Parking control method and device of vehicle, electronic equipment and storage medium

Abstract

The application provides a parking control method and device of a vehicle, electronic equipment and a storage medium. The method comprises the following steps: acquiring current parking scene information of the vehicle, and determining initial position information of a wheel chock and quantity information of the wheel chock according to the current parking scene information; determining parking space information of a target parking space corresponding to the wheel chock according to the initial position information; when the vehicle is parked in the target parking space, determining predicted position information of the wheel chock by performing dead reckoning according to the initial position information, and acquiring real-time position information of the wheel chock; determining position change information corresponding to the wheel chock according to the real-time position information and the predicted position information; determining target confidence corresponding to the wheel chock according to the parking space information, the quantity information and the position change information; performing parking path planning according to the target confidence and the initial position information to obtain an initial parking path, and performing parking control on the vehicle according to the initial parking path. The application can improve the detection accuracy of the wheel chock and improve the parking accuracy.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to a parking control method, device, electronic device, and storage medium for a vehicle. Background Technology

[0002] Currently, the development of automatic parking technology in the intelligent driving industry is rapid. It can achieve lateral and longitudinal control of vehicles through the collaboration of sensors, processors, and controllers, thus providing drivers with convenient parking services. However, the implementation of automatic parking functions still faces significant difficulties and challenges in some scenarios, such as handling automatic parking with limit blocks / wheel chocks. Existing technologies typically use the vehicle's perception module to detect limit blocks or wheel chocks through visual deep learning. However, this relies on high-cost sensors and controllers, has high requirements for lighting conditions, and suffers from the lack of standardized shapes and dimensions of limit blocks or wheel chocks in actual parking scenarios. This limits the accuracy and confidence of recognition, leading to misidentification / missed identification and consequently compromising the safety of automatic parking. Therefore, improving the recognition accuracy of wheel chocks during automatic parking is a pressing issue that needs to be addressed. Summary of the Invention

[0003] In view of this, embodiments of this application propose a parking control method, apparatus, electronic device, and storage medium for vehicles to improve the above-mentioned problems.

[0004] According to a first aspect of the embodiments of this application, a parking control method for a vehicle is provided. The method includes: acquiring current parking scenario information of the vehicle, and determining initial position information and quantity information of wheel chocks based on the current parking scenario information; determining parking space information of a target parking space corresponding to the wheel chocks based on the initial position information; when the vehicle parks in the target parking space, determining the predicted position information of the wheel chocks based on dead reckoning based on the initial position information, and acquiring real-time position information of the wheel chocks; determining position change information corresponding to the wheel chocks based on the real-time position information and the predicted position information; determining a target confidence level corresponding to the wheel chocks based on the parking space information, the quantity information, and the position change information; performing parking path planning based on the target confidence level and the initial position information to obtain a parking path, and performing parking control on the vehicle based on the parking path.

[0005] According to a second aspect of the embodiments of this application, a parking control device for a vehicle is provided. The device includes: a scene recognition module, configured to acquire current parking scene information of the vehicle, and determine initial position information of wheel chocks and quantity information of wheel chocks based on the current parking scene information; a predicted position information determination module, configured to determine parking space information of a target parking space corresponding to the wheel chocks based on the initial position information, and determine a first predicted position information of the vehicle and a second predicted position information of the wheel chocks based on the initial position information; a position change information determination module, configured to acquire real-time position information of the wheel chocks when the vehicle moves to the first predicted position information, and determine position change information corresponding to the wheel chocks based on the real-time position information and the second predicted position information; a target confidence determination module, configured to determine a target confidence level corresponding to the wheel chocks based on the parking space information, the quantity information, and the position change information; and a parking control module, configured to perform parking path planning based on the target confidence level and the initial position information to obtain a parking path, and perform parking control on the vehicle based on the parking path.

[0006] According to a third aspect of the embodiments of this application, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the parking control method for a vehicle as described above is implemented.

[0007] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, on which computer-readable instructions are stored, which, when executed by a processor, implement the parking control method for a vehicle as described above.

[0008] In this application's solution, the initial position information and quantity information of the wheel chocks are first determined by acquiring the current parking scenario. Based on the initial position information, the parking space information of the target parking space corresponding to the wheel chocks is determined. When the vehicle parks in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chocks and to acquire their real-time position information. Then, based on the predicted and real-time position information, the position change information corresponding to the wheel chocks is determined. This allows for the determination of the target confidence level corresponding to the wheel chocks based on the parking space information, quantity information, and position change information. Furthermore, parking path planning is performed based on the target confidence level and the initial position information to obtain the parking path. Parking control is then performed based on the parking path. Further filtering of the visual detection results of the wheel chocks, including the parking space information, quantity information, and position change information of the target parking space corresponding to the wheel chocks, improves the wheel chock detection accuracy and the vehicle's parking accuracy.

[0009] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0010] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0011] Figure 1 This is a schematic flowchart illustrating a vehicle parking control method according to an embodiment of this application.

[0012] Figure 2 This is a schematic flowchart illustrating a vehicle parking control method according to another embodiment of this application.

[0013] Figure 3 This is a flowchart illustrating the specific steps of step 270 according to an embodiment of this application.

[0014] Figure 4 This is a flowchart illustrating the specific steps prior to step 271 according to an embodiment of this application.

[0015] Figure 5 This is a schematic flowchart illustrating a vehicle parking control method according to another embodiment of this application.

[0016] Figure 6 This is a schematic flowchart illustrating a vehicle parking control method according to another embodiment of this application.

[0017] Figure 7 This is a schematic flowchart illustrating a vehicle parking control method according to another embodiment of this application.

[0018] Figure 8 This is a schematic diagram illustrating the process of actively identifying wheel chocks according to an embodiment of this application.

[0019] Figure 9 This is a schematic diagram of the process for passively identifying wheel chocks according to an embodiment of this application.

