibility of collision when opening the door, or it may be necessary to reduce the opening angle or adjust the opening speed to avoid collision, or a dynamic obstacle, such as a pedestrian or vehicle, is approaching the opening area and may affect the smooth opening of the trunk door, etc. The high-risk level situations may include that the obstacle is very close to the trunk door and a collision is almost inevitable when opening the door, which may cause damage to the trunk door or objects around the vehicle, or the obstacle occupies most of the opening area, or a dynamic obstacle, such as a vehicle or pedestrian approaching quickly, enters the opening area and may cause an immediate collision, etc.

[0072] Step 104, control the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle. Different risk levels correspond to different strategies.

[0073] In some embodiments, different risk levels correspond to different strategies. For example, for an obstacle with a low risk level, the corresponding strategy could be to control the trunk to open completely at a predetermined speed and angle, or the system can continue to monitor any potential changes during the opening process in real time without taking proactive intervention measures. For an obstacle with a medium risk level, the corresponding strategy could be to adjust the opening speed or angle of the trunk to reduce the likelihood of collision; if there are other people or system users near the vehicle, the system can issue a reminder through the warning system to notify the vehicle owner of the potential risk; if there is a dynamic obstacle, such as a pedestrian approaching, the system can control the trunk to perform a delayed opening operation until the obstacle completely leaves the target opening area. For an obstacle with a high risk level, the corresponding strategy could be to immediately stop the trunk opening operation to prevent any potential collision or damage; pause the current trunk opening operation. If the obstacle is within the target opening area, the system will continuously monitor whether the obstacle moves until the obstacle leaves the opening area or the conditions are safe before allowing the trunk to continue opening; in extreme cases, the system will notify the vehicle owner or surrounding people through emergency alarms inside and outside the vehicle, reminding them that a collision may occur during the trunk opening and asking them to take action.

[0074] In other embodiments, regardless of the risk level of the obstacle, the vehicle will continuously monitor the trunk opening area through real-time sensors such as radar, ultrasonic sensors, or cameras. Based on this data, it will be analyzed in real time whether a new obstacle enters or the position of the original obstacle changes. For dynamic obstacles such as pedestrians and other vehicles, the timing when they may enter the trunk opening area will be predicted, and corresponding adjustments will be made according to the movement speed and direction. If the obstacle suddenly approaches and poses a high risk, the system will automatically terminate the trunk opening operation. If the vehicle owner manually starts the trunk opening, the system will provide a reminder in the intelligent assistance mode, informing the vehicle owner of the current risk level and the recommended measures to be taken. If necessary, the vehicle owner can choose to bypass the automatic control through manual operation.

[0075] In this embodiment, first, the type of obstacles within a preset distance range of the vehicle's trunk is detected. Then, according to the size parameters of the trunk, the target opening area of the trunk is calculated. And based on the type of obstacles and the target opening area, the target risk level of the obstacles is determined. Finally, according to the target strategy corresponding to the target risk level of the obstacles, the vehicle's trunk is controlled. By detecting the type of obstacles within the preset distance range of the trunk, the vehicle system can evaluate in real time whether there are potential risks affecting the opening of the trunk. For example, if the obstacle is a hard object or an immovable object, the system can promptly identify and determine that this object may cause collisions or damage when the trunk is opened, thus taking appropriate actions to avoid accidents. By identifying different types of obstacles, such as vehicles, walls, people, etc., and evaluating the risk level according to the nature of different obstacles, finally, according to the risk level of the obstacles, different trunk control strategies are selected. By adjusting the trunk opening method according to the specific situation, it can effectively avoid damage or safety hazards caused by improper trunk opening. Through automatic recognition and intelligent control, users can still easily and safely open the trunk in different situations without too much intervention, providing users with higher convenience and comfort. Especially in narrow or complex space environments, the system can automatically recognize and adjust the opening method, enhancing the overall usage experience. By dynamically evaluating according to the environment and obstacle characteristics around the trunk, whether in a parking lot, a narrow space or a complex environment, the system can make the most appropriate decision according to different scenarios. This adaptability improves the performance of the vehicle in various actual usage scenarios, can meet the needs of different driving environments, and improves the intelligence level of the vehicle. Generally speaking, the intelligent control strategy for the trunk based on obstacle type detection and risk assessment can not only effectively improve safety and driving experience, but also intelligently manage the trunk opening process, reduce human intervention and misoperations, and thus optimize the vehicle performance and lifespan.

[0076] Based on the above embodiment, Figure 2 is a schematic flowchart of the implementation of the control method for the vehicle trunk provided in another embodiment of this application, as Figure 2 shown. This method may include the following steps:

[0077] Step 201, detect the type of obstacles within a preset distance range of the vehicle's trunk.

[0078] In some embodiments, multiple sensors or cameras can be installed around the area of the vehicle's trunk. For example, multiple ultrasonic sensors can be installed to detect the distance of an approaching object from the trunk. A radar sensor can be installed to detect obstacles within a wider range, especially for objects of different materials such as metal, plastic, cloth, etc., and can provide more distance information. Installing a camera can capture the image data around the trunk, and using image recognition algorithms, such as deep learning models, to identify the type and shape of obstacles. For example, to identify objects such as vehicles, walls, pedestrians, etc. An infrared sensor can be installed to detect heat sources or temperature differences, which is particularly suitable for detecting obstacles in poor lighting conditions, such as obstacles at night or in dim environments. The specific type of sensor or camera installed is not limited in this application.

[0079] It should be noted that generally when the user triggers the trunk opening instruction, the multiple sensors or cameras installed at the rear of the vehicle start to work and collect the obstacle information behind the trunk.

[0080] In some embodiments, the data of all sensors is collected and processed by the vehicle's central processing unit, and the information from different sensors is integrated together through data fusion technology to provide accurate obstacle detection information.

