Parking control method and device, vehicle, storage medium and program product

Abstract

The invention provides a parking control method and device, a vehicle, a storage medium and a program product, and relates to the technical field of vehicle control, and the method comprises the steps: obtaining a position relation between wheels of the vehicle and an obstacle corresponding to a target obstacle parking space when determining that the vehicle is parked in the target obstacle parking space, according to the position relation and a preset torque control rule, the motor output torque of the vehicle is determined, and according to the motor output torque, the vehicle is controlled to drive to the target obstacle parking space. Wherein the torque control rule comprises the steps that the torque is increased in the process that the wheels approach the obstacle, and the torque is kept unchanged when the wheels make contact with the obstacle. According to the method, the stability of the vehicle in the parking process can be ensured, the obvious pause feeling is prevented, and therefore the parking experience of a user is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a parking control method, device, vehicle, storage medium and program product. Background Art

[0002] With the rapid development and popularization of automatic parking technology, this technology has gradually spread from high-end configuration to mainstream models, significantly improving user convenience and safety in standard parking scenarios (such as open and flat vertical or parallel parking spaces). In these standard parking scenarios, the vehicle can efficiently identify the parking space and complete the parking operation accurately and smoothly.

[0003] Existing automated parking control solutions are primarily designed for standard parking scenarios, aiming to enhance the parking experience in these scenarios. However, when faced with non-standard scenarios, such as obstacles at the parking space entrance (such as curbs or steps), existing automated parking control solutions can cause significant jerking during the parking process, degrading the user's parking experience. Summary of the Invention

[0004] One of the objects of the present invention is to provide a parking control method to solve the problem of poor user parking experience in the prior art; a second object is to provide a parking control device; a third object is to provide a vehicle; a fourth object is to provide a computer-readable storage medium; and a fifth object is to provide a computer program product.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A parking control method, comprising:

[0007] When determining to park the vehicle in a target obstructed parking space, obtaining a positional relationship between the wheels of the vehicle and an obstacle corresponding to the target obstructed parking space;

[0008] Determining the motor output torque of the vehicle based on the positional relationship and a preset torque control rule, wherein the torque control rule includes increasing the torque as the wheel approaches the obstacle and maintaining the torque constant when the wheel contacts the obstacle;

[0009] The vehicle is controlled according to the motor output torque to drive into the target obstacle parking space.

[0010] The aforementioned technical approach effectively controls the vehicle's ability to navigate obstacles and reach the target obstructed parking space by acquiring the real-time positional relationship between the vehicle's wheels and obstacles and dynamically adjusting the torque control rules according to pre-set rules. Increasing torque as the wheels approach an obstacle ensures the vehicle can successfully overcome the obstacle's resistance, while maintaining torque as the wheels make contact with the obstacle, allowing for smoother wheel movement across the obstacle. This addresses the issue of existing automatic parking control solutions causing noticeable jerking during parking, degrading the user's parking experience, when the vehicle faces an obstructed parking space.

[0011] Furthermore, the torque control rule also includes: reducing the torque after the wheel passes over the obstacle.

[0012] According to the above technical means, the vehicle's wheels can be helped to quickly return to a stable driving state after crossing an obstacle, avoiding sudden acceleration or unnecessary energy consumption caused by excessive torque, and improving the stability and safety of vehicle driving.

[0013] Furthermore, determining the motor output torque of the vehicle according to the position relationship and a preset torque control rule includes:

[0014] If the positional relationship indicates that the wheels of the vehicle are approaching the obstacle, obtaining the motor output torque according to the torque increment corresponding to the height of the obstacle and the current motor torque;

[0015] If the positional relationship indicates that the wheel of the vehicle is in contact with the obstacle, the motor torque determined immediately before the wheel contacts the obstacle is used as the motor output torque;

[0016] If the positional relationship indicates that the wheels of the vehicle have crossed the obstacle and are moving away from the obstacle, the motor output torque is obtained by subtracting a torque increment corresponding to the height of the obstacle from the current motor torque.

[0017] The above-mentioned technical means enable precise control of the vehicle's motor output torque, avoiding jerking during parking. As the wheels approach an obstacle, the torque is adjusted based on the obstacle's height, ensuring the vehicle has sufficient power to overcome it. Upon contact with the obstacle, the torque output is maintained to prevent unstable vehicle wobbling. After overcoming the obstacle, the torque is reduced to restore smooth driving. This dynamic adjustment improves the smoothness of parking in complex obstructed spaces.

[0018] Furthermore, the method further comprises:

[0019] When the automatic parking function of the vehicle is turned on and an obstructed parking space within a preset range of the vehicle is detected, obtaining the height of the obstacle corresponding to the obstructed parking space; wherein the obstructed parking space is a parking space with an obstacle outside the entrance and no other obstacles within a preset distance on both sides;

[0020] If the height of the obstacle is less than the chassis height of the vehicle, the obstacle parking space is determined to be a target obstacle parking space, and the vehicle is determined to be parked in the target obstacle parking space.

[0021] Using these technologies, when the automatic parking feature is enabled, the vehicle proactively detects surrounding parking spaces and selects an appropriate parking location by determining whether the obstacle is lower than the vehicle chassis. This ensures that the vehicle chassis is not damaged by obstacles that are too high during parking, thereby protecting the vehicle's structural integrity and service life.

