Parking control method, computer program product and electronic device

Abstract

The invention provides a parking control method, a computer program product and electronic equipment, according to the parking control method provided by the invention, after an automatic parking function of a vehicle is activated, if a preset filtering condition for an initial target object existing in a target parking area of the vehicle is judged to be met according to vehicle operation data of the vehicle, the vehicle is parked according to the preset filtering condition; if yes, it can be considered that the credibility of the initial target object is poor, so that the initial target object can be filtered, and parking control is conducted on the vehicle according to the filtered target object in the target parking area.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and particularly to a parking control method, a computer program product, and an electronic device. Background Art

[0002] With the continuous development of technology, automobiles are gradually equipped with an automatic parking function, which combines the operating condition information of the vehicle itself and the environmental information around the vehicle to control the vehicle to park automatically. This function can not only improve the convenience of parking, but also reduce the vehicle collision accidents caused by unskilled driving skills of the driver. However, during the process of continuously controlling the vehicle to move forward and backward to attempt to park, the automatic parking function of the vehicle may be affected by the measurement errors of relevant sensors and the errors of relevant control algorithms, resulting in insufficient reliability and accuracy of the target objects detected in the parking area, thus affecting the normal operation of the automatic parking function. Summary of the Invention

[0003] Based on this, the present invention provides a parking control method, a computer program product, and an electronic device. By using this parking control method, the target objects with poor credibility detected in the target parking area of the vehicle can be filtered out to reduce the interference caused to the automatic parking function of the vehicle, which is beneficial to improving the reliability, accuracy, and parking success rate of the automatic parking function of the vehicle.

[0004] On the one hand, the present invention provides a parking control method, which includes:

[0005] After the automatic parking function of the vehicle is activated, obtain the initial target objects existing in the target parking area of the vehicle;

[0006] According to the vehicle operation data of the vehicle, determine whether the preset filtering condition for the initial target object is satisfied, and obtain a first judgment result; wherein, the preset filtering condition reflects that the initial target object is not credible;

[0007] If the first judgment result indicates that the preset filtering condition for the initial target object is satisfied, perform a filtering process on the initial target object to obtain the filtered target object in the target parking area;

[0008] Perform parking control on the vehicle according to the filtered target object in the target parking area.

[0009] Further, in some embodiments, the determining whether the preset filtering condition for the initial target object is satisfied according to the vehicle operation data of the vehicle includes:

[0010] Based on the vehicle operation data of this vehicle, determine whether the number of changes in the vehicle's traveling mode generated by this vehicle after the initial target object is first detected reaches a first threshold; or,

[0011] Based on the vehicle operation data of this vehicle, determine whether the difference between the current distance between this vehicle and the initial target object and the initial distance between this vehicle and the initial target object reaches a second threshold; wherein, the initial distance is the distance between this vehicle and the initial target object when the initial target object is first detected; or,

[0012] Based on the vehicle operation data of this vehicle, determine whether the cumulative driving distance of this vehicle after the initial target object is first detected reaches a third threshold.

[0013] Further, in some embodiments, the determining whether the number of changes in the vehicle's traveling mode generated by this vehicle after the initial target object is first detected reaches a first threshold according to the vehicle operation data of this vehicle includes:

[0014] Detect the vehicle's traveling mode change behavior according to at least one of the gear data, wheel speed sensor data, and steering wheel angle data of this vehicle; wherein, the vehicle's traveling mode change behavior is used to reflect that the vehicle's traveling mode of this vehicle has changed, and the vehicle's traveling mode includes at least some of the reverse traveling mode, forward traveling mode, and steering traveling mode;

[0015] Determine whether the number of vehicle's traveling mode change behaviors generated by this vehicle after the initial target object is first detected reaches a first threshold.

[0016] Further, in some embodiments, the determining whether the difference between the current distance between this vehicle and the initial target object and the initial distance between this vehicle and the initial target object reaches a second threshold according to the vehicle operation data of this vehicle includes:

[0017] According to the vehicle operation data of this vehicle and the target position data of the initial target object, determine the initial coordinate data of this vehicle and the initial target object in the preset coordinate system at the initial moment, and the current coordinate data of this vehicle and the initial target object in the preset coordinate system at the current moment; wherein, the initial moment is the moment when the initial target object is first detected;

[0018] According to the initial coordinate data and the current coordinate data of this vehicle and the initial target object, calculate the target distance difference between the current distance between this vehicle and the initial target object and the initial distance between this vehicle and the initial target object;

[0019] Determine whether the target distance difference reaches a second threshold.

