Vehicle door opening control method, device and equipment and vehicle

Abstract

The invention provides a vehicle door opening control method, device and equipment and a vehicle. The method comprises the steps that based on a target image, obstacle position information outside a target vehicle door is detected; according to the obstacle position information, the target opening degree of the target vehicle door is determined; in the process that the target vehicle door is controlled to be opened according to the target opening degree, the obstacle condition outside the target vehicle door is detected based on target radar information; and under the condition that it is determined that the obstacle collision risk exists on the vehicle door opening path according to the obstacle condition, the target vehicle door is controlled to stop opening, and the obstacle collision risk comprises the moving obstacle collision risk. The risk that the vehicle door collides with surrounding obstacles can be avoided, and efficient and reliable intelligent vehicle door control is achieved.

Description

Technical Field

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

[0002] With the development of the automotive industry and consumers' increasing demands for vehicle safety and convenience, the safety and intelligence of door opening have become important research directions. Traditional door opening methods rely primarily on manual operation, which has certain limitations and risks in many situations. For example, in confined parking spaces and complex surroundings (such as other vehicles, pedestrians, or obstacles), it is difficult for drivers or passengers to accurately determine the appropriate door opening angle, which can cause the door to collide with surrounding objects, resulting in property damage or even personal injury. Summary of the Invention

[0003] In view of this, the embodiments of the present application are dedicated to providing a door opening control method, device, equipment and vehicle, which can avoid the risk of collision between the door and surrounding obstacles and achieve efficient and reliable intelligent door control.

[0004] According to a first aspect of an embodiment of the present application, a vehicle door opening control method is provided, comprising:

[0005] Detecting obstacle position information outside the target vehicle door based on the target image; wherein the target image is acquired by an image information acquisition device provided on the vehicle, and the image information acquisition device is configured to at least acquire an image outside the target vehicle door;

[0006] determining a target opening of the target door according to the obstacle position information;

[0007] During the process of controlling the opening of the target door according to the target opening, detecting obstacles outside the target door based on target radar information; wherein the target radar information is acquired in real time by a radar information acquisition device provided on the vehicle, and the radar information acquisition device is configured to at least acquire radar information outside the target door;

[0008] When it is determined based on the obstacle situation that there is an obstacle collision risk on the door opening path, the target door is controlled to stop opening, and the obstacle collision risk includes a moving obstacle collision risk.

[0009] Optionally, detecting the position information of an obstacle outside the target vehicle door based on the target image includes:

[0010] Analyzing the target image to determine the obstacle category of the target obstacle outside the vehicle door;

[0011] The position of the obstacle is predicted according to the position prediction strategy corresponding to the obstacle category and the target image to determine the position information of the obstacle.

[0012] Optionally, detecting the position information of an obstacle outside the target vehicle door based on the target image includes:

[0013] The target image is input into a pre-trained position prediction model, and the position prediction model determines the position information of the obstacle outside the target vehicle door based on the target image.

[0014] Optionally, determining the target opening of the target door according to the obstacle position information includes:

[0015] The target opening corresponding to the obstacle position information is determined based on the obstacle position information and a first mapping relationship; wherein the first mapping relationship represents the correspondence between the door opening and the obstacle position information, and the first mapping relationship is pre-calibrated.

[0016] Optionally, when there are multiple obstacles outside the target door, determining the target opening corresponding to the obstacle position information according to the obstacle position information and the first mapping relationship includes:

[0017] Determining the door opening corresponding to each obstacle based on the position information of each obstacle outside the target door and the first mapping relationship;

[0018] Among the door openings corresponding to each obstacle, the smallest door opening is selected as the target opening.

[0019] Optionally, the method further includes:

[0020] When the vehicle state satisfies a first preset condition, acquiring a target image at a preset time interval; wherein the first preset condition represents a preset working state that allows the door to be opened;

[0021] The detecting, based on the target image, the position information of the obstacle outside the target door, and determining the target opening of the target door according to the obstacle position information, includes:

[0022] After each acquisition of the target image, detecting obstacle position information outside the target door based on the target image, and determining the real-time target opening of the target door according to the obstacle position information;

[0023] The method further comprises:

[0024] In response to receiving an opening request for the target door, the target door is controlled to be opened according to the real-time target opening degree.

[0025] Optionally, detecting an obstacle outside the target vehicle door based on target radar information includes:

[0026] Determining movement information of the moving obstacle outside the target vehicle door based on target radar information; wherein the movement information includes real-time positions of the moving obstacle and the target vehicle door and / or relative movement speed of the moving obstacle and the target vehicle door;

[0027] The method further comprises:

[0028] matching the movement information with preset collision risk assessment conditions;

[0029] When the movement information satisfies the collision risk assessment condition, it is determined that there is an obstacle collision risk on the door opening path.

[0030] According to a second aspect of an embodiment of the present application, a vehicle door opening control device is provided, comprising:

[0031] A first unit is configured to detect position information of an obstacle outside a target vehicle door based on a target image; wherein the target image is acquired by a camera provided on the vehicle, and the camera is configured to acquire at least an image outside the target vehicle door;

[0032] a second unit, configured to determine a target opening of the target door according to the obstacle position information;

[0033] a third unit configured to detect obstacles outside the target door based on target radar information during the process of controlling the opening of the target door according to the target opening; wherein the target radar information is acquired in real time by a radar provided on the vehicle, the radar being configured to at least acquire radar information outside the target door;

[0034] The fourth unit is used to control the target door to stop opening when it is determined that there is an obstacle collision risk on the door opening path based on the obstacle situation, and the obstacle collision risk includes a moving obstacle collision risk.

[0035] According to a third aspect of an embodiment of the present application, there is provided a vehicle door opening control device, comprising a memory and a processor;

[0036] The memory is connected to the processor and is used to store programs;

[0037] The processor is used to implement the vehicle door opening control method as described in any one of the first aspects of the embodiments of the present application by running the program in the memory.

[0038] According to the fourth aspect of the embodiment of the present application, a vehicle is provided, characterized in that it includes an image information acquisition device, a radar information acquisition device and a door opening control device as described in the third aspect of the embodiment of the present application; wherein the door opening control device is communicatively connected to the image information acquisition device and the radar information acquisition device respectively.

[0039] The door opening control method provided in the embodiment of the present application first identifies obstacles outside the target door through a target image, and can accurately determine the obstacle information outside the target door at the current moment, thereby calculating the optimal door opening to avoid collision between the door and the obstacle; then, during the door opening process, combined with the real-time acquired radar information, it quickly detects various collision risks such as the risk of collision with a moving obstacle on the door opening path. Once a collision risk is detected, the door opening is immediately stopped to prevent safety accidents caused by the sudden approach of dynamic obstacles.