[0020] Figure 10 This is a block diagram of a vehicle parking control device according to an embodiment of this application.

[0021] Figure 11 This is a hardware structure diagram of an electronic device according to an embodiment of this application.

[0022] The accompanying drawings have illustrated specific embodiments of the present invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the inventive concept in any way, but rather to illustrate the concept of the invention to those skilled in the art through specific embodiments. Detailed Implementation

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0026] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be decomposed, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0027] Please see Figure 1 , Figure 1 This application illustrates a vehicle parking control method according to an embodiment of the present application. In a specific embodiment, the vehicle parking control method can be applied to, for example... Figure 10 The parking control device 700 of the vehicle shown and the electronic equipment 800 equipped with the parking control device 700 of the vehicle are shown. Figure 11 The specific process of this embodiment will be described below. Of course, it is understood that this method can be executed by a cloud server with computing power. The following will focus on... Figure 1 The process shown will be explained in detail, and may include the following steps:

[0028] Step 110: Obtain the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information.

[0029] As one approach, before the vehicle uses the automatic parking function for parking control, an image acquisition device can be used to capture an image of the parking lot where the vehicle is located, thereby identifying the vehicle's current parking length. Optionally, the current parking scenario can be the limiters for each parking space in the parking lot where the vehicle is located. These limiters can be wheel chocks, limiters, or parking lines, etc. If the limiter is a wheel chock or a limit block, in order to ensure that the vehicle does not collide with the wheel chock as much as possible during automatic parking, and even if there is a collision, the impact should be minimal and secondary collisions should be prevented, the vehicle's current parking scenario can be obtained through the vehicle's image acquisition device when the automatic parking function is used.

[0030] Optionally, after acquiring the vehicle's current parking scene, a Bird's Eye View (BEV) network can be used to convert the acquired current parking scene into a bird's-eye view format. Then, a scene recognition model is used to determine the vehicle's current parking scene, thereby determining the initial position information and the number of wheel chocks within the current parking scene. The scene recognition model can be a recurrent neural network, a fully connected neural network, a convolutional neural network, etc. The specific neural network type can be set according to actual needs and is not specifically limited here. Optionally, to ensure the accuracy of the initial position information and the number of wheel chocks, before recognizing the current parking scene using the scene recognition model, multiple training image data can be used to identify the scene recognition model. The position and number of wheel chocks in the recognized scene are compared with the position and number of wheel chocks in the target scene in the training image data to determine the loss function. When the loss function converges, the training of the scene recognition model can be terminated, and the scene recognition model can be applied offline. If the loss function does not converge, the parameters of the scene recognition model are adjusted based on the loss value of the loss function, and the scene recognition model is trained again based on the adjusted parameters until the loss function converges.

[0031] Optionally, the initial position information of the wheel chock lever can be the relative position information of the wheel chock lever with respect to the vehicle, or the coordinate information of the wheel chock lever in the vehicle coordinate system with the vehicle's position as the origin of the coordinate system.

[0032] Step 120: Determine the parking space information of the target parking space corresponding to the wheel stop based on the initial position information.

[0033] One approach is to determine the initial position information of the wheel chock lever, first identifying the target parking space that matches the initial position information, and then determining the parking space information by identifying the target parking space. Optionally, the parking space information may include the length and width of the target parking space, as well as the position information of the parking line where the target parking space is located, etc., and the parking space information can be set according to actual needs.

[0034] Step 130: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0035] One approach involves determining the vehicle's predicted position when parking in a target space. After establishing the initial position of the wheel chock, the vehicle's current position and direction of travel can be used to determine its predicted position. The relative position between the vehicle and the wheel chock is then determined based on the initial position. Finally, the predicted position of the wheel chock is determined using the vehicle's previous relative position and its predicted position. The trajectory calculation refers to using the vehicle's inertial measurement unit (IMU) to collect its position and direction of travel, thereby calculating the predicted position.

[0036] Step 140: Determine the position change information corresponding to the stop wheel rod based on the real-time position information and the predicted position information.

[0037] One approach is to determine the real-time and predicted positions of the wheel chock lever after determining these positions. First, the positional error of the wheel chock lever relative to the vehicle is determined based on these two information, and this positional error is then defined as the corresponding positional change information of the wheel chock lever. Alternatively, the real-time and predicted positions can be converted to a vehicle coordinate system with the vehicle as the origin. This allows for the determination of the positional error between the predicted and real-time positions within the vehicle coordinate system.

[0038] Step 150: Determine the target confidence level corresponding to the wheel stop based on the parking space information, the quantity information, and the position change information.

[0039] One approach is to first determine the parking space information, the number of wheel stops, and the positional change information of the wheel stops after identifying them. Then, an initial confidence level for each wheel stop can be obtained. This initial confidence level is then adjusted sequentially based on the parking space information, the number of wheel stops, and the positional change information to obtain the target confidence level. Optionally, different adjustment ranges can be pre-set for the confidence levels corresponding to different parking space information, different numbers of wheel stops, and different positional change information. These pre-set ranges determine the first target adjustment range for the parking space information, the second target adjustment range for the number of wheel stops, and the third target adjustment range for the positional change information. Finally, the initial confidence level of the wheel stops is adjusted based on these three target adjustment ranges to obtain the target confidence level.

[0040] As another approach, the confidence weights can be determined based on the parking space information, quantity information, and location change information, respectively. This allows for the adjustment of the initial confidence of the wheel chock based on the respective confidence weights of the parking space information, quantity information, and location change information, thereby determining the target confidence of the wheel chock.

[0041] Step 160: Based on the target confidence level and the initial position information, a parking path is planned to obtain a parking path, and the vehicle is parked according to the parking path.

