Automatic parking method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicle intelligent control, and discloses an automatic parking method, device and equipment and a storage medium. The method comprises the steps that if it is detected that an automatic parking mode is triggered, environment information of a vehicle is obtained, and the environment information comprises an environment map and image data; determining a target parking space and a target getting-off point of the vehicle based on the environment map and the image data, so that a user gets off the vehicle at the target getting-off point; if the target parking space is the temporary parking space, the vehicle is controlled to complete automatic parking on the target parking space, and external interaction information of the vehicle is monitored; and if the external interaction information represents that a target vehicle appears, and the target vehicle is a fixed vehicle corresponding to the temporary parking space, controlling the vehicle to drive away from the temporary parking space, and re-determining a target parking space of the vehicle. According to the invention, the problem of automatic parking under complex conditions can be effectively solved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of automatic parking, and in particular to an automatic parking method and apparatus, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of autonomous driving technology and the increasing demand for intelligent parking, automated parking systems have become a key feature of modern smart cars. Existing automated parking systems utilize onboard sensors (such as ultrasonic radar, cameras, and millimeter-wave radar) to perceive the surrounding environment and, combined with vehicle control algorithms, enable vehicles to automatically park in and out of parking spaces with minimal or no human intervention.

[0003] In related technologies, since the automatic parking function usually requires users to get off the vehicle near the parking space, it brings great inconvenience to users when the parking space is far away from the pedestrian exit and freight elevator entrance. In addition, when the public parking spaces in the parking lot are full, it is impossible to provide a continuous parking solution, which affects the user experience. Summary of the Invention

[0004] To solve the above technical problems, embodiments of the present application provide an automatic parking method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of an embodiment of the present application, an automatic parking method is provided, comprising: if it is detected that an automatic parking mode is triggered, obtaining environmental information of the vehicle, the environmental information including an environmental map and image data; determining a target parking space and a target getting-off point of the vehicle based on the environmental map and the image data, so that a user can get off the vehicle at the target getting-off point; if the target parking space is a temporary parking space, controlling the vehicle to complete automatic parking at the target parking space, and monitoring external interaction information of the vehicle; if the external interaction information indicates that the target vehicle appears, and the target vehicle is a fixed vehicle corresponding to the temporary parking space, controlling the vehicle to leave the temporary parking space, and re-determining the target parking space of the vehicle.

[0006] According to one aspect of an embodiment of the present application, the above-mentioned external interaction information includes external language information, and the method further includes: performing semantic recognition on the external voice information and extracting target content in the semantic recognition result, wherein the target content includes content related to parking; if the target content represents the appearance of the target vehicle, controlling the vehicle to leave the temporary parking space and determining the target cruising strategy of the vehicle; controlling the vehicle to execute the target cruising strategy and redetermining the target parking space of the vehicle during the cruising process.

[0007] According to one aspect of an embodiment of the present application, determining the target cruise strategy of the vehicle includes: obtaining real-time environmental information of the vehicle, the real-time environmental information including real-time image data and a real-time environmental map; determining a cruising path of the vehicle based on the real-time image data and the real-time environmental map; and determining the target cruise strategy of the vehicle based on the cruising path.

[0008] According to one aspect of an embodiment of the present application, determining the target cruising strategy of the vehicle based on the cruising path includes: obtaining traffic flow data on the cruising path and a preset cruising speed threshold of the vehicle; determining the target cruising speed of the vehicle based on the traffic volume data and the preset cruising speed threshold; and determining the target cruising strategy of the vehicle based on the target cruising speed and the cruising path.

[0009] According to one aspect of an embodiment of the present application, determining the cruising path of the vehicle based on the real-time image data and the real-time environment map includes: determining a plurality of candidate cruising paths based on the real-time image data and the real-time environment map; obtaining available berth information and path access information corresponding to each of the plurality of candidate cruising paths; and determining the cruising path of the vehicle from the plurality of candidate cruising paths based on the available berth information and the path access information.

[0010] According to one aspect of an embodiment of the present application, the method also includes: if the target parking space is a public parking space, determining a target driving path for the vehicle to reach the public parking space; obtaining the parking space size of the public parking space and the vehicle size corresponding to the vehicle, and determining an automatic parking strategy for the vehicle based on the parking space size, the vehicle size and the target driving path; controlling the vehicle to execute the automatic parking strategy, and after the automatic parking strategy is completed, sending parking information carrying the target parking space to the user.

[0011] According to one aspect of an embodiment of the present application, the above method also includes: if the target parking space is a temporary parking space and it is detected that the vehicle has completed automatic parking, generating temporary parking prompt information; determining the light intensity corresponding to the environmental information based on the image data, and controlling the vehicle to project the temporary parking prompt information to the target position based on the light intensity, so as to trigger the external interaction information based on the temporary parking prompt information.

[0012] According to one aspect of an embodiment of the present application, an automatic parking device is provided, comprising: an acquisition module for acquiring environmental information of a vehicle if it is detected that an automatic parking mode is triggered, the environmental information including an environmental map and image data; a determination module for determining a target parking space and a target getting-off point of the vehicle based on the environmental map and the image data, so that a user can get off the vehicle at the target getting-off point; an interaction module for controlling the vehicle to complete automatic parking at the target parking space if the target parking space is a temporary parking space, and monitoring external interaction information of the vehicle; and a control module for controlling the vehicle to leave the temporary parking space and re-determine the target parking space of the vehicle if the external interaction information indicates the presence of a target vehicle, and the target vehicle is a fixed vehicle corresponding to the temporary parking space.

[0013] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the automatic parking method as described above.

[0014] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the automatic parking method as described above.

[0015] According to one aspect of an embodiment of the present application, a computer program product is further provided, including a computer program, which implements the steps in the automatic parking method described above when executed by a processor.

[0016] In the technical solution provided in the embodiments of the present application, by monitoring the occupancy of parking spaces, non-fixed vehicles are allowed to temporarily occupy idle vehicles and automatically vacate the space when fixed vehicles return, thereby improving the turnover rate of parking spaces in the parking lot. The target get-off point is determined through environmental maps and image data, reducing the risk of door opening accidents for users, improving the convenience and safety of users getting off the vehicle, and after leaving the temporary parking space, the target parking space is re-planned and a continuous parking solution is provided, which can effectively solve the problem of automatic parking in complex situations and improve the user experience.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and it is clear that a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort.