[0040] On the one hand, this application solves the problems of poor adaptability and insufficient safety of traditional door control solutions in complex environments through the dual protection mechanism of initial static obstacle judgment + real-time monitoring of dynamic obstacles, significantly reducing the risk of collision; on the other hand, this application first opens according to a reasonable opening, and then dynamically adjusts to avoid the frustration caused by the "repeated start and stop" of the door; on the other hand, this application only needs to use image information with higher computing power to calculate the optimal opening once when the door is started, and uses radar information with smaller data volume and faster response to detect moving obstacles in real time during the door opening process, which makes the system resource allocation more reasonable and the system response speed faster. In summary, this application adopts segmented control, and through the division of labor and cooperation of "pre-judgment planning + real-time correction", it has achieved significant improvements in safety, response speed, energy efficiency and user experience, providing an efficient and reliable technical solution for intelligent door control systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0042] Figure 1 A schematic structural diagram of a vehicle provided in an embodiment of the present application.

[0043] Figure 2 A flow chart of a vehicle door opening control method provided in an embodiment of the present application.

[0044] Figure 3A flow chart of another vehicle door opening control method provided in an embodiment of the present application.

[0045] Figure 4 A schematic structural diagram of a vehicle door opening control device provided in an embodiment of the present application.

[0046] Figure 5 A schematic structural diagram of a vehicle door opening control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The technical solution of the embodiment of the present application is suitable for use in scenarios where intelligent and safe control of the vehicle door opening process is required, involving various fields such as passenger cars, commercial vehicles, special vehicles, and autonomous driving vehicles. In the application scenario, users need to use an intelligent door control system to achieve safe and convenient door opening operations. Specifically, when the vehicle needs to open the door, the technical solution of the embodiment of the present application can accurately identify static obstacles and plan the optimal opening through the collaborative working mechanism of "image pre-judgment planning + radar real-time correction", while monitoring the changes in dynamic obstacles in real time, and immediately triggering the protection mechanism when a potential collision risk is found, ensuring the safety and smoothness of the door opening process, significantly improving the safety and intelligence level of the door opening process, and optimizing the user experience and system energy efficiency, providing a reliable door control solution for the development of intelligent connected vehicles and autonomous driving technology.

[0048] The technical solution provided in the embodiments of the present application can be exemplarily applied to hardware devices such as processors, electronic devices, servers (including cloud servers), or packaged into software programs to be run. When the hardware device executes the processing of the technical solution of the embodiment of the present application, or the above-mentioned software program is run, it can achieve automatic splitting of the target task and automatic calling of the application program interface required for the task, thereby completing the purpose of the target task. The embodiments of the present application only exemplarily introduce the specific processing process of the technical solution of the present application, and do not limit the specific implementation form of the technical solution of the present application. Any technical implementation form that can execute the processing process of the technical solution of the present application can be adopted by the embodiments of the present application.

[0049] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] Before introducing this application solution, we first introduce the relevant technologies:

[0051] With the development of the automotive industry and consumers' increasing demands for vehicle safety and convenience, the safety and intelligence of door opening have become important research directions. Traditional door opening methods rely primarily on manual operation, which has certain limitations and risks in many situations. For example, in confined parking spaces and complex surroundings (such as other vehicles, pedestrians, or obstacles), it is difficult for drivers or passengers to accurately determine the appropriate door opening angle, which can cause the door to collide with surrounding objects, resulting in property damage or even personal injury.

[0052] In view of this, the embodiments of the present application are dedicated to providing a door opening control method, device, equipment and vehicle, which can avoid the risk of collision between the door and surrounding obstacles and realize efficient and reliable intelligent door control, which will be described in detail one by one in the following embodiments.

[0053] Exemplary Systems

[0054] For ease of understanding, the implementation environment of the door opening control method provided in the embodiment of the present application is first introduced as an example. Figure 1 , Figure 1 This is a structural schematic diagram of a vehicle provided in an embodiment of the present application. The door opening control method provided in the present application can be exemplarily applied to the vehicle.

[0055] like Figure 1 As shown, the vehicle 100 is provided with doors. In some scenarios, the target door 110 on the vehicle 100 needs to be automatically opened. For example, when the user sends an opening command through a smart key or a mobile phone APP, or when the vehicle detects the user approaching and automatically unlocks, or when the user triggers the door opening button or the visual virtual button in the car, or when the door detects the user's intention to open the door, it is necessary to execute the door opening control method provided in the embodiment of the present application to control the target door 110 to open automatically.

[0056] The vehicle 100 may be a traditional fuel vehicle, a pure electric vehicle, a hybrid vehicle, or an autonomous vehicle, which is not limited in this application.

[0057] The target door 110 may be any door on the vehicle 100 (such as a front door, a rear door, etc.), and its selection is based on the user's specific opening requirements or the system's preset logic.

[0058] The vehicle 100 is also provided with a door opening control system, such as Figure 1As shown, the door opening control system includes an image information acquisition device 120, a radar information acquisition device 130, and a door opening control device 140. The door opening control device 140 is communicatively connected to the image information acquisition device 120 and the radar information acquisition device 130 respectively.

[0059] The image information acquiring device 120 is configured to at least capture an image of the exterior of the target vehicle door 110 .

[0060] Optionally, the image information acquisition device 120 can be installed in various locations that can collect image information outside the target door 110, such as the door rearview mirror, the roof, or near the door handle, to ensure that the field of view covers the door opening trajectory and the surrounding area. This application does not limit this.

[0061] Optionally, the image information acquisition device 120 can be various types of image acquisition devices such as a monocular camera, a binocular camera, a wide-angle camera or a fisheye camera. It can be a visible light camera, an infrared camera, or an image acquisition device such as a camera with night vision function. This application does not limit this.

[0062] Exemplarily, image information acquisition device 120 is a wide-angle camera mounted below the vehicle's rearview mirror, in place of the vehicle's existing surround-view imaging system camera. This reuses the existing surround-view system's camera hardware resources, eliminating the need for additional equipment costs. In this example, a wide-angle camera (e.g., with a 120-degree or 180-degree field of view) is mounted below each of the vehicle's rearview mirrors. This dual-camera configuration enables intelligent door opening control for all vehicle doors. Specifically, the wide-angle camera's wide viewing angle fully covers the door opening area, with each wide-angle camera capturing images outside the corresponding door on that side.

[0063] The radar information acquiring device 130 is configured to collect radar information outside the target door 110 at least.

[0064] Optionally, the radar information acquisition device 130 can be installed at various locations such as the side of the vehicle door, the rear of the vehicle, etc., which can collect radar information outside the target vehicle door 110. This application does not limit this.

[0065] Optionally, the radar information acquisition device 130 can be various radar detection equipment such as millimeter wave radar, ultrasonic radar or laser radar, and this application does not limit this.

[0066] Exemplarily, the radar information acquisition device 130 is an ultrasonic radar installed on both sides of the rear bumper of the vehicle, installed at the position of the existing automatic parking system radar of the vehicle, and realizes its function by reusing the existing radar sensor.

