Parking control method, system and vehicle

Abstract

The present application provides a parking control method, system, and vehicle, wherein the method includes: obtaining vehicle parameter information and parking information, wherein the parameter information includes vehicle width and lateral door opening distance, and the parking information includes vehicle position, parking space position, and obstacle information in the parking environment; performing an exit space assessment based on the parameter information and obstacle information to determine the lateral safety distance between the vehicle and the obstacle; constructing a safe driving corridor based on the parking information, and using the lateral safety distance as a constraint for path search to search for a target parking path within the safe driving corridor; and controlling the vehicle to complete parking according to the target parking path. During the automatic parking process, an exit space assessment is performed, and the lateral safety distance between the vehicle and the obstacle obtained from the assessment is used as a parking path constraint to control the vehicle to complete parking. This can effectively ensure that drivers and passengers have sufficient door opening space, allowing them to exit the vehicle safely and conveniently, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving assistance technology, and in particular to a parking control method, system and vehicle. Background Art

[0002] With the rapid development of autonomous driving technology, automated parking, a core feature of smart cars, has become a key technology for enhancing the driving experience and convenience. By integrating multiple technologies, including environmental perception, path planning, and safety assurance, automated parking technology aims to enable vehicles to autonomously find and park in parking spaces without human intervention, providing users with a more convenient and comfortable driving experience.

[0003] In related technologies, automatic parking primarily focuses on ensuring that the vehicle can be safely and accurately parked in a parking space that meets geometric constraints, while ignoring the convenience and safety of the driver and passengers getting out of the vehicle. That is, after parking is actually completed, the vehicle may be parked too close to surrounding obstacles, making it impossible for the driver and passengers to open the door and get out, or unable to open the door and get out safely, thus making it difficult or dangerous for the driver and passengers to open the door. To ensure that the driver and passengers can get out of the vehicle conveniently and safely, some methods set a fixed distance threshold as a standard to constrain the distance between the vehicle and obstacles when parking. However, this method is difficult to adapt to dynamically changing parking environments and complex and diverse parking space layout requirements. This is especially true when facing diagonal parking spaces or when there are moving vehicles around, as well as in crowded urban areas, where parking spaces are compact and there are many surrounding obstacles. There are still obvious shortcomings in ensuring the safety and convenience of the driver and passengers getting out of the vehicle. Summary of the Invention

[0004] In view of the above shortcomings, the present application discloses a parking control method, system and vehicle, which are used to solve the technical problem that parking technology cannot ensure the safety and convenience of drivers and passengers getting off the vehicle.

[0005] In a first aspect, the present application provides a parking control method, the method comprising: obtaining vehicle parameter information and parking information, the parameter information including vehicle width and door lateral opening distance, and the parking information including vehicle position, parking space position, and obstacle information in the parking environment; performing an exit space assessment based on the parameter information and the obstacle information to determine a lateral safety distance between the vehicle and the obstacle; constructing a safe driving corridor based on the parking information, and searching for a target parking path in the safe driving corridor using the lateral safety distance as a constraint condition for path search; and controlling the vehicle to complete parking according to the target parking path.

[0006] In one embodiment of the present application, determining the lateral safety distance between the vehicle and the obstacle includes: calculating the obstacle width, the vehicle width and the lateral opening distance of the door to obtain a theoretical safety distance between the vehicle and the obstacle, the obstacle information including the obstacle width; calculating the lateral safety distance based on the theoretical safety distance and a preset safety distance margin, the safety distance margin being a compensation distance set to prevent the vehicle from colliding with the obstacle.

[0007] In one embodiment of the present application, constructing a safe driving corridor based on the parking information includes: determining multiple candidate positions for the vehicle based on the vehicle position, the parking space position and at least one obstacle position, the obstacle information including the obstacle position of at least one obstacle, and the candidate positions being positions where the vehicle will not collide with all obstacles; determining the total potential energy value of each candidate position based on the distance between each candidate position and each obstacle; if the total potential energy value of the target candidate position is less than or equal to a preset safety potential energy threshold, determining the target candidate position as the target position; and generating the safe driving corridor based on each target position.

[0008] In one embodiment of the present application, the total potential energy value of each candidate position is determined based on the distance between each candidate position and each obstacle, including: calculating each obstacle position with the candidate position, the lateral safety distance and a preset sensitivity coefficient to obtain the potential energy value of each obstacle, wherein the sensitivity coefficient represents the sensitivity of the potential energy to changes in the obstacle distance; and calculating the sum of the potential energy values ​​of each obstacle to obtain the total potential energy value.

[0009] In one embodiment of the present application, using the lateral safety distance as a constraint for path search and searching for a target parking path in the safe driving corridor includes: monitoring the potential energy field gradient in the safe driving corridor and determining an initial parking path based on the descending direction of the potential energy field gradient, wherein the distance between each node in the initial parking path and each obstacle is greater than or equal to the lateral safety distance; and locally adjusting the initial parking path based on real-time changes in the safe driving corridor to obtain a target parking path, wherein the distance between each node in the target parking path and each obstacle is greater than or equal to the lateral safety distance.

[0010] In one embodiment of the present application, the method for obtaining the obstacle information includes: obtaining environmental perception data of the parking environment, the environmental perception data including lidar data, ultrasonic data, and image data; fusing the lidar data, the ultrasonic data, and the image data to obtain a multi-source environment model; and identifying obstacles in the multi-source environment model to obtain the obstacle information of at least one obstacle, the obstacle information including obstacle position, obstacle width, obstacle height, and obstacle type.

[0011] In one embodiment of the present application, the laser radar data, the ultrasonic data and the image data are fused to obtain a multi-source environment model, including: constructing a data fusion model according to the characteristics of the laser radar, ultrasonic sensor and camera, the data fusion model including a prediction sub-model and an update sub-model, the prediction sub-model including a system model matrix, a control input influence matrix and a process noise covariance matrix, and the update sub-model including a measurement model matrix; inputting the real-time control input vector of the obstacle into the prediction sub-model to obtain a predicted state vector and a predicted state covariance matrix, the predicted state vector and the predicted state covariance matrix being the state vector and state covariance matrix of the obstacle at the current moment; determining the measurement value vector and the measurement noise covariance matrix of the obstacle at the current moment according to the laser radar data, the ultrasonic data and the image data; and correcting the predicted state vector and the predicted state covariance matrix according to the measurement value vector, the measurement noise covariance matrix and the update sub-model to obtain the corrected state vector and state covariance matrix to form the multi-source environment model.

[0012] In one embodiment of the present application, controlling the vehicle to complete parking according to the target parking path includes: if the distance between a target node in the target parking path and each obstacle is less than the lateral safety distance, determining a target parking mode for the vehicle from multiple parking modes, the multiple parking modes being, in descending order of priority, a path lateral adjustment mode, a delay mode, and a remote control mode; if the target parking mode is the path lateral adjustment mode, performing lateral adjustments on the target parking path and controlling the vehicle to complete parking according to the adjusted target parking path; if the target parking mode is the delay mode, activating a first-level prompt and the delay mode, and controlling the vehicle to complete parking according to the target parking path; the first-level prompt includes suggesting that the driver and passengers exit the vehicle before parking and switching the parking mode to the delay mode; if the target parking mode is the remote control mode, activating a second-level prompt and the remote control mode, and upon receiving a remote parking command, controlling the vehicle to complete parking according to the target parking path; the second-level prompt includes suggesting that the driver and passengers exit the vehicle before parking and switching the parking mode to the remote control mode.