[0019] Figure 1 FIG. 1 is a schematic diagram showing an implementation environment for automatic parking according to an exemplary embodiment of the present application.

[0020] Figure 2 1 is a flow chart of an automatic parking method shown in an exemplary embodiment of the present application.

[0021] Figure 3 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0022] Figure 4 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0023] Figure 5 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0024] Figure 6 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0025] Figure 7 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0026] Figure 8 FIG. 4 is a flowchart of an automatic parking method shown in another exemplary embodiment of the present application.

[0027] Figure 9 The figure is a simplified flowchart of automatic parking in an exemplary application scenario.

[0028] Figure 10 It is a block diagram of an automatic parking device shown in an exemplary embodiment of the present application.

[0029] Figure 11 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0031] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0032] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0033] In this application, "plurality" refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0034] First, it's important to note that Automated Parking Assist (APA) is an intelligent system that uses onboard sensors (such as ultrasonic radar, cameras, and millimeter-wave radar) to perceive the surrounding environment and, combined with vehicle control algorithms, enables the vehicle to automatically park in and out of a parking space with minimal or no human intervention. This feature significantly improves parking convenience and safety, and is particularly useful in narrow spaces, complex parking environments, or for drivers with inexperienced parking skills.

[0035] Figure 1 This is a schematic diagram of a real-time environment for automatic parking during vehicle operation, as shown in an exemplary embodiment of the present application. Figure 1As shown, during the driving process of the vehicle, after the intelligent terminal 110 detects that the automatic parking mode of the vehicle is triggered, it can obtain the environmental information of the vehicle, wherein the environmental information of the vehicle includes an environmental map and image data. Then, the intelligent terminal 110 can determine the target parking space and target drop-off point of the vehicle based on the environmental map and image data, so that the user can get off at the target drop-off point. Then, after judgment, if the target parking space is a temporary parking space, the intelligent terminal 110 controls the vehicle to complete automatic parking at the target parking space and turns on the vehicle's sound pickup function to monitor the vehicle's external interaction information. If the external interaction information indicates the presence of the target vehicle, wherein the target vehicle is a fixed vehicle corresponding to the temporary parking space, the intelligent terminal 110 controls the vehicle to leave the temporary parking space and re-determines the target parking space corresponding to the vehicle. This provides a continuous automatic parking solution for the vehicle.

[0036] in, Figure 1 The smart terminal 110 shown can be any terminal device that supports data processing and vehicle control, such as a smart phone, an in-vehicle computer, a tablet computer, a laptop computer, or a wearable device, but is not limited thereto.

[0037] With the rapid development of autonomous driving technology and the increasing demand for intelligent parking, automated parking systems have become a key feature of modern smart cars. Existing automated parking systems utilize onboard sensors (such as ultrasonic radar, cameras, and millimeter-wave radar) to perceive the surrounding environment and, combined with vehicle control algorithms, enable vehicles to automatically park in and out of parking spaces with minimal or no human intervention.

[0038] In related technologies, since the automatic parking function usually requires users to get off the vehicle near the parking space, it brings great inconvenience to users when the parking space is far away from the pedestrian exit and freight elevator entrance. In addition, when the public parking spaces in the parking lot are full, it is impossible to provide a continuous parking solution, which affects the user experience.

[0039] The above-mentioned problems are generally applicable to common parking scenarios. To address these problems, the present invention provides an automatic parking method, an automatic parking device, an electronic device, a computer-readable storage medium, and a computer program product, which are described in detail below.

[0040] See also Figure 2 , Figure 2 This is a flow chart of an automatic parking method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1The implementation environment shown is specifically executed by the smart terminal 110 in the implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0041] like Figure 2 As shown, in an exemplary embodiment, the automatic parking method includes at least steps S210 to S240, which are described in detail as follows: In step S210 , if it is detected that the automatic parking mode is triggered, the vehicle's environment information is obtained, where the environment information includes an environment map and image data.

[0042] For example, in parking lots in shopping malls, office buildings, or residential areas, the system uses a map of the surroundings to identify available parking spaces. Combined with image data, the system verifies that the parking spaces are clearly marked and clear of obstacles, and automatically plans a parking route. The user can actively activate the automatic parking function via the central control screen, voice command, or physical button, or the system can automatically trigger the automatic parking mode based on preset conditions (such as low speed or approaching a parking space). If the vehicle has stored map data for the target parking lot (such as parking space layout and aisle width) in the on-board navigation system or cloud, the system directly uses that map. If a pre-stored map is unavailable, the vehicle uses SLAM (Simultaneous Localization and Mapping) technology, combined with lidar, millimeter-wave radar, or ultrasonic sensors, to scan the surrounding environment in real time and generate a local map. The environmental map includes information such as parking space location (e.g., parallel, perpendicular, or diagonal), aisle width, and obstacle locations (e.g., pillars, other vehicles). The vehicle activates its surround-view camera (360° panoramic camera), front-view camera, rear-view camera, and side-view cameras to capture real-time images of the surrounding environment. Image data includes visual information such as parking space lines, ground markings (such as arrows and text), surrounding vehicles, pedestrians, and low obstacles (such as curbs and cones). Computer vision algorithms (such as edge detection and semantic segmentation) analyze the images to extract key information (such as parking space boundaries and obstacle outlines).

[0043] Step S220 : determining a target parking space and a target getting-off point for the vehicle based on the environment map and the image data, so that the user can get off the vehicle at the target getting-off point.

[0044] For example, the environment map (such as a LiDAR point cloud or a local map generated by SLAM) is spatially and temporally aligned with the image data (images captured by the camera) to ensure that their coordinate systems are consistent. Data fusion can also be achieved through sensor calibration parameters (such as camera internal and external parameters and the spatial transformation matrix between the radar and camera). Potential parking spaces are identified based on geometric features in the environment map (such as rectangular areas and parallel lines) and parking space lines in the image data (such as white or yellow markings). Parking spaces are further classified (parallel, perpendicular, or diagonal) using machine learning algorithms (such as YOLO and Faster R-CNN) or traditional image processing (such as Hough transform line detection). Obstacle information in the environment map (such as other vehicles and pillars) and dynamic objects in the image data (such as pedestrians and moving vehicles) are combined to determine parking space availability. Parking spaces that are occupied or have insurmountable obstacles are excluded. Target parking spaces are selected from the available spaces based on pre-set criteria (such as closest distance, shortest path, and highest safety).