[0067] The vehicle door opening control device 140 is configured to execute the vehicle door opening control method provided in an embodiment of the present application, including: detecting obstacle position information outside a target vehicle door based on a target image; wherein the target image is acquired by an image information acquisition device provided on the vehicle, the image information acquisition device being configured to at least acquire an image outside the target vehicle door; determining a target opening of the target vehicle door based on the obstacle position information; while controlling the target vehicle door to open based on the target opening, detecting obstacle conditions outside the target vehicle door based on target radar information; wherein the target radar information is acquired in real time by a radar information acquisition device provided on the vehicle, the radar information acquisition device being configured to at least acquire radar information outside the target vehicle door; and controlling the target vehicle door to stop opening if, based on the obstacle conditions, it is determined that there is a risk of collision with an obstacle on the door opening path, the risk of collision with an obstacle including a risk of collision with a moving obstacle. The specific implementation of the vehicle door opening control method will be described in the corresponding subsequent method embodiments, and reference can be made to the contents of the subsequent embodiments, and will not be described in detail here.

[0068] The door opening control device 140 can be any device or system with certain computing and processing capabilities that can perform door control operations. It can be an existing controller of the vehicle, such as a body control module (BCM), a door control unit or a vehicle controller (VCU), or it can be a separately set controller independent of the existing controller of the vehicle. It can also be an in-vehicle infotainment system or an autonomous driving computing platform or a cloud server, etc. This application does not limit the type and structure of the door opening control device 140.

[0069] It should be noted that the above-mentioned communication connection can be any communication method that can realize data transmission between devices or systems, such as wired connection (such as Ethernet, USB, etc.), wireless connection (such as Wi-Fi, Bluetooth, etc.), serial communication interface (such as UART) or other suitable communication protocols, etc., and this application does not limit this.

[0070] Exemplary Methods

[0071] Figure 2 This is a flow chart of a door opening control method provided by an embodiment of the present application. Figure 2 As shown, the door opening control method can be exemplarily applied to Figure 1 The vehicle is specifically executed by the door opening control device 140 in the vehicle, and the method includes steps S201-S204:

[0072] S201. Detecting obstacle position information outside a target vehicle door based on a target image; wherein the target image is acquired by an image information acquisition device provided on the vehicle, and the image information acquisition device is configured to at least acquire an image outside the target vehicle door.

[0073] The target door can be understood as a specific door that currently needs to be opened, such as a driver's side door, a passenger side door, or a rear door.

[0074] The target image can be understood as digital image data containing environmental information of a certain area outside the target door at the time of image acquisition, and the area covers the movement trajectory range of the target door when it is opened.

[0075] The target image not only contains static environmental features (such as walls, other parked vehicles, etc.), but may also contain dynamic elements (such as pedestrians, vehicles and other moving obstacles) at the moment of acquisition.

[0076] The target image is acquired by an image information acquisition device installed on the vehicle. The image information acquisition device (such as a camera) is specifically configured to capture at least the image outside the target door, that is, its field of view should cover the area that may be touched when the door is opened. For other relevant information about the image information acquisition device, please refer to Figure 1 The embodiments are not described in detail here.

[0077] The obstacle position information can be understood as the spatial position parameters of the obstacle relative to the target door, including but not limited to dimensional information such as distance, azimuth, and height.

[0078] Specifically, before the door is opened, an image information acquisition device is first used to capture an image of a certain area outside the target door, namely, a target image. The captured target image is then processed and analyzed to determine the location information of the obstacle.

[0079] It should be noted that step S201 is mainly aimed at determining the instantaneous spatial position information of static obstacles. When there are dynamic elements in the target image, they are treated as instantaneous spatial placeholders and processed, and only their instantaneous spatial positions are detected. That is, the process of processing and analyzing the target image to determine the obstacle position information does not involve the analysis and processing of time series information. The risk monitoring of dynamic elements (i.e., moving obstacles) is performed by steps S203 and S204.

[0080] This setup detects the location of obstacles outside the target door based on the target image. This allows the system to accurately construct a spatial distribution model of obstacles outside the target door before the door is opened. This allows for a comprehensive assessment of the environment outside the door, helping the system determine potential obstacles and their corresponding locations during door opening. Based on this information, the system can determine the safe degree to which the door can be opened, i.e., the target opening degree for the target door. By identifying obstacles in advance, the system can take appropriate measures to avoid collisions, ensuring a safe and smooth door opening process.

[0081] The specific implementation method of detecting the position information of the obstacle outside the target vehicle door based on the target image can be implemented with reference to relevant existing technologies, and this application does not limit this.

[0082] As an optional implementation, detecting the location of an obstacle outside a target vehicle door based on a target image includes: analyzing the target image to determine the obstacle category of the obstacle outside the target vehicle door; and predicting the location of the obstacle based on a location prediction strategy corresponding to the obstacle category and the target image to determine the location of the obstacle. This will be explained in subsequent embodiments and is not described in detail here.

[0083] As an optional implementation, step S201 is implemented using a model-based processing concept. In this implementation, detecting the location information of obstacles outside the target vehicle door based on the target image includes inputting the target image into a pre-trained location prediction model, and having the location prediction model determine the location information of obstacles outside the target vehicle door based on the target image. This will be explained in subsequent embodiments and will not be described in detail here.

[0084] S202: Determine a target opening of the target door according to the obstacle position information.

[0085] The target opening can be understood as the maximum degree or angle the door should open to ensure it avoids collisions with obstacles. The target opening is designed to prevent collisions while maintaining functionality and convenience.

[0086] Specifically, after determining the obstacle position information, the system will perform a series of calculations and analyses based on the obstacle position information to accurately determine the maximum opening that the target door should reach during the opening process, that is, the target opening, to avoid collision with the obstacle detected in step S201 during the door opening process.

[0087] Optionally, the system includes one or more built-in algorithms that can calculate the maximum door opening angle in real time based on obstacle location information (such as distance, direction, and shape). These algorithms may involve complex mathematical and physical principles such as geometric calculations, collision detection, and kinematic simulation to ensure the accuracy and reliability of the calculation results.

[0088] As an optional implementation method, when determining the target opening based on obstacle location information, the system can also take into account factors such as the physical size of the door, the opening method, the safety margin, the actual needs of passengers or cargo getting on and off the vehicle, and the characteristics of the obstacle.

[0089] As an optional implementation method, determining the target opening of the target door based on the obstacle position information includes: determining the target opening corresponding to the obstacle position information based on the obstacle position information and a first mapping relationship; wherein the first mapping relationship represents the correspondence between the door opening and the obstacle position information, and the first mapping relationship is pre-calibrated.

[0090] The first mapping relationship may be understood as a pre-calibrated and stored logical correspondence, which establishes a direct connection between the door opening of the target door and the obstacle position information.

[0091] The first mapping relationship is based on in-depth research and experimental data on the interaction between obstacle position and door opening during the target door opening process. Through experiments, simulations, actual measurements, or empirical data, the safe and appropriate opening degree of the target door can be determined for different obstacle positions. Calibration using this data can generate the first mapping relationship.