[0081] Taking the example of a camera installed at the rear of the vehicle, a trained deep learning model, such as a convolutional neural network, can be used to analyze the images obtained by the camera to identify the type of obstacles. For example, they can be classified as static obstacles, dynamic obstacles, and ground depressions and puddles, etc. Taking the example of ultrasonic and radar sensors installed at the rear of the vehicle, the ultrasonic and radar sensors can further identify the nature of the obstacles based on the reflection intensity and distance. For example, the reflection characteristics of metal objects are different from those of soft objects, such as human clothing or cloth, and the radar system can help identify based on these characteristics.

[0082] Optionally, the preset distance range can be the range from 1 meter to 2 meters behind the vehicle.

[0083] Step 202, calculate the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located.

[0084] In some embodiments, the size parameters of the trunk generally include the height (h) of the trunk, the width (w) of the trunk, the length (l) of the trunk, and the opening angle (θ) of the trunk door. The height of the trunk generally refers to the vertical height from the ground to the top of the trunk door. The width of the trunk generally refers to the horizontal width from one side to the other side of the trunk door. The length of the trunk generally refers to the length of the trunk door, that is, the distance from the starting point of opening to the end of the trunk door. The opening angle generally refers to the opening angle of the trunk door, which can usually be set to a maximum angle, such as 90 degrees, 120 degrees, etc., and is automatically adjusted according to vehicle speed, environment, and obstacles.

[0085] Exemplarily, taking the current vehicle being on a horizontal ground as an example, please refer to Figure 3 , which is a schematic diagram of the size parameters of the vehicle trunk provided by an embodiment of the present application. As Figure 3 shown, at this time the trunk is in an open state. The height (h) of the trunk is the vertical height from the top of the trunk door to the ground. The width (w) of the trunk is the horizontal width of the trunk door. The length (l) of the trunk is the length of the trunk door. The opening angle (θ) of the trunk is the opening angle of the trunk door.

[0086] Optionally, the opening trajectory of the trunk is usually a curve, similar to an arc with the position where the trunk starts to rotate as the starting point and the length of the trunk door as the radius. For example, as Figure 4 shown, still taking the current vehicle being on a horizontal ground as an example, Figure 4 the curve in

[0087] is the dynamic envelope line of the opening trajectory.

[0088] Further, in the case where the vehicle is on a horizontal ground, the initial opening area is the target opening area.

[0089] In the case where the vehicle is not on a horizontal ground, for example, when the vehicle is on a slope, a vehicle inclination sensor is used to collect the inclination angle of the ground where the vehicle is located, and then based on this inclination angle and a pitch angle compensation algorithm, the coordinates of the initial opening area are corrected to obtain the target opening area.

[0090] Among them, the tilt sensor of the vehicle, usually part of an Inertial Measurement Unit (IMU), can measure the pitch angle and roll angle of the vehicle. These angles reflect the tilt of the vehicle on uphill, downhill, sloping, or uneven ground. The pitch angle refers to the tilt in the front-rear direction of the vehicle, with a positive value indicating that the front of the vehicle is tilted downward and a negative value indicating that the front of the vehicle is tilted upward. The roll angle refers to the tilt in the left-right direction of the vehicle, with a positive value indicating that the left side of the vehicle is tilted downward and a negative value indicating that the right side of the vehicle is tilted downward.

[0091] When the vehicle is on an inclined ground, the initial opening area of the trunk door also needs to be corrected accordingly. Assuming that the initial opening area is based on a standard angle on a horizontal ground, when the vehicle is on an inclined ground, the coordinates of the initial opening area need to be compensated.

[0092] As an example, assume that the coordinates of any position in the initial opening area of the trunk are (x0, y0), which are calculated based on the ground (horizontal) as a reference. When the vehicle is on an inclined ground, the inclination angle, especially the pitch angle, will cause changes in the spatial coordinates of the initial opening area. The pitch angle affects the vertical direction of the opening, so we need to adjust the height of the opening area.

[0093] Assume that the inclination angle of the ground where the vehicle is located is α, that is, the pitch angle is α, and the coordinates of the target opening area are (x target , y target ), then the calculation formula is as follows:

[0094] x target = x0,

[0095] y target = y0 + h * tanα.

[0096] Among them, x0 and y0 are the coordinates in the initial opening area, h is the vertical height from the top of the trunk door to the ground, that is, the vertical height of the trunk opening area, α is the pitch angle, in radians. If the angle unit returned by the sensor is in degrees, it needs to be converted to radians first.

[0097] It should be noted that when the front of the vehicle is tilted downward, the height of the trunk opening area will relatively increase. Therefore, (x target , y target ) will increase, and the opening area will shift backward relative to the vehicle. Conversely, when the front of the vehicle is tilted upward, the height of the trunk opening area will decrease, and the opening area will shift forward relative to the vehicle.

[0098] In some embodiments, based on the coordinates (xtarget , y target ), the target opening area of the trunk door can be determined. In this way, when the trunk door is opened on an inclined ground, the correct spatial position is ensured to avoid collisions or smooth opening. In the case of a tilted vehicle, the vehicle's control system adjusts the opening angle, speed, and path of the trunk based on the corrected coordinates, thereby ensuring the accuracy of the opening area and avoiding collisions with obstacles.

[0099] Step 203: Determine the status information of the obstacle according to the type of the obstacle, where the status information is used to indicate the distance between the obstacle and the trunk and / or the motion state of the obstacle.

[0100] In some embodiments, the type of the obstacle includes any one of a moving object, a static object, a ground depression, or a water accumulation type. A moving object, that is, a dynamic obstacle, such as a pedestrian who may be standing or walking, a running kitten or puppy, or other moving vehicles, etc. A static object, that is, a static obstacle, such as the wall of a parking lot, other vehicles, fences, or other items, etc.

[0101] In some embodiments, after identifying the type of the obstacle, different detection methods can be selected according to the type of the obstacle to determine the status information of the obstacle.

