Automatic parking method, device and equipment and storage medium

Abstract

The invention discloses an automatic parking method, device and equipment and a storage medium, and relates to the technical field of intelligent parking, and the automatic parking method comprises the steps that the surrounding environment of a vehicle is detected, and an environment sensing result is obtained; planning a parking path according to the environment perception result to obtain an initial parking path; parking is carried out according to the initial parking path, and whether the current position of the vehicle is a target parking position or not is determined; when the current position of the vehicle is the target garage rubbing position, whether the vehicle meets a state machine jumping condition or not is determined; when it is confirmed that the vehicle meets the state machine skipping condition, an automatic parking mode and an initial parking path are updated, and automatic parking is completed according to the updated automatic parking mode and the updated initial parking path. The parking mode and path are dynamically adjusted according to the current position and state of the vehicle in the automatic parking process, and the accuracy and automation degree of the parking process are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent parking technology, and in particular to automatic parking, devices, equipment and storage media. Background Art

[0002] With the increasing popularity of intelligent driving technology, consumers have higher and higher requirements for the functions and performance of intelligent driving functions, especially intelligent parking systems. In the early days, intelligent parking systems mainly focused on realizing the functions of automatic parking and body straightening. With the advancement of technology, in the application scenario of valet parking function, users are not only concerned about the performance of the parking function, but also have higher requirements for the smoothness of the parking process. In the parking scenario of valet parking, when the Automated Parking Assistance (APA) completes parking, the vehicle often slows down, and then switches to Automated Valet Parking (AVP) and accelerates again when cruising. Due to the functional jump of the state machine, there will be a sense of frustration in this process, which seriously affects the user's driving experience.

[0003] Traditional technology uses dynamic shifting technology to shorten the time required for the vehicle to switch between reverse gear (R gear) and forward gear (D gear) during parking operation, reduce the sense of frustration during shifting, and improve smoothness. However, traditional technical solutions only focus on the APA parking process, ignoring the smoothness issues from APA parking completion to AVP cruising stage.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present application is to provide an automatic parking method, device, equipment and storage medium, which aims to solve the technical problems of vehicle speed fluctuation and frustration caused by state machine jump when the vehicle switches to the automatic valet parking cruise stage after the automatic parking assisted parking is completed.

[0006] To achieve the above objectives, the present application proposes an automatic parking method, the method comprising:

[0007] Detect the vehicle's surroundings and obtain environmental perception results;

[0008] Planning a parking path according to the environmental perception result to obtain an initial parking path;

[0009] Parking according to the initial parking path, confirming whether the current position of the vehicle is the target parking position;

[0010] When the current position of the vehicle is the target storage position, confirm whether the vehicle meets the state machine jump condition;

[0011] When it is confirmed that the vehicle meets the state machine jump condition, the automatic parking mode and the initial parking path are updated, and the automatic parking is completed according to the updated automatic parking mode and the updated initial parking path.

[0012] In one embodiment, the automatic parking mode includes an automatic parking assist mode and an automatic valet parking cruise mode:

[0013] The step of updating the automatic parking mode and the initial parking path when confirming that the vehicle meets the state machine jump condition, and completing the automatic parking according to the updated automatic parking mode and the updated initial parking path includes:

[0014] When it is confirmed that the vehicle meets the state machine jump condition, updating the automatic parking assistance mode to the automatic valet parking cruise mode to obtain an initial automatic valet parking cruise mode;

[0015] Obtaining a target parking path according to the current position of the vehicle and the initial parking path;

[0016] Obtaining a target automatic valet parking cruise mode according to the target parking path and the initial automatic valet parking cruise mode;

[0017] The vehicle is controlled to travel in the target automatic valet parking cruise mode to complete automatic parking.

[0018] In one embodiment, the step of planning a parking path according to the environmental perception result to obtain an initial parking path includes:

[0019] According to the environmental perception results, the vehicle's current environmental information, vehicle control parameters, vehicle posture and target parking space information are obtained;

[0020] Generate a smooth parking path based on the vehicle's current environment information, the vehicle control parameters, the vehicle posture, the target parking space information, and a hybrid heuristic search strategy;

[0021] An initial parking path is obtained according to the vehicle control parameters, the current environment information of the vehicle and the smooth parking path.

[0022] In one embodiment, the step of obtaining an initial parking path according to the vehicle control parameters, the vehicle current environment information and the smooth parking path comprises:

[0023] Obtaining vehicle geometric constraints according to the vehicle control parameters and the vehicle current environment information;

[0024] According to the smoothed parking path and the vehicle geometric constraints, path smoothing processing is performed to obtain an initial parking path.

[0025] In one embodiment, when the current position of the vehicle is the target storage position, the step of confirming whether the vehicle meets the state machine jump condition includes:

[0026] When the current position of the vehicle is the target storage position, obtaining vehicle shift information and vehicle current environment information;

[0027] When the vehicle shift information is a shift from a reverse gear to a parking gear, generating a state machine switching signal;

[0028] According to the state machine switching signal and the current environment information of the vehicle, it is confirmed whether the vehicle meets the state machine jump condition.

[0029] In one embodiment, the step of parking according to the initial parking path and confirming whether the current position of the vehicle is the target parking position includes:

[0030] Obtain the target kneading library position according to the hybrid heuristic search algorithm;

[0031] Based on the target parking position, parking is performed according to the initial parking path and the automatic parking assistance mode, and the current position of the vehicle during the parking process is obtained;

[0032] According to the current position of the vehicle, it is confirmed whether the current position of the vehicle is the target storage position.