[0020] Further, in some embodiments, the filtering the initial target object to obtain the filtered target object at the target parking area includes:

[0021] Determining whether the size of the initial target object reaches a preset size to obtain a second determination result;

[0022] If the second determination result indicates that the size of the initial target object reaches the preset size, deleting the initial target object to obtain the filtered target object at the target parking area.

[0023] Further, in some embodiments, after deleting the initial target object to obtain the filtered target object at the target parking area, the method further includes:

[0024] Performing target detection processing on the target parking area of the vehicle to obtain the latest target object;

[0025] If the latest target object includes a specific target object not included in the filtered target object, when the vehicle travels in the direction approaching the target parking area, performing parking control on the vehicle according to the specific target object.

[0026] Further, in some embodiments, before filtering the initial target object, the method further includes:

[0027] Determining whether the vehicle is traveling in the direction of leaving the target parking area and / or whether the current distance between the vehicle and the initial target object reaches a fourth threshold to obtain a third determination result;

[0028] The filtering the initial target object includes:

[0029] If the third determination result indicates that the vehicle is traveling in the direction of leaving the target parking area and / or the current distance between the vehicle and the initial target object reaches the fourth threshold, filtering the initial target object.

[0030] Further, in some embodiments, the obtaining the initial target object existing at the target parking area of the vehicle includes:

[0031] Obtaining the initial target object obtained by processing the target parking area image collected by the image acquisition device; or,

[0032] Obtaining the initial target object obtained by processing the target parking area perception data collected by the radar device; or,

[0033] Obtain an initial target object obtained by processing the perception data of the target parking area collected by a radar device and the image of the target parking area collected by an image acquisition device.

[0034] On the other hand, the present invention also provides a computer program product, which includes a computer program that implements the steps of the above method when executed.

[0035] On the other hand, the present invention also provides an electronic device, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to implement the steps of the above method.

[0036] Further, in some embodiments, the electronic device includes at least one of an image acquisition device, a radar device, a parking controller, and a domain controller.

[0037] According to the parking control method provided by the present invention, after the automatic parking function of the vehicle is activated, if it is determined according to the vehicle operation data of the vehicle that a preset filtering condition for the initial target object existing in the target parking area of the vehicle is satisfied, it can be considered that the credibility of the initial target object is poor, so that the initial target object can be filtered, so as to perform parking control on the vehicle according to the filtered target object in the target parking area, which is beneficial to reducing the interference of the target object with poor credibility detected in the target parking area of the vehicle on the automatic parking function of the vehicle, thereby improving the reliability, accuracy, and parking success rate when the automatic parking function of the vehicle operates.

[0038] It should be understood that the content described in the summary of the invention is not intended to limit the key or important features of the embodiments of the present invention, nor to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of a parking scenario provided by an embodiment of the present invention;

[0040] Figure 2 It is a schematic flowchart of a parking control method provided by an embodiment of the present invention;

[0041] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0042] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0043] In the description of one or more embodiments of the present invention, the terms "including" and its similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions below.

[0044] Currently, the automatic parking function installed in vehicles can usually sense the surrounding environment of the vehicle through radar devices, image acquisition devices, etc., and plan the parking path and strategy of the vehicle according to the position, size, relative distance, angle, etc. of the target object existing in the target parking area where the vehicle needs to park as sensed, and then automatically control the vehicle to park in place by controlling the gear, steering, driving speed, etc. of the vehicle.

[0045] However, affected by the measurement error of in-vehicle sensors, as well as the errors existing during the operation of the target object positioning algorithm and the vehicle dead reckoning algorithm, if the vehicle changes its traveling mode multiple times or moves over a long distance during the process of continuously tracking and detecting the target object existing in the target parking area, it will often, under the influence of the continuously increasing cumulative error, result in a large difference between the positions of the same target object detected in adjacent target detection cycles, thus wrongly determining that the target object has moved or its position has abnormally jumped. Therefore, it is likely to interfere with the normal operation of the automatic parking function and affect the reliability, accuracy and parking success rate during the operation of the automatic parking function.