[0102] Among them, when the type of the obstacle is a moving object, the optical flow method can be used to determine the speed of the moving object, etc. The optical flow method is a computer vision technology that estimates the motion of an object based on the change of pixels between adjacent frames in an image. It is usually assumed that the motion of the object in adjacent frames causes the pixels in the image to translate. Through this method, the motion direction, speed, and relative distance of the object can be detected.

[0103] In the context of opening the vehicle trunk, the optical flow method can capture images of the area around the trunk through a camera, analyze the motion of obstacles (such as pedestrians, other vehicles, etc.), and determine whether there is a potential conflict with the opening area of the trunk. Through the optical flow method, the vehicle system can estimate the speed and direction of the moving object in real time, and then calculate whether the object will enter the opening path of the trunk. For example, if it is detected that an object is approaching the trunk at a high speed, the system can react in advance and adjust the opening behavior of the trunk. In addition, the optical flow method can also track the position and speed of the moving object in real time, dynamically update the obstacle status information, and predict the motion trajectory of the moving object in the next few frames to help predict whether it will conflict with the opening area of the trunk. The optical flow method is particularly suitable for dealing with complex dynamic scenes, such as environments with multiple obstacles or fast-moving objects, and can effectively track different types of moving objects (such as pedestrians, vehicles, animals, etc.) and judge their impact on the trunk opening process.

[0104] When the type of obstacle is a static object, the PointNet++ point cloud processing method can be adopted. PointNet++ is a deep learning-based point cloud processing network that can process and analyze point cloud data generated by sensors such as lidar, and is very effective for the detection, classification, and segmentation of static objects. PointNet++ improves the learning ability of complex geometries in point cloud data by introducing a hierarchical structure to process local region features, enabling it to handle irregular and unordered point cloud data, especially for static objects with details and complex structures; PointNet++ uses a multi-scale perception method to perform layer-by-layer feature extraction on the local and global structures in the point cloud data, enabling the network to efficiently capture geometric information at different levels.

[0105] When dealing with static objects such as parked vehicles, buildings, and trees on the roadside, point cloud data generated by lidar sensors is usually used for modeling. In the application of autonomous driving or intelligent vehicles, lidar sensors provide very accurate three-dimensional data of the surrounding environment, allowing the system to accurately identify surrounding obstacles. Further, PointNet++ preprocesses the original point cloud data, which usually includes denoising, sampling and downsampling denoising, and normalization and standardization. Among them, denoising means that the point cloud data may contain noise, which needs to be filtered during preprocessing; since the original point cloud data may be very dense, downsampling of the point cloud is usually performed to reduce computational complexity while retaining important geometric information. Normalization and standardization refer to normalizing the coordinates of the point cloud data to better handle objects of different scales and orientations. By performing multi-level global feature extraction on the point cloud data, PointNet++ can effectively capture the overall shape of static objects and identify the spatial relationships between different objects, providing real-time risk assessment for safety systems such as trunk opening.

[0106] When the type of obstacle is a ground depression or water accumulation type, multi-spectral analysis can be adopted. Multi-spectral analysis helps the system effectively detect ground conditions by combining light signals of different wavelengths, such as visible light, infrared light, short-wave infrared, etc., and is particularly important for special terrain changes such as water accumulation and ground depressions. Multi-spectral analysis analyzes the features of the target area by acquiring and processing image data of multiple different bands. Common multi-spectral sensors can capture information of multiple bands from visible light to infrared, and using this information, various obstacles and features on the ground can be identified and classified.

[0107] Exemplarily, multispectral analysis is used for water accumulation detection. The reflection characteristics of water accumulation are usually different from those of the surrounding environment. In multispectral analysis, water accumulation usually exhibits specific spectral reflection characteristics. Especially in the near-infrared and short-wave infrared bands, the reflectivity of water bodies is low, and in these bands, the contrast between the water surface and the surrounding ground will be more obvious. Specifically, the water accumulation area usually appears dark under visible light because water absorbs a lot of visible light; the reflectivity of water accumulation is low, so in the near-infrared image, the water accumulation area will appear very dark, while dry ground usually reflects more infrared light; the reflectivity of water in the short-wave infrared band is also low, so the water accumulation area can be clearly identified.

[0108] For another example, multispectral analysis is used for ground depression detection. The performance of ground depressions (such as potholes) in multispectral images is relatively complex, but they can also be identified by comparing the reflection characteristics of different bands. For example, in the visible light band, the spectral reflection of the depression area may be different because surface features affect the reflection of light; in the near-infrared and short-wave infrared bands, the depression may exhibit different spectral characteristics due to different humidity and material compositions of the ground. For example, the moisture or water accumulation in the depression may affect infrared reflection; in the thermal infrared band, due to temperature differences, the temperature of the ground depression area is usually different from that of the surrounding ground, especially at night or in the early morning, and thermal infrared images can reveal these differences.

[0109] In some embodiments, by combining multiple sensor technologies, accurately measuring and inferring the distance between the obstacle and the trunk, as well as the motion state of the obstacle, can help the vehicle system make real-time judgments and decisions, avoid collisions, and optimize operations.

[0110] Step 204, determine the risk level of the obstacle according to the status information of the obstacle and the target opening area.

[0111] In some embodiments, the status information of the obstacle is used to indicate the distance between the obstacle and the trunk and / or the motion state of the obstacle. The vehicle can determine the risk level of the obstacle according to the distance between the obstacle and the trunk and / or the motion state of the obstacle, as well as the target opening area.

[0112] Optionally, the risk level of the obstacle can be determined according to the distance between the obstacle and the trunk and the target opening area. The closer the obstacle is to the target opening area, the higher the risk level. For example, if the obstacle is within a few centimeters, the risk level is usually the highest. If the obstacle completely covers the target area or some of its important areas, the risk level will also increase accordingly.