[0022] Furthermore, the method further comprises:

[0023] In response to a user turning on the automatic parking function, detecting a parking space closest to the vehicle;

[0024] If there is an obstacle outside the parking space entrance, detect whether there are other obstacles within a preset distance on both sides of the parking space;

[0025] If there are no other obstacles within a preset distance range on both sides of the parking space, the parking space is determined as the obstacle parking space.

[0026] Using the aforementioned technologies, the vehicle can intelligently identify and select an appropriate parking space, especially when there are other obstacles in the space. When the user activates the automatic parking feature, the vehicle proactively detects the nearest parking space and assesses whether there are any obstacles outside the entrance. If there are obstacles, the vehicle can further detect whether there are other obstacles within a preset distance range on either side of the parking space. This multi-layered detection mechanism allows the vehicle to accurately determine the availability of parking spaces, ensuring that the selected space avoids potential collision risks, thereby improving the safety and reliability of parking in obstructed spaces.

[0027] Furthermore, the detecting the parking space closest to the vehicle includes:

[0028] Acquiring an image of the surroundings of the vehicle by an image acquisition device disposed outside the vehicle;

[0029] The parking space closest to the vehicle is identified from the parking spaces in the image through a preset parking space recognition model, wherein the parking space recognition model is a model for parking space recognition and distance judgment obtained by training a deep learning model.

[0030] Using these technologies, vehicles can significantly improve the accuracy and efficiency of parking space recognition. Specifically, using an image acquisition device mounted on the vehicle's exterior, the vehicle can capture real-time images of its surroundings. Combined with a parking space recognition model trained through deep learning, these images can quickly identify the nearest parking space, providing critical information for parking.

[0031] Furthermore, obtaining the positional relationship between the wheels of the vehicle and the obstacle corresponding to the target obstacle parking space includes:

[0032] If the distance between the vehicle and the obstacle is determined to be gradually decreasing by the distance measuring device, then determining that the positional relationship between the wheels of the vehicle and the obstacle is a close relationship;

[0033] If the distance between the vehicle and the obstacle is determined to be zero by the distance measuring device, then determining that the positional relationship between the wheel of the vehicle and the obstacle is a contact relationship;

[0034] If it is determined by the distance measuring device that the vehicle has passed over the obstacle and the distance from the obstacle gradually increases, it is determined that the positional relationship between the wheels of the vehicle and the obstacle is a crossing relationship.

[0035] This technology allows the vehicle to accurately monitor and determine the positional relationship between the wheels and obstacles, improving parking safety and accuracy. The distance measurement device detects changes in the distance between the vehicle and the obstacle in real time, determining whether the vehicle's wheels are approaching, contacting, or overtaking the obstacle. The motor output torque is then adjusted based on this positional relationship, enabling safer and more efficient parking without jerkiness.

[0036] A parking control device, comprising:

[0037] A first processing module is configured to obtain a positional relationship between the wheels of the vehicle and an obstacle corresponding to the target obstructed parking space when determining to park the vehicle in the target obstructed parking space;

[0038] a second processing module, configured to determine a motor output torque of the vehicle based on the positional relationship and a preset torque control rule, wherein the torque control rule includes increasing the torque as the wheel approaches the obstacle and maintaining the torque constant when the wheel contacts the obstacle;

[0039] A control module is used to control the vehicle according to the output torque of the motor so as to drive into the target obstacle parking space.

[0040] A vehicle, comprising: a vehicle body, a memory, and a processor;

[0041] The memory stores computer-executable instructions;

[0042] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the parking control method.

[0043] A computer-readable storage medium stores computer-executable instructions, which are used to implement the above-mentioned parking control method when executed by a processor.

[0044] A computer program product includes a computer program, wherein the computer program is used to implement the above parking control method when executed by a processor.

[0045] Beneficial effects of the present invention:

[0046] (1) By monitoring the positional relationship between the vehicle's wheels and the obstacle corresponding to the target parking space in real time, the motor output torque can be dynamically adjusted according to the preset torque control rules. The torque is increased when the wheel approaches the obstacle, remains unchanged when it contacts it, and is reduced after it passes it. This intelligent torque management improves the safety and smoothness of the parking process, avoids the obvious jerkiness that occurs when parking in an obstacle space with existing automatic parking control solutions, and improves the user's parking experience.

[0047] (2) When the automatic parking function is turned on, the vehicle can detect the parking space conditions around the vehicle, especially the comparison between the height of the obstacle parking space and the vehicle chassis. By determining whether the height of the obstacle is lower than the vehicle chassis, the vehicle can intelligently select the appropriate target obstacle parking space to ensure parking safety.

[0048] (3) Using an image acquisition device and a parking space recognition model trained through deep learning, the vehicle can accurately identify the nearest parking space and determine its availability. This high-precision recognition capability ensures that the vehicle can quickly find a suitable parking space in complex parking environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a parking control method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of a position relationship provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a process for determining a target obstructed parking space provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a process for determining an obstructed parking space provided in an embodiment of the present application;

[0053] Figure 5A schematic diagram of a parking space entrance with a curb provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of the sensing information clearing range provided in an embodiment of the present application;

[0055] Figure 7 The entrance curb parking system provided in the embodiment of the present application;

[0056] Figure 8 A flowchart of the automatic parking control method for curbside parking spaces provided in this application;

[0057] Figure 9 A schematic diagram of the structure of the parking control device provided in this application;

[0058] Figure 10 A schematic diagram of the structure of the vehicle provided for this application. DETAILED DESCRIPTION

[0059] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0060] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention 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 may be changed arbitrarily, and the component layout may also be more complex.