[0042] As one approach, after determining the target confidence level corresponding to the wheel chock, the system first determines whether the initial position information should be adjusted based on the target confidence level, and then performs parking path planning based on the adjusted initial position information, as well as whether parking path planning can be performed based on the initial position information. For example, if the target confidence level is greater than or equal to the first confidence threshold, parking path planning can be performed directly based on the initial position information; if the target confidence level is less than the first confidence threshold but greater than or equal to the second confidence threshold, the initial position information can be adjusted, and parking path planning can be performed based on the adjusted initial position information; if the target confidence level is less than the second confidence threshold, it is determined that parking path planning cannot be performed based on the initial position information, and the current parking scenario of the vehicle can be obtained again, and the initial position information of the wheel chock can be re-determined based on the current parking scenario.

[0043] Optionally, if it is determined that parking path planning can be performed directly based on the initial position information, the endpoint of the parking path can be determined first based on the initial position information of the wheel chock. This allows for parking path planning based on the endpoint of the parking path and the vehicle's current position. Optionally, to avoid collisions between the vehicle and the wheel chock during parking control according to the parking path, the endpoint of the parking path can be set at a preset distance from the initial position information of the wheel chock. For example, a point 20-30cm away from the wheel chock can be used as the endpoint of the parking path. The preset distance can be set according to actual needs and is not specifically limited here.

[0044] Optionally, after obtaining the parking path through parking path planning based on the initial position information of the wheel chock lever, the vehicle speed during the parking process can be actively reduced according to the parking path. Optionally, the vehicle's tire size, speed reduction coefficient, vehicle weight, and chassis tuning parameters can be predetermined, thereby enabling the determination of the vehicle's parking speed during parking control based on these parameters.

[0045] In the embodiments of this application, the initial position information and quantity information of the wheel chocks are first determined by acquiring the current parking scene. Based on the initial position information, the parking space information of the target parking space corresponding to the wheel chocks is determined. When the vehicle parks in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chocks and to acquire the real-time position information of the wheel chocks. Then, based on the predicted position information and the real-time position information, the position change information corresponding to the wheel chocks is determined. This allows for the determination of the target confidence level corresponding to the wheel chocks based on the parking space information, quantity information, and position change information. Furthermore, parking path planning is performed based on the target confidence level and the initial position information to obtain the parking path. Parking control is then performed on the vehicle based on the parking path. By further filtering the results of visual detection of the wheel chocks, including the parking space information, quantity information, and position change information of the target parking space corresponding to the wheel chocks, the detection accuracy of the wheel chocks is improved, thus improving the parking accuracy of the vehicle.

[0046] Please see Figure 2 , Figure 2 This application illustrates a parking control method for a vehicle according to an embodiment of the present application.

[0047] The following will address... Figure 2 The process shown will be explained in detail, and may include the following steps:

[0048] Step 210: Obtain the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information.

[0049] Step 220: Determine the parking space information of the target parking space corresponding to the wheel stop based on the initial position information.

[0050] Step 230: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0051] Step 240: Determine the position change information corresponding to the stop wheel rod based on the real-time position information and the predicted position information.

[0052] Step 250: Determine the target confidence level corresponding to the wheel stop based on the parking space information, the quantity information, and the position change information.

[0053] Step 260: Based on the target confidence level and the initial position information, a parking path is planned to obtain a parking path, and the vehicle is parked according to the parking path.

[0054] The specific steps of steps 210-260 can be found in steps 110-160, and will not be repeated here.

[0055] Step 270: During the process of parking the vehicle according to the initial parking path, the control parameters and driving parameters of the vehicle are obtained.

[0056] In one approach, during the process of an autonomous driving system actively identifying wheel chocks and planning a parking path based on the identified wheel chocks, and then controlling the vehicle to park, if it is impossible to distinguish whether the vehicle collides with a speed bump or a wheel chock during the parking lot parking process, the vehicle may not be able to accurately park in the target parking space. Therefore, during the vehicle parking control process, it is possible to passively identify whether the vehicle collides with a wheel chock, thereby enabling the vehicle to accurately park in the target parking space.

[0057] Optionally, the control parameters can be parameters determined by the vehicle based on the parking path after the parking path is determined, which are used to control the vehicle to park. The control parameters may include the vehicle's parking control speed, parking request direction, etc.

[0058] Optionally, the driving parameters can be the actual parameters of the vehicle during the parking process according to the parking path. These parameters may include the vehicle's actual parking speed, parking direction, wheel speed direction, and the positional relationship between the vehicle and the target parking space. They can be set according to actual needs and are not specifically limited here.

[0059] Optionally, the vehicle's control parameters can be determined in the vehicle's parking planning module. After determining the vehicle's parking path, the control parameters are determined based on the parking path and the vehicle's current position information. The vehicle's driving parameters can be obtained in real time by the vehicle's sensors during the parking control process according to the parking path. The vehicle's sensors can include wheel speed sensors, acceleration sensors, ultrasonic sensors, and vision sensors, etc.

[0060] Step 280: If it is determined that the vehicle collides with the wheel chock based on the control parameters and the driving parameters, then the vehicle's position and posture information is determined, and parking control is performed on the vehicle based on the position and posture information.

[0061] One method to determine whether a vehicle has collided with the wheel chock can be based on the vehicle's driving parameters and control parameters. Optionally, the control parameters can be compared with the vehicle's driving parameters to determine if they are the same. If they are, it can be determined that the vehicle has collided with the speed bump, and parking control based on the parking path can continue. If they are different, it can be determined that the vehicle has collided with the wheel chock.

[0062] Optionally, after determining that the vehicle has collided with the wheel chock, the vehicle's position and orientation information can be used to determine whether the vehicle has fully parked in the target parking space. If the vehicle has not fully parked in the target parking space, parking control can be applied to the vehicle based on its position and orientation information to adjust the vehicle's position and orientation so that the vehicle can be fully parked in the target parking space.