[0033] In one embodiment, the step of detecting the vehicle surrounding environment and obtaining an environment perception result includes:

[0034] Obtain parking space boundary information, vehicle information around the vehicle, obstacle information around the vehicle, pedestrian detection information, and lane line information based on vehicle-mounted sensors;

[0035] An environmental perception result is obtained according to the parking space boundary information, the vehicle information around the vehicle, the obstacle information around the vehicle, the pedestrian detection information and the lane line information.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an automatic parking device, which includes: an environment perception module, which is used to detect the surrounding environment of the vehicle and obtain an environment perception result;

[0037] A path planning module, used to plan a parking path according to the environmental perception result to obtain an initial parking path;

[0038] An automatic parking module, used to park the vehicle according to the initial parking path and confirm whether the current position of the vehicle is the target parking position;

[0039] A state confirmation module, used to confirm whether the vehicle meets the state machine jump condition when the current position of the vehicle is the target storage position;

[0040] The automatic parking module is further configured to update the automatic parking mode and the initial parking path when confirming that the vehicle meets the state machine jump condition, and complete automatic parking according to the updated automatic parking mode and the updated initial parking path.

[0041] In addition, to achieve the above objectives, the present application also proposes an automatic parking device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the automatic parking method described above.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the automatic parking method described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the automatic parking method described above are implemented.

[0044] One or more technical solutions proposed in this application have at least the following technical effects:

[0045] Due to the real-time detection of the vehicle's surrounding environment, acquisition and analysis of environmental perception results, the path planning can be dynamically adjusted in each parking stage to ensure that the vehicle can accurately track the target path at each step, and when the vehicle reaches the target parking position, it can accurately determine whether the state machine jump conditions are met. If the conditions are met, the system will update the automatic parking mode and path to optimize the parking process. Compared with the existing technology, the problem of path planning and state transition lag in the existing technology is avoided through dynamic path adjustment and state machine switching. Traditional technology may cause the parking process to be not smooth enough or errors in path planning due to the failure of the state machine to switch in time when the vehicle approaches the target position. This solution ensures a seamless transition from the initial parking path to the target position through real-time response and update, effectively improving the smoothness, accuracy and automation of the parking process, thereby improving the user experience and the intelligence level of automatic parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the automatic parking method of the present application;

[0049] Figure 2 A schematic diagram of a flow chart provided for the second embodiment of the automatic parking method of the present application;

[0050] Figure 3 A schematic diagram of a brief process of the automatic parking method provided in the second embodiment of the present application;

[0051] Figure 4 This is a schematic diagram of the module structure of the automatic parking device according to an embodiment of the present application;

[0052] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the automatic parking method in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The main solution of the embodiment of the present application is: detect the vehicle's surrounding environment to obtain an environmental perception result; plan a parking path according to the environmental perception result to obtain an initial parking path; park according to the initial parking path to confirm whether the vehicle's current position is the target parking position; when the vehicle's current position is the target parking position, confirm whether the vehicle meets the state machine jump condition; when it is confirmed that the vehicle meets the state machine jump condition, update the automatic parking mode and the initial parking path, and complete the automatic parking according to the updated automatic parking mode and the updated initial parking path.

[0057] In this embodiment, for ease of description, the following description is made by taking the identification of the automatic parking device as the execution subject.

[0058] Since the vehicle speed fluctuates and feels jerkier due to the state machine jump when the vehicle switches to the automatic valet parking cruise stage after the prior art automatic parking assisted parking is completed, the present application provides a solution. Due to the real-time detection of the vehicle's surrounding environment, the environmental perception results are obtained and analyzed, and the path planning can be dynamically adjusted in each parking stage to ensure that the vehicle can accurately track the target path at each step, and when the vehicle reaches the target storage position, it can accurately determine whether the state machine jump condition is met. If the conditions are met, the system will update the automatic parking mode and path to optimize the parking process. Compared with the prior art, the problem of path planning and state conversion lag in the prior art is avoided through dynamic path adjustment and state machine switching. Traditional technology may cause the parking process to be not smooth enough or errors in path planning due to the failure of the state machine to switch in time when the vehicle approaches the target position. This solution ensures a seamless transition from the initial parking path to the target position through real-time response and update, effectively improving the stability, accuracy and automation of the parking process, thereby improving the user experience and the intelligence level of automatic parking.

[0059] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an automatic parking device, etc. The following takes the automatic parking device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the present application embodiment provides an automatic parking method, referring to Figure 1 , Figure 1 This is a flowchart diagram of the first embodiment of the automatic parking method of the present application.

[0061] In this embodiment, the automatic parking method includes steps S10 to S50:

[0062] Step S10, detecting the vehicle's surrounding environment and obtaining an environmental perception result;

[0063] It should be noted that the environmental perception results are the surrounding environment data obtained by sensors such as radar, camera, lidar, etc. These data include information about obstacles, pedestrians, lane lines, parking spaces, other vehicles, etc. around the vehicle. The environmental perception results provide real-time space and object information for path planning and parking decisions.

[0064] It is understandable that vehicles use multiple sensors, such as radar, lidar, cameras, etc. to monitor the surrounding environment in real time. The data collected by the sensors include information about obstacles around the vehicle, other vehicles, pedestrians, lane lines, etc. These perception results provide important input data for subsequent path planning, ensuring that the vehicle can adapt to various changes in the environment, avoid collisions, and ensure the safety and smoothness of parking operations.