[0061] First, the background technology involved in this application is described in detail.

[0062] With the development and popularization of automated parking technology, its application has gradually expanded into thousands of households, greatly improving the convenience and safety of users in standard parking scenarios (such as spacious, flat perpendicular or parallel parking spaces). In these standard parking scenarios, the vehicle can efficiently identify the parking space and complete the parking maneuver accurately and smoothly. However, with the acceleration of urbanization and the increase in parking demand, the parking environment has become increasingly complex, and non-standard parking scenarios are becoming more and more common.

[0063] Existing automated parking control solutions are primarily designed for standard parking scenarios, aiming to optimize the parking experience in these situations. These solutions typically rely on sensors and cameras surrounding the vehicle to identify parking spaces and implement automated parking through pre-set path planning and control algorithms. However, in non-standard scenarios, such as those with obstructions at the parking space entrance (such as curbs or steps), the vehicle can experience noticeable jerkiness during parking, degrading the user's parking experience.

[0064] Based on the above issues, the technical concept of this application is as follows: When it is determined that a vehicle will park in a target obstructed parking space, the positional relationship between the vehicle's wheels and the obstacle corresponding to the target obstructed parking space can be obtained. Based on this positional relationship and preset torque control rules, the vehicle's motor output torque is determined. The torque control rules may include increasing the torque as the wheels approach the obstacle and maintaining the torque unchanged when the wheels contact the obstacle. Finally, the vehicle is controlled based on the determined motor output torque to smoothly enter the target obstructed parking space, achieving smooth parking without any sense of frustration, thereby improving the user's parking experience.

[0065] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0066] Figure 1 This is a flow chart of the parking control method provided in the embodiment of the present application. The method can be specifically applied to vehicles with automatic parking functions, taking the vehicle as the execution subject as an example. Figure 1 As shown, the method may include:

[0067] S101. When it is determined that a vehicle is to be parked in a target obstructed parking space, a positional relationship between wheels of the vehicle and an obstacle corresponding to the target obstructed parking space is obtained.

[0068] An obstructed parking space is one with an obstruction outside the entrance and no other obstructions within a preset distance on either side. Obstacles outside the entrance can include curbs, steps, and other obstacles that affect smooth vehicle movement. "No other obstacles within a preset distance on either side" means there are no other vehicles, ice cream cones, pillars, or other obstacles within the preset distance on either side of the parking space. For ease of understanding, let's use a curb outside the entrance as an example, meaning the obstructed parking space is a curbside parking space.

[0069] In one possible implementation, a distance measuring device disposed outside the vehicle can be used to obtain the positional relationship between the vehicle's wheels and the obstacle corresponding to the target obstructed parking space, wherein the positional relationship can be a proximity relationship, a contact relationship, or a span relationship.

[0070] If the distance between the vehicle and the obstacle is gradually decreasing as determined by the distance measuring device, it is determined that the positional relationship between the wheels of the vehicle and the obstacle is a close relationship;

[0071] If the distance between the vehicle and the obstacle is determined to be zero by the distance measuring device, then the positional relationship between the wheels of the vehicle and the obstacle is determined to be a contact relationship;

[0072] If it is determined by the distance measuring device that the vehicle has passed over the obstacle and the distance to the obstacle gradually increases, it is determined that the positional relationship between the wheels of the vehicle and the obstacle is a crossing relationship.

[0073] The distance measuring device may be a laser radar arranged outside the vehicle.

[0074] A vehicle generally includes rear wheels and front wheels. For ease of understanding, the following embodiments are described using the rear wheels of the vehicle as an example.

[0075] Figure 2 This is a schematic diagram of a position relationship provided in an embodiment of the present application. Figure 2 As shown, the obstacle parking space is a curb parking space with a curb. If the laser radar determines that the distance between the rear wheel and the curb is gradually decreasing (from distance D1 to distance D2), it can be determined that the positional relationship between the rear wheel and the curb is a proximity relationship; if the laser radar determines that the distance between the rear wheel and the curb is 0, it can be determined that the positional relationship between the rear wheel and the curb is a contact relationship; if the laser radar determines that the rear wheel passes over the curb and the distance to the curb is gradually increasing (from 0 to D3), it can be determined that the positional relationship between the rear wheel and the curb is a straddling relationship.

[0076] In this implementation, the vehicle can accurately monitor and determine the positional relationship between the wheels and obstacles, thereby improving parking safety and accuracy. The distance measurement device can detect changes in the distance between the vehicle and the obstacle in real time, determining whether the vehicle's wheels are approaching, contacting, or overtaking the obstacle. The motor output torque is then adjusted based on this positional relationship, achieving safer and more efficient parking without jerkiness.

[0077] S102: Determine the motor output torque of the vehicle according to the position relationship and a preset torque control rule.

[0078] The torque control rule may include increasing the torque when the wheel approaches the obstacle and keeping the torque unchanged when the wheel contacts the obstacle.

[0079] For example, the torque is increased as the rear wheel approaches the curb and maintained when the rear wheel contacts the curb.

[0080] In an optional implementation, the torque control rule further includes: reducing the torque after the wheel passes over an obstacle.

[0081] In the above implementation, the vehicle's wheels can be helped to quickly return to a stable driving state after crossing an obstacle, avoiding sudden acceleration or unnecessary energy consumption caused by excessive torque, and improving the vehicle's driving stability and safety.