[0013] In a second aspect, the present application provides a parking control system, which includes: a data acquisition module for acquiring vehicle parameter information and parking information, the parameter information including vehicle width and door lateral opening distance, and the parking information including vehicle position, parking space position and obstacle information in the parking environment; a space assessment module for performing an exit space assessment based on the parameter information and the obstacle information, and determining a lateral safety distance between the vehicle and the obstacle; a path planning module, in which a user constructs a safe driving corridor based on the parking information, and uses the lateral safety distance as a constraint condition for path search, and searches for a target parking path in the safe driving corridor; and a parking control module for controlling the vehicle to complete parking according to the target parking path.

[0014] In a third aspect, the present application provides a vehicle, using the parking control method as described in the first aspect, or including the parking control system as described in the second aspect.

[0015] As described above, the parking control method, system, and vehicle provided by the embodiments of the present application have the following beneficial effects:

[0016] First, the system obtains vehicle parameters and parking information. The parameters include vehicle width and lateral door opening distance, while the parking information includes vehicle position, parking space location, and obstacle information in the parking environment. Then, based on the parameters and obstacle information, it performs an exit space assessment to determine the safe lateral distance between the vehicle and obstacles. A safe driving corridor is then constructed based on the parking information. The target parking path is searched within the safe driving corridor using the safe lateral distance as a constraint in the path search. Finally, the vehicle is controlled to complete parking according to the target parking path. During the automated parking process, the exit space is pre-assessed using the safe exit space assessment mechanism. This mechanism integrates vehicle width, lateral door opening distance, and obstacle information to determine the safe lateral distance between the vehicle and obstacles. This lateral distance is used as a parking path constraint to control the vehicle to complete parking, ensuring sufficient door opening space after parking. This effectively ensures that drivers and passengers have ample door opening space, allowing them to exit the vehicle safely and conveniently, enhancing 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, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0019] Figure 1 is a schematic diagram of an implementation environment of a parking control system shown in an exemplary embodiment of the present application;

[0020] Figure 2 is a flowchart of a parking control method shown in an exemplary embodiment of the present application;

[0021] Figure 3 is a flowchart of a specific parking control method shown in an exemplary embodiment of the present application;

[0022] Figure 4 is a block diagram of a parking control system shown in an exemplary embodiment of the present application;

[0023] Figure 5 It is a block diagram of another parking control system shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0025] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0026] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0027] Automatic parking technology has corresponding technical applications in environmental perception, path planning, and safety assurance. However, the inventors of this application have discovered that automatic parking primarily focuses on safely and accurately parking a vehicle in a parking space that meets geometric constraints, while ignoring the convenience and safety of passengers exiting the vehicle. Specifically, after parking is completed, the vehicle may be parked too close to surrounding obstacles, making it impossible for passengers to open the door to exit or unable to open the door safely to exit, thus making it difficult or dangerous for passengers to open the door. In order to ensure that drivers and passengers can get off the vehicle conveniently and safely, some solutions set a fixed distance threshold as a standard to constrain the distance between the vehicle and obstacles when parking. However, this method is difficult to adapt to the dynamically changing parking environment and the complex and diverse parking space layout requirements, especially when facing diagonal parking spaces or when there are moving vehicles around, and in crowded urban areas, where parking spaces are compact and there are many obstacles around, the fixed threshold cannot adjust the safety margin in time. There are still obvious shortcomings in ensuring the safety and convenient exit of drivers and passengers. Therefore, how to ensure the safety and convenient exit of drivers and passengers during automatic parking has become an urgent problem to be solved.

[0028] Therefore, see Figure 1 , Figure 1 FIG. 1 is a schematic diagram of an implementation environment of a parking control system according to an exemplary embodiment of the present application. Figure 1 As shown, the implementation environment includes a vehicle 110 and a parking control system 120, wherein the parking control system 120 is embedded in the vehicle 110 and is used to implement parking control of the vehicle 110. The parking control system 120 includes but is not limited to a vehicle-mounted system and an onboard computer. During the automatic parking process, the parking control system 120 pre-evaluates the parking space through a safe exit space assessment mechanism. That is, the lateral safe distance between the vehicle and the obstacle is determined by comprehensively considering the vehicle width, the lateral opening distance of the door, and obstacle information. The lateral safe distance is used as a parking path constraint to ensure that there is sufficient space for the door to open after parking. The vehicle is controlled to complete parking, thereby effectively ensuring that the driver and passengers have sufficient door opening space, allowing them to exit the vehicle safely and conveniently, thereby improving the user's driving experience.

[0029] See Figure 2 , Figure 2 This is a flow chart of a parking control method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1 The implementation environment shown is shown. It should be understood that the method can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0030] like Figure 2As shown, in an exemplary embodiment, the parking control method includes at least steps S210 to S240, which are described in detail as follows:

[0031] Step S210 , obtaining vehicle parameter information and parking information, wherein the parameter information includes vehicle width and door lateral opening distance, and the parking information includes vehicle position, parking space position, and obstacle information in the parking environment.

[0032] Step S220 : performing an alighting space assessment based on the parameter information and the obstacle information to determine a lateral safety distance between the vehicle and the obstacle.

[0033] In step S230 , a safe driving corridor is constructed based on the parking information, and the lateral safety distance is used as a constraint condition for path search to search for a target parking path in the safe driving corridor.

[0034] Step S240: Control the vehicle to complete parking according to the target parking path.

[0035] Among them, the lateral opening distance of the door refers to the maximum horizontal distance from the outermost edge of the door to the side of the car body when the door is open, that is, the space required by the door in the lateral direction; the lateral safety distance refers to the minimum lateral distance that must be maintained between the vehicle and the obstacle to avoid the door colliding with the obstacle when it is opened based on the lateral opening distance of the door; the safe driving corridor refers to the drivable area of ​​the vehicle, within which the vehicle always moves within a safe range.

[0036] In addition, the vehicle width can be obtained from the cloud database, and the lateral opening distance of the door can be obtained from the door control system. The lateral opening distance of the door can be the distance corresponding to when the door is fully open, or the distance corresponding to the user's personalized opening angle; the vehicle position can be obtained based on the on-board positioning system, and the parking space position can be obtained by calling the digital map of the parking lot, or based on the camera. The obstacle information in the parking environment can be obtained based on lidar, ultrasonic sensors, cameras and their combination.

[0037] In step S210 , the vehicle's parameter information and parking information are obtained to provide input for subsequent alighting space assessment and parking path planning.