[0065] Step S20, planning a parking path according to the environmental perception result to obtain an initial parking path;

[0066] It should be noted that the initial parking path is the path that the vehicle takes from its current position to the target parking space. This path needs to avoid obstacles and take into account the vehicle's kinematic constraints, such as turning radius and speed limit. The path planning algorithm generates a suitable driving route based on this information.

[0067] In addition, the vehicle's surroundings refer to all objects and features in the space around the vehicle that may affect parking. This includes information such as parking space boundaries, lane line obstacles, traffic signs, etc. such as other vehicles, pedestrians, walls, pillars, etc. The accuracy of environmental perception directly affects the reliability of parking path planning and the safety of the vehicle.

[0068] It is understandable that according to the environmental perception result obtained in step S10, the parking path will be planned. This path planning needs to take into account the current position of the vehicle, the position of the target parking space, surrounding obstacles, and the kinematic limitations of the vehicle, such as turning radius, acceleration, etc. Through the algorithm, an initial parking path that is most suitable for the vehicle will be generated.

[0069] In a feasible implementation, step S20 may include steps S21 to S23:

[0070] Step S21, obtaining vehicle current environment information, vehicle control parameters, vehicle position and target parking space information according to the environment perception result;

[0071] It should be noted that the vehicle's current environment information refers to the real-time data obtained by the vehicle at its current location and surrounding environment. This information includes surrounding obstacles, parking space layout, distances to surrounding vehicles, locations of pedestrians, etc. The vehicle's current environment information directly affects the planning of the parking path and the smoothness of parking.

[0072] In addition, vehicle control parameters refer to various key physical parameters that affect vehicle movement, including steering angle, acceleration, maximum speed, braking distance, turning radius, etc.

[0073] In addition, vehicle pose refers to the position and orientation of the vehicle relative to a reference coordinate system, such as a parking lot or road. Usually including the coordinates of the vehicle and its orientation angle, vehicle pose is crucial for path planning because the position and orientation of the vehicle determine how it approaches the parking space and how it turns.

[0074] In addition, the target parking space information refers to the specific location and size of the target parking space for the vehicle. This includes data such as the boundaries of the parking space, the angle of the parking space, and the current position of the parking space relative to the vehicle. This information provides necessary reference for planning the parking path.

[0075] It can be understood that the vehicle's current environment information is comprehensively calculated and confirmed based on the data obtained from environmental perception. Assuming that the vehicle is preparing to enter an empty parking space, the sensor detects surrounding obstacles, lane lines, distances to other vehicles, etc., and generates the vehicle's current environment information. This information helps the system identify the layout of the parking lot, the distribution of obstacles, and provides basic data for subsequent path planning. At the same time, it is necessary to confirm the vehicle control parameters and vehicle posture, identify the target parking space information, and determine the target parking space that the vehicle will enter.

[0076] Step S22, generating a smooth parking path based on the vehicle's current environment information, the vehicle control parameters, the vehicle posture, the target parking space information, and a hybrid heuristic search strategy;

[0077] It should be noted that the hybrid heuristic search strategy is a hybrid A* algorithm, which is a path planning algorithm that takes into account vehicle kinematic constraints, such as turning radius, acceleration, speed, etc., and is suitable for parking path planning in complex environments. The optimal path is planned by discretizing the vehicle state space, defining the cost function, path search, path smoothing and optimization, and other steps.

[0078] In addition, a smooth parking path refers to a path from the current vehicle position to the target parking space planned by a hybrid heuristic search strategy, which has fewer turns and sudden acceleration or deceleration, and can ensure that the vehicle parks at a smooth speed and direction.

[0079] It can be understood that, using the hybrid A* algorithm, a smooth parking path can be generated based on the vehicle's current environment information, control parameters, posture, and target parking space information obtained in step S21. The target parking space is identified, and vehicle control parameters such as maximum steering angle and acceleration are set. The path planning algorithm will ensure that the vehicle can smoothly enter the parking space without any abrupt changes.

[0080] Step S23, obtaining an initial parking path according to the vehicle control parameters, the current environment information of the vehicle and the smooth parking path.

[0081] It is understandable that the aforementioned vehicle control parameters and current environment information are used to adjust the parking path and finally obtain an initial parking path, which will serve as a reference path for the vehicle to perform a parking operation.

[0082] In a feasible implementation, step S23 may include steps S231 to S232:

[0083] Step S231, obtaining vehicle geometric constraints according to the vehicle control parameters and the vehicle current environment information;

[0084] It should be noted that vehicle geometric constraints refer to the physical limitations imposed on the vehicle during driving, including vehicle size, turning radius, minimum speed, vehicle steering capability, etc. These geometric constraints will affect the vehicle's path planning, ensuring that the planned path is adapted to the vehicle's actual dynamic capabilities.

[0085] It is understandable that in the planning of the parking path, in addition to considering the shortest path, it is also necessary to ensure that the path meets the vehicle's vehicle geometric constraints, namely the kinematic constraints. Kinematic constraints mainly include turning radius. The steering angle and minimum turning radius of the vehicle determine the curvature of the path. When planning the path, the turning radius of the vehicle should be greater than or equal to the minimum turning radius; maximum acceleration and speed. When parking, the acceleration and speed of the vehicle should be limited to avoid sudden acceleration or sudden braking. These restrictions should be considered during path planning to maintain smooth driving; obstacle avoidance. The distance to surrounding obstacles needs to be considered during path planning to ensure that the vehicle maintains a safe distance from surrounding obstacles, such as walls and other vehicles.