[0082] Specifically, if the positional relationship indicates that the wheels of the vehicle are approaching an obstacle, the motor output torque is obtained based on the torque increment corresponding to the height of the obstacle and the current motor torque.

[0083] The current motor torque may be the torque output by the motor when the distance between the vehicle's wheels and the obstacle meets a distance threshold. The distance threshold may be pre-set based on user needs.

[0084] For example, when the distance between the rear wheel and the curb is a distance threshold of 30 centimeters (cm), the current motor torque of the motor may be 100 Newton meters (N·m).

[0085] Optionally, the distance threshold may be used as a judgment condition for a proximity relationship. When the wheels of the vehicle approach an obstacle and the distance between the two is equal to the distance threshold, the position relationship is determined to be a proximity relationship.

[0086] In an optional embodiment, the torque increment corresponding to the obstacle height can be obtained by looking up a table. In a specific implementation, a lookup table of torque increments corresponding to obstacle heights can be pre-established. Once the obstacle height is determined, the torque increment can be obtained by looking up the table. For example, if the curb height is 10 cm, the torque increment can be obtained by looking up the table as 200 N·m.

[0087] In another optional embodiment, the torque increment corresponding to the height of the obstacle may be calculated based on the determined height of the obstacle according to a preset torque increment calculation formula.

[0088] The height of obstacles can also be measured by a lidar installed outside the vehicle.

[0089] For example, if the positional relationship indicates that the rear wheel is close to the curb, the motor output torque is obtained as 300 N·m based on the torque increment of 200 N·m corresponding to the curb height of 10 cm and the current motor torque of 100 N·m.

[0090] Specifically, if the positional relationship indicates that the vehicle wheel is in contact with the obstacle, the motor torque determined immediately before the wheel contacts the obstacle is used as the motor output torque. The motor torque determined immediately before the wheel contacts the obstacle may be the torque immediately after the vehicle wheel contacts the obstacle.

[0091] For example, if the positional relationship indicates that the rear wheel has contacted a curb, the motor torque of 300 N·m determined immediately before the rear wheel contacts the curb is used as the motor output torque. It should be understood that motor output torque typically increases gradually rather than suddenly, so the motor output torque can reach 300 N·m immediately before the rear wheel contacts the curb.

[0092] Specifically, if the positional relationship indicates that the wheels of the vehicle have crossed the obstacle and are moving away from the obstacle, the torque increment corresponding to the height of the obstacle is subtracted from the current motor torque to obtain the motor output torque.

[0093] For example, if the positional relationship indicates that the rear wheel is over the curb and away from the curb, the torque increment of 200 N·m corresponding to the curb height of 10 cm is subtracted from the current motor torque of 300 N·m to obtain the motor output torque of 100 N·m.

[0094] This implementation enables precise control of the vehicle's motor output torque, avoiding jerking during parking. As the wheels approach an obstacle, the torque is adjusted based on the obstacle's height, ensuring the vehicle has sufficient power to overcome it. Upon contact with the obstacle, the torque output is maintained to prevent unstable vehicle wobbling. After overcoming the obstacle, the torque is reduced to restore smooth driving. This dynamic adjustment improves the smoothness of parking in complex, obstructed spaces.

[0095] S103: Control the vehicle according to the motor output torque to drive to the target obstacle parking space.

[0096] Among them, the position relationship can indicate that the vehicle's wheels are approaching an obstacle, and the torque is increased in the process of the wheels approaching the obstacle. The position relationship can indicate that the vehicle's wheels are in contact with the obstacle, and the torque is kept unchanged when the wheels are in contact with the obstacle. The position relationship can indicate that the vehicle's wheels are crossing the obstacle and moving away from the obstacle, and the torque is reduced after the wheels have crossed the obstacle.

[0097] For example, when the rear wheel is 30 cm away from the curb, the position relationship can be used to instruct the rear wheel to approach the curb, and the torque can be increased in the process of the rear wheel approaching the curb. According to the torque increment of 200 N·m corresponding to the height of 10 cm of the curb and the current motor torque of 100 N·m, the motor output torque of 300 N·m can be obtained; when the rear wheel is in contact with the curb according to the position relationship, the torque of 300 N·m can be kept unchanged, and the rear wheel can be instructed to cross the curb and move away from the curb according to the position relationship. The torque increment of 200 N·m corresponding to the height of 10 cm of the curb is subtracted from the current motor torque of 300 N·m to obtain the motor output torque of 100 N·m, so as to drive to the target obstacle parking space.

[0098] In one optional embodiment, the front wheels' obstacle-passing process is similar to the rear wheels'. When the front wheels clear the obstacle, the vehicle is nearing its target parking location. At this point, the motor's output torque can be further limited to direct the vehicle into the target obstructed parking space. The target location can be the center of the obstructed parking space. For example, after the front wheels clear the curb, the motor's output torque can be reduced from 300 N·m to 0 N·m. The motor no longer provides driving force, and the vehicle can continue to move by inertia or other external forces (such as gravity) until it reaches the target location.

[0099] In this embodiment of the present application, by acquiring the real-time positional relationship between the vehicle's wheels and obstacles and dynamically adjusting torque according to pre-set torque control rules, the vehicle can be effectively guided over obstacles and into the target obstructed parking space. As the wheels approach the obstacle, the motor's output torque is increased to ensure the vehicle can overcome the obstacle's resistance. When the wheels contact the obstacle, the torque is maintained constant for a smoother crossing. By dynamically adjusting torque, the vehicle can more smoothly pass over obstacles and park into the target obstructed parking space, ensuring a smooth and comfortable parking process and improving the user's parking experience.