[0038] In step S220, the vehicle width, door opening requirements, and obstacle information are comprehensively considered to evaluate the exit space and determine the lateral safety distance between the vehicle and the obstacle. This is the minimum distance between the vehicle and the obstacle that must be maintained after parking. Different door opening requirements or different obstacle information will result in different lateral safety distances, and a dynamic evaluation mechanism for safe exit space has been established.

[0039] In step S230, a safe driving corridor is constructed based on the vehicle position, parking space position, and obstacle information to ensure that the vehicle can park within a safe range. The lateral safety distance is used as a constraint for path search, and the target parking path is searched in the safe driving corridor to meet the lateral safety distance requirements throughout the entire process, ensuring that there is enough space for the vehicle to get off after parking.

[0040] In step S240 , the vehicle is controlled to accurately track the target parking path, thereby completing parking safely and leaving enough space for the driver and passengers to get off the vehicle.

[0041] In this embodiment, during the automatic parking process, the exit space is pre-evaluated through the safe exit space assessment mechanism. That is, the vehicle width, the lateral door opening distance and obstacle information are comprehensively considered to determine the lateral safe distance between the vehicle and the obstacle. This lateral safe distance is used as a parking path constraint to ensure that there is enough space for the door to open after parking. The vehicle is controlled to complete parking, thereby effectively ensuring that the driver and passengers have sufficient space to open the door, allowing them to exit the vehicle safely and conveniently, thereby improving the user's driving experience.

[0042] In addition, in this embodiment, based on changes in parking progress and dynamic changes in the environment, the safe driving corridor and the target parking path are also dynamically updated.

[0043] In one embodiment, a method for obtaining obstacle information includes: acquiring environmental perception data of the parking environment, the environmental perception data including lidar data, ultrasonic data, and image data; fusing the lidar data, ultrasonic data, and image data to obtain a multi-source environment model; and identifying obstacles in the multi-source environment model to obtain obstacle information of at least one obstacle, the obstacle information including obstacle position, obstacle width, obstacle height, and obstacle type.

[0044] Among them, the lidar data is captured by the lidar and is three-dimensional point cloud data. Each point cloud data point can be expressed as ,in, is the index of the point cloud data point, Indicates the The spatial coordinate value of the point cloud data point in the X-axis direction, Indicates the The spatial coordinate value of the point cloud data point in the Y-axis direction, Indicates the The spatial coordinate value of each point cloud data point in the Z-axis direction; ultrasonic data is captured by ultrasonic sensors to supplement close-range obstacle detection, especially soft obstacles (such as pedestrians), and provide a series of distance measurement values ,in Represents different ultrasonic sensors; image data is captured by the camera, which is a high-resolution image used for visual recognition and scene understanding, generating image frames. Each pixel can be represented as ,in is the index of the pixel, Represents pixel points The color component value in the red channel, Represents pixel points The color component value in the green channel, Represents pixel points The color component value in the blue channel. LiDAR provides high-precision 3D point cloud data, clearly showing the spatial structure of the surrounding environment. Ultrasonic sensors focus on close-range obstacle detection, especially for soft obstacles. Cameras capture rich visual images, facilitating scene understanding and target recognition.

[0045] In this embodiment, most parking control solutions rely on a single sensor to perceive environmental data, but a single sensor cannot guarantee the accuracy of environmental perception. For example, although ultrasonic sensors can detect close-range obstacles, they are easily interfered with by environmental noise in complex environments, resulting in an increased false detection rate. In noisy city streets or parking lots, surrounding noise signals may be misinterpreted as obstacle signals. Cameras are severely affected by lighting conditions. In harsh environments such as low light, rain, and snow, image quality is greatly degraded, significantly reducing the accuracy of obstacle detection based on image recognition. In addition, a single sensor has weak real-time tracking capabilities for moving pedestrians, vehicles, and other obstacles, and has a low recognition rate for unstructured obstacles such as temporary roadblocks and irregular debris. Therefore, in this embodiment, multi-sensor fusion technology is adopted to organically combine lidar, camera, and ultrasonic sensor to form a complementary perception system, which makes up for the limitations of a single sensor and realizes all-round perception of the vehicle's surrounding environment. In this way, obstacle recognition is performed based on the multi-source environment model obtained by all-round perception. Regardless of light changes, obstacle obstruction or severe weather conditions, the vehicle's surrounding environment can be stably perceived, ensuring the accuracy of obstacle recognition in complex environments.

[0046] In one possible embodiment, a deep learning algorithm is used to identify obstacles in a multi-source environment model and determine the obstacle boundary and obstacle type. The obstacle boundary is represented as ,in, 、 is the center point coordinate, indicating the obstacle position, 、 are the obstacle width and obstacle height, is the index of the obstacle. Semantic segmentation can be used to define the obstacle boundary. The segmentation network predicts the obstacle bounding box, significantly enhancing obstacle recognition. Obstacle types include vehicles, pedestrians, and rock piers.

[0047] For example, the deep learning algorithm is CNN (Convolutional Neural Network). The present application embodiment does not limit the deep learning algorithm. The CNN algorithm is used to extract features from the multi-source environment model, and then the obstacles are classified through the fully connected layer, and the probability of each pixel belonging to an obstacle is output. , define the threshold To determine whether a pixel belongs to an obstacle:

[0048] Formula (1)

[0049] in, Represents pixels Whether it is recognized as an obstacle (1 for yes, 0 for no).

[0050] In a possible embodiment, the obstacle type also includes ground obstacles and off-ground obstacles. If it is a ground obstacle, the obstacle height refers to the vertical distance from the ground to the top of the obstacle. If it is an off-ground obstacle, the obstacle height is the vertical distance from the lowest point of the obstacle to the ground.

[0051] For example, ground obstacles include stone pillars, pedestrians, etc. on the ground, and off-ground obstacles include hanging warning lights, branches of large trees, etc.

[0052] In a possible embodiment, the obstacle height is used to filter obstacles that do not affect the opening of the vehicle door.

[0053] In this embodiment, if the obstacle is on the ground, the obstacle's height is compared with the height of the lower edge of the vehicle door from the ground. If the obstacle's height is less than the lower edge of the vehicle door from the ground, the vehicle door will not collide with the obstacle when it is opened. If the obstacle is above the ground, the obstacle's height is compared with the height of the upper edge of the vehicle door from the ground. If the obstacle's height is greater than the upper edge of the vehicle door from the ground, the vehicle door will not collide with the obstacle when it is opened. This introduces the height dimension for intelligent obstacle filtering. During parking control, these obstacles are not considered when calculating the lateral safety distance or planning the target parking path, significantly improving parking efficiency while ensuring parking safety.

[0054] In one embodiment, laser radar data, ultrasonic data, and image data are fused to obtain a multi-source environment model, including: constructing a data fusion model based on the characteristics of the laser radar, ultrasonic sensor, and camera, the data fusion model including a prediction sub-model and an update sub-model, the prediction sub-model including a system model matrix, a control input influence matrix, and a process noise covariance matrix, and the update sub-model including a measurement model matrix; inputting a real-time control input vector of an obstacle into the prediction sub-model to obtain a predicted state vector and a predicted state covariance matrix, the predicted state vector and the predicted state covariance matrix being the state vector and state covariance matrix of the obstacle at the current moment; determining a measurement value vector and a measurement noise covariance matrix of the obstacle at the current moment based on the laser radar data, ultrasonic data, and image data; and correcting the predicted state vector and the predicted state covariance matrix based on the measurement value vector, the measurement noise covariance matrix, and the update sub-model to obtain the corrected state vector and state covariance matrix, thereby forming the multi-source environment model.