[0092] It should be noted that different vehicle doors interact differently with obstacles during the opening process due to differences in design, size, opening method, and installation location. Therefore, to ensure the safety and effectiveness of door opening, it is necessary to conduct experiments or measurements for each vehicle door and establish an appropriate first mapping relationship. This means that the first mapping relationship may vary for different vehicle doors and needs to be calibrated and stored based on the specific situation.

[0093] Exemplarily, the door opening of the target door is divided into multiple gears (such as 10 gears), and accurately calibrated within the actual vehicle opening range. Through the calibration process, the trajectory frame range corresponding to each gear on the ground is determined. The first mapping relationship is the correspondence between the target opening corresponding to each gear and the trajectory frame range corresponding to the gear. After determining the position information of the obstacle, based on the position information, it is possible to accurately determine which gear's trajectory frame range the obstacle is located within, thereby determining the door opening corresponding to the gear, that is, the target opening. In order to improve the robustness of the system, a certain error margin should be reserved for the trajectory frame corresponding to each gear during the calibration process. For example, it can be calibrated according to an error range of 5%.

[0094] Specifically, after the system obtains the obstacle position information outside the target vehicle door, it uses the obstacle position information as input and maps it through the first mapping relationship to quickly and accurately determine the target opening corresponding to the obstacle position information. The mapping process may involve mathematical calculations, logical judgments, or table lookup operations to determine the target door opening based on the obstacle position information.

[0095] In this implementation, by utilizing a pre-calibrated first mapping relationship, the obstacle position information is directly mapped to the target opening of the vehicle door. On the one hand, the target opening can be determined quickly and accurately, thereby improving the real-time and accuracy of the door opening control. On the other hand, the first mapping relationship can be calibrated and adjusted according to different vehicle models, door types and obstacle characteristics, and has strong flexibility.

[0096] In some scenarios, multiple obstacles may exist simultaneously outside the target door, each of which may limit the maximum opening angle of the door. As an optional implementation, when multiple obstacles exist outside the target door, determining the target door opening corresponding to the obstacle position information based on the obstacle position information and the first mapping relationship includes: determining the door opening corresponding to each obstacle based on the position information of each obstacle outside the target door and the first mapping relationship; and selecting the smallest door opening corresponding to each obstacle as the target door opening.

[0097] In this implementation, there are multiple obstacles, each of which may limit the maximum opening angle of the door. Therefore, the system needs to evaluate the impact of each obstacle on the door opening and determine an optimal target opening accordingly.

[0098] Specifically, for each obstacle, the system individually assesses its impact on door opening. Using the obstacle's location information and the first mapping relationship, the system determines the maximum angle at which the door can safely open given the presence of the obstacle, i.e., the door opening angle corresponding to the obstacle. After determining the door opening angle corresponding to each obstacle, the system selects the smallest of these opening angles as the final target opening angle, ensuring that the door maintains a safe distance from all obstacles during opening, thus avoiding collisions even in the most unfavorable scenario (i.e., the presence of the nearest obstacle).

[0099] Of course, despite selecting the minimum door opening, this opening is still as wide as possible while ensuring safety, ensuring the convenience and comfort of passengers getting on and off the vehicle. In this way, the system can effectively determine a safe and practical target opening even in the presence of multiple obstacles, significantly improving vehicle safety and user experience.

[0100] S203. In the process of controlling the opening of the target door according to the target opening, detecting obstacles outside the target door based on target radar information; wherein, the target radar information is collected in real time by a radar information acquisition device provided on the vehicle, and the radar information acquisition device is configured to collect at least radar information outside the target door.

[0101] After determining the target opening in step S202, the target door can be controlled to open according to the target opening. The specific implementation of controlling the target door to open according to the target opening can be based on relevant existing technologies and is not limited in this application. For example, a corresponding target opening instruction is generated and sent to the door actuator to drive the door actuator to open according to the specified opening.

[0102] As can be seen from the preceding, the target opening is determined based on analysis of the target image. This target image is captured instantaneously and primarily reflects the static environmental characteristics outside the target door at the moment of capture. However, during the actual door opening process, the environment changes dynamically, especially with the potential for moving obstacles (such as pedestrians, cyclists, and other vehicles) to enter the door opening path. Therefore, while controlling the target door opening according to the target opening, it is necessary to monitor the presence of obstacles outside the door in real time to ensure safe door opening.

[0103] In step S203, the target radar information can be understood as the reflected signal data of the object outside the target vehicle door collected in real time by the radar information acquisition device. After processing, these data can provide information such as the position and speed of the object.

[0104] The target radar information is collected in real time by a radar information acquisition device (such as a radar sensor) installed on the vehicle. The radar information acquisition device is specifically configured to collect radar information at least outside the target door, that is, its detection range should cover the area that may be touched when the door is opened, so as to ensure that obstacles entering the door opening path can be detected in real time. For other relevant content of the radar information acquisition device, please refer to Figure 1 The embodiments are not described in detail here.

[0105] The obstacle condition can be understood as the state of objects outside the target door detected by the radar information acquisition device, including the object's existence, location, speed, and possible movement trend. This information is crucial for assessing whether there is a collision risk during the door opening process.

[0106] Specifically, in step S203, the system receives real-time target radar information from the radar information acquisition device and processes and analyzes this information. This processing may include signal filtering, target detection, tracking, and identification to accurately identify obstacles outside the target door. By analyzing the obstacle's real-time position, speed, and shape, the system can determine whether the obstacle is likely to enter the door opening path, thereby assessing the safety of the door opening process.

[0107] As an optional implementation, the obstacle situation includes obstacle movement information, which can be understood as real-time position change and / or speed change information of the moving obstacle relative to the target door.

[0108] In this implementation, based on the target radar information, the obstacle situation outside the target vehicle door is detected, including: based on the target radar information, determining the movement information of the moving obstacle outside the target vehicle door, the movement information including the real-time position of the moving obstacle and the target vehicle door and / or the relative movement speed of the moving obstacle and the target vehicle door.

[0109] Specifically, in the process of controlling the target door to open according to the target opening, the radar information acquisition device will emit electromagnetic waves in real time and receive echoes reflected from obstacles. By processing these echo signals, key information such as the position and speed of the obstacle can be extracted.

[0110] Optionally, by continuously monitoring the radar echo, the position of the moving obstacle relative to the target door can be updated in real time. This process usually involves calculating the relative distance between the obstacle and the radar (or vehicle), as well as the specific position of the obstacle in the vehicle coordinate system (such as lateral distance, longitudinal distance).

[0111] Optionally, radar systems can measure the speed of moving obstacles using the Doppler effect. The Doppler effect is a phenomenon whereby the frequency of a wave received by an observer changes when there is relative motion between the source and the observer. In automotive radar, this frequency shift can be used to calculate the relative speed of an obstacle, including its approach or retreat.