[0063] In some embodiments, such as Figure 3 As shown, step 270 includes:

[0064] Step 271: If it is determined that the vehicle collides with the wheel chock based on the control parameters and the driving parameters, then determine the vehicle's position and orientation information, and determine whether the vehicle is fully parked in the target parking space based on the position and orientation information.

[0065] One method is to determine whether a vehicle is fully parked in the target parking space by checking whether the vehicle's positional information and the deviations in front-to-back distance, left-to-right distance, and angle between these deviations and the corresponding parking space lines meet the vehicle's parking conditions. These parking conditions can be based on the requirement that the vehicle will not collide with other vehicles or obstacles when parked in the target space. When the vehicle's positional information meets these parking conditions, it avoids traffic accidents such as scrapes or collisions with other vehicles parked near the target space due to the vehicle's positional information not meeting the parking conditions, thus ensuring the safety of the vehicle parked in the target space.

[0066] In some embodiments, step 271 includes: determining the distance deviation and angle deviation between the vehicle and the target parking space based on the parking space information and the pose information; if the distance deviation meets a first preset condition and the angle deviation meets a second preset condition, then determining that the vehicle is fully parked in the target parking space; if the distance deviation does not meet the first preset condition and / or the angle deviation does not meet the second preset condition, then determining that the vehicle is not fully parked in the target parking space.

[0067] One approach is to define the distance deviation between a vehicle and a target parking space as including both front-to-back and left-to-right distance deviations. Optionally, the positional relationship between the vehicle and the target parking space can be determined based on the coordinates of the parking space lines in the world coordinate system and the vehicle's pose information, thereby determining the distance deviation. For example, the vehicle's front and rear positions can be determined based on its pose information, and the corner positions of the four corner points of the target parking space can be determined based on the target parking space's information. Then, the distance deviation between the vehicle and the target parking space can be determined based on the front, rear, and corner position information.

[0068] Optionally, the angle between the straight line containing the vehicle's left front wheel and left rear wheel (or right front wheel or right rear wheel) and the left parking line corresponding to the target parking space can be determined based on the vehicle's position information and the target parking space's position information. This angle can then be used to determine the angular deviation between the vehicle and the target parking space.

[0069] Optionally, the first preset condition may be that the distance deviation between the vehicle and the target parking space is within a preset distance deviation range, and the second preset condition may be that the angle deviation between the vehicle and the target parking space is within a preset angle deviation range.

[0070] Optionally, if either the first or the second preset condition is not met, it can be determined that the vehicle may collide with a vehicle or obstacle near the target parking space based on its current position information. Therefore, it is necessary to re-plan the path based on the vehicle's position information and the parking space information of the target parking space.

[0071] Step 272: If it is determined that the vehicle has not been fully parked in the target parking space, the parking path is replanned based on the pose information and the location information of the target parking space, and the parking control of the vehicle is performed based on the replanned parking path.

[0072] As one approach, when it is determined that a vehicle is not fully parked in the target parking space, to ensure parking safety, the vehicle's parking path can be replanned based on the vehicle's pose information and the target parking space's location information. This results in a replanned parking path, which is then used for parking control. Alternatively, the pose deviation between the vehicle and the target parking space can be determined based on the vehicle's pose information and the target parking space's location information. Multiple location points can be determined based on this pose deviation, where the ordinates of these points in the world coordinate system can be an arithmetic sequence. The parking path can then be replanned based on the ordinates of this arithmetic sequence, resulting in a replanned parking path.

[0073] Optionally, when replanning the parking path based on the vehicle's pose information and the target parking space's location information, the number of replanning operations is counted. When the number of replanning operations is greater than or equal to a threshold, the replanning of the parking path can be terminated, and parking control can be performed according to the parking path obtained from the last replanning operation.

[0074] In some embodiments, the control parameters include the requested direction and a first longitudinal acceleration, and the driving parameters include wheel speed direction, a second longitudinal acceleration, and braking parameters. Before step 270, such as Figure 4 As shown, the method further includes:

[0075] Step 310: Obtain the real-time location information of the vehicle, determine whether the vehicle has started to enter the target parking space based on the real-time location information, and determine whether the remaining distance of the vehicle on the initial parking path is less than or equal to a distance threshold based on the real-time location information.

[0076] In one approach to accurately determine whether a vehicle has collided with the wheel chock, the vehicle's real-time location information can be used to determine whether the vehicle has begun to enter the target parking space. The remaining distance between the vehicle's real-time location and the target parking space can then be used to determine whether the vehicle has begun to enter the target parking space. Thus, it is possible to determine whether the vehicle may have collided with the wheel chock after it has begun to enter the target parking space.

[0077] Optionally, the remaining distance can be used to indicate the positional relationship between the vehicle and the target parking space. When the remaining distance is less than or equal to a distance threshold, it can be determined that the vehicle has begun to enter the target parking space. When the remaining distance is greater than the distance threshold, it can be determined that the vehicle has not begun to enter the target parking space.

[0078] Step 320: If it is determined that the wheel speed direction is opposite to the requested direction, the second longitudinal acceleration is greater than the first longitudinal acceleration, the vehicle is not actively requesting braking, the vehicle begins to enter the target parking space and the remaining distance is less than or equal to the distance threshold, then it is determined that the vehicle has collided with the wheel stop.

[0079] As one approach, when the requested direction is opposite to the vehicle's wheel speed direction, it can be determined that the vehicle's wheels may have collided with the wheel chock, causing the wheel speed direction to be opposite to the requested direction. Optionally, the first longitudinal acceleration can be determined based on the vehicle's minimum longitudinal acceleration during parking, thereby ensuring parking safety during parking control. If the second longitudinal acceleration is greater than the first longitudinal acceleration, it can be determined that the vehicle is in a slow-moving process. Optionally, if it is determined that the vehicle is not actively requesting braking, it can be determined that the vehicle may have collided with the wheel chock or other obstacles. Optionally, when it is determined that the vehicle has begun to enter the target parking space and the remaining distance is less than or equal to a distance threshold, it can be determined that the vehicle has entered the target parking space and completed the final parking step. Furthermore, since the vehicle's wheel speed direction is opposite to the requested direction, the second longitudinal acceleration is greater than the first longitudinal acceleration, and the vehicle is not actively requesting braking, it can be accurately determined that the vehicle has entered the target parking space and collided with the wheel chock corresponding to the target parking space.