[0055] Among them, the state vector is used to describe the position, velocity, acceleration, etc. of obstacles (i.e. objects around the vehicle).

[0056] In this embodiment, traditional multi-source data fusion methods, such as fusing 3D point cloud data generated by lidar with visual image data captured by cameras, struggle to effectively handle nonlinear dynamic environments. This results in insufficient environmental modeling accuracy in actual parking scenarios, failing to accurately reflect the actual conditions surrounding the vehicle, impacting subsequent path planning and safety assessments. Therefore, multi-source data fusion based on the Kalman filter algorithm can better handle nonlinear dynamic environments, improving both the efficiency of fusion of heterogeneous multi-source data and the accuracy of environmental modeling.

[0057] Furthermore, this embodiment designs a system model matrix, a control input influence matrix, a process noise covariance matrix, and a measurement model matrix based on the characteristics of the lidar, ultrasonic sensor, and camera. After constructing the data fusion model, the obstacle's real-time control input vector is input into the prediction sub-model, which predicts the obstacle's current state vector and state covariance matrix. Next, the obstacle's measurement value vector and measurement noise covariance matrix are determined based on the lidar, ultrasonic, and image data. Combined with the update sub-model, the predicted state vector and predicted state covariance matrix are modified to obtain the obstacle's final state vector and state covariance matrix, forming a multi-source environmental model. Subsequently, the obstacle's state vector and state covariance matrix are continuously predicted and modified at the next moment, generating a real-time multi-source environmental model. This provides reliable environmental data support for subsequent obstacle identification, safe exit space assessment, and parking path planning.

[0058] For example, the data fusion model is a Kalman filter model, that is, the fusion of multi-source data is realized based on the Kalman filter, and its core lies in the two steps of the prediction stage and the update stage. The expression of the prediction sub-model is:

[0059] Formula (2)

[0060] Formula (3)

[0061] in, represents the state vector predicted at the current moment, represents the state vector predicted at the previous moment, represents the system model matrix, represents the control input influence matrix, represents the control input vector, represents the state covariance matrix predicted at the current moment, represents the state covariance matrix predicted at the previous moment, represents the process noise covariance matrix;

[0062] The expression for updating the submodel is:

[0063] Formula (4)

[0064] Formula (5)

[0065] Formula (6)

[0066] in, represents the Kalman gain, represents the state covariance matrix predicted at the current moment, represents the measurement model matrix, represents the measurement noise covariance matrix, represents the corrected state vector at the current moment, represents the state vector predicted at the current moment, represents the measurement value vector, represents the corrected state covariance matrix at the current moment, Represents the identity matrix.

[0067] In the prediction sub-model, The spatial position information of the object obtained by the laser radar (reflected in (middle), distance information measured by ultrasonic sensor and the feature information of the object recognized by the camera (such as shape, color, etc., which are indirectly reflected in the state vector); It is the system model matrix, which is used to describe the transition of system state over time. Its connection with sensor data lies in that the setting of its parameters needs to consider the environmental change laws reflected by different sensor data; is the control input influence matrix, is the control input vector, which is mainly related to the position and velocity of the obstacle; is the predicted state covariance matrix, which is used to measure the uncertainty of the obstacle prediction state. Its calculation depends on the accuracy and reliability of different sensor data. For example, the accuracy of lidar data, the measurement error of ultrasonic sensors, and the accuracy of camera recognition all affect the calculation of the covariance matrix. It is the process noise covariance matrix, which is used to represent the noise interference in the system process. The sensor will inevitably be affected by various noises during the data collection process, such as the measurement noise of the lidar, the environmental noise interference of the ultrasonic sensor, and the image noise of the camera. These noise factors will be reflected in middle.

[0068] In the update submodel, is the Kalman gain, which is used to weigh the predicted value and the measured value. Its calculation is closely related to the accuracy of the sensor data; It is a measurement model matrix used to map the obstacle state to the measurement space, that is, to map the 3D point cloud data measured by the lidar, the distance measurement value of the ultrasonic sensor, and the visual feature information of the camera to a unified measurement space for data fusion; It is a measurement value vector, which directly corresponds to the data collected by each sensor, that is, the three-dimensional point cloud data of the lidar , distance measurement value of ultrasonic sensor And the camera's pixel information The feature vector obtained after processing; It is the measurement noise covariance matrix, which is used to represent the noise interference in the measurement process. Different sensors have different measurement noise characteristics, such as the measurement noise distribution of lidar, the measurement error range of ultrasonic sensors, and the image noise characteristics of cameras. The value of .

[0069] In one embodiment, determining the lateral safety distance between a vehicle and an obstacle includes: calculating the obstacle width, the vehicle width, and the lateral door opening distance to obtain a theoretical safety distance between the vehicle and the obstacle, where the obstacle information includes the obstacle width; calculating the lateral safety distance based on the theoretical safety distance and a preset safety distance margin, where the safety distance margin is a compensation distance set to prevent the vehicle from colliding with the obstacle.

[0070] In this embodiment, considering that during automatic parking, the vehicle door needs to have enough space to open safely and allow the driver and passengers to get off the vehicle safely and conveniently, and the setting method of the fixed distance threshold cannot dynamically adapt to various parking scenarios and various environmental changes, and cannot effectively ensure that the driver and passengers can get off the vehicle safely and conveniently, a dynamic lateral safety distance calculation method is proposed, that is, combining the obstacle width, vehicle width and the lateral opening distance of the door to first determine the theoretical safety distance. The theoretical safety distance varies based on the different obstacle widths in the environment. At the same time, in order to avoid the occurrence of accidental collisions, a safety margin, that is, a safety distance allowance, is added on the basis of the theoretical safety distance. In this way, the shortcomings of the static safety distance model are effectively solved and the reliability of the obtained lateral safety distance is guaranteed.

[0071] For example, the safety distance margin is a compensation distance set to prevent the vehicle from colliding with an obstacle due to obstacle recognition errors, changes in the parking environment, and parking position deviations.

[0072] In this way, the calculated lateral safety distance is more in line with the actual situation. No matter how complex the parking space layout is or how the surrounding obstacles change dynamically, it can ensure that there is enough space on both sides of the vehicle for drivers and passengers to get off safely and conveniently after the vehicle is parked.

[0073] For example, the calculation formula for the lateral safety distance is:

[0074] Formula (7)

[0075] in, Indicates the lateral safety distance, Indicates the width of the vehicle, Indicates the width of the obstacle, Indicates the horizontal opening distance of the door. Indicates the safety distance margin.

[0076] In a possible embodiment, if multiple obstacles are identified, it is necessary to calculate the lateral safety distance between the vehicle and each obstacle.