[0046] Figure 1 This is a schematic diagram of a parking scenario provided for an embodiment of the present invention. For ease of understanding, here in combination with Figure 1 An example is given for the problems existing in the current automatic parking process. Such as Figure 1As shown in the figure, it is assumed that there are parking spaces 13 and 14 on one side of the road 12 where the vehicle 11 is located. If the vehicle 11 currently needs to park at the parking space 14, after the automatic parking function of the vehicle 11 is activated, the target object existing in the area where the parking space 14 is located can be continuously detected and tracked. If the vehicle 11 continuously moves forward, backward, turns or drives for a long distance along the path 15, path 16 or path 17 during the automatic parking process, it is likely to affect the accuracy of the target object existing in the area where the detected parking space 14 is located, and there may even be an abnormal situation where a stationary target object undergoes a sudden position change in a short period of time (for example, the same target object is at position 101 at the previous moment and at position 105 at the current moment), thus easily interfering with the normal operation of the automatic parking function and affecting the reliability, accuracy and parking success rate during the operation of the automatic parking function.

[0047] Based on this, the present invention proposes a parking control method. After the automatic parking function of the vehicle is activated, if it is determined according to the vehicle operation data of the vehicle that the preset filtering condition for the initial target object existing in the target parking area of the vehicle is satisfied, it can be considered that the credibility of the initial target object is poor, and thus the initial target object can be filtered, so as to perform parking control on the vehicle according to the filtered target object with good credibility in the target parking area, which is beneficial to reducing the interference caused by the target object with poor credibility detected in the target parking area of the vehicle to the automatic parking function of the vehicle, and thus can improve the reliability, accuracy and parking success rate during the operation of the automatic parking function of the vehicle.

[0048] Please refer to Figure 2 , which is a schematic flowchart of a parking control method provided by an embodiment of the present invention. From a program perspective, the execution subject of this process can be a program installed in a vehicle, a vehicle control device, a radar device or an image acquisition device. Or, the execution subject of this process can also be a vehicle, a vehicle control device, a radar device or an image acquisition device, or other devices that can communicate with a vehicle, a vehicle control device, a radar device or an image acquisition device. No specific limitation is made in this regard.

[0049] Next, for Figure 2 the process shown, the parking control method specifically may include the following steps:

[0050] Step S202, after the automatic parking function of the vehicle is activated, obtain the initial target object existing in the target parking area of the vehicle.

[0051] In an embodiment of the present invention, the Automatic Parking System (APS) can be a function that automatically controls a vehicle to complete a parking operation through intelligent technology. In practical applications, the automatic parking function usually supports one or more parking methods. For example, it can be a parallel parking method, an angled parking method, a reverse parking method into a parking space, etc., and no specific limitation is made thereto.

[0052] In an embodiment of the present invention, when the automatic parking function runs, it usually needs to determine a target parking area required for the vehicle itself, so as to plan a parking path. Among them, the target parking area can be a specific parking area manually selected by the driver and passengers of the vehicle itself from the available parking areas detected by the vehicle itself, or it can also be a specific parking area automatically selected by the automatic parking function from the available parking areas, with good flexibility.

[0053] In practical applications, the target parking area can be any planned parking space determined by ground parking space markings, parking space guardrails, parked vehicles, etc. detected by image target detection technology or radar target detection technology, and the area within a preset range around it, or it can also be any area that can meet the parking requirements and the area within a preset range around it (such as a parking space without parking lines) determined from an area not occupied by other target objects, and no specific limitation is made thereto.

[0054] In an embodiment of the present invention, after the automatic parking function of the vehicle itself is activated, target detection technology can usually be used to obtain target-related information of an initial target object existing in the target parking area of the vehicle itself, so as to perform target filtering processing and automatic parking control in combination with the target-related information of the above initial target object. Among them, there can be various types of target-related information of the initial target object. For example, it can include the position information, size information, etc. of the initial target object, and no specific limitation is made thereto.

[0055] Step S204: According to the vehicle operation data of the vehicle itself, determine whether a preset filtering condition for the initial target object is satisfied, and obtain a first judgment result; wherein, the preset filtering condition reflects that the initial target object is not credible.

[0056] In an embodiment of the present invention, after the vehicle first detects an initial target object, if there are multiple changes in the vehicle traveling mode of the vehicle, or when the vehicle has a long-distance driving situation, for example, when the numerical value of the increase or decrease in the distance between the vehicle and the initial target object is large, or when the numerical value of the cumulative driving distance of the vehicle is large, it may be affected by relevant sensor measurement errors and relevant control algorithm errors, etc., resulting in poor credibility of the position of the initial target object existing in the currently tracked and detected target parking area. Therefore, the initial target object should be filtered out to avoid interference of the initial target object with poor credibility on the automatic parking process of the vehicle.