[0080] Step 330: If it is determined that the wheel speed direction is not opposite to the requested direction, the second longitudinal acceleration is less than or equal to the first longitudinal acceleration, the vehicle actively requests braking, the vehicle has not started to enter the target parking space, and / or the remaining distance is greater than the distance threshold, then it is determined that the vehicle has collided with the speed bump, and parking control of the vehicle continues according to the initial parking path.

[0081] As one approach, when the requested direction is not opposite to the vehicle's wheel speed direction, it can be determined that the vehicle continues to travel in the requested direction determined by the parking path. Optionally, when the vehicle enters the target parking space and begins parking, the direction of reversing is taken as the positive direction. During reversing, the vehicle's longitudinal acceleration is positive and greater than the first longitudinal acceleration. If the vehicle approaches the target parking space according to the parking path, its corresponding second longitudinal acceleration is less than the first longitudinal acceleration, and its value may be negative. That is, if the second longitudinal acceleration is less than or equal to the first longitudinal acceleration, it can be determined that the vehicle is moving towards the target parking space according to the parking path. Optionally, if it is determined that the vehicle actively requests braking, it can be determined that the vehicle decelerates in advance to smoothly cross the speed bump and improve the driver's driving experience while approaching the target parking space according to the parking path. Optionally, when it is determined that the vehicle has not started entering the target parking space or the remaining distance is greater than a distance threshold, it can be determined that the vehicle has not entered the target parking space and may be moving towards the target parking space according to the parking path. It can be determined that at this time, the vehicle may collide with the speed bump, and parking control can continue according to the parking path.

[0082] In this embodiment, during the process of actively identifying wheel chocks and planning parking paths based on the identified wheel chocks to obtain a parking path, and then controlling the vehicle's parking based on the parking path, the vehicle's control parameters and driving parameters are obtained to determine whether the vehicle will collide with the wheel chocks. This can prevent secondary collisions when the vehicle collides with the target parking space, ensuring parking safety and improving the user experience.

[0083] Please see Figure 5 , Figure 5 This application illustrates a parking control method for a vehicle according to an embodiment of the present application.

[0084] The following will address... Figure 5 The process shown will be explained in detail, and may include the following steps:

[0085] Step 410: Obtain the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information.

[0086] Step 420: Determine the parking space information of the target parking space corresponding to the wheel stop lever based on the initial position information.

[0087] Step 430: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0088] Step 440: Obtain the predicted pose information of the vehicle, and determine the first position information of the wheel stop lever in the vehicle coordinate system based on the predicted pose information and the predicted position information.

[0089] One approach is to determine the vehicle's predicted position information using a trajectory estimation algorithm. This predicted pose information can be the vehicle's real-time pose information after a preset time period. Optionally, the vehicle's predicted pose information can be information located in a world coordinate system. To accurately determine the position of the wheel chock relative to the vehicle, a vehicle coordinate system with the vehicle as the origin can be first determined based on the vehicle's predicted pose information. Then, based on the vehicle's pose information at the initial position information of the wheel chock and the initial position information of the wheel chock, the positional relationship between the vehicle and the wheel chock in the world coordinate system can be determined. Based on this positional relationship, the vehicle's predicted pose information, and the wheel chock's predicted position information, the first position information of the wheel chock in the vehicle coordinate system can be determined.

[0090] Step 450: Determine the real-time pose information of the vehicle, and determine the second position information of the wheel stop lever in the vehicle coordinate system based on the real-time pose information and the real-time position information.

[0091] One approach is to acquire the vehicle's real-time pose information using its sensors. After determining that the error between the real-time pose information and the predicted pose information is less than an error threshold, the real-time position information of the wheel chock can be determined by recognizing the image of the wheel chock captured by the vehicle. Based on the real-time pose information and the real-time position information of the wheel chock, a second position information of the wheel chock in the vehicle coordinate system can be determined. Optionally, the second position information is information in the vehicle coordinate system with the real-time pose information of the vehicle as the origin.

[0092] Step 460: Determine the position change information of the stop wheel rod based on the first position information and the second position information.

[0093] One approach is to calculate the position difference between the first and second position information after determining the first and second position information, using this difference as the position change information of the wheel chock. Optionally, the position difference between the first and second position information can be determined by calculating the Euclidean distance between them. Optionally, if the identified wheel chock is a real wheel chock, its position information in the map coordinate system or world coordinate system will not change or the position change will be small (possibly due to the sensing accuracy of the vehicle's sensors or the positioning accuracy of the positioning module). If the identified wheel chock is a similar wheel chock or an image of it, its corresponding position information in the world coordinate system or map coordinate system will change when the vehicle's position changes. Therefore, the confidence level of the identified wheel chock can be determined using the position change information of the wheel chock.

[0094] In one approach, to accurately determine the positional change information of the wheel stop, the first and second positional information of the wheel stop can be converted to information in a map coordinate system, thereby enabling the determination of the positional change information of the wheel stop in map coordinates.

[0095] Step 470: Determine the parking space information of the target parking space corresponding to the wheel stop based on the initial position information, and determine the target confidence level corresponding to the wheel stop based on the parking space information, the quantity information and the position change information.

[0096] Step 480: Based on the target confidence level and the initial position information, a parking path is planned to obtain a parking path, and the vehicle is parked according to the parking path.

[0097] The specific steps of steps 410-420 and 470-480 can be found in steps 110-120 and 140-150, and will not be repeated here.