[0112] As an optional implementation, the obstacle information may also include the location information of static obstacles. While the target image in step S201 primarily reflects the static environmental characteristics outside the target door at the time of acquisition, the real-time radar data provided by the radar information acquisition device can continuously verify and update the locations of these static obstacles. Even if the camera is obstructed or the line of sight is unclear in certain situations, radar information can still provide accurate static obstacle location information, thereby increasing the redundancy and reliability of the system's perception of the door opening environment.

[0113] As an optional implementation, the obstacle information may also include detailed information such as the obstacle's type, size, and shape. This information can be obtained through further analysis and processing of the target radar information, such as using pattern recognition techniques to identify the obstacle type (e.g., pedestrian, vehicle, etc.) or estimating the obstacle's size and shape through signal strength and analysis algorithms. This information helps the system more comprehensively assess the collision risk during the door opening process and implement appropriate obstacle avoidance measures.

[0114] After real-time monitoring of the obstacle situation through step S203, the system will match the obstacle situation with the preset collision risk assessment conditions. If the obstacle situation meets any one of the collision risk assessment conditions, the system will determine that there is an obstacle collision risk on the door opening path, and then execute step S204. If the obstacle situation does not meet the collision risk assessment conditions, the target door will be controlled to open according to the target opening, and the obstacle situation outside the target door will continue to be detected based on the target radar information.

[0115] Among them, the collision risk assessment conditions can be understood as specific standards or criteria for determining whether there is a risk of collision with an obstacle on the door opening path, which are usually pre-set based on obstacle information such as the obstacle's position, speed, acceleration, as well as the door's size, opening trajectory, etc.

[0116] The obstacle collision risk includes the risk of collision with a moving obstacle, and may also include other types of risks such as the risk of collision with a static obstacle and the dangerous encirclement situation formed by multiple obstacles.

[0117] Optionally, the collision risk assessment condition includes a safety distance threshold. When the movement information of the obstacle (such as the real-time position of the moving obstacle and the vehicle door) meets the collision risk assessment condition (i.e., it is less than the safety distance threshold), the system will consider that there is a moving obstacle collision risk. Optionally, the collision risk assessment condition also includes a relative motion speed safety threshold. When the relative motion speed of the moving obstacle and the target vehicle door meets the collision risk assessment condition (i.e., it is greater than a preset safety threshold, and its motion trajectory may intersect with the vehicle door opening path), the system will consider that there is a moving obstacle collision risk. Optionally, the collision risk assessment condition also includes a collision time threshold. When the estimated collision time calculated based on the real-time position of the moving obstacle and the relative motion speed of the moving obstacle and the target vehicle door meets the collision risk assessment condition (i.e., it is less than the collision time threshold), the system will consider that there is a moving obstacle collision risk. Optionally, the collision risk assessment criteria also include the positional relationship of static obstacles. When a static obstacle (such as a parked vehicle, roadside pillars, or trees) is detected and its relative positional relationship with the target door meets specific conditions (i.e., the static obstacle is in the door opening path or too close to the door opening path, potentially preventing the door from opening normally), the system will deem a static obstacle collision risk to exist. Optionally, the collision risk assessment criteria also include multiple obstacles forming a dangerous encirclement situation, and this application does not limit this.

[0118] S204: When it is determined based on the obstacle condition that there is an obstacle collision risk on the door opening path, controlling the target door to stop opening, wherein the obstacle collision risk includes a moving obstacle collision risk.

[0119] Once the system determines there's a risk of collision with an obstacle, it immediately generates a control command to stop the target door from opening. Upon receiving this command, the door actuator immediately takes action to stop the door from opening.

[0120] Optionally, the system can also provide user feedback, such as displaying a warning message on the instrument panel, issuing an audible alarm or a vibration reminder, to inform the driver or passenger that there is a risk of collision and that measures have been taken to stop the vehicle.

[0121] Optionally, after the door stops opening, the system should continue to monitor the obstacle situation outside the door in real time through sensors such as radar information acquisition devices to ensure that the door can be safely reopened after the risk is eliminated.

[0122] The door opening control method provided in the embodiment of the present application first identifies obstacles outside the target door through a target image, and can accurately determine the obstacle information outside the target door at the current moment, thereby calculating the optimal door opening to avoid collision between the door and the obstacle; then, during the door opening process, combined with the real-time acquired radar information, it quickly detects various collision risks such as the risk of collision with a moving obstacle on the door opening path. Once a collision risk is detected, the door opening is immediately stopped to prevent safety accidents caused by the sudden approach of dynamic obstacles.

[0123] On the one hand, this application solves the problems of poor adaptability and insufficient safety of traditional door control solutions in complex environments through a dual protection mechanism of initial static obstacle judgment + real-time monitoring of dynamic obstacles, significantly reducing the risk of collision. On the other hand, this application first opens the door at a reasonable opening and then dynamically adjusts it to avoid the frustration caused by the door's "repeated start and stop". On the other hand, this application only needs to calculate the optimal opening once when the door is started using image information with higher computing power requirements. During the door opening process, radar information with smaller data volume and faster response is used to detect moving obstacles in real time, making system resource allocation more reasonable and the system response faster. In summary, this application adopts segmented control and achieves significant improvements in safety, response speed, energy efficiency and user experience through the division of labor and cooperation of "pre-judgment planning + real-time correction", providing an efficient and reliable technical solution for intelligent door control systems. In addition, this method can be adapted to existing intelligent door systems (such as electric doors, gull-wing doors, etc.) without significantly changing the hardware architecture. It can be implemented by integrating camera and radar data (relying on existing vehicle accessories without increasing hardware costs).

[0124] As an optional implementation (this implementation introduces the obstacle category), step S201 "detecting the obstacle position information outside the target door based on the target image" includes steps A1-A2:

[0125] A1. Analyze the target image to determine the obstacle category of the target obstacle outside the vehicle door.

[0126] The obstacle categories can be understood as categories divided according to the geometric characteristics, material properties and spatial distribution characteristics of the obstacles. Different categories of obstacles correspond to different position prediction strategies.

[0127] In step A1, the system performs category analysis on the target image collected by the image information acquisition device. The analysis process may include two processes: image segmentation and target detection.

[0128] Among them, image segmentation is used to extract obstacle boundaries. By dividing the image into different areas, image segmentation can effectively identify and extract the outline of obstacles, thereby helping the system to analyze the scene more accurately. Specifically, image segmentation can distinguish obstacles from the background, more accurately extract the boundary information of obstacles, and provide basic data for subsequent processing and decision-making. Image segmentation marks areas with unique properties of static obstacles such as pillars to better identify and extract targets of interest in the image. Through image segmentation, the system can effectively eliminate background interference (such as ground texture and shadows) and retain only obstacles that may affect the opening of the door.

[0129] Optionally, a semantic segmentation algorithm (such as UNet, DeepLab) is used to perform pixel-level analysis on the image to mark the precise outlines of obstacles.