[0045] In scenarios where multiple parking spaces are available, priority can be given to spaces closest to entrances or elevators, or to spaces that avoid narrow aisles. Based on the type and location of the target parking space, potential drop-off point candidates are generated. For parallel parking spaces, the target drop-off point can be selected behind or to the side of the space to avoid conflicts with adjacent vehicles or obstacles. For perpendicular spaces, the target drop-off point may be selected in front of or to the side of the space, ensuring sufficient clearance for the door to open. For angled spaces, the target drop-off point is determined based on the inclination angle of the space and the surrounding environment. For example, the safety of the candidate drop-off point can be assessed using environmental maps and image data. Specifically, the target drop-off point must avoid road edges, deep potholes, and low obstacles (such as curbs and fire hydrants), and ensure that there are no dynamic obstacles (such as pedestrians or bicycles) near the drop-off point. The location of the target parking space and the target drop-off point can also be displayed to the user via the vehicle's display or AR-HUD. This visualization includes the parking space boundaries, drop-off point markings, and the parking path.

[0046] Step S230: If the target parking space is a temporary parking space, the vehicle is controlled to complete automatic parking at the target parking space, and external interaction information of the vehicle is monitored.

[0047] For example, if the target parking space is a temporary parking space, the environmental map and image data of the parking location can be used to determine whether it is a temporary parking space. Temporary parking space characteristics may include: no clear parking space markings or blurred markings (such as temporary roadside parking areas); significant dynamic changes in the surrounding environment (such as frequent pedestrian and non-motorized vehicle traffic); and the absence of fixed obstacles (such as cones, temporary roadblocks) or movable obstacles. Alternatively, through license plate recognition, if the parking space has a license plate (such as a private parking space temporarily available), the legitimacy of the parking space is confirmed through license plate recognition technology (OCR). Combined with historical data or cloud information, the temporary availability of the parking space is verified (such as data from a shared parking platform). Furthermore, if the parking space has a license plate but no vehicle is parked, further confirmation is required to determine whether temporary use is permitted (such as through parking space management rules or user authorization).

[0048] After determining that a temporary parking space is available for parking, a parking path can be planned based on the location and environmental information of the temporary parking space. The parking path needs to avoid surrounding obstacles (such as pillars, other vehicles) and dynamically adjust the path during parking to cope with temporary environmental changes (such as the sudden appearance of pedestrians). Through camera and radar data, ensure that the vehicle is parked in the center of the parking space or a designated location. After the vehicle is parked, the distance between the vehicle and the surrounding boundary must meet a safety threshold (such as ≥20cm). Optionally, during the parking process, the system can display the real-time path and parking space status to the user, and the user can confirm through the screen or voice. Through sensors such as cameras, radars, lidars, and voice sensors, the vehicle's external environment is monitored in real time, and external interaction information corresponding to the external environment is obtained.

[0049] In step S240 , if the external interaction information indicates that the target vehicle appears and the target vehicle is a fixed vehicle corresponding to the temporary parking space, the vehicle is controlled to leave the temporary parking space and the target parking space of the vehicle is re-determined.

[0050] For example, a vehicle parked in a temporary parking space continuously monitors external interaction information. This external interaction information may include notifications from the parking management system (e.g., a stationary vehicle is about to return), on-board sensors detecting surrounding vehicle activity (e.g., a stationary vehicle entering the parking lot), and external voice commands received by the vehicle's audio pickup device (e.g., a stationary vehicle returning and requesting the vehicle to leave). Specifically, based on the monitored external interaction information, the vehicle determines whether the target vehicle (the stationary vehicle corresponding to the temporary parking space) has appeared. This determination may be based on information such as the vehicle identification code, license plate number, and user authentication. Once the target vehicle has been confirmed, the vehicle immediately initiates the process for exiting the temporary parking space. The vehicle safely exits the temporary parking space by following a pre-set exit route or a re-planned route based on real-time circumstances. After exiting the temporary parking space, the vehicle searches for and determines a new target parking space. This search process may involve communication with the parking management system and environmental sensing by on-board sensors. After determining the new target parking space, the vehicle re-executes the automated parking process (e.g., the automated parking process described in the aforementioned embodiment).

[0051] In an embodiment of the present application, upon detecting that the automatic parking mode has been triggered, the system rapidly acquires information about the vehicle's surroundings, including environmental maps and image data, ensuring that it can make reasonable decisions based on the real-time environment. Subsequently, the system determines the vehicle's target parking space and target exit point based on this environmental information. This not only considers parking convenience but also takes into account the safety and comfort of the user when exiting the vehicle, thereby enhancing the user experience. Furthermore, if the target parking space is a temporary space, the system continuously monitors the vehicle's external interaction information after completing automatic parking, enabling it to promptly detect the presence of the temporary space owner (i.e., the target vehicle) and proactively control the vehicle's departure, avoiding potential disputes or inconveniences. Finally, the system can re-determine the target parking space. This dynamic adjustment capability ensures that the vehicle can find a suitable parking location in any situation, improving parking flexibility and efficiency.

[0052] Further, based on the above embodiment, please refer to Figure 3 In one exemplary embodiment provided in this application, the external interaction information includes external voice information. The specific implementation process of the automatic parking method may further include steps S310 to S330, which are described in detail as follows: Step S310: performing semantic recognition on the external voice information and extracting target content from the semantic recognition result, wherein the target content includes parking-related content; Step S320: If the target content indicates that the target vehicle appears, the vehicle is controlled to leave the temporary parking space and a target cruising strategy of the vehicle is determined; Step S330: Control the vehicle to execute the target cruising strategy and re-determine the target parking space of the vehicle during the cruising process.