[0057] It can be seen that the running behavior of the vehicle after the vehicle first detects an initial target object will affect the credibility of the subsequent tracking and detection result of the initial target object by the vehicle. Based on this, a preset filtering condition for reflecting the incredibility of the initial target object can be preset according to actual needs, and the preset filtering condition can be combined with the vehicle running data of the vehicle to determine whether it is satisfied. Therefore, after the automatic parking function of the vehicle is activated, the vehicle running data of the vehicle can be combined to determine whether the preset filtering condition for the initial target object is satisfied to decide whether to filter out the initial target object.

[0058] It can be understood that the situation where the vehicle first detects an initial target object may refer to the situation where a certain initial target object detected in the current target detection cycle does not belong to the same object as each target object detected in the previous target detection cycle, which will not be elaborated here.

[0059] Step S206, if the first judgment result indicates that the preset filtering condition for the initial target object is satisfied, filter the initial target object to obtain the filtered target object at the target parking area.

[0060] In an embodiment of the present invention, if the preset filtering condition for the initial target object is satisfied, it usually means that the credibility of the initial target object tracked and detected in the current target detection cycle is poor, so the initial target object can be filtered. In practical applications, the initial target object can be deleted when the preset filtering condition is satisfied to filter out the initial target object; or, in order to effectively avoid the collision risk between the vehicle and the initial target object, other factors can also be combined to comprehensively decide whether to filter out the initial target object; thus, it can not only reduce the interference of the incredible initial target object on the operation of the automatic parking function of the vehicle, but also effectively avoid the collision risk during the automatic parking process of the vehicle based on the filtered target object at the target parking area.

[0061] Step S208: Perform parking control on the vehicle according to the filtered target object at the target parking area.

[0062] In the embodiments of the present invention, the automatic parking function of the vehicle can be used to combine the filtered target object with good credibility at the target parking area to plan the parking trajectory of the vehicle and control the vehicle to drive according to the parking trajectory to park in place; or, when it is determined that there is a collision risk between the vehicle and the above-mentioned filtered target object with good credibility and it is impossible to complete parking in place, the execution of the automatic parking function can be interrupted or aborted to achieve safe and accurate parking control for the vehicle, and no specific limitation is made thereto.

[0063] Figure 2 In the method in [reference], after the automatic parking function of the vehicle is activated, if it is determined according to the vehicle operation data of the vehicle that the preset filtering condition for the initial target object existing at the target parking area of the vehicle is satisfied, it can be considered that the credibility of the initial target object is poor, and thus the initial target object can be filtered to facilitate parking control of the vehicle according to the filtered target object at the target parking area, which is beneficial to reducing the interference of the target object with poor credibility detected at the target parking area of the vehicle to the automatic parking function of the vehicle and the situation of interrupting or aborting the operation of the automatic parking function, and is beneficial to improving the reliability, accuracy and parking success rate when the automatic parking function of the vehicle operates.

[0064] In addition, during the target detection process performed after filtering the initial target object, the initially filtered target object may be detected again. Since the target-related information of the currently redetected initial target object is less affected by cumulative error and its credibility is good, the automatic parking process of the vehicle can be controlled according to the redetected initial target object with good credibility, which is beneficial to ensuring the reliability and accuracy when the automatic parking function of the vehicle operates. Since the subsequent embodiments will explain this in detail, it will not be elaborated here.

[0065] In a feasible implementation manner, the obtaining of the initial target object existing at the target parking area of the vehicle may include:

[0066] Obtain the initial target object obtained by processing the target parking area image collected by the image acquisition device. Or,

[0067] Obtain the initial target object obtained by processing the target parking area perception data collected by the radar device. Or,

[0068] Obtain the initial target object obtained by processing the target parking area perception data collected by the radar device and the target parking area image collected by the image acquisition device.

[0069] In an embodiment of the present invention, if the vehicle is equipped with an image acquisition device capable of acquiring images of the vehicle's surrounding environment, the image acquisition device can be used to acquire images of the target parking area of the vehicle to obtain a target parking area image, and then through target detection processing of the target parking area image, an initial target object existing in the target parking area of the vehicle can be obtained.

[0070] Alternatively, if the vehicle is equipped with a radar device capable of environmental perception, the radar target can be used to collect data for the target parking area of the vehicle, and through radar target detection of the target parking area perception data collected thereby, an initial target object existing in the target parking area of the vehicle can also be obtained.