[0100] In one possible implementation, before determining to park the vehicle in the target obstacle parking space, it is necessary to turn on the vehicle's automatic parking function, and judge whether the obstacle parking space detected within the preset range of the vehicle is the target obstacle parking space. If the obstacle parking space within the preset range of the vehicle is the target obstacle parking space, it can be determined that the vehicle will be parked in the target obstacle parking space.

[0101] Figure 3 This is a flow chart of determining a target obstructed parking space provided in an embodiment of the present application. Figure 3 As shown, the method may include:

[0102] S301: When the automatic parking function of the vehicle is turned on and an obstructed parking space within a preset range of the vehicle is detected, obtain the height of the obstacle corresponding to the obstructed parking space.

[0103] Obstructed parking spaces are defined as spaces with an obstruction outside the entrance and no other obstructions within a preset distance on either side. The preset range can be set based on actual parking needs.

[0104] Before automatic parking, if there are other obstacles (such as other vehicles, ice cream cones, and pillars) within a preset distance on both sides of the obstacle parking space, the obstacle parking space can be regarded as a narrow parking space. Narrow parking spaces are usually not suitable for the strategy of increasing torque in advance to overcome them because there is a risk of subsequent collision.

[0105] In addition, during the automatic parking process, when the vehicle's wheels approach an obstacle parking space, since there is a certain angle between the vehicle and the obstacle parking space when parking (the direction of the vehicle's movement trend), and the vehicle is close to other obstacles (such as other vehicles, ice cream cones, and pillars), the strategy of increasing torque in advance to overcome them is not suitable. You can choose not to send a command to increase torque to the motor controller.

[0106] For example, when the automatic parking function of the vehicle is turned on and a curb parking space within a preset range of the vehicle is detected, the curb height corresponding to the curb parking space is obtained as 10 cm.

[0107] S302: If the height of the obstacle is less than the chassis height of the vehicle, the obstructed parking space is determined to be a target obstructed parking space, and the vehicle is determined to be parked in the target obstructed parking space.

[0108] Specifically, whether a vehicle can park in a parking space with an obstacle is often determined based on the vehicle's chassis height. When the height of the obstacle is less than the vehicle's chassis height, the vehicle is deemed to be able to cross the obstacle. The obstacle parking space can then be determined as a target obstacle parking space, and the vehicle can be parked in the target obstacle parking space.

[0109] On the contrary, if the height of the obstacle is greater than or equal to the chassis height of the vehicle, it can be determined that the vehicle cannot cross the obstacle and there is a risk of collision with the vehicle chassis. By identifying the parking space, the risk of vehicle collision damage caused by obstacle height problems can be avoided.

[0110] In an embodiment of the present application, when the automatic parking function is activated, the vehicle can actively detect the surrounding obstacle parking spaces and select the target obstacle parking space by judging whether the height of the obstacle is lower than the vehicle chassis, ensuring that the vehicle chassis will not be damaged due to the obstacle being too high during the parking process, thereby maintaining the structural integrity of the vehicle and extending its service life.

[0111] Figure 4 This is a flow chart of determining an obstructed parking space provided in an embodiment of the present application. Figure 4 As shown, the method may include:

[0112] S401: In response to a user turning on an automatic parking function, detecting a parking space closest to the vehicle.

[0113] Specifically, the vehicle's automatic parking function can be activated in any of the following ways.

[0114] Method (1): The user can activate the automatic parking function by pressing a dedicated button or switch inside the car;

[0115] Method (2): In a vehicle equipped with a touch screen, the user can select and activate the automatic parking function through the interface of the vehicle's infotainment system;

[0116] Method (3): In a vehicle equipped with voice recognition function, the user can activate the automatic parking function through voice commands.

[0117] In one possible implementation, detecting the parking space closest to the vehicle can be achieved through the following steps 1 and 2:

[0118] Step 1: Acquire images of the vehicle's surroundings using an image acquisition device disposed outside the vehicle.

[0119] The image acquisition device may be a camera arranged outside the vehicle, and images around the vehicle may be acquired through the camera.

[0120] Step 2: Use a preset parking space recognition model to identify the parking space closest to the vehicle from the parking spaces in the image. The parking space recognition model is a model trained by a deep learning model to perform parking space recognition and distance judgment.

[0121] For example, a deep learning model can employ a convolutional neural network model. By annotating images containing parking spaces, it can generate corresponding labels, which may include the location of the parking space and the distance between the parking space and the vehicle. By constructing a training set to train the convolutional neural network model, the resulting parking space recognition model can effectively identify parking spaces and their distances from images. The training set can include a large number of images containing parking spaces, each accurately annotated with the location of the parking space and the distance between the parking space and the vehicle.

[0122] In the above implementation, by utilizing the image acquisition device outside the vehicle and combining it with a parking space recognition model trained by deep learning, the parking space closest to the vehicle can be efficiently identified from the images captured by the image acquisition device, providing key information for parking.

[0123] S402: If there is an obstacle outside the parking space entrance, detect whether there are other obstacles within a preset distance range on both sides of the parking space.

[0124] Among them, whether there are other obstacles within the preset distance range on both sides of the parking space can be identified by the distance measuring device.