[0053] For example, multiple high-sensitivity microphones are installed in a vehicle, distributed at various locations (such as the front, rear, and near the doors) to capture voice information from the surrounding environment. These microphones must have excellent anti-interference capabilities and be able to filter out ambient noise such as wind noise and engine noise. When the vehicle is in a specific state (such as parked in a temporary parking space with the voice monitoring function enabled), the microphones continuously collect external voice data and transmit the data in real time to the vehicle's voice processing module. Signal enhancement technologies, such as adaptive beamforming algorithms, are used to fuse the voice signals collected by multiple microphones, enhancing the strength of the target voice signal, suppressing interfering signals from other directions, and improving voice clarity and intelligibility. The preprocessed voice signal is input into a speech recognition engine, which uses deep learning models (such as those based on recurrent neural network-long short-term memory (RNN-LSTM) or Transformer architecture) to perform speech-to-text conversion. These models, trained with extensive voice data, can accurately recognize speech with different accents, speaking speeds, and intonations, and convert them into corresponding text information. Semantic analysis is then performed on the text information generated by the speech-to-text conversion. Natural language processing (NLP) techniques, such as semantic understanding algorithms based on word embeddings and deep learning models, are used to map words in the text into a low-dimensional vector space, capturing the semantic relationships between words. Based on the semantic recognition results, target content related to parking is extracted from the text. If the semantic recognition results indicate that the text contains information related to the presence of the target vehicle (such as phrases such as "The stationary vehicle has returned," "The owner of this vehicle has arrived," "This is my parking space," or "Please leave my parking space"), this information is extracted as target content. Once the target vehicle is detected, the vehicle's central control system immediately initiates the process of exiting the temporary parking space. First, the system plans a safe and efficient exit path based on the vehicle's current position, surrounding environment, and a pre-set exit path planning algorithm. The vehicle's powertrain, steering system, and braking system are coordinated to control the planned path. The powertrain provides appropriate driving force for smooth vehicle launch; the steering system precisely controls the vehicle's direction to avoid collisions with other vehicles or obstacles; and the braking system applies braking when necessary to ensure safe driving. During the drive, the vehicle continuously monitors its surroundings, acquiring real-time information about the location and movement of surrounding objects through onboard sensors (such as cameras, radar, and lidar). If a potential hazard (such as a pedestrian or other vehicle) is detected, the system immediately adjusts the vehicle's driving state and takes evasive or braking measures.

[0054] Optionally, in some feasible embodiments, after leaving a temporary parking space, the vehicle enters a cruise mode. During this mode, the vehicle utilizes multiple sensors to comprehensively perceive the surrounding environment, including information such as parking space distribution within the parking lot, vehicle trajectories, and pedestrian movements. Sensor fusion technology integrates and processes data from various sensors to improve the accuracy and reliability of environmental perception. For example, visual information from cameras can be integrated with distance and speed information from radar to provide a more comprehensive understanding of the state of surrounding objects. A targeted cruise strategy is planned based on the environmental perception results and the vehicle's current status (such as remaining battery power and range). Targeted cruise strategies may include the following: shortest path cruise: This strategy seeks the nearest available parking space to the current location and plans the shortest driving route to quickly reach the target parking space; low-energy cruise: This strategy considers the vehicle's energy consumption and plans a cruise path with the lowest energy consumption, prioritizing sections with gentler slopes and less resistance; and safety-first cruise: In complex parking environments or those with numerous potential hazards, this strategy plans a safest cruise path, avoiding crowded areas and areas prone to collisions. When planning a target cruise strategy, the vehicle also considers parking lot regulations (such as one-way driving and designated access areas) to ensure compliance with these requirements. During the cruise, the vehicle uses onboard sensors to search for available parking spaces in real time. These sensors detect information such as space size, location, and occupancy. When an available space is found, the vehicle evaluates it, selecting the most suitable target space based on factors such as distance, convenience, and safety.

[0055] In the embodiments of this application, semantic recognition of external voice information is performed, and target content related to parking is precisely extracted. This enables accurate understanding of key information in the external environment, particularly voice commands or notifications related to parking rights, thus providing a strong basis for subsequent decision-making. Furthermore, when the target content clearly indicates the presence of the target vehicle (i.e., the owner of the temporary parking space), the system can quickly respond and control the vehicle to leave the temporary parking space, effectively avoiding disputes that may arise from occupying other people's parking spaces and ensuring harmonious parking order. Furthermore, by implementing a targeted cruising strategy, the vehicle can efficiently and orderly maneuver through complex environments, seeking new parking opportunities. Ultimately, the target parking space is re-determined during the cruising process, ensuring that the vehicle remains in a suitable parking state, thus meeting the user's parking needs and improving the utilization of parking resources.

[0056] Further, based on the above embodiment, please refer to Figure 4 In one of the exemplary embodiments provided in this application, the specific implementation process of determining the target cruise strategy of the vehicle may further include steps S410 to S430, which are described in detail as follows: Step S410, obtaining real-time environmental information of the vehicle, the real-time environmental information including real-time image data and a real-time environmental map; Step S420, determining a cruising path of the vehicle based on the real-time image data and the real-time environment map; Step S430: determining a target cruising strategy for the vehicle based on the cruising path.

[0057] For example, a vehicle continuously captures visual information of its surroundings using a system of high-definition cameras (front, rear, side, and surround view cameras) deployed in various locations on the vehicle, generating a 360-degree panoramic image data stream. Simultaneously, an onboard high-precision positioning system (such as RTK-GPS) and an inertial measurement unit (IMU) provide real-time data on the vehicle's position, posture, and motion. Using SLAM (Simultaneous Localization and Mapping) technology, this real-time point cloud data (from lidar) is dynamically fused with pre-stored high-precision maps. The HD map contains static information such as road geometry, traffic signs, and lane markings, while the real-time point cloud data supplements the instantaneous position and motion trends of dynamic obstacles (other vehicles, pedestrians, etc.), forming a four-dimensional map of the environment that includes a temporal dimension. Deep learning processing is performed on the real-time image data, using convolutional neural networks (such as YOLO or ResNet variants) to identify and classify road users (vehicles, pedestrians, bicycles, etc.), traffic light status, and traversable areas. Furthermore, this data is combined with the road topology in the environment map to generate scene understanding results containing semantic information. Based on the results of scene understanding, the path planning module identifies multiple candidate feasible paths on the raster representation of the environmental map. It then performs secondary optimization on the initially generated feasible paths, predicts the motion trajectories of surrounding obstacles within a short time window, and adjusts the vehicle's path accordingly to generate a smooth and executable cruising path. The vehicle's target cruising strategy is then determined based on the cruising path and the current traffic situation.