[0113] Optionally, the risk level of the obstacle can be determined based on the motion state of the obstacle and the target opening area. Dynamic obstacles, such as moving vehicles and pedestrians, may change their positions at any time, which will affect their relationship with the target opening area. Therefore, special attention needs to be paid. For example, if the obstacle is stationary and has no direct conflict with the target opening area, its risk level is usually low. If the obstacle is moving and may enter the target opening area, the risk level will change according to its speed and direction. The faster the speed and the more uncertain the direction, the higher the risk level.

[0114] Optionally, the sensitivity of the target opening area also affects the assessment of the obstacle risk level. For example, if the target opening area is a critical operation area, such as a transportation corridor, the presence of any obstacle will result in a higher risk. If the surrounding safety area is an area that does not affect the current task, the presence of an obstacle may not cause a high risk.

[0115] In a possible implementation manner, according to the state information of the obstacle and the target opening area, when the obstacle meets the target preset condition during the opening process of the trunk along the target opening area, the risk level corresponding to the target preset condition is determined as the target risk level, and different preset conditions correspond to different risk levels.

[0116] Optionally, different preset conditions correspond to different risk levels. The preset conditions may include any one of the following: there is no obstacle within the preset distance range of the trunk; the moving obstacle is located more than 1 meter away from the trunk; the static obstacle is located within 50 centimeters of the target opening area; the obstacle invades the safety boundary of the target opening area; the contact risk probability with the trunk is greater than 65%; human body contacts the trunk or mechanical overload.

[0117] Optionally, the risk level can be divided into a low risk level, a medium risk level, and a high risk level, or the corresponding risk level can be set according to the preset conditions. For example, when the preset condition is that there is no obstacle within the preset distance range of the trunk, the risk level is set as L0; when the preset condition is that the moving obstacle is located more than 1 meter away from the trunk, the risk level is set as L1; when the preset condition is that the static obstacle is located within 50 centimeters of the target opening area, the risk level is set as L2; when the preset condition is that the obstacle invades the safety boundary of the target opening area, the risk level is set as L3; when the preset condition is that the contact risk probability with the trunk is greater than 65%, the risk level is set as L4; when the preset condition is that the human body contacts the trunk or mechanical overload, the risk level is set as L5; the specific setting form is not limited in this application.

[0118] In some embodiments, when an obstacle meets a target preset condition during the opening of the trunk along a target opening area, the risk level corresponding to the target preset condition is determined as the target risk level. The target preset condition is any one of the preset conditions. For example, if an obstacle intrusion into the safety boundary of the target opening area is detected during the opening of the trunk along the target opening area, the target risk level is determined as L3.

[0119] In a possible implementation manner, a laser-assisted texture projector may also be provided in the trunk area of the vehicle. The laser-assisted texture projector can help the driver, passengers, and surrounding pedestrians better understand the spatial layout, position, and current state of the trunk area by projecting textures, images, or warning signals.

[0120] In some embodiments, the laser-assisted texture projector can project virtual textures or lines to help the driver more clearly know the opening range and spatial layout of the trunk. For example, the laser lines projected onto the ground can show the range when the trunk door is fully opened, or show the specific area after opening, which provides very valuable assistance for parking in narrow spaces, especially in garages or busy parking lots. The laser-assisted texture projector can also be used to display obstacles in the trunk opening area. If the system detects an object approaching during the opening of the trunk, the laser projector can issue a warning by changing the projected pattern. For example, when an object is located in the target opening area of the trunk, that is, the opening path, the laser pattern can flash or change color to remind the vehicle owner of the potential collision risk. In addition, in low-light or nighttime environments, the laser-assisted texture projector is very useful. It can clearly mark the trunk opening range and possible obstacles, helping the vehicle owner operate the trunk in a dark environment and avoid accidentally touching or hitting an object. Furthermore, when the trunk is opened, the laser can be projected onto the ground or surrounding areas by a laser beam to help pedestrians avoid approaching the trunk area, thereby reducing the possibility of accidents.

[0121] That is to say, the vehicle can determine the risk level of the obstacle through the laser-assisted texture projector according to the status information of the obstacle and the target safety area.

[0122] Step 205, within the target response duration corresponding to the target risk level, control the trunk of the vehicle according to the target strategy. Different risk levels correspond to different response durations.

[0123] It should be understood that the response duration can be set according to experience, or can be a preset fixed value, or can be determined by other means. The present application does not make any limitations in this regard.

[0124] In some embodiments, the target strategy includes any one of the following strategies: a strategy for indicating normal opening of the trunk, a strategy for indicating reduction of the opening speed of the trunk, a strategy for indicating maintaining the current open state of the trunk unchanged, and a strategy for indicating closing of the trunk.

[0125] In some embodiments, different risk levels correspond to different strategies, and different risk levels also correspond to different response durations. Taking the setting of the corresponding risk level according to the preset conditions in the above steps as an example, assume that the preset condition is that there is no obstacle within the preset distance range of the trunk, the risk level is set to L0, and the corresponding control strategy is to open the trunk normally, and the response time can be set to less than or equal to 50 ms; the preset condition is that the moving obstacle is more than 1 meter away from the trunk, the risk level is set to L1, and the corresponding control strategy is to open the trunk normally, and at the same time, audible and visual warnings can be attached, such as dual-frequency beeping + flashing of the breathing light of the light emitting diode (LED), and the response time can be set to less than or equal to 100 ms; the preset condition is that the static obstacle is within 50 cm of the target opening area, the risk level is set to L2, and the corresponding control strategy is to control the opening speed of the trunk to be reduced to 50% of the initial calibration value, and the response time can be set to less than or equal to 200 ms; the preset condition is that the obstacle invades the safety boundary of the target opening area, the risk level is set to L3, and the corresponding control strategy is to maintain the current opening degree of the trunk and start continuous monitoring, and the response time can be set to less than or equal to 300 ms; the preset condition is that the contact risk probability with the trunk is greater than 65%, the risk level is set to L4, and the corresponding control strategy is to close the trunk in reverse steps, and the response time can be set to less than or equal to 500 ms; the preset condition is that a human body touches the trunk or there is mechanical overload, the risk level is set to L5, and the corresponding control strategy is to maintain the current opening degree of the trunk and trigger SOS in an emergency, and the response time can be set to less than or equal to 1 s.