[0125] Specifically, the range of the preset distances on both sides of the parking space can be preset. For example, the range of the preset distances on both sides of the parking space can be a range of 0.5 m from the left side of the parking space and a range of 0.5 m from the right side of the parking space.

[0126] In one possible implementation, whether there are other obstacles within a preset distance on both sides of the parking space can also be obtained through ultrasonic sensors, millimeter-wave radars, cameras combined with computer vision, infrared sensors, or multi-sensor fusion.

[0127] Specifically, when it is determined that there is an obstacle outside the parking space entrance (such as a curb or steps), it can be further detected whether there are other obstacles (vehicles, ice cream cones, pillars) within a preset range on both sides of the parking space, and whether the parking space is an obstacle parking space can be determined based on the detection results.

[0128] S403: If there are no other obstacles within the preset distance range on both sides of the parking space, the parking space is determined as an obstructed parking space.

[0129] For example, the parking space can be determined as an obstructed parking space based on the presence of a curb outside the parking space entrance and the absence of other vehicles, ice cream cones, and pillars within 0.5 meters on both sides of the parking space.

[0130] In one possible implementation, for scenarios where obstacles (such as curbs or steps) exist outside some parking space entrances that are not recognized by the parking space recognition model, or scenarios where obstacles exist outside some parking space entrances that are not included in the training set used to train the deep learning model, post-processing can be used to identify the parking spaces in the image by setting a judgment area to determine whether there are obstacles outside the parking space entrances in the image.

[0131] Figure 5 This is a schematic diagram of a parking space with a curb outside the entrance provided in the embodiment of the present application. Figure 5 As shown, the AB sides are the parking space entrance sides, and the upper and lower 0.3m are the judgment areas. Based on the presence of a curb in the judgment area, it is determined that there is a curb outside the parking space entrance. The judgment area consists of the area surrounded by points E, F, G, and H.

[0132] In some embodiments, through a parking space recognition model or post-processing, the presence of obstacles outside the parking space entrance is sensed and identified, and usually a series of perception information of impassable points is output, which makes the vehicle unable to pass. Therefore, the perception information including the impassable points output outside the parking space entrance can be cleared.

[0133] Specifically, if the height of the obstacle is less than the vehicle's chassis height, the sensor can clear the sensor's output of the impassable point outside the parking space entrance. After the sensor information of the impassable point is cleared, the subsequent parking operation is performed. The clearing range can be pre-set.

[0134] Figure 6 This is a schematic diagram of the sensing information clearing range provided in the embodiment of this application. Figure 6 As shown, the preset clearing range may include 1m in front of the parking space entrance (AB side), 0.3m behind the parking space entrance (AB side), 0.5m to the left side of the parking space (AC side), and 0.5m to the right side of the parking space (BD side).

[0135] In an embodiment of the present application, the vehicle can intelligently identify and select a suitable parking space, especially when there are other obstacles in the parking space. When the user turns on the automatic parking function, the vehicle can actively detect the parking space closest to the vehicle and assess whether there are any obstacles outside the parking space entrance. If there are obstacles, it can further detect whether there are other obstacles within a preset distance range on both sides of the parking space. Through this multi-level detection mechanism, the vehicle can accurately determine the availability of parking spaces and ensure that the selected parking space can avoid potential collision risks, thereby improving the safety and reliability of the vehicle when parking in obstructed parking spaces.

[0136] Figure 7 The entrance curb parking system provided in the embodiment of the present application. Figure 7 As shown, a vehicle can park in a curb parking space through the entrance curb parking system. Specifically, the entrance curb parking system 700 includes: a parking space sensing processing module 701, a longitudinal speed planning module 702, and a longitudinal control module 703.

[0137] The parking space sensing and processing module 701 includes a curbside parking space scene recognition module 7011, a curb height recognition module 7012, and a perception information clearing module 7013. The curbside parking space scene recognition module 7011 is used to identify the parking space closest to the vehicle. This is determined by the presence of a curb outside the parking space entrance and the absence of other vehicles, ice cream cones, pillars, and other obstacles within a preset distance on either side of the parking space. The curb height recognition module 7012 is used to identify the height of the curb. The perception information clearing module 7013 is used to clear the perception information of the impassable point outside the parking space entrance, as output by the perception output, based on the curb height being less than the vehicle's chassis height.

[0138] Longitudinal speed planning module 702 includes a curb position relationship recognition module 7021 and a scenario restriction module 7022. Curb position relationship recognition module 7021 is used to identify the positional relationship between the vehicle's wheels and the curb during parking; positional relationships include proximity, contact, or overtaking. Scenario restriction module 7022 is primarily used to restrict certain scenarios where premature torque increase over the curb is unsuitable (e.g., in narrow parking spaces, or when the vehicle's direction of motion is close to other vehicles, pillars, or ice cream cones).

[0139] The longitudinal speed control module 703 is used to adjust the motor output torque according to the position relationship determined by the curb position relationship recognition module 721 to change the vehicle speed and control the vehicle to travel to the curb parking space.

[0140] The aforementioned curb parking system enables vehicles to park more intelligently in curb spaces. The system utilizes multiple modules working together to achieve parking environment perception, torque planning, and control. This system enables vehicles to park more efficiently and safely in curb spaces, reducing the driver's workload and improving the user's parking experience.

[0141] Figure 8 This is a flow chart of the automatic parking control method for curbside parking spaces provided in this application. Figure 8 As shown, the method may include:

[0142] S801. Start parking and look for a parking space.