[0077] In one embodiment, a safe driving corridor is constructed based on parking information, including: determining multiple candidate positions for the vehicle based on the vehicle position, the parking space position, and the position of at least one obstacle, the obstacle information including the obstacle position of at least one obstacle, and the candidate positions being positions where the vehicle will not collide with all obstacles; determining a total potential energy value for each candidate position based on the distance between each candidate position and each obstacle; if the total potential energy value of the target candidate position is less than or equal to a preset safety potential energy threshold, determining the target candidate position as the target position; and generating a safe driving corridor based on each target position.

[0078] In this embodiment, in order to ensure that the vehicle is always in a safe state in a complex environment during the automatic parking process, a safe driving corridor construction algorithm is proposed to dynamically generate a channel for the vehicle to safely drive through real-time analysis and calculation of the vehicle's surrounding environment information.

[0079] In this embodiment, the total potential energy value is used to measure the safe distance between the vehicle and surrounding obstacles when it is at a certain candidate position, that is, to evaluate the possibility of a collision of the vehicle at a certain candidate position. The smaller the total potential energy value, the safer the candidate position.

[0080] In this embodiment, all positions where the vehicle will not collide with any obstacles are first selected from the parking environment as candidate positions for forming a safe driving corridor. Then, based on whether the total potential energy value of each candidate position meets the safety potential energy threshold condition, the target positions that ultimately form the safe driving corridor are screened from the candidate positions. In this way, by constructing a safe driving corridor through the potential energy field, the safest vehicle driving area can be selected, the robustness of environmental modeling is optimized, it is adaptable to various complex environments, and the collision risk of the vehicle can be effectively reduced.

[0081] Exemplarily, the safe driving corridor is defined by the following formula:

[0082] Formula (8)

[0083] in, Indicates that the vehicle is Safe driving corridor at all times, Indicates that the vehicle is A candidate position at the moment, Indicates that the vehicle is Free configuration space at all times, Indicates that the vehicle is Always in the selected position The total potential energy value when Indicates the safety potential energy threshold.

[0084] In this exemplary embodiment, The candidate locations of all vehicles that meet specific conditions The specific condition is From the vehicle Free configuration space at all times , which means the candidate position It is the position that the vehicle can theoretically reach without colliding with any known obstacles. The conditions that need to be met are , that is, the vehicle is Always in the selected position The total potential energy value The potential energy safety threshold cannot be exceeded , thereby selecting the safest vehicle driving area and forming a safe driving corridor.

[0085] In addition, as the vehicle moves and the state of the surrounding obstacles changes (such as the movement of other vehicles, the movement of pedestrians, etc.), the total potential energy value of the vehicle at different positions at each moment will also change accordingly. When the total potential energy value of the vehicle at a certain candidate position meets When a position is considered safe, it is connected to all these locations that meet the safety conditions to form a dynamically changing area within which the vehicle can travel, known as a safe driving corridor. This safe driving corridor adjusts its shape and position in real time as the vehicle moves and the surrounding environment changes. For example, when a previously stationary obstacle begins to move towards the vehicle, the new total potential energy value of that position is calculated in real time. If the safety conditions are not met, the boundary of the safe driving corridor will shrink accordingly, away from the obstacle, to ensure that the vehicle always stays within the safe area.

[0086] In one embodiment, the total potential energy value of each candidate position is determined based on the distance between each candidate position and each obstacle, including: calculating each obstacle position with the candidate position, the lateral safety distance and a preset sensitivity coefficient to obtain the potential energy value of each obstacle, where the sensitivity coefficient represents the sensitivity of the potential energy to changes in the obstacle distance; and calculating the sum of the potential energy values ​​of each obstacle to obtain the total potential energy value.

[0087] Among them, the potential energy value of each obstacle is used to measure the safe distance between the vehicle and a certain obstacle when it is at a certain candidate position, that is, to evaluate the possibility of the vehicle colliding with a certain obstacle at a certain candidate position. The smaller the potential energy value, the smaller the possibility of collision with the obstacle at a certain candidate position, that is, the obstacle is farther away from the vehicle.

[0088] Additionally, the sensitivity coefficient indicates the potential energy function's sensitivity to changes in obstacle distance. In other words, it reflects the rate or magnitude of change in the potential energy value when the distance between the vehicle and the obstacle changes. A high sensitivity coefficient means that even a small change in the distance between the vehicle and the obstacle will result in a significant change in the potential energy value, indicating that the potential energy is sensitive to distance changes. A low sensitivity coefficient indicates that the potential energy value is less responsive to distance changes. The sensitivity coefficient adjusts the steepness of the potential energy function. By properly setting the sensitivity coefficient, the sensitivity of the potential energy function to changes in the distance between the vehicle and the obstacle can be controlled, thereby optimizing the generation of safe driving corridors.

[0089] In this embodiment, to ensure that the vehicle remains safe in complex environments during automated parking and that drivers and passengers have ample space to exit the vehicle, all obstacles are comprehensively considered and the total potential energy of the vehicle at a specific candidate position is comprehensively calculated. Furthermore, the calculation of the total potential energy for each candidate position not only takes into account the distance between the vehicle and the obstacle but also incorporates the lateral safety distance and sensitivity coefficient. This ensures that the potential energy value is closely correlated with the safe space required for safe exiting and the sensitivity to changes in obstacle distance. This effectively optimizes the generation of a safe driving corridor.

[0090] In this embodiment, the corresponding lateral safety distance is used when calculating the potential energy value of each obstacle.

[0091] For example, the total potential energy value is calculated as follows:

[0092] Formula (9)

[0093] in, Indicates that the vehicle is Always in the selected position The total potential energy value when Indicates the number of obstacles currently perceived. Indicates that the vehicle is A candidate position at the moment, Indicates the Obstacles in The obstacle position at the moment, Indicates the lateral safety distance, Represents the sensitivity coefficient.

[0094] In this exemplary embodiment, It can be the vehicle's coordinate information or a set of parameters that can describe the vehicle's posture in space; Real-time updates ensure that the potential energy function can accurately reflect the real-time distance between the vehicle and each obstacle.

[0095] In a possible embodiment, if the parking space is in an environment with dense obstacles, a larger sensitivity coefficient is set to ensure higher safety; if the parking space is in an environment with sparse obstacles, a smaller sensitivity coefficient is set to avoid overreaction.

[0096] As one possible embodiment, the criteria for determining whether obstacles are dense or sparse can be determined based on both the number and distance of surrounding obstacles. For example, if the number of obstacles detected within a preset distance range is greater than or equal to a preset threshold, the obstacle situation is considered dense. Conversely, if the number of obstacles is less than the preset threshold, the obstacle situation is considered sparse. Furthermore, the sensitivity coefficient can be varied based on the obstacle density.

[0097] In one embodiment, a target parking path is searched within a safe driving corridor using the lateral safety distance as a constraint for path search. This includes: monitoring the potential energy field gradient within the safe driving corridor and determining an initial parking path based on the descending direction of the potential energy field gradient, wherein the distance between each node in the initial parking path and each obstacle is greater than or equal to the lateral safety distance; and locally adjusting the initial parking path based on real-time changes in the safe driving corridor to obtain a target parking path, wherein the distance between each node in the target parking path and each obstacle is greater than or equal to the lateral safety distance.