[0071] Of course, it is also possible to jointly analyze and process the data collected by the radar device and the image acquisition device carried by the vehicle, etc., to obtain an initial target object existing in the target parking area of the vehicle, which is beneficial to improving the comprehensiveness and credibility of the initial target object. Among them, the radar device carried by the vehicle may include an ultrasonic radar device, a lidar device, etc., and no specific limitation is made thereto.

[0072] In a feasible implementation manner, determining whether a preset filtering condition for the initial target object is satisfied according to the vehicle operation data of the vehicle may include:

[0073] According to the vehicle operation data of the vehicle, determining whether the number of changes in the vehicle traveling mode generated after the vehicle first detects the initial target object reaches a first threshold. Or,

[0074] According to the vehicle operation data of the vehicle, determining whether the difference between the current distance between the vehicle and the initial target object and the initial distance between the vehicle and the initial target object reaches a second threshold. Wherein, the initial distance is the distance between the vehicle and the initial target object when the initial target object is first detected. Or,

[0075] According to the vehicle operation data of the vehicle, determining whether the cumulative driving distance of the vehicle after the vehicle first detects the initial target object reaches a third threshold.

[0076] In an embodiment of the present invention, when the vehicle first detects an initial target object in the target parking area, the position data of the initial target object determined is less affected by the cumulative measurement / calculation error, and thus has better credibility. Moreover, as the vehicle continuously changes its traveling mode and moves, the cumulative error of the vehicle pose data determined according to the wheel speed sensor data, wheel pulse data, steering wheel angle data, yaw angle data, etc. at the vehicle will continuously increase, thereby making the credibility of the position data of the initial target object determined in combination with the vehicle pose data in subsequent target detection cycles gradually deteriorate.

[0077] Based on this, the preset filtering condition for reflecting the incredibility of the initial target object can include: the number of changes in the vehicle traveling mode generated by the vehicle after first detecting the initial target object reaches a first threshold, the change value of the distance between the vehicle and the initial target object at the current moment compared to when the initial target object was first detected reaches a second threshold, or the cumulative driving distance of the vehicle after first detecting the initial target object reaches a third threshold. Thus, when there are multiple changes in the vehicle traveling mode or the moving distance is relatively long after the vehicle first detects the initial target object, the initial target object with poor credibility affected by the cumulative measurement / calculation error can be effectively filtered out.

[0078] In practical applications, the first threshold, the second threshold, and the third threshold can be set according to actual needs. For example, the first threshold can be several times, and the second threshold and the third threshold can be several meters to dozens of meters, and no specific limitation is made thereto.

[0079] In a feasible implementation manner, determining whether the number of changes in the vehicle traveling mode generated by the vehicle after first detecting the initial target object reaches the first threshold according to the vehicle operation data of the vehicle can include:

[0080] Detecting the vehicle traveling mode change behavior of the vehicle according to at least one of the gear data, wheel speed sensor data, and steering wheel angle data of the vehicle; wherein, the vehicle traveling mode change behavior is used to reflect that the vehicle traveling mode of the vehicle has changed, and the vehicle traveling mode includes at least some of the reverse traveling mode, forward traveling mode, and steering traveling mode.

[0081] Determining whether the number of vehicle traveling mode change behaviors generated by the vehicle after first detecting the initial target object reaches the first threshold.

[0082] In an embodiment of the present invention, since the number of vehicle driving mode change behaviors of the vehicle can be incremented by one each time the vehicle performs a vehicle driving mode change behavior, it is possible to determine whether a preset filtering condition for the initial target object is satisfied by counting whether the number of vehicle driving mode change behaviors generated by the vehicle after the initial target object is first detected reaches a first threshold.

[0083] In an embodiment of the present invention, changing the vehicle from a reverse driving mode to a forward driving mode can be regarded as the vehicle performing a vehicle driving mode change behavior. Or, changing the vehicle from a forward driving mode to a reverse driving mode can be regarded as the vehicle performing a vehicle driving mode change behavior. In addition, since the vehicle may also increase the error existing in the target detection result when making a large turn or frequent small turns, thereby affecting the credibility of the currently detected initial target object, it is also possible to regard the vehicle as performing a vehicle driving mode change behavior when it changes between the left-turn driving mode, the straight-ahead driving mode, and the right-turn driving mode once or multiple times. It has good flexibility and is not specifically limited in this regard.