[0143] In response to the user turning on the automatic parking function, the parking space closest to the vehicle is detected.

[0144] S802: The parking space sensing processing module identifies the roadside parking space.

[0145] Among them, the parking space perception processing module can identify the entrance parking space scene and give the parking space type as a curb parking space. The attributes of the curb parking space include the presence of a curb outside the entrance, no other obstacles within a preset distance on both sides of the curb parking space, and the height of the curb is less than the chassis height of the vehicle.

[0146] Furthermore, the sensory output of the impassable point outside the parking space entrance can be cleared. It should be understood that if the curb height is greater than or equal to the vehicle's chassis height, the sensory output of the impassable point outside the parking space entrance can be omitted and the curb parking space can be directly determined as unavailable.

[0147] S803: Determine the target parking space and start path planning.

[0148] Specifically, the determined roadside parking space can be determined as the target obstacle parking space, and the automatic parking path planning can be started.

[0149] S804: Identify the position relationship during the automatic parking process and send it to the longitudinal speed control module.

[0150] Specifically, the longitudinal speed planning module can identify the position relationship during the automatic parking process and send it to the longitudinal speed control module. The position relationship can be a proximity relationship, a contact relationship, or a crossing relationship.

[0151] S805: When the position relationship is close, start increasing the torque and increasing the vehicle speed.

[0152] Specifically, the longitudinal speed control module can instruct the vehicle's wheels to approach the curb based on the proximity relationship, and obtain the motor output torque based on the torque increment corresponding to the height of the curb and the current motor torque.

[0153] S806: When the position relationship is a contact relationship, the motor maintains the torque output after the torque is increased.

[0154] Specifically, the longitudinal speed control module may indicate that the wheels of the vehicle are in contact with the curb based on the positional relationship being a contact relationship, and use the motor torque determined immediately before the wheels contact the curb as the motor output torque.

[0155] S807: When the positional relationship is a spanning relationship, start canceling the torque increase.

[0156] Specifically, the longitudinal speed control module can instruct the vehicle's wheels to cross the curb and move away from the curb based on the position relationship being a crossing relationship, and subtract the torque increment corresponding to the height of the curb from the current motor torque to obtain the motor output torque.

[0157] Furthermore, if the rear wheels cross the curb first, the timing for the front wheels to start crossing the curb can be determined based on the vehicle's current speed and wheelbase when the rear wheels cross the curb, and the motor output torque can be adjusted to achieve smooth speed control in the transition stage from the rear wheels crossing the curb to the front wheels crossing the curb, preventing sudden acceleration or deceleration from causing a decline in user experience.

[0158] The specific execution process of the automatic parking control method for curbside parking spaces provided in the embodiment of the present application can be referred to the technical solution shown in the above method embodiment. Its implementation principles and beneficial effects are similar and will not be repeated here.

[0159] Figure 9 This is a schematic diagram of the structure of the parking control device provided in this application. Figure 9 As shown, the parking control device 900 provided in this embodiment includes:

[0160] The first processing module 901 is configured to obtain a positional relationship between the wheels of the vehicle and an obstacle corresponding to the target obstructed parking space when determining to park the vehicle in the target obstructed parking space;

[0161] A second processing module 902 is configured to determine the motor output torque of the vehicle based on the position relationship and a preset torque control rule, wherein the torque control rule includes increasing the torque as the wheel approaches the obstacle and maintaining the torque constant when the wheel contacts the obstacle;

[0162] The control module 903 is configured to control the vehicle according to the motor output torque so as to drive to the target obstacle parking space.

[0163] Optionally, the torque control rule also includes: reducing the torque after the wheel passes over an obstacle.

[0164] Optionally, the second processing module 902 is specifically configured to:

[0165] If the positional relationship indicates that the wheels of the vehicle are approaching the obstacle, obtaining the motor output torque according to the torque increment corresponding to the height of the obstacle and the current motor torque;

[0166] If the positional relationship indicates that the wheel of the vehicle is in contact with the obstacle, the motor torque determined immediately before the wheel contacts the obstacle is used as the motor output torque;

[0167] If the positional relationship indicates that the wheels of the vehicle have crossed the obstacle and are moving away from the obstacle, the motor output torque is obtained by subtracting a torque increment corresponding to the height of the obstacle from the current motor torque.

[0168] Optionally, the first processing module 901 is further configured to:

[0169] When the automatic parking function of the vehicle is turned on and an obstructed parking space within a preset range of the vehicle is detected, obtaining the height of the obstacle corresponding to the obstructed parking space; wherein the obstructed parking space is a parking space with an obstacle outside the entrance and no other obstacles within a preset distance on both sides;

[0170] If the height of the obstacle is less than the chassis height of the vehicle, the obstacle parking space is determined to be a target obstacle parking space, and the vehicle is determined to be parked in the target obstacle parking space.

[0171] Optionally, the parking control device 900 further includes a detection module 904, wherein the detection module 904 is configured to:

[0172] In response to a user turning on the automatic parking function, detecting a parking space closest to the vehicle;

[0173] If there is an obstacle outside the parking space entrance, detect whether there are other obstacles within a preset distance on both sides of the parking space;

[0174] If there are no other obstacles within a preset distance range on both sides of the parking space, the parking space is determined as the obstacle parking space.

[0175] Optionally, the detection module 904 is specifically configured to:

[0176] Acquiring an image of the surroundings of the vehicle by an image acquisition device disposed outside the vehicle;

[0177] The parking space closest to the vehicle is identified from the parking spaces in the image through a preset parking space recognition model, wherein the parking space recognition model is a model for parking space recognition and distance judgment obtained by training a deep learning model.