[0126] Exemplarily, the corresponding relationship between the above different risk levels, different control strategies, and response durations can be shown in Table 1 below:

[0127] Table 1

[0128]

[0129] Furthermore, within the target response duration corresponding to the target risk level, the vehicle controls the trunk of the vehicle to perform corresponding operations according to the instructions of the central processing unit and the target strategy.

[0130] In this embodiment, first, the type of the obstacle within the preset distance range of the vehicle's trunk is detected. Then, according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located, the target opening area is calculated. According to the type of the obstacle, the status information of the obstacle is determined, and the status information is used to indicate the distance between the obstacle and the trunk and / or the movement state of the obstacle. Further, according to the status information of the obstacle and the target opening area, the risk level of the obstacle is determined. Within the target response duration corresponding to the target risk level, the vehicle's trunk is controlled according to the target strategy, and different risk levels correspond to different response durations. The vehicle can detect the obstacles within the trunk opening area in real time, judge the type and position of the obstacles. Through precise perception, it can avoid accidental touching, scratching or collision, especially in spaces such as garages and narrow parking spaces, reducing the safety hazards of the vehicle owner and pedestrians. By detecting the movement state of the obstacle, such as whether it is moving or approaching, the possible threat level is further judged to avoid accidents during the trunk opening process. By calculating the relationship between the target opening area of the trunk and the obstacle state, the system can adopt precise response strategies according to different risk levels. For example, it can be quickly opened in case of low risk, while it will be delayed or completely stopped from opening in case of high risk, greatly improving the accuracy of obstacle avoidance when controlling the trunk opening, as well as the safety, intelligence and convenience of the vehicle trunk opening process. This automated and precise control method can not only reduce potential collision accidents, but also make the driver more confident in operating the trunk in complex or narrow environments, improving the overall usage experience of the vehicle.

[0131] Based on the above embodiment, Figure 5 FIG. is a schematic flowchart of the implementation of the control method for the vehicle trunk provided in another embodiment of the present application. In this embodiment, it is taken as an example that the vehicle includes a camera module, as Figure 5 shown, the method may include the following steps:

[0132] Step 501, obtain the obstacles within the preset distance range of the vehicle's trunk through the camera module to obtain the obstacle depth map.

[0133] In some embodiments, the camera module is arranged in the middle area of the vehicle's trunk, and all areas of the trunk are covered by the field of view. According to the design of the vehicle and the size of the trunk, the position and perspective of the camera module can be adjusted. Further, the preset distance range is determined, for example, the area from 1 meter to 3 meters of the trunk, which is the preset obstacle detection range.

[0134] In some embodiments, the camera module may be a binocular wide-angle camera (190° FOV). A binocular wide-angle camera (190° FOV) is a vision system with a large field of view (FOV) and two cameras, and is typically used in scenarios such as depth perception, 3D modeling, and object recognition. A field of view of 190° for a wide-angle camera means that it can capture a very wide field of view, approaching the horizontal field of view of the human eye.

[0135] Optionally, due to the characteristics of the lens, the images captured by the camera may be distorted and need to be de-distorted to ensure image accuracy. Also, only the images of obstacles within a preset distance range in the trunk are retained, and irrelevant areas are removed.

[0136] In some embodiments, taking the camera module as a binocular wide-angle camera as an example, first, feature matching is performed on the images captured by the two wide-angle cameras to find corresponding points. Then, based on the disparity, that is, the difference in the same object seen by the two cameras, the depth value of each pixel is calculated. The greater the disparity, the closer the object is to the camera; the smaller the disparity, the farther the object is from the camera. Further, through depth estimation, a depth map is generated, and each pixel point in the image will have a corresponding depth value. After the depth map is generated, object detection algorithms, such as the deep learning algorithm (You Only Look Once, YOLO), can be used to identify the objects near the trunk. Based on the detected object positions, the depth map is filtered to mark the obstacles within the preset distance range. In the obstacle depth map, obstacles usually appear in brighter or darker colors to indicate their distances.

[0137] Optionally, the semi-global matching algorithm (SGM) can also be used to generate the obstacle depth map. SGM is an algorithm used in stereo vision and is typically used to obtain depth information from binocular cameras. SGM generates an accurate disparity map by optimizing in multiple scan line directions, and then calculates the depth value of each pixel. The advantage of this algorithm is that it can handle large-scale images and generate high-precision disparity maps.

[0138] Optionally, the obstacle depth map may have noise, especially in low-light or complex environments. Filtering algorithms, such as median filtering and mean filtering, can be used to reduce the noise. If necessary, object tracking algorithms can be combined to track the positions and movement trajectories of obstacles in consecutive images.

[0139] Step 502: Based on the obstacle depth map, perform type recognition on the obstacles within the preset distance range to determine the types of the obstacles within the preset distance range.

[0140] In some embodiments, the depth value of each pixel in the obstacle depth map can be converted into the relative position with respect to the camera module, which is convenient for further analysis. For the segmented and analyzed obstacle regions, traditional image processing methods can be used. For example, edge-based segmentation or depth information-based segmentation methods can be used to extract geometric features of the obstacles, such as size, shape, surface smoothness, angle, etc., and spatial information. Further, based on the extracted features, machine learning or deep learning models can be used for obstacle classification. The classification model can be traditional machine learning methods, such as Support Vector Machine (SVM), etc., or models based on deep neural networks, such as Convolutional Neural Network (CNN), etc. This application does not make any limitations in this regard.