[0084] In practical applications, since the gear data of the vehicle can reflect whether the gear in which the vehicle is currently located belongs to a gear that can control the vehicle to move forward / backward, it is possible to combine the gear data of the vehicle to identify whether the vehicle has performed a vehicle driving mode change behavior involving the reverse driving mode and the forward driving mode. And, since the wheel speed sensor data of the vehicle can reflect the rotation direction (forward rotation or reverse rotation) of the vehicle wheels, and thus can reflect whether the vehicle is currently moving forward or in reverse, it is also possible to combine the wheel speed sensor data of the vehicle to identify whether the vehicle has performed a vehicle driving mode change behavior involving the reverse driving mode and the forward driving mode. Also, since the steering wheel angle data of the vehicle can reflect whether the vehicle can go straight, turn left, or turn right currently, it is also possible to combine the steering wheel angle data of the vehicle to identify whether the vehicle has performed a vehicle driving mode change behavior involving the steering driving mode. Of course, it is also possible to combine other types of vehicle operation data to identify the vehicle driving mode change behavior performed by the vehicle. It has good flexibility and is not specifically limited in this regard.

[0085] In a feasible implementation manner, the determining whether the difference between the current distance between the vehicle and the initial target object and the initial distance between the vehicle and the initial target object reaches a second threshold according to the vehicle operation data of the vehicle may include:

[0086] Based on the vehicle operation data of the vehicle and the target position data of the initial target object, determine the initial coordinate data of the vehicle and the initial target object in a preset coordinate system at the initial moment, and the current coordinate data of the vehicle and the initial target object in the preset coordinate system at the current moment, where the initial moment is the moment when the initial target object is first detected.

[0087] Calculate the target distance difference between the current distance between the vehicle and the initial target object and the initial distance between the vehicle and the initial target object according to the initial coordinate data and the current coordinate data of the vehicle and the initial target object.

[0088] Determine whether the target distance difference reaches a second threshold

[0089] In the embodiments of the present invention, a vehicle motion model can be used to determine the pose data of the vehicle at each moment based on the vehicle operation data of the vehicle (for example, steering wheel angle data, yaw angle data, wheel speed sensor data, vehicle pulse data). Thus, after detecting the target position data of the initial target object existing in the target parking area, the coordinate data of the two in the preset coordinate system can be accurately determined according to the target position data of the initial target object and the current pose data of the vehicle, which is convenient, fast, and has good accuracy.

[0090] Based on this, the initial distance between the two can be accurately calculated according to the initial coordinate data of the two in the preset coordinate system determined when the initial target object is first detected. And, the current distance between the vehicle and the initial target object can also be accurately calculated according to the current coordinate data of the vehicle and the initial target object in the preset coordinate system. So as to calculate the difference between the current distance and the initial distance between the vehicle and the initial target object.

[0091] In practical applications, the preset coordinate system can be either the vehicle coordinate system of the vehicle, or, alternatively, other coordinate systems that do not change with the movement of the vehicle or the initial target object. And, the initial / current distance between the vehicle and the initial target object can be either the straight-line distance between the two, or, alternatively, the distance along the horizontal or vertical axis of the preset coordinate system, and no specific limitation is made on this.

[0092] In a feasible implementation manner, the determining whether the cumulative driving distance of the vehicle after first detecting the initial target object reaches a third threshold according to the vehicle operation data of the vehicle includes:

[0093] Calculate the difference between the current odometer data of the vehicle and the historical odometer data of the vehicle when the initial target object is first detected, to obtain the cumulative driving distance of the vehicle after first detecting the initial target object.

[0094] Determine whether the cumulative driving distance reaches a third threshold value.

[0095] In an embodiment of the present invention, the odometer data of the vehicle can generally reflect the total distance traveled by the vehicle since it left the factory. Therefore, the change value of the odometer data of the vehicle during the period from the moment when the initial target object is first detected to the current moment can be used as the cumulative driving distance of the vehicle, which is convenient and fast. Of course, a vehicle motion model can also be used to accurately track the driving trajectory of the vehicle, so as to determine the cumulative driving distance of the vehicle after the initial target object is first detected by analyzing the historical trajectory data of the vehicle during the period from the moment when the initial target object is first detected to the current moment. No specific limitation is made thereto.

[0096] In a feasible implementation manner, the filtering the initial target object to obtain a filtered target object at the target parking area may include:

[0097] Determine whether the size of the initial target object reaches a preset size to obtain a second determination result.