[0058] In some embodiments of the present application, real-time environmental information of the vehicle is obtained, including real-time image data and real-time environmental maps, to ensure that the environmental conditions around the vehicle can be fully and instantly understood, providing a rich and accurate data basis for subsequent path planning. Then, based on this real-time information, the vehicle's cruising path can be intelligently determined. This path not only takes into account the physical layout of the current environment, but may also incorporate dynamic factors such as traffic flow and obstacle distribution, thereby ensuring the feasibility and efficiency of the path. Finally, a target cruising strategy is further formulated based on the determined cruising path. This strategy may include speed control, steering timing, obstacle avoidance strategy and other aspects, aiming to guide the vehicle to travel safely and smoothly along the cruising path, so that automatic parking can autonomously plan the optimal driving plan in a complex and changing environment, which not only improves the automation level of the parking process, but also greatly enhances the adaptability and robustness, bringing users a more convenient and safe parking experience.

[0059] Further, based on the above embodiment, please refer to Figure 5 In one of the exemplary embodiments provided in this application, the specific implementation process of determining the target cruise strategy of the vehicle based on the cruise path may further include steps S510 to S530, which are described in detail as follows: Step S510, obtaining traffic flow data on the cruising path and a preset cruising speed threshold of the vehicle; Step S520, determining a target cruising speed of the vehicle based on traffic flow data and a preset cruising speed threshold; Step S530: determining a target cruising strategy for the vehicle based on the target cruising speed and the cruising path.

[0060] For example, first, it is necessary to collect real-time traffic flow data on the vehicle's current cruising path, including but not limited to: parking lot type (open-air parking lot, indoor parking lot, underground parking lot, etc.) parking lot layout: parking space distribution, aisle width, entrance and exit locations; dynamic obstacles: pedestrians, other vehicles (moving or parked), carts, etc.; vacant parking space information: the location and size of available parking spaces are obtained through sensors or parking lot management; preset cruising speed threshold: usually set to an extremely low speed (such as 2-5km / h) to ensure the safety of the parking process; at the same time, the vehicle's preset cruising speed threshold, that is, the maximum and minimum safe cruising speeds allowed for the vehicle, needs to be obtained. The target cruising speed is dynamically adjusted based on the parking lot environment and preset thresholds. For example, in an open passage, if the path is clear and there is ample space, the vehicle can approach the preset maximum threshold (e.g., 5 km / h). In a narrow area, the speed needs to be significantly reduced (e.g., 1-2 km / h) at turns, next to pillars, or when the distance between adjacent vehicles is small. When an obstacle approaches, the vehicle immediately decelerates to a near-stationary state when a pedestrian or vehicle approaches. Safety redundancy is also required: a speed buffer is always retained to ensure sufficient time to respond to emergencies (e.g., a child suddenly running out).

[0061] The vehicle's target cruising speed and cruising path can then be used to determine its target cruising strategy. These strategies include: constant-speed cruising (maintaining a low, stable speed on straight roads without interference); segmented deceleration (gradually reducing speed before entering a curve or parking space); and a start-stop strategy (pausing upon encountering pedestrians or oncoming vehicles, and resuming after safety). Furthermore, during parking in / out, the vehicle uses cameras or radar to precisely align with parking space lines, adjusting direction and speed. If the initial parking attempt is unsuccessful, a "parking maneuver" (small forward / backward adjustments) is automatically performed.

[0062] In some embodiments of the present application, traffic flow data along the cruise path is acquired. This data reflects the current traffic conditions on the road, including key information such as traffic volume and speed distribution, providing real-time, dynamic traffic environment awareness. Furthermore, combined with the vehicle's preset cruise speed threshold, the cruise speed can be flexibly adjusted based on actual traffic conditions while ensuring driving safety, avoiding traffic risks or inefficiencies caused by excessive or insufficient speed. Furthermore, the target cruise speed determined based on the traffic flow data and the preset cruise speed threshold not only takes into account real-time changes in the traffic environment, but also takes into account the vehicle's own performance limitations and the user's travel needs, achieving a balance between speed and efficiency. Finally, based on the determined target cruise speed and cruise path, a more accurate and efficient target cruise strategy is developed. This strategy can guide the vehicle to travel safely and smoothly in complex traffic environments, effectively improving the overall performance and user experience of automated parking.

[0063] Further, based on the above embodiment, please refer to Figure 6In one of the exemplary embodiments provided in this application, the specific implementation process of determining the cruising path of the vehicle based on the real-time image data and the real-time environment map may further include steps S610 to S630, which are described in detail as follows: Step S610, determining a plurality of candidate cruise paths based on the real-time image data and the real-time environment map; Step S620: Obtain available berth information and path access information corresponding to each of the plurality of candidate cruise paths; Step S630 : determining a cruising path of the vehicle from a plurality of candidate cruising paths based on the available berth information and the path access information.

[0064] Continuing with the above-mentioned embodiments, the vehicle captures real-time images of the parking lot using an onboard camera, identifying parking space lines, obstacles, pedestrians, and so on. Alternatively, the vehicle can combine pre-stored high-precision maps or dynamically updated parking lot maps to annotate fixed structures (such as pillars and walls) and known parking spaces. Image recognition or parking management system data is used to determine whether there are vacant parking spaces at the end of the route or along the route. Compatible spaces are selected, taking into account vehicle size (e.g., SUVs require spacious spaces). Dynamic and static obstacles such as parked vehicles, pedestrians, and shopping carts are avoided. Then, based on a pre-set algorithm or similar method, several feasible paths (e.g., straight-ahead paths, paths around pillars, etc.) are generated from the current location to the target area. The vehicle then evaluates the safety of each of the candidate cruising paths (e.g., allowing at least 30 cm of margin), checks whether sharp bends in the path fit within the vehicle's minimum turning radius, and estimates the path length, estimated travel time, and congestion risk (e.g., in areas with multiple vehicles). Based on available parking spaces and traffic information, the final route is selected using the following logic. Priority sorting can be used, for example, based on parking availability: routes with available spaces at the end of the route are prioritized. Route safety: routes with narrow passages or sharp turns are excluded. Specifically, under the premise of safety, the route with the shortest distance or the fewest obstacles is selected. If multiple paths lead to available parking spaces, the path with fewer turns or longer straight sections is selected. If path A has more parking spaces but path B is closer, the decision can be made based on user preferences (e.g., prioritizing parking difficulty).