[0141] In some embodiments, the types of obstacles include any one of moving objects, static objects, ground depressions, or water accumulation types. Moving objects, that is, dynamic obstacles, such as pedestrians who may be standing or walking, running kittens or puppies, or other moving vehicles, etc. Static objects, that is, static obstacles, such as the walls of a parking lot, other vehicles, fences, or other items, etc.

[0142] Step 503: Calculate the target opening area of the trunk according to the size parameters of the trunk.

[0143] In some embodiments, the size parameters of the trunk generally include the height (h) of the trunk, the width (w) of the trunk, the length (l) of the trunk, and the opening angle (θ) of the trunk door. The trunk height generally refers to the vertical height from the ground to the top of the trunk door. The trunk width generally refers to the horizontal width from one side to the other side of the trunk door. The trunk length generally refers to the length of the trunk door, that is, the distance from the starting point of opening to the end of the trunk door. The opening angle generally refers to the opening angle of the trunk door, which can generally be set to a maximum angle, such as 90 degrees, 120 degrees, etc., and is automatically adjusted according to the vehicle speed, environment, and obstacles.

[0144] In some embodiments, according to the size parameters of the trunk, the opening trajectory envelope of the trunk can be obtained, and then the target opening area of the trunk can be calculated. Assuming that the shape of the trunk door is rectangular or elliptical, the size of the opening area can be estimated by calculating the space volume occupied by the trunk when opening the door.

[0145] Step 504: Determine the target risk level of the obstacle according to the type of the obstacle and the target opening area.

[0146] In a possible implementation, by comprehensively considering the type of the current obstacle, the target opening area of the trunk, and the potential impact of the obstacle on the opening of the trunk, the target risk level of the obstacle can be determined. Assuming the risk levels are divided into low risk, medium risk, and high risk, the low-risk level situations may include that the obstacle is far from the trunk door and there is almost no possibility of collision when opening the door, or the obstacle does not affect the opening angle of the trunk door or the smooth opening and closing of the door, or the moving obstacle, such as a pedestrian or a vehicle, is far away and moving slowly and is unlikely to enter the opening area in a short time, etc. The medium-risk level situations may include that the obstacle is relatively close to the trunk door and there is a slight possibility of collision when opening the door, or it may be necessary to reduce the opening angle or adjust the opening speed to avoid collision, or the dynamic obstacle, such as a pedestrian or a vehicle, is approaching the opening area and may affect the smooth opening of the trunk door, etc. The high-risk level situations may include that the obstacle is very close to the trunk door and a collision is almost inevitable when opening the door, which may cause damage to the trunk door or the objects around the vehicle, or the obstacle occupies most of the opening area, or the dynamic obstacle, such as a fast-approaching vehicle or pedestrian, enters the opening area and may cause an immediate collision, etc.

[0147] In a possible implementation, if the number of obstacles is multiple, then the risk level of each obstacle among the multiple obstacles can be determined according to the type and the target opening area of each obstacle among the multiple obstacles, and then the highest risk level among the risk levels of the multiple obstacles is determined as the target risk level. That is to say, the obstacles with a high-risk level have a higher priority.

[0148] Step 505, according to the preset corresponding relationship, determine the target strategy corresponding to the target risk level of the obstacle. The preset corresponding relationship is used to indicate the corresponding relationship between the multiple risk levels of the obstacle and the multiple strategies. The multiple risk levels include the target risk level, and the multiple strategies include the target strategy.

[0149] In some embodiments, the corresponding relationship between the multiple risk levels of the obstacle and the multiple strategies is stored in the vehicle in advance, as described above Figure 2As shown in Table 1 in the illustrated embodiment, if the risk level of the obstacle is L0, the corresponding control strategy is to normally open the trunk; if the risk level of the obstacle is L1, the corresponding control strategy is to normally open the trunk, and at the same time, audible and visual warnings can be attached, such as dual-frequency beeping + LED breathing light flashing; if the risk level of the obstacle is L2, the corresponding control strategy is to control the opening speed of the trunk to be reduced to 50% of the initial calibrated value; if the risk level of the obstacle is L3, the corresponding control strategy is to maintain the current opening degree of the trunk and start continuous monitoring; if the risk level of the obstacle is L4, the corresponding control strategy is to reverse stepwise to close the trunk; if the risk level of the obstacle is L5, the corresponding control strategy is to maintain the current opening degree of the trunk and trigger SOS in an emergency. Further, the vehicle determines the corresponding target strategy according to the target risk level of the obstacle and the preset corresponding relationship.

[0150] Step 506, control the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, and different risk levels correspond to different strategies.

[0151] In some embodiments, the target strategy includes any one of the following strategies: a strategy for indicating normal opening of the trunk, a strategy for indicating reduction of the opening speed of the trunk, a strategy for indicating maintaining the current opening state of the trunk unchanged, and a strategy for indicating closing of the trunk.

[0152] In some embodiments, different risk levels correspond to different strategies. Still taking the corresponding relationship between multiple risk levels and multiple strategies in the above steps as an example, if the risk level of the obstacle is L0, the target strategy is to normally open the trunk. Further, control the trunk to open normally; if the risk level of the obstacle is L1, the target strategy is to normally open the trunk, and at the same time, audible and visual warnings can be attached, such as dual-frequency beeping + LED breathing light flashing. Further, control the trunk to open normally and start audible and visual warnings; if the risk level of the obstacle is L2, the target strategy is to control the opening speed of the trunk to be reduced to 50% of the initial calibrated value. Further, control the opening speed of the trunk to be reduced to 50% of the initial calibrated value; if the risk level of the obstacle is L3, the target strategy is to maintain the current opening degree of the trunk and start continuous monitoring. Further, control the trunk to maintain the current opening degree and start continuous monitoring; if the risk level of the obstacle is L4, the target strategy is to reverse stepwise to close the trunk. Further, control to close the trunk; if the risk level of the obstacle is L5, the target strategy is to maintain the current opening degree of the trunk and trigger SOS in an emergency. Further, control the trunk to maintain the current opening degree and trigger SOS in an emergency.