[0098] If the second determination result indicates that the size of the initial target object reaches the preset size, delete the initial target object to obtain a filtered target object at the target parking area.

[0099] In an embodiment of the present invention, among the initial target objects detected for the target parking area, there may be target objects with relatively small sizes and limited areas (for example, small obstacles such as pedestrians and columns). Since the number of radar reflection points that can be detected for such target objects is small, or the amount of relevant information that can be collected is small, it is usually necessary to detect the same small-sized target object multiple times before it is considered a credible target object, and then the automatic parking control of the vehicle is combined with this target object. Therefore, if such small-sized initial target objects are deleted, it may affect the safety of the subsequent automatic parking control of the vehicle due to the lag in creating the initial target object later.

[0100] Based on this, when the preset filtering condition of the initial target object is satisfied and the initial target object needs to be filtered, the initial target object can be deleted when it is determined that the size of the initial target object is greater than or equal to the preset size, so that the filtered target object in the target parking area no longer includes the initial target object; if the size of the initial target object is less than the preset size, the initial target object does not need to be deleted, so that the filtered target object in the target parking area can still include the initial target object. The preset size can be set according to actual needs. For example, it can be dozens of centimeters to several meters, and no specific limitation is made in this regard.

[0101] For the sake of easy understanding, in combination with the content in Figure 1 , an example is given to illustrate the filtering principle of the initial target object existing in the target parking area. As Figure 1 shown, it is assumed that there are initial target object 101, initial target object 102, initial target object 103, and initial target object 104 in the target parking area. If the preset filtering conditions for the above four initial target objects are all satisfied, and only the size of initial target object 101 is greater than the preset size, when filtering the above initial target objects, the obtained filtered target objects can include initial target object 102, initial target object 103, and initial target object 104, and no longer include initial target object 101.

[0102] In a feasible implementation manner, after deleting the initial target object to obtain the filtered target object in the target parking area, it may further include:

[0103] Performing target detection processing on the target parking area of the vehicle to obtain the latest target object.

[0104] If there is a specific target object in the latest target object that is not included in the filtered target object, when the vehicle is moving in the direction approaching the target parking area, parking control of the vehicle is performed according to the specific target object.

[0105] In the embodiments of the present invention, the situation where the vehicle is moving in the direction approaching the target parking area may refer to the situation where as the vehicle moves, the distance between the vehicle and the target parking area can be continuously reduced. And the situation where the vehicle is moving in the direction away from the target parking area may refer to the situation where as the vehicle moves, the distance between the vehicle and the target parking area can be continuously increased.

[0106] Since when the vehicle is driving in the direction away from the target parking area, the target objects existing in the target parking area usually do not pose a collision risk to the vehicle, even if the initial target objects that were once deleted during the target object filtering process are currently detected, it is not necessary to perform parking control on the vehicle based on the initial target objects that have been detected again currently.

[0107] When the vehicle is driving in the direction approaching the target parking area, if the initial target objects that were once deleted during the target object filtering process are currently detected, parking control on the vehicle can be allowed to continue based on the initial target objects; and if new added target objects that newly enter the target parking area are detected during the current target detection process, parking control on the vehicle can also be performed in combination with the new added target objects; thus, the collision risks faced by the vehicle can be avoided from being missed. That is, the specific target objects included in the latest target objects but not included in the filtered target objects can include: the initial target objects that are currently detected and were once deleted, and the new added target objects that newly enter the target parking area. Among them, the acquisition principles of the latest target objects and the initial target objects can be consistent, which will not be elaborated here.

[0108] It can be understood that since the cumulative error corresponding to the target-related information of the initial target objects that are detected again currently is small, its credibility is good. Therefore, when performing automatic parking control on the vehicle based on the initial target objects with good credibility detected again, it can not only reduce the situation of erroneously aborting or interrupting the automatic parking function of the vehicle, but also effectively avoid the collision risk between the vehicle and the target objects existing in the target parking area, which is beneficial to improving the safety and reliability during the operation of the automatic parking function.

[0109] In practical applications, the target distance values at each moment between the preset position of the vehicle (such as the center point of the vehicle's rear axle, the center of mass of the vehicle, the end point of the rear bumper, etc.) and the specified position in the target parking area (such as the corner points of the target parking area, the center points between adjacent corner points, etc.) can be calculated based on the coordinate data in the preset coordinate system; if the target distance value at the current moment is getting smaller compared to the previous moment, it can indicate that the vehicle is driving in the direction approaching the target parking area; and if the target distance value at the current moment is getting larger compared to the previous moment, it can indicate that the vehicle is driving in the direction away from the target parking area.