[0130] Object detection is used to determine obstacle categories. Based on image segmentation, object detection algorithms (such as YOLO and Faster R-CNN) are used to classify obstacles and determine their category. This process primarily involves matching the obstacle's image features (including shape, texture, and aspect ratio) with a predefined obstacle category library or a trained classification model. The matching results determine the obstacle category of the target vehicle door obstacle.

[0131] Optionally, the obstacle categories in step A1 are mainly distinguished based on the geometric types of the obstacles (such as square columns, cylinders, plane walls, irregular objects, interference objects, etc.). This distinction is mainly because obstacles of different geometric types require different position measurement strategies and differentiated distance measurement reference points to ensure accuracy. For example, for square column obstacles (such as right-angled walls), the distance to the bottom of the vertical edge can be directly measured, the nearest vertical edge can be identified, and the distance from the bottom of the edge to the vehicle door can be directly measured; for cylindrical obstacles (such as telephone poles and street light poles), the distance value cannot be estimated by ground projection. The tangent distance measurement method needs to be used to determine the cylinder ground contact point, and the nearest line of intersection between the vehicle end parallel line and the obstacle on the ground is used as the distance value. For spherical objects (such as round piers), the projection of the ground contact point needs to be used as the basis.

[0132] A2. Predict the position of the obstacle based on the position prediction strategy corresponding to the obstacle category and the target image to determine the position information of the obstacle.

[0133] After completing the classification, the system will select the most appropriate location measurement strategy based on the type of obstacle to calculate its location information.

[0134] Optionally, for obstacles like square columns, the edge distance method is used to locate the nearest vertical edge for distance measurement. For cylindrical obstacles, the ground tangent distance method is used to calculate the closest tangent distance between a line parallel to the vehicle body and the cylinder. For flat walls, the vertical distance between the wall and the vehicle door is directly measured. For irregular objects, the most convex point of the bottom contour is extracted as a reference point for distance measurement. This classification-driven, differentiated position prediction strategy can significantly improve the accuracy and reliability of obstacle position detection.

[0135] As an optional implementation, step S201 is implemented using a model-based processing concept. In this implementation, step S201, "Detecting the location information of obstacles outside the target vehicle door based on the target image," includes inputting the target image into a pre-trained location prediction model, and having the location prediction model determine the location information of obstacles outside the target vehicle door based on the target image.

[0136] In this implementation, a location prediction model is pre-trained.

[0137] The position prediction model can be any deep learning model suitable for image processing and object detection, such as convolutional neural network (CNN), U-Net, Faster R-CNN, etc., which is not limited in this application. A pre-trained model can be selected and fine-tuned according to the specific task to adapt to the dataset.

[0138] The position prediction model is trained using a supervised training method. Specifically, the position prediction model is trained using a first training sample.

[0139] The first training sample includes a sample image and annotated obstacle position information (label information).

[0140] Optionally, the sample images should include a variety of possible obstacle scenarios and objects to ensure the generalization ability of the model. Examples include different weather conditions (sunny, rainy, snowy, etc.), different lighting conditions (daytime, nighttime, shadows, etc.), different obstacle types (pedestrians, vehicles, animals, etc.), and different obstacle sizes and shapes. Data augmentation techniques, such as rotation and scaling, can also be used to increase the diversity of the training data and further improve the robustness of the model.

[0141] You can also consider adding data enhancement techniques, such as rotation, scaling, translation, etc., to increase the diversity of samples and improve the robustness of the model.

[0142] Optionally, the obstacle location information can be annotated by annotating the objects in each image and their corresponding depth information. Existing depth map datasets can be used as a reference, or real-world scene data can be acquired through a depth sensor. The obstacle location information can be represented as a bounding box, mask, or other form, depending on the selected model type and task requirements.

[0143] The position prediction model is trained using the first training sample, ensuring that it can generate obstacle location information corresponding to the sample image in the first training sample. The goal is to ensure that the loss function, determined by comparing the obstacle location information output by the position prediction model with the labeled obstacle location information, meets preset requirements. During training, the model parameters are continuously adjusted to minimize the loss function, thereby improving the model's accuracy in obstacle location analysis. Once the position prediction model is trained, it can be applied in real-world scenarios to detect obstacles outside the target vehicle door in real time.

[0144] This implementation leverages deep learning technology and a pre-trained position prediction model to detect the location of obstacles outside the target vehicle door. This method is efficient, accurate, and scalable, making it suitable for a variety of complex obstacle detection scenarios.

[0145] Figure 3 A flow chart of another door opening control method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method includes steps S301-S305:

[0146] S301. When a vehicle state satisfies a first preset condition, acquiring a target image at a preset time interval; wherein the first preset condition represents a preset working state that allows a vehicle door to be opened.

[0147] S302 . After each acquisition of the target image, detect obstacle position information outside the target door based on the target image, and determine the real-time target opening of the target door according to the obstacle position information.

[0148] S303 : In response to receiving a request to open the target door, controlling the target door to open according to the real-time target opening degree.

[0149] S304. In the process of controlling the opening of the target door according to the real-time target opening, the obstacle situation outside the target door is detected based on the target radar information; wherein, the target radar information is collected in real time by a radar information acquisition device provided on the vehicle, and the radar information acquisition device is configured to collect at least the radar information outside the target door.

[0150] S305: When it is determined based on the obstacle condition that there is an obstacle collision risk on the door opening path, controlling the target door to stop opening, wherein the obstacle collision risk includes a moving obstacle collision risk.

[0151] In step S301, the first pre-set conditions can be understood as a set of necessary conditions for triggering the system to begin periodic monitoring of the environment outside the vehicle door. These conditions ensure that the system operates only in a safe and appropriate working state, avoiding false triggering of the door control function when the vehicle is moving or in other dangerous situations.

[0152] Optionally, the first preset condition includes that the vehicle has come to a complete stop or the speed is lower than a certain safety threshold (such as 5 km / h), the vehicle's engine has been turned off or is idling, the target door is unlocked, the vehicle's power system is in normal operating mode, no emergency situation (such as collision, failure, etc.) is detected, etc.

[0153] For the vehicle to meet the first pre-condition, it must simultaneously meet all of the requirements listed in the first pre-condition. This means that only when the vehicle meets all of the specified conditions, including the stopped state, speed standard, and engine status, will the first pre-condition be considered met, allowing target images to be acquired at the preset interval and subsequent obstacle detection and door opening determination processes to proceed.

[0154] In step S303, the target door opening request can be understood as a legitimate opening command from any of the following sources: direct user operation via physical buttons or touchscreens, remote control signals from a smart key or mobile app, the vehicle's automatic sensing system detecting a user's approach, voice commands received by the vehicle's voice control system, or door control commands from the automated driving system. This request triggers the actual door opening action based on the most recently calculated target opening angle.