[0065] In some embodiments of the present application, multiple candidate cruising paths are determined based on real-time image data and a real-time environmental map. This leverages the dual advantages of visual perception and environmental modeling, ensuring comprehensive and diverse path planning and providing a rich set of options for subsequent route selection. Next, available parking space information and route traffic information corresponding to each candidate path are obtained. This information directly correlates to the practicality and feasibility of the path and is a key indicator for evaluating the quality of the path. By collecting this information, an in-depth quantitative analysis of each path can be performed to more accurately determine whether it meets the vehicle's parking needs. Finally, based on the available parking space information and route traffic information, the optimal cruising path is intelligently selected from the multiple candidate paths. This path not only considers parking space availability but also takes into account route traffic efficiency, ensuring that the vehicle can reach the appropriate parking space in the shortest time and safest route. Through the implementation of this series of features, automated parking can quickly and accurately plan the optimal cruising path in complex and changing environments, effectively improving the success rate and efficiency of parking, while also enhancing adaptability and robustness, providing users with a more intelligent and convenient parking experience.

[0066] Further, based on the above embodiment, please refer to Figure 7 In one of the exemplary embodiments provided in this application, the specific implementation process of the automatic parking method may further include steps S710 to S730, which are described in detail as follows: Step S710: If the target parking space is a public parking space, determine a target driving path for the vehicle to reach the public parking space; Step S720: Obtain the parking space size of the public parking space and the vehicle size corresponding to the vehicle, and determine the automatic parking strategy of the vehicle based on the parking space size, the vehicle size, and the target driving path; Step S730: Control the vehicle to execute the automatic parking strategy, and after the automatic parking strategy is completed, send parking information containing the target parking space to the user.

[0067] For example, the vehicle's onboard camera or parking management system confirms the availability of the public parking space selected by the user (e.g., no occupied vehicles, no no-parking signs). If the target parking space is occupied, the user is prompted to reselect or automatically searches for nearby available spaces. A driving route is planned from the current location to the target parking space based on a real-time environmental map and sensor data. This route must avoid obstacles (e.g., other vehicles and pedestrians) and prioritize routes with more straights and fewer turns to improve efficiency. The dimensions (length, width, and depth) of the target parking space are obtained from a parking database or image recognition. The vehicle's dimensions are compared (using onboard sensors or preset data) to ensure the space can accommodate the vehicle (e.g., space length ≥ vehicle length + 50cm margin). The parking angle is determined based on the orientation of the parking space (perpendicular, parallel, or diagonal) (e.g., reverse parking is required for perpendicular spaces). The route can also be designed in segments: During the approach phase, the vehicle approaches the parking space at a low speed, maintaining a safe distance (e.g., 1 meter). During the adjustment phase, the vehicle's alignment with the parking space is gradually corrected using steering and braking. During the parking phase, the vehicle is reversed into the parking space at an extremely low speed (e.g., 2 km / h), and the distance between the rear of the vehicle and obstacles is monitored in real time. A certain degree of safety redundancy needs to be set, for example, pausing at key operating points (e.g., when the steering wheel is fully turned) and continuing after confirming that there is no risk of collision. During the automatic parking process, sensor data (e.g., ultrasonic radar, camera) is monitored in real time, and the path is dynamically adjusted to cope with sudden obstacles (e.g., pedestrians who suddenly appear). When the vehicle is completely parked in the parking space and all four wheels are within the parking space lines, parking is considered successful. If multiple attempts fail (e.g., 3 times), the user is prompted to take over or select another parking space. Parking information is sent to the user via the in-vehicle screen or mobile phone app, including: parking space number (e.g., No. 123, Zone A), parking completion time, and optional additional information (e.g., walking path and distance from the parking space to the elevator).

[0068] In the embodiments provided herein, when a target parking space is determined to be a public parking space, a target driving path for the vehicle to reach the space is first planned. This step ensures the vehicle can efficiently and accurately reach the parking location, avoiding delays or errors caused by improper path planning. Next, the system obtains the dimensions of the public parking space and the vehicle itself. Based on this key data and the target driving path, an automatic parking strategy for the vehicle is intelligently determined. This strategy not only considers the size match between the parking space and the vehicle, but may also incorporate factors such as the vehicle's dynamic characteristics and turning radius, ensuring the accuracy and safety of the parking process. This strategy formulation provides personalized parking solutions for different parking spaces and vehicles, significantly improving parking success rates. Finally, after the automatic parking strategy is successfully executed, a parking notification is sent to the user with detailed information about the target parking space. This not only allows users to be informed of the parking results in a timely manner, but also facilitates subsequent search and departure, enhancing practicality and user-friendliness.

[0069] Further, based on the above embodiment, please refer to Figure 8 In one of the exemplary embodiments provided in this application, the specific implementation process of the automatic parking method may further include steps S810 and S820, which are described in detail as follows: Step S810: If the target parking space is a temporary parking space and the vehicle is detected to have completed automatic parking, a temporary parking prompt message is generated; Step S820: determining the light intensity corresponding to the environmental information based on the image data, and controlling the vehicle to project the temporary parking prompt information to the target location based on the light intensity, so as to trigger external interaction information based on the temporary parking prompt information.