[0098] In this embodiment, the first position information of the wheel stop lever in the vehicle coordinate system can be determined firstly based on the vehicle's predicted pose information and predicted position information. Then, the second position information of the wheel stop lever in the vehicle coordinate system can be determined based on the vehicle's real-time pose information and the wheel stop lever's real-time position information. Finally, the position change information of the wheel stop lever can be determined based on the first and second position information, thereby ensuring the accuracy of the wheel stop lever's position change information.

[0099] Please see Figure 6 , Figure 6 This application illustrates a parking control method for a vehicle according to an embodiment of the present application.

[0100] The following will address... Figure 6 The process shown will be explained in detail, and may include the following steps:

[0101] Step 510: Obtain the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information.

[0102] Step 520: Obtain the multiple available parking spaces for the vehicle in the garage.

[0103] As one approach, in a garage or parking lot, there may be multiple available parking spaces, meaning a vehicle can park in any of these available spaces. Therefore, the multiple available parking spaces for a vehicle in the garage can be determined first. Optionally, the multiple available parking spaces for a vehicle in the garage can be obtained by identifying available parking spaces in the vehicle's current parking scenario.

[0104] Step 530: Perform parking space matching based on the initial location information, determine the target parking space from the plurality of available parking spaces, and determine the parking space information of the target parking space.

[0105] As one approach, to ensure accurate parking in the identified wheel chocks, the initial position information of the wheel chocks can be used to determine the target parking space. Optionally, the garage manager can pre-mark each wheel chock in the garage with its corresponding parking space, thus obtaining a mapping relationship between the position information of each wheel chock and the parking space. This mapping relationship is then uploaded to a cloud server. When a vehicle enters the garage, the cloud server retrieves the position information of each wheel chock and the mapping relationship. After determining the initial position information of the wheel chocks, parking space matching is performed based on the initial position information of the wheel chocks and the mapping relationship between the position information of each wheel chock and the parking space, thereby determining the target parking space from multiple available parking spaces.

[0106] Optionally, after determining the target parking space, the parking space information can be determined by acquiring the image information corresponding to the target parking space and then identifying the image information corresponding to the target parking space.

[0107] Step 540: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0108] Step 550: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0109] Step 560: Determine the position change information corresponding to the stop wheel rod based on the real-time position information and the predicted position information.

[0110] Step 570: Determine the target confidence level corresponding to the wheel stop based on the parking space information, the quantity information, and the position change information.

[0111] Step 580: Based on the target confidence level and the initial position information, a parking path is planned to obtain a parking path, and the vehicle is parked according to the parking path.

[0112] The specific steps of steps 510-520 and 550-460 can be found in steps 110-120 and 140-150, and will not be repeated here.

[0113] In this embodiment, before determining the parking space information of the target parking space, multiple available parking spaces for the vehicle in the garage can be determined first. Then, the target parking space corresponding to the wheel chock can be determined based on the initial position information of the wheel chock, thereby determining the parking space information of the target parking space and ensuring the accuracy of the parking space information of the target parking space.

[0114] Please see Figure 7 , Figure 7 This application illustrates a parking control method for a vehicle according to an embodiment of the present application.

[0115] The following will address... Figure 7 The process shown will be explained in detail, and may include the following steps:

[0116] Step 610: Obtain the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information.

[0117] Step 620: Determine the parking space information of the target parking space corresponding to the wheel stop lever based on the initial position information.

[0118] Step 630: When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained.

[0119] Step 640: Determine the position change information corresponding to the stop wheel rod based on the real-time position information and the predicted position information.

[0120] Step 650: Determine a first weight based on the parking space information, a second weight based on the quantity information, and a third weight based on the location change information.

[0121] As one approach, a first weight mapping relationship between different parking space information and weights, a second weight mapping relationship between different quantity information and weights, and a third weight mapping relationship between different location change information and weights can be pre-set. Then, after determining the parking space information, the number of wheel stops, and the number of wheel stops of the target parking space, the first weight is determined based on the first weight mapping relationship and the parking space information, the second weight is determined based on the second weight mapping relationship and the number of wheel stops, and the third weight is determined based on the third weight mapping relationship.

[0122] Step 660: Obtain the initial confidence level corresponding to the wheel stop lever, and adjust the initial confidence level according to the first weight, the second weight and the third weight to obtain the target confidence level.

[0123] As one approach, after determining the first, second, and third weights, the initial confidence level of the wheel chock can be obtained first. This initial confidence level can then be adjusted based on the first, second, and third weights to obtain the target confidence level.

[0124] Optionally, an initial confidence level can be pre-set for each wheel chock in the garage. The initial confidence level for each wheel chock can be the same, or a different confidence level can be set for each wheel chock. After the vehicle enters the garage and the initial position information of the wheel chock is determined, the initial position information of the wheel chock can be sent to the cloud server, so that the initial confidence level corresponding to the initial position information of the wheel chock can be determined in the cloud server.

[0125] Optionally, the weight product can be determined first based on the first, second, and third weights, and then the weight product can be multiplied by the initial confidence level to obtain the target weight.

[0126] Step 670: Based on the target confidence level and the initial position information, a parking path is planned to obtain a parking path, and the vehicle is parked according to the parking path.

[0127] The specific steps of steps 610-640 can be found in steps 110-140, and will not be repeated here.

[0128] In this embodiment, a first weight is determined based on the determined parking space information, a second weight is determined based on the determined quantity information, and a third weight is determined based on the determined position change information. The initial confidence of the wheel chock is adjusted based on the first weight, the second weight, and the third weight to obtain the target confidence, thus ensuring the accuracy of the target confidence of the wheel chock.