[0086] Step S232: performing path smoothing processing according to the smoothed parking path and the vehicle geometric constraint to obtain an initial parking path.

[0087] It is understood that path smoothing refers to the optimization of the generated path to eliminate jerky turns or unnatural changes in the path. The purpose of path smoothing is to ensure that the vehicle can smoothly execute the path without causing unnecessary vibration or unsafe operation of the vehicle due to path unevenness. This process usually relies on mathematical methods such as curve fitting, spline interpolation, etc.

[0088] In addition, it can be understood that the path smoothing process is performed according to the smooth parking path and the geometric constraints of the vehicle to obtain the initial parking path. Assuming that the geometric constraints of the vehicle are calculated in step S231, for example, the minimum turning radius of the vehicle is 5 meters, the smooth parking path will be adjusted based on this constraint to ensure that each curve in the path meets the turning capability of the vehicle.

[0089] For example, during the planning process, the path may pass through multiple bends, and the turning radius of these bends is too small, exceeding the turning limit of the vehicle. Path smoothing will be performed to adjust the curve of the path and increase the turning radius to ensure that the path adapts to the geometric constraints of the vehicle.

[0090] Step S30, parking according to the initial parking path, and confirming whether the current position of the vehicle is the target parking position;

[0091] It should be noted that the target parking position is a specific position that the vehicle must reach during the parking process. In this embodiment, it is the last parking position of the vehicle, that is, the position that the vehicle must reach when completing the last reversing or adjustment. Usually, this position marks the final stage of the vehicle entering or exiting the parking space.

[0092] It is understood that the vehicle starts to drive along the initial parking path and confirms whether its current position has reached the target parking position. The vehicle detects through the sensor that the current position is close to the boundary of the parking space, and then the target parking position will be confirmed. The goal of the vehicle is to park at the final adjustment position of the parking space, that is, the vehicle position reaches the precise requirement and completes the parking.

[0093] In a feasible implementation, step S30 may include steps S31 to S33:

[0094] Step S31, obtaining the target kneading warehouse position according to the hybrid heuristic search algorithm;

[0095] It is understandable that the hybrid heuristic search algorithm can obtain the target parking position based on environmental information, vehicle control parameters and path planning requirements. Assuming that the vehicle's goal is to enter a standard parking space, the system evaluates the optimal path through the hybrid heuristic search algorithm and calculates the target parking position, which is usually the most accurate position where the vehicle needs to park after entering the parking space. After the vehicle reaches the target parking position through the planned path, the final adjustment is completed.

[0096] Step S32, based on the target parking position, parking is performed according to the initial parking path and the automatic parking assistance mode, and the current position of the vehicle during the parking process is obtained;

[0097] It should be noted that Automated Parking Assistance (APA) is a control mode used by the vehicle during the automatic parking process. It usually involves the vehicle performing automatic parking operations based on external sensor data without driver intervention. APA modes may include forward or reverse parking, adjusting the control strategy based on the vehicle's current position and the target parking space.

[0098] Step S33, confirming whether the current position of the vehicle is the target storage position according to the current position of the vehicle.

[0099] It should be noted that the current position of the vehicle refers to the real-time monitoring of the vehicle's position through sensors and positioning systems to ensure that the vehicle travels according to the route and is accurately positioned when it reaches the target storage location.

[0100] It is understandable that the vehicle starts to perform parking operations based on the target parking position and the initial parking path. Assuming that the vehicle drives to the target parking space according to the initial parking path through the path planning system, the vehicle is automatically controlled according to the APA mode, and the system will update the current position of the vehicle in real time according to the actual parking progress.

[0101] Exemplarily, when the vehicle reaches the last parking space, the vehicle maintains the APA state machine unchanged, that is, continues to execute the APA parking process.

[0102] Step S40, when the current position of the vehicle is the target storage position, confirm whether the vehicle meets the state machine jump condition;

[0103] It should be noted that the state machine jump condition refers to the standard for the state machine to switch from one operating mode to another operating mode when the vehicle meets certain preset conditions during the parking process.

[0104] It is understandable that when the vehicle reaches the target parking position, it checks whether the vehicle meets the state machine jump conditions. The vehicle has completed the final adjustment and will check whether it meets the conditions for entering the automatic valet parking cruise mode, such as the parking space is ready, there are no obstacles, and the vehicle position is accurate. If the conditions are met, the state machine will be prepared to jump.

[0105] In a feasible implementation, step S40 may include steps S41 to S43:

[0106] Step S41, when the current position of the vehicle is the target storage position, obtaining vehicle shift information and vehicle current environment information;

[0107] It should be noted that the gear shift information refers to the current gear switching state of the vehicle, and the gears usually include reverse gear (R gear), forward gear (D gear), parking gear (P gear), etc. During parking, the vehicle needs to switch from reverse gear to parking gear, or from other gears to a gear suitable for parking, to ensure that the vehicle can perform parking operations correctly.

[0108] It is understandable that the vehicle has approached the target parking position and will obtain the current gear shift information and environmental information. Assuming that the vehicle has reversed to a parking space, the system will obtain the current gear shift information and simultaneously perceive the surrounding environment, such as whether the parking space in front is empty and there are no obstacles, whether there are vehicles on the side, etc. This information helps the system determine whether the vehicle can perform the next operation: that is, switching from reverse gear to parking gear.