[0070] For example, an on-board camera or sensor detects whether the target parking space is a temporary one (e.g., a time-limited curbside parking space or a shared parking space). The vehicle confirms that the space has no fixed occupancy markers (e.g., a private parking lock) and complies with temporary parking regulations (e.g., time limits). Automatic parking is considered complete when the vehicle is fully parked in the space, with all four wheels aligned with the parking space lines. If an obstacle or malfunction is detected during parking, the system immediately pauses, prompts the user to intervene, and generates a temporary parking reminder message. This reminder message may include key information such as the license plate number for external identification; the parking time period, which displays the estimated parking time (e.g., "estimated parking time"). Contact information, which may optionally display the vehicle owner's emergency contact number (requiring user authorization). The message format should be concise and eye-catching, for example, "Temporary parking, please do not occupy, contact: 138****1234." Alternatively, the vehicle's light sensor or camera can analyze the current ambient light intensity (e.g., bright daylight, dim nightlight). Light intensity is categorized into multiple levels (e.g., bright, medium, and dim) corresponding to different projection modes. The projection control logic can also include: In bright light environments (such as midday on a sunny day), high-brightness projection mode is activated to ensure clear visibility of the information; the projection color can be adjusted to a high-contrast setting (such as black text on a white background); in low-light environments (such as at night or in tunnels), night vision mode is activated to reduce brightness to avoid glare while ensuring information is visible; dynamic flashing effects can be added to attract attention; and in medium light, default projection settings are used. Projection location selection: The ground in front of the vehicle or the wall next to the parking space is preferred to ensure easy detection by pedestrians and other vehicles; projection onto glass or reflective surfaces should be avoided to prevent information distortion. After determining the projection strategy, the vehicle's onboard projection device (such as the embedded projector on the front of the vehicle) can be controlled to project the information to the target location. The projection duration is synchronized with the parking period (e.g., 15 minutes for a 15-minute parking period). Furthermore, if a passerby or parking attendant scans the QR code (if present) in the projection, they will be redirected to the parking management page. The projected information can be used as an electronic certificate of temporary parking for verification by traffic police or parking lot attendants.

[0071] In the embodiments provided herein, when a vehicle is detected to have successfully parked in a temporary parking space, a temporary parking reminder message is automatically generated. This mechanism ensures the immediacy and traceability of parking activity, providing clear feedback to the vehicle owner that parking has been completed and facilitating subsequent management or inquiries. Next, the lighting intensity in the ambient information is further analyzed based on the image data, demonstrating meticulous consideration of environmental factors, as lighting conditions directly impact the effectiveness and readability of information display. By intelligently adjusting projection parameters based on light intensity, the temporary parking reminder message is clearly and accurately projected onto the target location, such as the ground or a nearby wall, in varying lighting environments, effectively attracting the attention of nearby personnel (such as parking attendants and other vehicle owners). This adaptive projection control based on light intensity not only improves the efficiency and accuracy of information transmission but also prevents information omissions or misunderstandings caused by environmental factors. Ultimately, the clearly displayed temporary parking reminder message can proactively trigger external interactions, such as attracting the attention of others, promoting the rational allocation of parking resources, or avoiding potential disputes, further enhancing the intelligent level of parking management and user experience.

[0072] Figure 9 This is a brief flowchart of automatic parking in an exemplary application scenario. Figure 9 In the illustrated application scenario, if the automatic parking mode is detected to be triggered, the vehicle's surrounding environment is acquired, including an environmental map and image data. Based on the environmental map and image data, the vehicle's target parking space and target drop-off point are determined, allowing the user to exit the vehicle at the target drop-off point. If the target parking space is a temporary space, the vehicle is controlled to complete automatic parking in the target space and monitor external interaction information. Semantic recognition is performed on external speech information within the external interaction information, and target content, including parking-related content, is extracted from the semantic recognition results. If the target content indicates the presence of a target vehicle, the vehicle is controlled to exit the temporary parking space and a target cruise strategy is determined. The vehicle is controlled to execute the target cruise strategy and, during the cruise, the target parking space is redefined. If the target vehicle is a stationary vehicle corresponding to a temporary parking space, the vehicle is controlled to exit the temporary parking space and the target parking space is redefined. If the target parking space is a public parking space, a target driving path for the vehicle to reach the public parking space is determined; the dimensions of the public parking space and the corresponding vehicle dimensions are obtained, and an automatic parking strategy for the vehicle is determined based on the dimensions of the parking space, the vehicle dimensions, and the target driving path; the vehicle is controlled to execute the automatic parking strategy, and after the automatic parking strategy is completed, parking information containing the target parking space is sent to the user. The detailed implementation process is described in the aforementioned embodiments and will not be repeated here.

[0073] Figure 10This is a block diagram of an automatic parking device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown is specifically configured in the smart terminal 110. The apparatus may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the apparatus is applicable.

[0074] like Figure 10 As shown, the exemplary automatic parking device includes: an acquisition module 1010, which is used to obtain environmental information of the vehicle if it is detected that the automatic parking mode is triggered, and the environmental information includes an environmental map and image data; a determination module 1020, which is used to determine the target parking space and target getting-off point of the vehicle based on the environmental map and image data, so that the user can get off the vehicle at the target getting-off point; an interaction module 1030, which is used to control the vehicle to complete automatic parking in the target parking space if the target parking space is a temporary parking space, and monitor external interaction information of the vehicle; a control module 1040, which is used to control the vehicle to leave the temporary parking space if the external interaction information indicates that the target vehicle appears and the target vehicle is a fixed vehicle corresponding to the temporary parking space, and to re-determine the target parking space of the vehicle.

[0075] According to one aspect of an embodiment of the present application, the above-mentioned control module 1040 is also used to perform semantic recognition on external voice information and extract target content in the semantic recognition results, where the target content includes content related to parking; if the target content represents the appearance of a target vehicle, the vehicle is controlled to leave the temporary parking space and the target cruising strategy of the vehicle is determined; the vehicle is controlled to execute the target cruising strategy and the target parking space of the vehicle is re-determined during the cruising process.

[0076] According to one aspect of an embodiment of the present application, the above-mentioned control module 1040 is also used to obtain real-time environmental information of the vehicle, the real-time environmental information including real-time image data and real-time environmental map; determine the cruising path of the vehicle based on the real-time image data and the real-time environmental map; and determine the target cruising strategy of the vehicle based on the cruising path.

[0077] According to one aspect of an embodiment of the present application, the above-mentioned control module 1040 is also used to obtain traffic flow data on the cruising path and a preset cruising speed threshold of the vehicle; determine the target cruising speed of the vehicle based on the traffic flow data and the preset cruising speed threshold; and determine the target cruising strategy of the vehicle based on the target cruising speed and the cruising path.