[0098] In this embodiment, conventional path planning algorithms, such as the A-star algorithm (a search algorithm) and the Rapidly Exploring Random Trees (RRT) algorithm, lack the ability to dynamically adjust after initial planning. This means they are unable to quickly respond to sudden environmental changes during parking, such as the appearance of an obstacle or the sudden intrusion of another vehicle, and thus increase the risk of collision. Therefore, to ensure that the vehicle remains within a safe zone and that there is ample space for passengers to exit the vehicle after parking, a parking path is searched within a constructed safe driving corridor. The lateral safety distance is used as a constraint for the path search, and local path adjustments are performed in real time to ensure the target parking path is searched and a preferred parking path is obtained. In this way, the application of a graph search algorithm combined with these constraints to plan a parking path within the safe driving corridor not only avoids obstacles but also ensures that passengers can exit the vehicle safely and conveniently after parking.

[0099] In this embodiment, the search for a vehicle parking path is guided by the real-time potential energy field gradient within the safe driving corridor. The potential energy field gradient reflects the spatial variation of potential energy values. The initial parking path is determined based on the direction of the potential energy field gradient descent. Specifically, the vehicle drives toward areas with lower potential energy values, thereby maximizing distance from obstacles and maintaining the safe corridor. Furthermore, the distance between each node in the determined initial parking path and each obstacle must be greater than or equal to the lateral safety distance. In other words, if the initial parking path selected based on a particular potential energy field gradient descent direction fails to meet this condition, i.e., if a node fails to meet the condition, the path is deemed infeasible and a path in a different potential energy field gradient descent direction is selected as the initial parking path. Each node in the initial parking path represents a vehicle position. At any node, the lateral safety distance of each obstacle is used as a criterion to determine whether the distance between each obstacle and the node meets the condition.

[0100] For example, the initial parking path is determined according to the direction in which the potential energy field gradient drops fastest. However, if the lateral safety distance condition is not met, the initial parking path is determined in the direction in which the potential energy field gradient drops second fastest. Similarly, an initial parking path that meets the lateral safety distance condition is determined.

[0101] In this embodiment, throughout the parking process, the initial parking path is locally adjusted in real time, taking into account changes in parking progress and the dynamic environment, which can affect the safety of the initial parking path and the space available for exiting after parking. Specifically, based on changes in parking progress and the dynamic environment, if the initially planned parking path is detected to be inconsistent with safe exit conditions, a dynamic trajectory replanning mechanism is immediately triggered. Based on real-time obstacle information, the initial parking path is dynamically and flexibly adjusted to achieve the target parking path. During dynamic replanning, not only must the path be aligned with the descending potential energy field gradient, but each node must also maintain a safe lateral distance from each obstacle to ensure parking safety and adequate exit space for the driver and passengers. In response to adjustments to the parking path, the vehicle's driving direction and speed will be adjusted accordingly. For example, when it is detected that the potential energy value on one side of the vehicle is higher, which means that there is a closer obstacle in that direction, the vehicle's steering will be automatically adjusted to make the vehicle drive toward the other side with lower potential energy value, thereby avoiding collision with the obstacle. The path optimization mechanism based on the potential energy field gradient will continue to run, and can flexibly respond to various emergencies during the parking process, ensure the vehicle's driving safety in real time, and create conditions for the driver and passengers to finally get off the vehicle safely, greatly improving the success rate and safety of parking.

[0102] In addition, as a possible embodiment, the lateral safety distance is referenced twice during the parking process. First, when constructing the safe driving corridor, the lateral safety distance is introduced into the calculation of the total potential energy value of each candidate vehicle position. Second, during the path search, the lateral safety distance is introduced as a constraint condition. Considering the lateral safety distance twice can effectively ensure that there is sufficient space for drivers and passengers to get off the vehicle after parking.

[0103] In one possible embodiment, path planning also needs to consider the turning radius, where the turning radius is directly related to the operability and safety of parking, and needs to meet the actual kinematic characteristics of the vehicle, and introduce curvature constraints to limit the curvature of the path to ensure the smoothness of the parking path.

[0104] In one embodiment, controlling a vehicle to complete parking according to a target parking path includes: if the distance between a target node in the target parking path and each obstacle is less than a lateral safety distance, determining a target parking mode for the vehicle from multiple parking modes, the multiple parking modes being, in descending order of priority, a path lateral adjustment mode, a delay mode, and a remote control mode; if the target parking mode is the path lateral adjustment mode, lateral adjustment is performed on the target parking path, and the vehicle is controlled to complete parking according to the adjusted target parking path; if the target parking mode is the delay mode, activating a first-level prompt and a delay mode, and controlling the vehicle to complete parking according to the target parking path; the first-level prompt includes suggesting that the driver and passengers exit the vehicle before parking and switching the parking mode to the delay mode; if the target parking mode is the remote control mode, activating a second-level prompt and a remote control mode, and upon receiving a remote parking command, controlling the vehicle to complete parking according to the target parking path; the second-level prompt includes suggesting that the driver and passengers exit the vehicle before parking and switching the parking mode to the remote control mode.

[0105] This embodiment, considering that there may still be insufficient space for passengers to exit the vehicle after parking is complete, fails to fully consider the need for human-machine collaboration. This is particularly true in extreme scenarios, such as extremely narrow spaces or complex obstacle distribution. This forces passengers to risk exiting the vehicle or abandon parking, significantly reducing the user experience. Therefore, a hierarchical decision-making mechanism is implemented, whereby parking modes with different priorities are adopted based on the real-time obstacle situation and path replanning results. This ensures safe and convenient parking solutions for passengers in a variety of complex situations.

[0106] In this embodiment, a three-level decision-making mechanism is designed, corresponding to three parking modes, which are path lateral adjustment mode, delay mode and remote control mode in descending order of priority. Among them, the path lateral adjustment mode refers to controlling the vehicle to complete parking by adjusting the path laterally, the delay mode refers to controlling the vehicle to complete parking by delaying parking, and the remote control mode refers to controlling the vehicle to complete parking by remote control, fully considering the safety requirements and human-machine collaboration in different parking scenarios.

[0107] Illustratively, determining a target parking mode for the vehicle from a plurality of parking modes includes: if the end point in the target parking path does not satisfy the lateral safety distance condition and all occupants in the vehicle can exit the vehicle from the main driver's side, determining the target parking mode to be the path lateral adjustment mode; if all occupants in the vehicle cannot exit the vehicle from the main driver's side or the lateral safety distance condition is still not satisfied after the path lateral adjustment, determining the target parking mode to be the delayed mode; and if delayed parking still does not satisfy the lateral safety distance condition, determining the target parking mode to be the remote control mode.