[0109] Step S42, when the vehicle shift information is a shift from a reverse gear to a parking gear, generating a state machine switching signal;

[0110] It should be noted that the reverse gear refers to the gear in which the vehicle is in reverse driving state (R gear). During parking, the vehicle is usually first shifted into the reverse gear to reverse until the vehicle approaches the target parking space. The parking gear refers to the gear in which the vehicle is stopped and ready to stop (P gear). When the vehicle completes the parking operation and parks in the parking space, it is usually necessary to switch the vehicle to the parking gear to ensure that the vehicle is completely stationary.

[0111] In addition, the state machine switching signal refers to a signal that triggers the state change of the automatic parking system. When the vehicle switches from the reverse gear to the parking gear, the system will send a state machine switching signal, indicating that the automatic parking mode needs to be switched from one operating mode to another operating mode to perform a new operation.

[0112] It is understandable that when the system detects that the vehicle switches from reverse gear to parking gear, a state machine switching signal is generated, which indicates that the state machine of the vehicle needs to switch from automatic parking assist mode to automatic valet parking mode, preparing to enter the next stage of parking operation.

[0113] Step S43, confirming whether the vehicle meets the state machine jump condition according to the state machine switching signal and the current environment information of the vehicle.

[0114] It is understandable that the state machine switching signal and the vehicle's current environmental information can be used to confirm whether the jump condition is met. For example, assuming that the vehicle has switched from reverse gear to parking gear, and the sensor confirms that the parking space is empty and the vehicle has been accurately parked in the parking space, it will be determined whether the state machine jump condition is met based on this information. If the vehicle's current position matches the target parking position and there are no obstacles around, the state machine switching signal will be confirmed and the system will trigger a mode switch. Otherwise, the vehicle may need to continue to adjust or wait for confirmation to ensure that parking is complete.

[0115] Step S50, when it is confirmed that the vehicle meets the state machine jump condition, the automatic parking mode and the initial parking path are updated, and the automatic parking is completed according to the updated automatic parking mode and the updated initial parking path.

[0116] It should be noted that the automatic parking mode refers to the control strategy and method used by the vehicle during the automatic parking process. Different modes may be adapted to different parking scenarios, such as the automatic parking assistance mode or the Automated Valet Parking (AVP) mode. In addition, updating the initial parking path refers to replanning or adjusting the parking path according to new environmental information or changes in vehicle status during the parking process. This ensures that the vehicle can accurately follow the new path in a dynamic environment.

[0117] It is understandable that when the vehicle confirms that it meets the state machine jump conditions, it will update the automatic parking mode and re-plan the path. The vehicle switches from APA mode to AVP mode, and the parking path needs to be updated to adapt to the new control mode. Path updates include recalculating the vehicle's motion trajectory and steering angle, and ensuring that the vehicle completes parking according to the new path. The vehicle continues to perform parking operations under the new control mode until it is completely parked in the parking space. Through the jump of the state machine and the update of the path, the vehicle can smoothly transition to the new operating mode and successfully complete the parking task. For example, after the vehicle completes APA parking and meets the conditions for entering the AVP mode, the system will automatically update the path and mode to allow the vehicle to continue parking until parking is completed.

[0118] In a feasible implementation, step S50 may include steps S51 to S54:

[0119] Step S51, when it is confirmed that the vehicle meets the state machine jump condition, updating the automatic parking assistance mode to the automatic valet parking cruise mode to obtain an initial automatic valet parking cruise mode;

[0120] It should be noted that the automatic parking assist mode is an operating mode used by the vehicle during the parking process. The system usually provides assistance under the control of the driver to help the vehicle complete the parking task. In this mode, the vehicle performs actions such as reversing and turning, but the driver still intervenes in some operations. In addition, the automatic valet parking cruise mode means that the vehicle performs parking operations under complete autonomous control without driver intervention. In this mode, the vehicle makes autonomous decisions based on sensor data and completes the parking task. This mode is usually used in more advanced autonomous driving systems, which can automatically complete the parking process without driver control. The initial automatic valet parking cruise mode indicates that the switching operation has just been performed and the automatic valet parking cruise mode of the remaining driving path has not yet been entered.

[0121] It can be understood that the vehicle has accurately reached the target parking position and there are no obstacles around. When the conditions are met, the system will update the automatic parking assistance mode to the automatic valet parking cruise mode. This means that the vehicle will change from relying on the driver's auxiliary operation to fully autonomous parking control.

[0122] Step S52, obtaining a target parking path according to the current position of the vehicle and the initial parking path;

[0123] It should be noted that the target parking path refers to the planned route from the current position of the vehicle to the target parking space, that is, the remaining parking path planning. This path usually takes into account the kinematic limitations of the vehicle and changes in the environment to ensure that the vehicle can park smoothly.

[0124] It can be understood that the target parking path is generated according to the current position of the vehicle and the initial parking path. Assume that the vehicle has transitioned from the APA mode to the AVP mode and has approached a parking space.

[0125] Step S53, obtaining a target automatic valet parking cruise mode according to the target parking path and the initial automatic valet parking cruise mode;

[0126] It should be noted that the target automatic valet parking cruise mode refers to the final automatic valet parking control mode that is adjusted and optimized according to the current position of the vehicle, the target parking path and the current parking environment. The generation of this mode takes into account the dynamic changes of the actual parking environment and ensures that the vehicle can successfully complete the parking task through path adjustment.