[0178] Optionally, the first processing module 901 is specifically configured to:

[0179] If the distance between the vehicle and the obstacle is determined to be gradually decreasing by the distance measuring device, then determining that the positional relationship between the wheels of the vehicle and the obstacle is a close relationship;

[0180] If the distance between the vehicle and the obstacle is determined to be zero by the distance measuring device, then determining that the positional relationship between the wheel of the vehicle and the obstacle is a contact relationship;

[0181] If it is determined by the distance measuring device that the vehicle has passed over the obstacle and the distance from the obstacle gradually increases, it is determined that the positional relationship between the wheels of the vehicle and the obstacle is a crossing relationship.

[0182] The parking control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0183] Figure 10 This is a schematic diagram of the structure of the vehicle provided in this application. Figure 10 As shown, the vehicle 1000 provided in this embodiment includes: a vehicle body 1001, at least one processor 1002, and a memory 1003. Optionally, the vehicle 1000 also includes a communication component 1004. The processor 1002, the memory 1003, and the communication component 1004 are connected via a bus 1005.

[0184] During the specific implementation process, at least one processor 1002 executes the computer-executable instructions stored in the memory 1003, so that the at least one processor 1002 performs the above method.

[0185] The specific implementation process of the processor 1002 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0186] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0187] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0188] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0189] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0190] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0191] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0192] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0193] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0194] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0196] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0197] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0198] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

[0199] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or modification made by those skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A parking control method, characterized in that: include: When determining to park the vehicle in a target obstructed parking space, obtaining a positional relationship between the wheels of the vehicle and an obstacle corresponding to the target obstructed parking space; Determining the motor output torque of the vehicle based on the positional relationship and a preset torque control rule, wherein the torque control rule includes increasing the torque as the wheel approaches the obstacle and maintaining the torque constant when the wheel contacts the obstacle; The vehicle is controlled according to the motor output torque to drive into the target obstacle parking space.

2. The method according to claim 1, characterized in that The torque control rule also includes: reducing the torque after the wheel passes the obstacle.

3. The method according to claim 2, characterized in that Determining the motor output torque of the vehicle according to the position relationship and a preset torque control rule includes: If the positional relationship indicates that the wheels of the vehicle are approaching the obstacle, obtaining the motor output torque according to the torque increment corresponding to the height of the obstacle and the current motor torque; If the positional relationship indicates that the wheel of the vehicle is in contact with the obstacle, the motor torque determined immediately before the wheel contacts the obstacle is used as the motor output torque; If the positional relationship indicates that the wheels of the vehicle have crossed the obstacle and are moving away from the obstacle, the motor output torque is obtained by subtracting a torque increment corresponding to the height of the obstacle from the current motor torque.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: When the automatic parking function of the vehicle is turned on and an obstructed parking space within a preset range of the vehicle is detected, obtaining the height of the obstacle corresponding to the obstructed parking space; wherein the obstructed parking space is a parking space with an obstacle outside the entrance and no other obstacles within a preset distance on both sides; If the height of the obstacle is less than the chassis height of the vehicle, the obstacle parking space is determined to be a target obstacle parking space, and the vehicle is determined to be parked in the target obstacle parking space.

5. The method according to claim 4, characterized in that The method further comprises: In response to a user turning on the automatic parking function, detecting a parking space closest to the vehicle; If there is an obstacle outside the parking space entrance, detect whether there are other obstacles within a preset distance on both sides of the parking space; If there are no other obstacles within a preset distance range on both sides of the parking space, the parking space is determined as the obstacle parking space.

6. The method according to claim 5, characterized in that The detecting the parking space closest to the vehicle includes: Acquiring an image of the surroundings of the vehicle by an image acquisition device disposed outside the vehicle; The parking space closest to the vehicle is identified from the parking spaces in the image through a preset parking space recognition model, wherein the parking space recognition model is a model for parking space recognition and distance judgment obtained by training a deep learning model.

7. The method according to any one of claims 1 to 3, characterized in that The obtaining of the positional relationship between the wheels of the vehicle and the obstacle corresponding to the target obstacle parking space includes: If the distance between the vehicle and the obstacle is determined to be gradually decreasing by the distance measuring device, then determining that the positional relationship between the wheels of the vehicle and the obstacle is a close relationship; If the distance between the vehicle and the obstacle is determined to be zero by the distance measuring device, then determining that the positional relationship between the wheel of the vehicle and the obstacle is a contact relationship; If it is determined by the distance measuring device that the vehicle has passed over the obstacle and the distance from the obstacle gradually increases, it is determined that the positional relationship between the wheels of the vehicle and the obstacle is a crossing relationship.

8. A parking control device, characterized in that: include: A first processing module is configured to obtain a positional relationship between the wheels of the vehicle and an obstacle corresponding to the target obstructed parking space when determining to park the vehicle in the target obstructed parking space; a second processing module, configured to determine a motor output torque of the vehicle based on the positional relationship and a preset torque control rule, wherein the torque control rule includes increasing the torque as the wheel approaches the obstacle and maintaining the torque constant when the wheel contacts the obstacle; A control module is used to control the vehicle according to the output torque of the motor so as to drive into the target obstacle parking space.

9. A vehicle, characterized in that: include: Vehicle body, memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 7 when executed by a processor.

Images