[0155] In this implementation, when the vehicle state satisfies the first preset condition, a target image is acquired at a preset time interval. Each time a target image is acquired, step S302 is executed to determine the target door's target opening based on the acquired target image. Upon receiving a request to open the target door, the target door is then controlled to open based on the most recently determined target opening. This configuration allows the system to dynamically adapt to changes in the surrounding environment. Once an opening request is received, the door opening strategy is immediately adjusted based on the latest obstacle location information to ensure operational safety. Furthermore, the target opening is determined in advance before receiving a door opening request, avoiding the waiting time associated with data collection and processing only after the request is received. This reduces response delays when opening the door, enabling "pre-heating" intelligent preparation and improving the user experience.

[0156] Exemplary devices

[0157] Corresponding to the above-mentioned vehicle door opening control method, an embodiment of the present application also provides a vehicle door opening control device. Figure 4 : is a structural diagram of a door opening control device provided in an embodiment of the present application, such as Figure 4 As shown, the vehicle door opening control device provided in the embodiment of the present application includes:

[0158] The first unit 401 is configured to detect the position information of an obstacle outside a target vehicle door based on a target image; wherein the target image is acquired by a camera provided on the vehicle, and the camera is configured to acquire at least the image outside the target vehicle door;

[0159] The second unit 402 is configured to determine a target opening of the target door according to the obstacle position information;

[0160] The third unit 403 is configured to detect obstacles outside the target door based on target radar information during the process of controlling the opening of the target door according to the target opening degree; wherein the target radar information is acquired in real time by a radar provided on the vehicle, and the radar is configured to acquire at least radar information outside the target door;

[0161] The fourth unit 404 is used to control the target door to stop opening when it is determined that there is an obstacle collision risk on the door opening path based on the obstacle situation, and the obstacle collision risk includes a moving obstacle collision risk.

[0162] The door opening control device provided in the embodiment of the present application first identifies obstacles outside the target door through a target image, and can accurately determine the obstacle information outside the target door at the current moment, thereby calculating the optimal door opening to avoid collision between the door and the obstacle; then, during the door opening process, combined with the real-time acquired radar information, it quickly detects various collision risks such as the risk of collision with a moving obstacle on the door opening path. Once a collision risk is detected, the door opening is immediately stopped to prevent safety accidents caused by the sudden approach of dynamic obstacles.

[0163] On the one hand, this application solves the problems of poor adaptability and insufficient safety of traditional door control solutions in complex environments through the dual protection mechanism of initial static obstacle judgment + real-time monitoring of dynamic obstacles, significantly reducing the risk of collision; on the other hand, this application first opens according to a reasonable opening, and then dynamically adjusts to avoid the frustration caused by the "repeated start and stop" of the door; on the other hand, this application only needs to use image information with higher computing power to calculate the optimal opening once when the door is started, and uses radar information with smaller data volume and faster response to detect moving obstacles in real time during the door opening process, which makes the system resource allocation more reasonable and the system response speed faster. In summary, this application adopts segmented control, and through the division of labor and cooperation of "pre-judgment planning + real-time correction", it has achieved significant improvements in safety, response speed, energy efficiency and user experience, providing an efficient and reliable technical solution for intelligent door control systems.

[0164] Optionally, the first unit 401 may be specifically used for:

[0165] Analyzing the target image to determine the obstacle category of the target obstacle outside the vehicle door;

[0166] The position of the obstacle is predicted according to the position prediction strategy corresponding to the obstacle category and the target image to determine the position information of the obstacle.

[0167] Optionally, the first unit 401 may be specifically used for:

[0168] The target image is input into a pre-trained position prediction model, and the position prediction model determines the position information of the obstacle outside the target vehicle door based on the target image.

[0169] Optionally, the second unit 402 may be specifically configured to:

[0170] The target opening corresponding to the obstacle position information is determined based on the obstacle position information and a first mapping relationship; wherein the first mapping relationship represents the correspondence between the door opening and the obstacle position information, and the first mapping relationship is pre-calibrated.

[0171] Optionally, when there are multiple obstacles outside the target vehicle door, the second unit 402 may be specifically configured to:

[0172] Determining the door opening corresponding to each obstacle based on the position information of each obstacle outside the target door and the first mapping relationship;

[0173] Among the door openings corresponding to each obstacle, the smallest door opening is selected as the target opening.

[0174] Optionally, the device further includes:

[0175] A fifth unit is configured to acquire a target image at a preset time interval when the vehicle state satisfies a first preset condition; wherein the first preset condition represents a preset working state in which the vehicle door is allowed to be opened;

[0176] The first unit 401 and the second unit 402 can be specifically used for:

[0177] After each acquisition of the target image, detecting obstacle position information outside the target door based on the target image, and determining the real-time target opening of the target door according to the obstacle position information;

[0178] The device further comprises:

[0179] The sixth unit is configured to, in response to receiving an opening request for the target door, control the target door to open according to the real-time target opening degree.

[0180] Optionally, the third unit 403 may be specifically used to:

[0181] Determining movement information of the moving obstacle outside the target vehicle door based on target radar information; wherein the movement information includes real-time positions of the moving obstacle and the target vehicle door and / or relative movement speed of the moving obstacle and the target vehicle door;

[0182] The device further comprises:

[0183] The seventh unit is used to match the movement information with a preset collision risk assessment condition; when the movement information meets the collision risk assessment condition, determine that there is an obstacle collision risk on the door opening path.

[0184] The vehicle door opening control device provided in this embodiment is based on the same concept as the vehicle door opening control method provided in the aforementioned embodiments of this application. It can execute the vehicle door opening control method provided in any of the aforementioned embodiments of this application and has the corresponding functional modules and beneficial effects of executing the vehicle door opening control method. For technical details not fully described in this embodiment, please refer to the specific processing content of the vehicle door opening control method provided in the aforementioned embodiments of this application and will not be repeated here.

[0185] The functions implemented by the above-mentioned first unit 401, second unit 402, third unit 403 and fourth unit 404 can be respectively implemented by the same or different processors, which is not limited in the embodiment of the present application.

[0186] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device. The processor can be a general-purpose processor, such as a CPU or a microprocessor, and the memory can be a memory within the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits. The functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units can be realized by designing the logical relationships between the components within the circuit. For another example, in another implementation, the hardware circuit can be implemented by a PLD. For example, an FPGA can include a large number of logic gate circuits. The connection relationships between the logic gate circuits are configured through a configuration file to realize the functions of some or all of the above units. All units of the above devices can be implemented entirely in the form of a processor calling software, or entirely in the form of hardware circuits, or partially in the form of a processor calling software, with the remaining parts implemented in the form of hardware circuits.

[0187] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0188] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0189] In addition, the various units in the above apparatus may be fully or partially integrated together, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the apparatus. The at least one processor may be of different types, such as a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0190] Exemplary electronic devices

[0191] Another embodiment of the present application further provides an electronic device, see Figure 5 As shown, the device includes:

[0192] Memory 200 and processor 210;

[0193] The memory 200 is connected to the processor 210 and is used to store programs;

[0194] The processor 210 is configured to implement the vehicle door opening control method disclosed in any of the above embodiments by running the program stored in the memory 200 .

[0195] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0196] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are interconnected via a bus.