[0078] According to one aspect of an embodiment of the present application, the above-mentioned determination module 1020 is also used to, if the target parking space is a public parking space, determine the target driving path of the vehicle to reach the public parking space; obtain the parking space size of the public parking space and the vehicle size corresponding to the vehicle, and determine the automatic parking strategy of the vehicle based on the parking space size, vehicle size and target driving path; control the vehicle to execute the automatic parking strategy, and after the automatic parking strategy is completed, send parking information containing the target parking space to the user.

[0079] According to one aspect of an embodiment of the present application, the above-mentioned interaction module 1030 is also used to generate temporary parking prompt information if the target parking space is a temporary parking space and it is detected that the vehicle has completed automatic parking; determine the light intensity corresponding to the environmental information based on the image data, and control the vehicle to project the temporary parking prompt information to the target position based on the light intensity, so as to trigger external interaction information based on the temporary parking prompt information.

[0080] It should be noted that the automatic parking device provided in the above-described embodiments and the automatic parking method provided in the above-described embodiments share the same concept. The specific manner in which the various modules and units perform their operations has been described in detail in the method embodiments and will not be repeated here. In actual applications, the automatic parking device provided in the above-described embodiments may, as needed, distribute the aforementioned functions among different functional modules, i.e., divide the internal structure of the device into different functional modules to perform all or part of the aforementioned functions. This is not intended to be limiting herein.

[0081] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the automatic parking method provided in the above-mentioned embodiments.

[0082] Figure 11 The following is a schematic diagram showing the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application. Figure 11 The computer system 1100 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0083] like Figure 11As shown, computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in read-only memory (ROM) 1102 or programs loaded from storage 1108 into random access memory (RAM) 1103. RAM 1103 also stores various programs and data required for system operation. CPU 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to bus 1104.

[0084] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, mouse, and the like; an output section 1107 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 1108 including a hard disk; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. Removable media 1111, such as magnetic disks, optical disks, magneto-optical disks, and semiconductor memories, are installed in the drive 1110 as needed, allowing computer programs read from these media to be installed in the storage section 1108 as needed.

[0085] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 1109 and / or installed from removable media 1111. When executed by the central processing unit (CPU) 1101, the computer program performs the various functions defined in the system of the present application.

[0086] It should be noted that the computer-readable medium described in the embodiments of this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. This propagated data signal may take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0087] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0088] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0089] Another aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned automatic parking method. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0090] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the automatic parking method provided in each of the above embodiments.

[0091] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main ideas and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. An automatic parking method, characterized in that: include: acquiring image data and sensor data of a user on a seat, the sensor data including pressure sensing data; determining a real-time status of the user based on the image data, and determining a weight distribution characteristic of the user on the seat based on the pressure sensing data; determining a target seat posture of the seat based on the real-time state and the weight distribution characteristic; Acquire the driving duration and driving mode of the user, determine an adjustment strategy for the target seat posture based on the driving duration and / or the driving mode, and perform posture adjustment on the seat based on the adjustment strategy.

2. The method according to claim 1, wherein The external interaction information includes external voice information, and the method further includes: Performing semantic recognition on the external voice information and extracting target content from the semantic recognition result, wherein the target content includes content related to parking; If the target content indicates that the target vehicle appears, controlling the vehicle to leave the temporary parking space and determining a target cruising strategy for the vehicle; The vehicle is controlled to execute the target cruising strategy, and the target parking space of the vehicle is re-determined during the cruising process.

3. The method according to claim 2, wherein Determining the target cruising strategy of the vehicle includes: Acquiring real-time environmental information of the vehicle, the real-time environmental information including real-time image data and a real-time environmental map; determining a cruising path of the vehicle based on the real-time image data and the real-time environment map; A target cruising strategy for the vehicle is determined based on the cruising path.

4. The method according to claim 3, wherein Determining the target cruise strategy of the vehicle based on the cruise path includes: Obtaining traffic flow data on the cruising path and a preset cruising speed threshold of the vehicle; determining a target cruising speed for the vehicle based on the traffic flow data and the preset cruising speed threshold; A target cruising strategy for the vehicle is determined based on the target cruising speed and the cruising path.

5. The method according to claim 3, wherein The determining of the cruising path of the vehicle based on the real-time image data and the real-time environment map includes: determining a plurality of candidate cruise paths based on the real-time image data and the real-time environment map; Obtaining available berth information and path access information corresponding to each of the plurality of candidate cruise paths; A cruising path of the vehicle is determined from the plurality of candidate cruising paths based on the available berth information and the path access information.

6. The method according to claim 1, wherein The method further comprises: If the target parking space is a public parking space, determining a target driving path for the vehicle to reach the public parking space; Obtaining a parking space size of the public parking space and a vehicle size corresponding to the vehicle, and determining an automatic parking strategy for the vehicle based on the parking space size, the vehicle size, and the target driving path; The vehicle is controlled to execute the automatic parking strategy, and after the automatic parking strategy is completed, parking information containing a target parking space is sent to the user.

7. The method according to claim 1, wherein: The method further comprises: If the target parking space is a temporary parking space and it is detected that the vehicle has completed automatic parking, a temporary parking prompt message is generated; The light intensity corresponding to the environmental information is determined based on the image data, and the vehicle is controlled to project the temporary parking prompt information to a target location based on the light intensity, so as to trigger the external interaction information based on the temporary parking prompt information.

8. An automatic parking device, characterized in that: The device comprises: an acquisition module, configured to acquire environmental information of the vehicle if it is detected that the automatic parking mode is triggered, the environmental information including an environmental map and image data; a determination module, configured to determine a target parking space and a target getting-off point of the vehicle based on the environment map and the image data, so that the user gets off the vehicle at the target getting-off point; an interaction module, configured to control the vehicle to complete automatic parking at the target parking space if the target parking space is a temporary parking space, and monitor external interaction information of the vehicle; The control module is configured to control the vehicle to leave the temporary parking space and re-determine the target parking space of the vehicle if the external interaction information indicates that a target vehicle has appeared and the target vehicle is a fixed vehicle corresponding to the temporary parking space.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the automatic parking method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the automatic parking method according to any one of claims 1 to 7.

Images