[0129] Figure 8 This is a schematic diagram of a vehicle actively identifying wheel chock lever according to an embodiment of this application, as shown below. Figure 8 As shown, firstly, multiple wheel chocks and their corresponding data are determined based on the vehicle's sensors and parking space perception network. Then, the data for each wheel chock is analyzed and clustered to identify the target wheel chock closest to the vehicle. Next, it is determined whether the target wheel chock's data meets the wheel chock management conditions. If the conditions are not met, the target wheel chock and its corresponding data are deleted. If the conditions are met, trajectory calculation is performed based on the target wheel chock data. The system matches the trajectory calculation points and detection points corresponding to the wheel chocks to match the wheel chocks with the managed parking spaces, thus determining the target parking space. Then, it detects the target parking space and the target wheel chock to determine the confidence level of the target wheel chock, as well as the target confidence level and position information of the target wheel chock. Based on the target confidence level and position information of the target wheel chock, it can perform path planning to obtain a parking path and control the vehicle according to the parking path. This achieves active identification of wheel chocks for path planning and vehicle parking control.

[0130] Figure 9 This is a schematic flowchart illustrating a vehicle passive wheel chock identification process according to an embodiment of this application, as shown below. Figure 9As shown, during the parking control process based on the parking path, the system determines whether the vehicle is in the target parking space based on the vehicle's ultrasonic and visual sensors, whether the vehicle's wheel speed direction is opposite to the requested direction based on the vehicle's wheel speed sensors, whether the vehicle's longitudinal acceleration is greater than the longitudinal acceleration threshold based on the vehicle's acceleration sensors, acquires the vehicle's braking signal and determines whether the braking signal is caused by non-applied braking or an unintended braking request, and whether the remaining distance of the vehicle in the parking path from its current position is less than a distance threshold. Therefore, if the vehicle is in the target parking space, the vehicle's wheel speed direction is opposite to the requested direction, the vehicle's longitudinal acceleration is greater than the longitudinal acceleration threshold, the vehicle's braking signal is caused by non-applied braking or an unintended braking request, or the remaining distance is less than the distance threshold, it is determined that the vehicle has collided with the wheel chock. To ensure that the vehicle is parked in the target parking space without scraping other vehicles, the system can determine whether the vehicle's position and posture information meets the front-to-rear distance deviation range and the vehicle's position and posture. The system checks whether the vehicle's position and orientation information meet the lateral distance deviation range and the angular deviation range. If the vehicle's position and orientation information meets the lateral distance deviation range, the parking is considered complete. If the vehicle's position and orientation information does not meet the lateral distance deviation range, the parking path is replanned based on the vehicle's position and orientation information. Parking control is then performed based on the replanned parking path until the vehicle's position and orientation information meets the lateral distance deviation range, the angular deviation range, and the angular deviation range. This allows for determining whether the vehicle collides with the gear shift lever or the speed bump when a collision is suspected, thus enabling parking control through a passive strategy to avoid repeated collisions and forceful collisions before reaching the torque limit, thereby improving the user experience.

[0131] Figure 10 This is a block diagram of a vehicle parking control device according to an embodiment of this application, such as... Figure 8 As shown, the parking control device 700 of the vehicle includes: a scene recognition module 710, a parking space information determination module 720, a predicted position information determination module 730, a position change information determination module 740, a target confidence determination module 750, and a parking control module 760.

[0132] Scene recognition module 710 is used to acquire the current parking scene information of the vehicle and determine the initial position information and the quantity information of the wheel chocks based on the current parking scene information; parking space information determination module 720 is used to determine the parking space information of the target parking space corresponding to the wheel chocks based on the initial position information; predicted position information determination module 730 is used to determine the predicted position information of the wheel chocks based on the initial position information when the vehicle parks in the target parking space, and acquire the real-time position information of the wheel chocks; position change information determination module 740 is used to determine the position change information corresponding to the wheel chocks based on the real-time position information and the predicted position information; target confidence determination module 750 is used to determine the target confidence level corresponding to the wheel chocks based on the parking space information, the quantity information and the position change information; parking control module 760 is used to plan a parking path based on the target confidence level and the initial position information to obtain a parking path, and to control the parking of the vehicle based on the parking path. In some embodiments, the position change information determination module 740 includes: a first position information determination submodule, configured to acquire the predicted pose information of the vehicle, and determine the first position information of the wheel stop lever in the vehicle coordinate system based on the predicted pose information and the predicted position information; a second position information determination submodule, configured to determine the real-time pose information of the vehicle, and determine the second position information of the wheel stop lever in the vehicle coordinate system based on the real-time pose information and the real-time position information; and a position change information determination submodule, configured to determine the position change information of the wheel stop lever based on the first position information and the second position information.

[0133] In some embodiments, the location change information determination module 740 further includes: a plurality of available parking spaces acquisition submodule, used to acquire a plurality of available parking spaces for the vehicle in the garage; and a parking space information determination submodule, used to perform parking space matching based on the initial location information, determine the target parking space among the plurality of available parking spaces, and determine the parking space information of the target parking space.

[0134] In some embodiments, the target confidence level determination module 750 includes: a weight determination submodule, configured to determine a first weight based on the parking space information, a second weight based on the quantity information, and a third weight based on the position change information; and a target confidence level determination submodule, configured to obtain an initial confidence level corresponding to the wheel chock, and adjust the initial confidence level based on the first weight, the second weight, and the third weight to obtain the target confidence level.

[0135] In some embodiments, the parking control device 700 further includes: a parameter acquisition module, configured to acquire control parameters and driving parameters of the vehicle during the process of parking control of the vehicle according to the initial parking path; and a passive parking control module, configured to determine the position and posture information of the vehicle and perform parking control of the vehicle according to the position and posture information if it is determined that the vehicle collides with the wheel chock based on the control parameters and the driving parameters.

[0136] In some embodiments, the passive parking control module includes: a determination submodule, configured to determine the vehicle's position and orientation information if a collision between the vehicle and the wheel chock is determined based on the control parameters and the driving parameters, and to determine whether the vehicle is fully parked in the target parking space based on the position and orientation information; and a passive parking control submodule, configured to replan the parking path based on the position and orientation information and the location information of the target parking space if it is determined that the vehicle is not fully parked in the target parking space, and to perform parking control on the vehicle based on the replanned parking path.