[0127] It can be understood that a target automatic valet parking cruise mode is generated based on the target parking path and the initial automatic valet parking cruise mode. This target mode adjusts the control strategy based on the dynamic characteristics of the vehicle, changes in the target path, and real-time feedback from the surrounding environment. For example, the vehicle may encounter an obstacle during driving, and the system needs to adjust the target mode to ensure that the vehicle can bypass the obstacle and smoothly enter the parking space.

[0128] Step S54: Control the vehicle to travel based on the target automatic valet parking cruise mode to complete automatic parking.

[0129] It is understandable that the vehicle's driving is controlled according to the target automatic valet parking cruise mode to ensure that the vehicle performs the parking task and completes parking according to the planned path. For example, in the final stage when the vehicle is about to complete parking, the vehicle's steering angle, acceleration, etc. will continue to be fine-tuned according to the target mode to ensure that the vehicle can park smoothly in the parking space. Assuming that the vehicle is approaching the parking space, the steering and speed of the vehicle will be automatically adjusted according to the target automatic valet parking cruise mode to ensure that the vehicle is parked smoothly in the parking space. If a new obstacle is encountered, the control strategy will be adjusted in time to ensure that the vehicle completes parking safely.

[0130] This embodiment provides an automatic parking method, which solves the technical problems of path planning, environmental adaptability and mode switching in the automatic parking process through technical means such as environmental perception of on-board sensors, path planning of a hybrid heuristic search algorithm, and switching of automatic parking modes, and achieves the goal of accurately and safely completing automatic parking tasks in complex environments, improving parking accuracy, fluency and user experience, ensuring that the vehicle can complete parking operations autonomously and smoothly, and avoiding collision risks.

[0131] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S10 of the automatic parking method further includes steps S11 to S12:

[0132] Step S11, obtaining parking space boundary information, vehicle information around the vehicle, obstacle information around the vehicle, pedestrian detection information, and lane line information according to the vehicle-mounted sensor;

[0133] It should be noted that vehicle-mounted sensors are various sensing devices installed on vehicles, such as radar, LIDAR, camera, ultrasonic sensor, etc. Vehicle-mounted sensors are used to sense the environment around the vehicle and transmit the sensed data to the system for processing, supporting functions such as automatic parking, collision warning, and automatic driving.

[0134] In addition, parking space boundary information refers to the boundary position data of the parking space, which is usually obtained by sensors or visual systems. The parking space boundary information helps the system identify the spatial size, shape and positioning of the parking space relative to the vehicle, thereby determining whether the vehicle can enter the parking space smoothly.

[0135] In addition, the vehicle surrounding information refers to the position, speed and relative direction of other vehicles adjacent to or around the vehicle obtained by the vehicle-mounted sensors or environmental perception system. This information is crucial for obstacle avoidance, path planning and parking operations, helping the system determine the safe distance between vehicles.

[0136] In addition, the obstacle information around the vehicle refers to the detection information of any obstacles around the vehicle that may hinder driving or parking, including fixed obstacles such as walls, pillars, trees, or other dynamic obstacles. The sensor provides this information to the system to help determine whether there is a potential collision risk.

[0137] In addition, pedestrian detection information is information about the location, movement status, etc. of surrounding pedestrians obtained through sensors or visual systems.

[0138] In addition, lane line information refers to the lane marking information obtained by the vehicle through sensors or visual systems. This includes lane boundaries, lane directions, whether the lane is widening or narrowing, etc. Lane line information is very important for vehicle path planning, lane keeping and automatic parking operations.

[0139] It is understandable that the vehicle obtains environmental information around the vehicle through on-board sensors, covering parking space boundaries, surrounding vehicles, obstacles, pedestrians, lane lines and other aspects. Assuming that the vehicle is performing an automatic parking operation in a parking lot, the sensors collect this information in real time. For example, the on-board sensor detects the boundary of the parking space in front and determines the size and shape of the parking space. At the same time, it also detects other nearby vehicles, possible obstacles such as pillars or walls, and approaching pedestrians. Lane line information helps the vehicle confirm its driving route and direction during parking.

[0140] Step S12, obtaining an environmental perception result according to the parking space boundary information, the vehicle information around the vehicle, the obstacle information around the vehicle, the pedestrian detection information and the lane line information.

[0141] It is understandable that the various data collected in step S11, such as parking space boundary information, surrounding vehicle information, obstacle information, pedestrian information, and lane line information, are comprehensively processed to generate environmental perception results. Such information helps the system understand the environmental status of the vehicle, evaluate the safety of the surrounding space, and provide a basis for subsequent automatic parking path planning.

[0142] For example, suppose a vehicle is in a parking lot, there are other vehicles parked around it, the boundary of the parking space is identified by the sensor, obstacles are detected, and pedestrians are in front of the vehicle. This information will be comprehensively analyzed to generate environmental perception results, clarifying the relative position of the vehicle and the target parking space and the potential risks around it. Through these comprehensive data, it is possible to accurately determine whether the vehicle can enter the target parking space, whether there is a risk of collision, and whether the parking path needs to be adjusted. The environmental perception results not only help with path planning, but also dynamically adjust the parking strategy to avoid collisions and ensure the safety of the parking process.

[0143] This embodiment provides an automatic parking method, which solves the problems of environmental perception accuracy and real-time performance during automatic parking through data collection and comprehensive processing technology of vehicle-mounted sensors, and achieves accurate perception of obstacles, pedestrians, lane lines and other information around the vehicle in a complex environment, ensuring the reliability and safety of parking path planning, effectively avoiding collision risks, and optimizing the smoothness and safety of the parking process.