[0153] In this embodiment, first, an obstacle within a preset distance range in the trunk of the vehicle is obtained through a camera module to obtain an obstacle depth map. Based on the obstacle depth map, the type of the obstacle within the preset distance range is identified to determine the type of the obstacle within the preset distance range. According to the size parameters of the trunk, the target opening area of the trunk is calculated. According to the type of the obstacle and the target opening area, the target risk level of the obstacle is determined. According to the preset corresponding relationship, the target strategy corresponding to the target risk level of the obstacle is determined. The preset corresponding relationship is used to indicate the corresponding relationship between multiple risk levels of the obstacle and multiple strategies. The multiple risk levels include the target risk level, and the multiple strategies include the target strategy. By using the camera module to obtain the obstacle depth map near the vehicle trunk, the position and size of the obstacle can be accurately captured. Each pixel value in the depth map represents the distance from the corresponding object to the camera, which can help the system identify the spatial distribution of the obstacle. Using the preset correspondence table to map the relationship between different risk levels and strategies, the role of this corresponding relationship is similar to a rule engine. According to different obstacle types and risk levels, appropriate strategies are selected. Through the real-time evaluation of the risk level and strategy feedback, the user can receive accurate prompts about the trunk status, avoiding possible accidents and enhancing the confidence in using the intelligent system. Through the analysis of the depth map data, the identification of the obstacle type, the risk assessment of the trunk, and the formulation of corresponding strategies, an intelligent, efficient, and safe solution is provided for the vehicle system, which can improve the accuracy of obstacle avoidance when controlling the trunk to open and enhance the user experience and operation convenience at the same time.

[0154] It should be understood that although each step in the above flowcharts is shown sequentially according to the arrow indication, these steps are not necessarily executed in the order indicated by the arrow. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0155] Based on the foregoing embodiments, an embodiment of the present application provides a control device for a vehicle trunk. The device includes each module included, as well as each unit included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits. During the implementation process, the processor can be a central processing unit, a microprocessor, a digital signal processor, or a field programmable gate array, etc.

[0156] Figure 6A structural schematic diagram of a control device for a vehicle trunk provided by an embodiment of the present application is shown as Figure 6 shown. The control device for the vehicle trunk includes a detection module 601, a calculation module 602, a determination module 603, and a control module 604, where:

[0157] The detection module 601 is configured to detect the type of an obstacle within a preset distance range of the trunk of the vehicle; the calculation module 602 is configured to calculate a target opening area of the trunk according to the size parameters of the trunk; the determination module 603 is configured to determine a target risk level of the obstacle according to the type of the obstacle and the target opening area; the control module 604 is configured to control the trunk of the vehicle according to a target strategy corresponding to the target risk level of the obstacle, and different risk levels correspond to different strategies.

[0158] In some embodiments, the calculation module 602 is specifically configured to calculate the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located.

[0159] In some embodiments, the calculation module 602 is specifically configured to calculate an initial opening area of the trunk according to the size parameters, and correct the initial opening area according to the inclination angle of the ground where the vehicle is located to obtain the target opening area.

[0160] In some embodiments, the determination module 603 is specifically configured to determine status information of the obstacle according to the type of the obstacle, where the status information is used to indicate the distance between the obstacle and the trunk and / or the motion state of the obstacle; and determine the risk level of the obstacle according to the status information of the obstacle and the target opening area.

[0161] In some embodiments, the determination module 603 is specifically configured to determine, when the obstacle satisfies a target preset condition during the process of the trunk opening along the target opening area, that the risk level corresponding to the target preset condition is the target risk level, and different preset conditions correspond to different risk levels.

[0162] In some embodiments, different risk levels correspond to different response durations, and the control module 604 is specifically configured to control the trunk of the vehicle according to the target strategy within the target response duration corresponding to the target risk level.

[0163] In some embodiments, the vehicle includes a camera module. The detection module 601 is specifically configured to: obtain obstacles within a preset distance range in the trunk of the vehicle through the camera module to obtain an obstacle depth map; and based on the obstacle depth map, identify the types of the obstacles within the preset distance range to determine the types of the obstacles within the preset distance range.

[0164] In some embodiments, the number of the obstacles is multiple. The determination module 603 is specifically configured to: determine the risk level of each obstacle among the multiple obstacles according to the type of each obstacle and the target opening area; and determine the highest risk level among the risk levels of the multiple obstacles as the target risk level.

[0165] In some embodiments, the type of the obstacle includes any one of a moving object, a static object, a ground depression or a water accumulation type.

[0166] In some embodiments, the target strategy includes any one of the following strategies: a strategy for instructing the normal opening of the trunk, a strategy for instructing to reduce the opening speed of the trunk, a strategy for instructing to keep the current opening state of the trunk unchanged, and a strategy for instructing to close the trunk.

[0167] In some embodiments, the determination module 603 is further configured to determine a target strategy corresponding to the target risk level of the obstacle according to a preset correspondence relationship. The preset correspondence relationship is used to indicate the correspondence relationship between multiple risk levels of the obstacle and multiple strategies. The multiple risk levels include the target risk level, and the multiple strategies include the target strategy.

[0168] The description of the above device embodiments is similar to the description of the above method embodiments and has similar beneficial effects to the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0169] It should be noted that in the embodiments of the present application Figure 6 The division of the modules of the control device for the vehicle trunk shown is illustrative, and is only a logical function division. In actual implementation, there may be other division methods. In addition, each functional unit in the various embodiments of the present application may be integrated in one processing unit, may exist separately physically, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software functional unit, or may be implemented in the form of a combination of software and hardware.