[0197] A bus may include a pathway that transfers information between components of a computer system.

[0198] Processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, or the like, or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention. Alternatively, it can be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

[0199] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0200] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include program code, which includes computer operating instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash memory, etc.

[0201] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0202] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speakers, etc.

[0203] The communication interface 220 may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0204] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any vehicle door opening control method provided in the above embodiments of the present application.

[0205] An embodiment of the present application also proposes a chip, which includes a processor and a data interface. The processor reads and runs the program stored in the memory through the data interface to execute the vehicle door opening control method introduced in any of the above embodiments. The specific processing process and its beneficial effects can be found in the embodiment introduction of the above-mentioned vehicle door opening control method.

[0206] Exemplary computer program products and storage media

[0207] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the vehicle door opening control method according to various embodiments of the present application described in any of the above-mentioned embodiments of this specification.

[0208] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0209] In addition, the embodiment of the present application may also be a storage medium having a computer program stored thereon. The computer program is used by a processor to execute the steps of the vehicle door opening control method according to various embodiments of the present application described in any of the above embodiments of this specification. Specifically, the following steps may be implemented:

[0210] Step S201: Based on the target image, detect the position information of the obstacle outside the target vehicle door; wherein, the target image is acquired by an image information acquisition device provided on the vehicle, and the image information acquisition device is configured to at least acquire the image outside the target vehicle door.

[0211] Step S202: Determine the target opening of the target door according to the obstacle position information.

[0212] Step S203: In the process of controlling the opening of the target door according to the target opening, the obstacle situation outside the target door is detected based on the target radar information; wherein, the target radar information is collected in real time by a radar information acquisition device provided on the vehicle, and the radar information acquisition device is configured to collect at least the radar information outside the target door.

[0213] Step S204: When it is determined that there is an obstacle collision risk on the door opening path according to the obstacle situation, the target door is controlled to stop opening, and the obstacle collision risk includes a moving obstacle collision risk.

[0214] For the sake of simplicity, the aforementioned method embodiments are described as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0215] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant parts, reference can be made to the description of the method embodiments.

[0216] The steps in the methods of each embodiment of the present application can be adjusted in sequence, merged, and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0217] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be merged, divided, and deleted according to actual needs.

[0218] In the several embodiments provided in this application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the terminal embodiments described above are merely illustrative. For example, the division of modules or submodules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0219] The modules or submodules described as separate components may or may not be physically separate, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules may be selected to achieve the purpose of this embodiment according to actual needs.

[0220] In addition, each functional module or submodule in each embodiment of the present application may be integrated into a processing module, each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into a single module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or software functional modules or submodules.

[0221] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0222] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, software units executed by a processor, or a combination of the two. The software units may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0223] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0224] The above description of the disclosed embodiments will enable those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is to be construed in the widest manner consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle door opening control method, characterized in that: include: Detecting obstacle position information outside the target vehicle door based on the target image; wherein the target image is acquired by an image information acquisition device provided on the vehicle, and the image information acquisition device is configured to at least acquire an image outside the target vehicle door; determining a target opening of the target door according to the obstacle position information; During the process of controlling the opening of the target door according to the target opening, detecting obstacles outside the target door based on target radar information; wherein the target radar information is acquired in real time by a radar information acquisition device provided on the vehicle, and the radar information acquisition device is configured to at least acquire radar information outside the target door; When it is determined based on the obstacle situation that there is an obstacle collision risk on the door opening path, the target door is controlled to stop opening, and the obstacle collision risk includes a moving obstacle collision risk.

2. The method according to claim 1, characterized in that The detecting of the obstacle position information outside the target vehicle door based on the target image includes: Analyze the target image to determine the obstacle category of the obstacle outside the target vehicle door; The position of the obstacle is predicted according to the position prediction strategy corresponding to the obstacle category and the target image to determine the position information of the obstacle.

3. The method according to claim 1, characterized in that The detecting of the obstacle position information outside the target vehicle door based on the target image includes: The target image is input into a pre-trained position prediction model, and the position prediction model determines the position information of the obstacle outside the target vehicle door based on the target image.

4. The method according to claim 1, wherein Determining the target opening of the target door according to the obstacle position information includes: The target opening corresponding to the obstacle position information is determined based on the obstacle position information and a first mapping relationship; wherein the first mapping relationship represents the correspondence between the door opening and the obstacle position information, and the first mapping relationship is pre-calibrated.

5. The method according to claim 4, characterized in that In a case where there are multiple obstacles outside the target door, determining the target opening corresponding to the obstacle position information according to the obstacle position information and the first mapping relationship includes: Determining the door opening corresponding to each obstacle based on the position information of each obstacle outside the target door and the first mapping relationship; Among the door openings corresponding to each obstacle, the smallest door opening is selected as the target opening.

6. The method according to claim 1, characterized in that The detecting of obstacles outside the target vehicle door based on target radar information includes: Determining movement information of the moving obstacle outside the target vehicle door based on target radar information; wherein the movement information includes real-time positions of the moving obstacle and the target vehicle door and / or relative movement speed of the moving obstacle and the target vehicle door; The method further comprises: matching the movement information with preset collision risk assessment conditions; When the movement information satisfies the collision risk assessment condition, it is determined that there is an obstacle collision risk on the door opening path.

7. The method according to claim 1, characterized in that The method further comprises: When the vehicle state satisfies a first preset condition, acquiring a target image at a preset time interval; wherein the first preset condition represents a preset working state that allows the door to be opened; The detecting, based on the target image, the position information of the obstacle outside the target door, and determining the target opening of the target door according to the obstacle position information, includes: After each acquisition of the target image, detecting obstacle position information outside the target door based on the target image, and determining the real-time target opening of the target door according to the obstacle position information; The method further comprises: In response to receiving an opening request for the target door, the target door is controlled to be opened according to the real-time target opening degree.

8. A vehicle door opening control device, characterized in that: include: A first unit is configured to detect position information of an obstacle outside a target vehicle door based on a target image; wherein the target image is acquired by a camera provided on the vehicle, and the camera is configured to acquire at least an image outside the target vehicle door; a second unit, configured to determine a target opening of the target door according to the obstacle position information; a third unit configured to detect obstacles outside the target door based on target radar information during the process of controlling the opening of the target door according to the target opening; wherein the target radar information is acquired in real time by a radar provided on the vehicle, the radar being configured to at least acquire radar information outside the target door; The fourth unit is used to control the target door to stop opening when it is determined that there is an obstacle collision risk on the door opening path based on the obstacle situation, and the obstacle collision risk includes a moving obstacle collision risk.

9. A vehicle door opening control device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the vehicle door opening control method as described in any one of claims 1 to 7 by running the program in the memory.

10. A vehicle, characterized in that: It comprises an image information acquisition device, a radar information acquisition device and the vehicle door opening control device as claimed in claim 9; wherein the vehicle door opening control device is communicatively connected to the image information acquisition device and the radar information acquisition device respectively.

Images