[0144] For example, to help understand the implementation process of the automatic parking method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flow chart of an automatic parking method is provided, specifically:

[0145] The vehicle's surrounding environment is sensed through on-board sensors to obtain environmental data such as obstacles, other vehicles, lane lines, etc. around the vehicle. Next, based on these perception results, the system plans the outbound route to ensure that the vehicle can smoothly leave the parking space. If this is not the last parking operation, the system will continue the parking operation. If it is the last parking, the system will check whether the state machine jump conditions are met. If the conditions are met, the parking state machine will be triggered to jump and enter the automatic valet parking cruise mode. At this time, the vehicle will park autonomously according to the planned path until the vehicle is completely parked in the parking space.

[0146] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the automatic parking method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0147] This application also provides an automatic parking device, please refer to Figure 4 , the automatic parking device comprises:

[0148] The environment perception module 10 is used to detect the environment around the vehicle and obtain the environment perception result;

[0149] A path planning module 20, configured to plan a parking path according to the environmental perception result to obtain an initial parking path;

[0150] The automatic parking module 30 is used to park the vehicle according to the initial parking path and confirm whether the current position of the vehicle is the target parking position;

[0151] A state confirmation module 40 is used to confirm whether the vehicle meets the state machine jump condition when the current position of the vehicle is the target storage position;

[0152] The automatic parking module 30 is further configured to update the automatic parking mode and the initial parking path when confirming that the vehicle meets the state machine jump condition, and complete automatic parking according to the updated automatic parking mode and the updated initial parking path.

[0153] The automatic parking device provided by the present application adopts the automatic parking method in the above embodiment, which can solve the technical problems of vehicle speed fluctuation and jerkiness caused by the state machine jump when the vehicle switches to the automatic valet parking cruise stage after the automatic parking assisted parking is completed. Compared with the prior art, the beneficial effects of the automatic parking device provided by the present application are the same as the beneficial effects of the automatic parking method provided by the above embodiment, and the other technical features of the automatic parking device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0154] In one embodiment, the automatic parking module 30 is further configured to update the automatic parking assistance mode to the automatic valet parking cruise mode to obtain an initial automatic valet parking cruise mode when confirming that the vehicle meets the state machine jump condition; obtain a target parking path according to the current position of the vehicle and the initial parking path; obtain a target automatic valet parking cruise mode according to the target parking path and the initial automatic valet parking cruise mode; and control the vehicle driving based on the target automatic valet parking cruise mode to complete automatic parking.

[0155] In one embodiment, the path planning module 20 is further used to obtain the vehicle's current environmental information, vehicle control parameters, vehicle posture and target parking space information based on the environmental perception result; generate a smooth parking path based on the vehicle's current environmental information, the vehicle control parameters, the vehicle posture and the target parking space information and a hybrid heuristic search strategy; and obtain an initial parking path based on the vehicle control parameters, the vehicle's current environmental information and the smooth parking path.

[0156] In one embodiment, the path planning module 20 is further used to obtain vehicle geometric constraints based on the vehicle control parameters and the vehicle current environment information; perform path smoothing processing based on the smoothed parking path and the vehicle geometric constraints to obtain an initial parking path.

[0157] In one embodiment, the state confirmation module 40 is also used to obtain vehicle shifting information and vehicle current environmental information when the current position of the vehicle is the target storage position; generate a state machine switching signal when the vehicle shifting information is switching from reverse gear to parking gear; and confirm whether the vehicle meets the state machine jump conditions based on the state machine switching signal and the vehicle current environmental information.

[0158] In one embodiment, the automatic parking module 30 is further used to obtain a target parking position according to a hybrid heuristic search algorithm; based on the target parking position, parking is performed according to the initial parking path and the automatic parking assistance mode, and the current position of the vehicle during the parking process is obtained; based on the current position of the vehicle, confirm whether the current position of the vehicle is the target parking position.

[0159] In one embodiment, the environmental perception module 10 is also used to obtain parking space boundary information, vehicle information around the vehicle, obstacle information around the vehicle, pedestrian detection information and lane line information based on vehicle-mounted sensors; and obtain environmental perception results based on the parking space boundary information, the vehicle information around the vehicle, obstacle information around the vehicle, the pedestrian detection information and the lane line information.

[0160] The present application provides an automatic parking device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the automatic parking method in the above-mentioned embodiment 1.

[0161] Reference below Figure 5 , which shows a schematic diagram of the structure of an automatic parking device suitable for implementing the embodiment of the present application. The automatic parking device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The automatic parking device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0162] like Figure 5As shown, the automatic parking device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the automatic parking device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the automatic parking device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an automatic parking device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0163] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0164] The automatic parking device provided by the present application adopts the automatic parking method in the above embodiment, which can solve the technical problems of vehicle speed fluctuation and jerkiness caused by the state machine jump when the vehicle switches to the automatic valet parking cruise stage after the automatic parking assisted parking is completed. Compared with the prior art, the beneficial effects of the automatic parking device provided by the present application are the same as the beneficial effects of the automatic parking method provided by the above embodiment, and the other technical features in the automatic parking device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0165] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0166] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0167] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the automatic parking method in the above-mentioned embodiment.

[0168] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0169] The computer-readable storage medium may be included in the automatic parking device; or may exist independently without being assembled into the automatic parking device.