[0170] It should be noted that in the embodiments of the present application, if the above-mentioned method is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0171] The embodiments of the present application provide a computer device, which can be a server, and its internal structural diagram can be as Figure 7 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the above method.

[0172] The embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the method provided in the above embodiments.

[0173] The embodiments of the present application provide a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the steps in the method provided in the above method embodiments.

[0174] Those skilled in the art can understand that Figure 7 the structure shown in

[0175] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout. Figure 7It runs on the computer device shown. Each program module that makes up the above device can be stored in the memory of the computer device. The computer program composed of each program module enables the processor to execute the steps in the methods of the various embodiments of the present application described in this specification.

[0176] It should be noted here that the descriptions of the above storage medium and device embodiments are similar to those of the above method embodiments and have beneficial effects similar to those of the method embodiments. For the technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0177] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" or "in some embodiments" that appear throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the order of the numbers of the above processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments. The descriptions of the above embodiments tend to emphasize the differences between the embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated herein.

[0178] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, object A and / or object B can represent: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0179] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the element.

[0180] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0181] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules; they can be located in one place or distributed to multiple network units; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional module in the embodiments of the present application can be all integrated in a processing unit, or each module can be separately used as a unit, or two or more modules can be integrated in a unit; the above-mentioned integrated modules can be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0183] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), magnetic disks, or optical disks and other various media that can store program codes.

[0184] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application essentially or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable an electronic device to execute all or part of the methods described in the embodiments of the present application. And the foregoing storage medium includes: removable storage devices, ROM, magnetic disks, or optical disks and other various media that can store program codes.

[0185] The methods disclosed in several method embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0186] The features disclosed in several product embodiments provided by this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0187] The features disclosed in several method or device embodiments provided by this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0188] As mentioned above, it is only the implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A control method for a vehicle trunk, characterized in that, Applied to a vehicle, the method includes: Detecting the type of an obstacle within a preset distance range of the trunk of the vehicle; Calculating a target opening area of the trunk according to the size parameters of the trunk; Determining a target risk level of the obstacle according to the type of the obstacle and the target opening area; Controlling the trunk of the vehicle according to a target strategy corresponding to the target risk level of the obstacle, where different risk levels correspond to different strategies.

2. The method according to claim 1, wherein The calculating the target opening area of the trunk according to the size parameters of the trunk includes: Calculating the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located.

3. The method according to claim 2, characterized in that, The calculating the target opening area according to the size parameters of the trunk and the inclination angle of the ground where the vehicle is located includes: Calculating an initial opening area of the trunk according to the size parameters; Correcting the initial opening area according to the inclination angle of the ground where the vehicle is located to obtain the target opening area.

4. The method according to claim 1, characterized in that, The determining the target risk level of the obstacle according to the type of the obstacle and the target opening area includes: Determining status information of the obstacle according to the type of the obstacle, where the status information is used to indicate the distance between the obstacle and the trunk and / or the movement state of the obstacle; Determining the risk level of the obstacle according to the status information of the obstacle and the target opening area.

5. The method according to claim 4, characterized in that, The determining the risk level of the obstacle according to the status information of the obstacle and the target opening area includes: Determining that the risk level corresponding to the target preset condition is the target risk level when the obstacle meets the target preset condition during the process of the trunk opening along the target opening area according to the status information of the obstacle and the target opening area, where different preset conditions correspond to different risk levels.

6. The method according to claim 1, wherein Different risk levels correspond to different response durations. The controlling the trunk of the vehicle according to a target strategy corresponding to the target risk level of the obstacle includes: Controlling the trunk of the vehicle according to the target strategy within the target response duration corresponding to the target risk level.

7. The method according to claim 1, wherein The vehicle includes a camera module. The detecting the type of an obstacle within a preset distance range of the trunk of the vehicle includes: Obtaining an obstacle within a preset distance range of the trunk of the vehicle through the camera module to obtain an obstacle depth map; Based on the obstacle depth map, performing type recognition on the obstacles within the preset distance range to determine the types of the obstacles within the preset distance range.

8. The method according to claim 1, characterized in that, The number of the obstacles is multiple. The determining the target risk level of the obstacle according to the type of the obstacle and the target opening area includes: Determining the risk level of each of the multiple obstacles according to the type of each obstacle among the multiple obstacles and the target opening area; Determining the highest risk level among the risk levels of the multiple obstacles as the target risk level.

9. The method according to claim 1, wherein The types of the obstacles include any one of moving objects, static objects, ground depressions or water accumulation types.

10. The method according to claim 1, wherein The target strategies include any one of the following strategies: a strategy for indicating normal opening of the trunk, a strategy for indicating reduction of the opening speed of the trunk, a strategy for indicating maintaining the current open state of the trunk, and a strategy for indicating closing of the trunk.

11. The method according to claim 1, characterized in that, Before controlling the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, the method further includes: Determining a target strategy corresponding to the target risk level of the obstacle according to a preset correspondence relationship, where the preset correspondence relationship is used to indicate the correspondence relationship between multiple risk levels of the obstacle and multiple strategies, the multiple risk levels include the target risk level, and the multiple strategies include the target strategy.

12. A control device for a vehicle trunk, characterized in that, Applied to a vehicle, the device includes: A detection module, configured to detect the type of an obstacle within a preset distance range of the trunk of the vehicle; A calculation module, configured to calculate a target opening area of the trunk according to the size parameters of the trunk; A determination module, configured to determine the target risk level of the obstacle according to the type of the obstacle and the target opening area; A control module, configured to control the trunk of the vehicle according to the target strategy corresponding to the target risk level of the obstacle, where different risk levels correspond to different strategies.

13. A computer device, comprising a memory and a processor, the memory storing a computer program that can run on the processor, characterized in that, When the processor executes the program, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images