[0137] In some embodiments, the determining submodule includes: a deviation determining unit, configured to determine the distance deviation and angle deviation between the vehicle and the target parking space based on the parking space information and the pose information; a first determining unit, configured to determine that the vehicle is fully parked in the target parking space if the distance deviation meets a first preset condition and the angle deviation meets a second preset condition; and a second determining unit, configured to determine that the vehicle is not fully parked in the target parking space if the distance deviation does not meet the first preset condition and / or the angle deviation does not meet the second preset condition.

[0138] According to one aspect of the embodiments of this application, an electronic device is also provided, such as... Figure 11 As shown, the vehicle 800 includes a processor 810 and one or more memories 820. The one or more memories 820 are used to store program instructions executed by the processor 810. When the processor 810 executes the program instructions, it implements the above-described vehicle parking control method.

[0139] Furthermore, the processor 810 may include one or more processing cores. The processor 810 runs or executes instructions, programs, code sets, or instruction sets stored in the memory 820, and retrieves data stored in the memory 820. Optionally, the processor 810 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 810 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor and may be implemented using a separate communication chip.

[0140] According to one aspect of this application, a computer-readable storage medium is also provided, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable storage medium carries computer-readable instructions that, when executed by a processor, implement the methods in any of the above embodiments.

[0141] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0142] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0144] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0145] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A parking control method for a vehicle, characterized in that, The method includes: Obtain the current parking scenario information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scenario information; The parking space information of the target parking space corresponding to the wheel stop is determined based on the initial position information; When the vehicle is parked in the target parking space, dead reckoning is performed based on the initial position information to determine the predicted position information of the wheel chock, and the real-time position information of the wheel chock is obtained. The position change information corresponding to the stop wheel lever is determined based on the real-time position information and the predicted position information; The target confidence level corresponding to the wheel chock is determined based on the parking space information, the quantity information, and the position change information; Parking path planning is performed based on the target confidence level and the initial position information to obtain a parking path, and parking control of the vehicle is performed based on the parking path.

2. The method according to claim 1, characterized in that, The step of determining the position change information corresponding to the wheel stop based on the real-time position information and the predicted position information includes: The predicted pose information of the vehicle is obtained, and the first position information of the wheel stop lever in the vehicle coordinate system is determined based on the predicted pose information and the predicted position information. The real-time pose information of the vehicle is determined, and the second position information of the wheel stop lever in the vehicle coordinate system is determined based on the real-time pose information and the real-time position information. The position change information of the stop wheel rod is determined based on the first position information and the second position information.

3. The method according to claim 1, characterized in that, The step of determining the parking space information of the target parking space corresponding to the wheel chock based on the initial position information includes: Obtain the multiple available parking spaces for the vehicle in the garage; Parking space matching is performed based on the initial location information, the target parking space is determined from the plurality of available parking spaces, and the parking space information of the target parking space is determined.

4. The method according to claim 1, characterized in that, Determining the target confidence level corresponding to the wheel chock based on the parking space information, the quantity information, and the position change information includes: A first weight is determined based on the parking space information, a second weight is determined based on the quantity information, and a third weight is determined based on the location change information. Obtain the initial confidence level corresponding to the wheel stop lever, and adjust the initial confidence level according to the first weight, the second weight and the third weight to obtain the target confidence level.

5. The method according to claim 1, characterized in that, The step of controlling the parking of the vehicle according to the parking path includes: During the process of parking the vehicle according to the parking path, the control parameters and driving parameters of the vehicle are acquired. If it is determined that the vehicle collides with the wheel chock based on the control parameters and the driving parameters, the vehicle's position and posture information is determined, and parking control is performed on the vehicle based on the position and posture information.

6. The method according to claim 5, characterized in that, If it is determined that the vehicle has collided with the wheel chock based on the control parameters and the driving parameters, then the vehicle's position and orientation information is determined, and parking control is performed on the vehicle based on the position and orientation information, including: If it is determined that the vehicle collides with the wheel chock based on the control parameters and the driving parameters, then the vehicle's position and orientation information is determined, and whether the vehicle is fully parked in the target parking space is determined based on the position and orientation information. If it is determined that the vehicle is not fully parked in the target parking space, the parking path is replanned based on the pose information and the location information of the target parking space, and the parking control of the vehicle is performed based on the replanned parking path.

7. The method according to claim 6, characterized in that, Determining whether the vehicle is fully parked in the target parking space based on the pose information includes: The distance and angle deviations between the vehicle and the target parking space are determined based on the parking space information and the pose information. If the distance deviation meets the first preset condition and the angle deviation meets the second preset condition, then it is determined that the vehicle is completely parked in the target parking space; If the distance deviation does not meet the first preset condition and / or the angle deviation does not meet the second preset condition, then it is determined that the vehicle has not been fully parked in the target parking space.

8. A parking control device for a vehicle, characterized in that, The device includes: The scene recognition module is used to acquire the current parking scene information of the vehicle, and determine the initial position information of the wheel chocks and the number of wheel chocks based on the current parking scene information; The parking space information determination module is used to determine the parking space information of the target parking space corresponding to the wheel stop based on the initial position information; The predicted position information determination module is used to determine the predicted position information of the wheel chock based on the initial position information when the vehicle is parked in the target parking space, and to obtain the real-time position information of the wheel chock. The position change information determination module is used to determine the position change information corresponding to the stop wheel lever based on the real-time position information and the predicted position information; The target confidence determination module is used to determine the target confidence level corresponding to the wheel stop based on the parking space information, the quantity information, and the position change information. The parking control module is used to plan a parking path based on the target confidence level and the initial position information, obtain a parking path, and control the vehicle to park based on the parking path.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

Images