[0170] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the automatic parking device, the automatic parking device: detects the surrounding environment of the vehicle to obtain an environmental perception result; plans a parking path according to the environmental perception result to obtain an initial parking path; parks according to the initial parking path, and confirms whether the current position of the vehicle is the target parking position; when the current position of the vehicle is the target parking position, confirms whether the vehicle meets the state machine jump condition; when it is confirmed that the vehicle meets the state machine jump condition, updates the automatic parking mode and the initial parking path, and completes the automatic parking according to the updated automatic parking mode and the updated initial parking path.

[0171] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0172] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0174] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned automatic parking method, and can solve the technical problems of vehicle speed fluctuation and jerkiness caused by state machine jump when the vehicle switches to the automatic valet parking cruise phase after the automatic parking assisted parking is completed. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the automatic parking method provided by the above-mentioned embodiment, and will not be repeated here.

[0175] The present application also provides a computer program product, including a computer program, which implements the steps of the automatic parking method as described above when executed by a processor.

[0176] The computer program product provided by the present application can solve the technical problem of vehicle speed fluctuation and jerkiness caused by state machine jump when the vehicle switches to the automatic valet parking cruise phase after the automatic parking assisted parking is completed. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the automatic parking method provided by the above embodiment, and will not be elaborated here.

[0177] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An automatic parking method, characterized in that: The method comprises: Detect the vehicle's surroundings and obtain environmental perception results; Planning a parking path according to the environmental perception result to obtain an initial parking path; Parking according to the initial parking path, confirming whether the current position of the vehicle is the target parking position; When the current position of the vehicle is the target storage position, confirm whether the vehicle meets the state machine jump condition; When it is confirmed that the vehicle meets the state machine jump condition, the automatic parking mode and the initial parking path are updated, and the automatic parking is completed according to the updated automatic parking mode and the updated initial parking path.

2. The method according to claim 1, characterized in that The automatic parking mode includes automatic parking assistance mode and automatic valet parking cruise mode: The step of updating the automatic parking mode and the initial parking path when confirming that the vehicle meets the state machine jump condition, and completing the automatic parking according to the updated automatic parking mode and the updated initial parking path includes: When it is confirmed that the vehicle meets the state machine jump condition, updating the automatic parking assistance mode to the automatic valet parking cruise mode to obtain an initial automatic valet parking cruise mode; Obtaining a target parking path according to the current position of the vehicle and the initial parking path; Obtaining a target automatic valet parking cruise mode according to the target parking path and the initial automatic valet parking cruise mode; The vehicle is controlled to travel in the target automatic valet parking cruise mode to complete automatic parking.

3. The method according to claim 1, characterized in that The step of planning a parking path according to the environmental perception result to obtain an initial parking path comprises: According to the environmental perception results, the vehicle's current environmental information, vehicle control parameters, vehicle posture and target parking space information are obtained; Generate a smooth parking path based on the vehicle's current environment information, the vehicle control parameters, the vehicle posture, the target parking space information, and a hybrid heuristic search strategy; An initial parking path is obtained according to the vehicle control parameters, the current environment information of the vehicle and the smooth parking path.

4. The method according to claim 3, characterized in that The step of obtaining an initial parking path according to the vehicle control parameters, the vehicle current environment information and the smooth parking path comprises: Obtaining vehicle geometric constraints according to the vehicle control parameters and the vehicle current environment information; According to the smoothed parking path and the vehicle geometric constraints, path smoothing processing is performed to obtain an initial parking path.

5. The method according to claim 1, characterized in that When the current position of the vehicle is the target storage position, the step of confirming whether the vehicle meets the state machine jump condition includes: When the current position of the vehicle is the target storage position, obtaining vehicle shift information and vehicle current environment information; When the vehicle shift information is a shift from a reverse gear to a parking gear, generating a state machine switching signal; According to the state machine switching signal and the current environment information of the vehicle, it is confirmed whether the vehicle meets the state machine jump condition.

6. The method according to claim 1, characterized in that The step of parking the vehicle according to the initial parking path and confirming whether the current position of the vehicle is the target parking position comprises: Obtain the target kneading library position according to the hybrid heuristic search algorithm; Based on the target parking position, parking is performed according to the initial parking path and the automatic parking assistance mode, and the current position of the vehicle during the parking process is obtained; According to the current position of the vehicle, it is confirmed whether the current position of the vehicle is the target storage position.

7. The method according to claim 1, characterized in that The step of detecting the vehicle's surrounding environment and obtaining an environmental perception result comprises: Obtain parking space boundary information, vehicle information around the vehicle, obstacle information around the vehicle, pedestrian detection information, and lane line information based on vehicle-mounted sensors; An environmental perception result is obtained according to the parking space boundary information, the vehicle information around the vehicle, the obstacle information around the vehicle, the pedestrian detection information and the lane line information.

8. An automatic parking device, characterized in that: The device comprises: The environmental perception module is used to detect the vehicle's surrounding environment and obtain environmental perception results; A path planning module, used to plan a parking path according to the environmental perception result to obtain an initial parking path; An automatic parking module, used to park the vehicle according to the initial parking path and confirm whether the current position of the vehicle is the target parking position; A state confirmation module, used to confirm whether the vehicle meets the state machine jump condition when the current position of the vehicle is the target storage position; The automatic parking module is further configured to update the automatic parking mode and the initial parking path when confirming that the vehicle meets the state machine jump condition, and complete automatic parking according to the updated automatic parking mode and the updated initial parking path.

9. An automatic parking device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the automatic parking method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the automatic parking method according to any one of claims 1 to 7 are implemented.

Images