[0108] In this exemplary embodiment, if the target parking path does not meet safe exit conditions, a slight deviation from the original parking path is prioritized to resolve the issue. This ensures adequate exit space on at least one side of the vehicle during the parking process, maximizing safe and convenient exit for the driver and passengers without compromising overall parking efficiency. If the safe exit conditions are still not met after the path deviation adjustment, a first-level prompt and delayed entry strategy is activated. This prompts the driver and passengers promptly, advising them to exit before parking begins. Simultaneously, the vehicle will adopt a delayed entry strategy, waiting until safe exit conditions are met before continuing the parking maneuver. This provides the driver and passengers with ample time to exit safely, effectively reducing safety risks during exit. In extremely narrow parking spaces, if neither of the first two strategies can effectively ensure safe exit, a second-level prompt and remote parking strategy is activated. This requires the driver and passengers to exit the vehicle in advance. The vehicle can then complete the parking maneuver remotely via a specially developed in-vehicle app (Application) or smart device, completely eliminating the safety risks of exiting during parking and providing users with a safer and more flexible parking solution.

[0109] In addition, for the first-level and second-level prompts, the node that prompts the driver and passengers to get off the vehicle is the node in the target parking path that meets the lateral safety distance conditions.

[0110] See Figure 3 , Figure 3 FIG. 1 is a flowchart of a specific parking control method shown in an exemplary embodiment of the present application. Figure 3 As shown, the specific parking control method includes at least steps S310 to S390, which are described in detail as follows:

[0111] Step S310: configuring sensors and using the sensors to sense environmental data;

[0112] Step S320, performing multi-source data fusion on the environmental data sensed by the various sensors;

[0113] Step S330, performing obstacle identification based on the fused multi-source environment model;

[0114] Step S340: determining a lateral safety distance based on the obstacle recognition result and the vehicle parameter information;

[0115] Step S350, constructing a safe driving corridor based on the obstacle recognition results, the vehicle position, and the parking space position;

[0116] Step S360: Using the lateral safety distance as a constraint for path search, an initial parking path is searched in the safe driving corridor;

[0117] Step S370: dynamically replanning the initial parking path in real time to obtain a target parking path;

[0118] Step S380, determining a target parking mode based on the target parking path;

[0119] In step S390 , the vehicle is controlled to complete parking according to the target parking mode and the target parking path or the target parking path after lateral adjustment.

[0120] In this way, the integration of multi-source environmental perception technology, parking path planning and re-planning technology, and multi-level intelligent decision-making technology effectively improves the obstacle recognition accuracy and real-time performance in complex scenarios, and effectively resolves the contradiction between automatic parking and the safe exit of drivers and passengers, thereby providing users with a safer and more convenient parking experience.

[0121] The parking control method first obtains vehicle parameter information and parking information. The parameter information includes vehicle width and lateral door opening distance, and the parking information includes vehicle position, parking space location, and obstacle information in the parking environment. Then, based on the parameter information and obstacle information, an exit space assessment is performed to determine the safe lateral distance between the vehicle and obstacles. A safe driving corridor is then constructed based on the parking information. The target parking path is searched within the safe driving corridor using the safe lateral distance as a constraint in the path search. Finally, the vehicle is controlled to complete parking according to the target parking path. During the automated parking process, the exit space is pre-assessed using the safe exit space assessment mechanism. Specifically, the safe lateral distance between the vehicle and obstacles is determined by integrating vehicle width, lateral door opening distance, and obstacle information. This lateral distance is then used as a parking path constraint. The vehicle is controlled to complete parking with the goal of ensuring sufficient door opening space after parking. This effectively ensures that drivers and passengers have sufficient door opening space, allowing them to exit the vehicle safely and conveniently, thereby enhancing the user experience.

[0122] See Figure 4 , Figure 4 This is a block diagram of a parking control system shown in an exemplary embodiment of the present application. The system can be applied to Figure 1 The implementation environment shown is shown. It should be understood that the system can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the system is applicable.

[0123] like Figure 4 As shown, in an exemplary embodiment, the parking control system 400 includes at least a data acquisition module 410, a space assessment module 420, a path planning module 430 and a parking control module 440, which are described in detail as follows:

[0124] Data acquisition module 410, for acquiring vehicle parameter information and parking information, wherein the parameter information includes vehicle width and door lateral opening distance, and the parking information includes vehicle position, parking space position, and obstacle information in the parking environment;

[0125] The space assessment module 420 is used to perform a space assessment for getting off the vehicle based on the parameter information and the obstacle information, and determine the lateral safe distance between the vehicle and the obstacle;

[0126] Path planning module 430: The user constructs a safe driving corridor based on parking information and uses the lateral safety distance as a constraint for path search to search for the target parking path within the safe driving corridor.

[0127] The parking control module 440 is configured to control the vehicle to complete parking according to the target parking path.

[0128] It should be noted that the parking control system provided in the above embodiment and the parking control method provided in the above embodiment belong to the same concept, wherein the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0129] See Figure 5 , Figure 5 This is a block diagram of another parking control system shown in an exemplary embodiment of the present application. Figure 1 The implementation environment shown is shown. It should be understood that the system can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the system is applicable.

[0130] like Figure 5 As shown, in an exemplary embodiment, the alternative parking control system 500 includes at least an environment perception and processing module 510, a safe exit space assessment module 520, and an intelligent decision-making module 530, which are described in detail as follows:

[0131] The environment perception and processing module 510 includes a data acquisition device 511, a data fusion device 512, and an obstacle recognition device 513. The data acquisition device 511 is used to acquire environmental data sensed by various sensors, the data fusion device 512 is used to perform multi-source data fusion on the environmental data sensed by the various sensors, and the obstacle recognition device 513 is used to identify obstacles based on the fused multi-source environment model.

[0132] The safe exit space assessment module 520 includes a safe distance calculation device 521, a corridor construction device 522, a path planning device 523, and a path replanning device 524. The safe distance calculation device 521 is used to determine the lateral safe distance based on the obstacle recognition results and vehicle parameter information. The corridor construction device 522 is used to construct a safe driving corridor based on the obstacle recognition results, the vehicle position, and the parking space position. The path planning device 523 is used to use the lateral safe distance as a constraint condition for path search and search for an initial parking path in the safe driving corridor. The path replanning device 524 is used to dynamically replan the initial parking path in real time to obtain a target parking path.

[0133] The intelligent decision module 530 includes a parking mode determining device 531 , which is used to determine a target parking mode based on a target parking path;

[0134] The control module 540 includes a parking control device 541 , which is configured to control the vehicle to complete parking according to a target parking mode and a target parking path or a target parking path after lateral adjustment.

[0135] It should be noted that the parking control system provided in the above embodiment and the parking control method provided in the above embodiment belong to the same concept, wherein the contents of the operations performed by each module have been described in detail in the method embodiment and will not be repeated here.

[0136] In addition, the parking control system 500 includes all the functions of the parking control system 400. The data acquisition device 511, the data fusion device 512 and the obstacle recognition device 513 in the parking control system 500 are equivalent to the data acquisition module 410 in the parking control system 400. The safety distance calculation device 521 in the parking control system 500 is equivalent to the space assessment module 420 in the parking control system 400. The corridor construction device 522, the path planning device 523 and the path re-planning device 524 in the parking control system 500 are equivalent to the path planning module 430 in the parking control system 400. The parking control device 541 in the parking control system 500 is equivalent to the parking control module 440 in the parking control system 400.

[0137] 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.

[0138] 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.

[0139] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A parking control method, characterized in that: The method comprises: Obtaining vehicle parameter information and parking information, wherein the parameter information includes vehicle width and door lateral opening distance, and the parking information includes vehicle position, parking space position, and obstacle information in the parking environment; Performing an exit space assessment based on the parameter information and the obstacle information to determine a lateral safety distance between the vehicle and the obstacle; Constructing a safe driving corridor based on the parking information, and using the lateral safety distance as a constraint condition for path search, searching for a target parking path in the safe driving corridor; Controlling the vehicle to complete parking according to the target parking path; The constructing of a safe driving corridor based on the parking information includes: determining a plurality of candidate positions for the vehicle based on the vehicle position, the parking space position, and the position of at least one obstacle, wherein the obstacle information includes the obstacle position of at least one obstacle, and the candidate positions are positions where the vehicle will not collide with any obstacles; determining a total potential energy value of each candidate position based on a distance between each candidate position and each obstacle; determining the target candidate position as a target position if the total potential energy value of the target candidate position is less than or equal to a preset safety potential energy threshold; and generating the safe driving corridor based on each target position; The total potential energy value of each candidate position is determined based on the distance between each candidate position and each obstacle, including: calculating each obstacle position with the candidate position, the lateral safety distance and a preset sensitivity coefficient to obtain the potential energy value of each obstacle, wherein the sensitivity coefficient represents the sensitivity of the potential energy to the change in the obstacle distance; and calculating the sum of the potential energy values ​​of each obstacle to obtain the total potential energy value.

2. The parking control method according to claim 1, characterized in that: Determining the lateral safety distance between the vehicle and the obstacle includes: Calculating the width of the obstacle, the width of the vehicle, and the lateral opening distance of the door to obtain a theoretical safe distance between the vehicle and the obstacle, wherein the obstacle information includes the width of the obstacle; The lateral safety distance is calculated based on the theoretical safety distance and a preset safety distance margin, where the safety distance margin is a compensation distance set to prevent the vehicle from colliding with an obstacle.

3. The parking control method according to claim 1, characterized in that: The step of using the lateral safety distance as a constraint condition for path search and searching for a target parking path in the safe driving corridor includes: monitoring a potential energy field gradient in the safe driving corridor and determining an initial parking path based on a descending direction of the potential energy field gradient, wherein a distance between each node in the initial parking path and each obstacle is greater than or equal to the lateral safety distance; The initial parking path is partially adjusted according to real-time changes in the safe driving corridor to obtain a target parking path, wherein the distance between each node in the target parking path and each obstacle is greater than or equal to the lateral safety distance.

4. The parking control method according to claim 1, characterized in that: The method for obtaining the obstacle information includes: Acquiring environmental perception data of the parking environment, the environmental perception data including lidar data, ultrasonic data, and image data; fusing the laser radar data, the ultrasonic data, and the image data to obtain a multi-source environment model; Obstacles in the multi-source environment model are identified to obtain the obstacle information of at least one obstacle, wherein the obstacle information includes obstacle position, obstacle width, obstacle height, and obstacle type.

5. The parking control method according to claim 4, characterized in that: The fusing of the laser radar data, the ultrasonic data and the image data to obtain a multi-source environment model includes: A data fusion model is constructed based on the characteristics of the lidar, ultrasonic sensor, and camera. The data fusion model includes a prediction sub-model and an update sub-model. The prediction sub-model includes a system model matrix, a control input influence matrix, and a process noise covariance matrix. The update sub-model includes a measurement model matrix. Inputting the real-time control input vector of the obstacle into the prediction sub-model to obtain a predicted state vector and a predicted state covariance matrix, wherein the predicted state vector and the predicted state covariance matrix are the state vector and state covariance matrix of the obstacle at the current moment; Determining a measurement value vector and a measurement noise covariance matrix of the obstacle at a current moment based on the lidar data, the ultrasonic data, and the image data; The predicted state vector and the predicted state covariance matrix are corrected according to the measurement value vector, the measurement noise covariance matrix and the update sub-model to obtain a corrected state vector and state covariance matrix to form the multi-source environment model.

6. The parking control method according to any one of claims 1 to 5, characterized in that: Controlling the vehicle to complete parking according to the target parking path includes: If the distance between the target node in the target parking path and each obstacle is less than the lateral safety distance, determining a target parking mode for the vehicle from a plurality of parking modes, the plurality of parking modes being, in descending order of priority, a path lateral adjustment mode, a delay mode, and a remote control mode; If the target parking mode is the path lateral adjustment mode, the target parking path is adjusted laterally, and the vehicle is controlled to complete parking according to the adjusted target parking path; If the target parking mode is the delay mode, the first-level prompt and the delay mode are activated, and the vehicle is controlled to complete parking according to the target parking path. The first-level prompt includes suggesting that the driver and passengers get off the vehicle before parking and switching the parking mode to the delay mode. If the target parking mode is the remote control mode, the secondary prompt and the remote control mode are activated. After receiving the remote parking command, the vehicle is controlled to complete parking according to the target parking path. The secondary prompt includes asking the driver and passengers to get off the vehicle before parking and switching the parking mode to the remote control mode.

7. A parking control system, characterized in that: The system comprises: A data acquisition module, configured to acquire vehicle parameter information and parking information, wherein the parameter information includes vehicle width and door lateral opening distance, and the parking information includes vehicle position, parking space position, and obstacle information in the parking environment; a space assessment module, configured to assess the space for getting off the vehicle based on the parameter information and the obstacle information, and determine a lateral safety distance between the vehicle and the obstacle; A path planning module, in which the user constructs a safe driving corridor based on the parking information and searches for a target parking path within the safe driving corridor using the lateral safety distance as a constraint for path search; A parking control module, configured to control the vehicle to complete parking according to the target parking path; The path planning module is specifically configured to determine a plurality of candidate positions for the vehicle based on the vehicle position, the parking space position, and the position of at least one obstacle, wherein the obstacle information includes the obstacle position of at least one obstacle, and the candidate positions are positions where the vehicle will not collide with any obstacles; determine a total potential energy value of each candidate position based on the distance between each candidate position and each obstacle; determine the target candidate position as the target position if the total potential energy value of the target candidate position is less than or equal to a preset safety potential energy threshold; and generate the safe driving corridor based on each target position; The path planning module is further specifically used to calculate the position of each obstacle with the candidate position, the lateral safety distance and a preset sensitivity coefficient to obtain the potential energy value of each obstacle, where the sensitivity coefficient represents the sensitivity of the potential energy to changes in the obstacle distance; and calculate the sum of the potential energy values ​​of each obstacle to obtain the total potential energy value.

8. A vehicle, characterized in that: Using the parking control method according to any one of claims 1 to 6, or including the parking control system according to claim 7.

Images