[0110] In addition, since the initial target object is usually located at the target parking area, the distance value between the host vehicle and the initial target object can be determined according to the coordinate data of the two under the preset coordinates, so as to determine whether the distance value is decreasing. If so, it can also reflect that the host vehicle is driving in the direction approaching the target parking area. Similarly, if the distance value is increasing, it can reflect that the host vehicle is driving in the direction away from the target parking area, and no specific limitation is made in this regard.

[0111] In a feasible implementation manner, before filtering the initial target object, it may further include:

[0112] Determine whether the host vehicle is driving in the direction away from the target parking area, and / or whether the current distance between the host vehicle and the initial target object reaches a fourth threshold value to obtain a third determination result.

[0113] Correspondingly, filtering the initial target object may include:

[0114] If the third determination result indicates that the host vehicle is driving in the direction away from the target parking area, and / or the current distance between the host vehicle and the initial target object reaches the fourth threshold value, then filter the initial target object.

[0115] In the embodiments of the present invention, when the host vehicle is too close to the initial target object, or when the host vehicle is continuously approaching the initial target object, even if the accuracy of the position data of the currently detected initial target object is poor, but if the initial target object is retained, the collision risk of the host vehicle can still be significantly reduced. Based on this, before filtering the initial target object, it may also be determined whether the host vehicle is currently driving in the direction away from the target parking area, and / or whether the current distance between the host vehicle and the initial target object reaches the fourth threshold value. If so, it may indicate that the distance between the host vehicle and the initial target object can continue to increase, and / or the distance between the host vehicle and the initial target object is already large enough, so that the initial target object can be filtered. Among them, the fourth threshold value can be set according to actual needs, such as dozens of centimeters to several meters, and no specific limitation is made in this regard.

[0116] The present invention also provides a computer program product, which includes a computer program. When the computer program is executed, the steps of the parking control method in the above embodiments are implemented. The specific execution process can refer to the specific descriptions in the above embodiments, and will not be elaborated here.

[0117] In one embodiment, the present invention also provides Figure 3 The structural schematic diagram of the electronic device shown. As Figure 3, at the hardware level, the electronic device may include a processor 31 and a memory 35. Of course, it may also include an internal bus 32, a network interface 33, a memory 34, and other hardware required for other services. The processor 31 among them can read the corresponding computer-readable instructions from the memory 35 into the memory and then run them to implement the above-mentioned parking control method. The specific execution process can refer to the specific descriptions in the above-mentioned embodiments and will not be elaborated here.

[0118] In a feasible implementation manner, the electronic device may include at least one of an image acquisition device, a radar device, a parking controller, and a domain controller, and no specific limitation is made thereto.

[0119] Finally, the various embodiments in the present invention are described in a progressive manner. The same or similar parts among the various embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for embodiments such as computer program products and electronic devices, since they are basically similar to the method embodiments, the descriptions are relatively simple, and the relevant parts can refer to the partial descriptions of the method embodiments.

[0120] The above are only the embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A parking control method, comprising: After the automatic parking function of the vehicle is activated, obtaining an initial target object existing in the target parking area of the vehicle; According to the vehicle operation data of the vehicle, determining whether a preset filtering condition for the initial target object is satisfied, and obtaining a first determination result; wherein, the preset filtering condition reflects that the initial target object is not credible; If the first determination result indicates that the preset filtering condition for the initial target object is satisfied, performing a filtering process on the initial target object to obtain a filtered target object in the target parking area; Performing parking control on the vehicle according to the filtered target object in the target parking area.

2. The method according to claim 1, wherein the determining whether a preset filtering condition for the initial target object is satisfied according to the vehicle operation data of the vehicle comprises: According to the vehicle operation data of the vehicle, determining whether the number of vehicle travel mode changes generated after the vehicle first detects the initial target object reaches a first threshold; Or, According to the vehicle operation data of the vehicle, determining whether the difference between the current distance between the vehicle and the initial target object and the initial distance between the vehicle and the initial target object reaches a second threshold; wherein, the initial distance is the distance between the vehicle and the initial target object when the initial target object is first detected; or, According to the vehicle operation data of the vehicle, determining whether the cumulative driving distance of the vehicle after the vehicle first detects the initial target object reaches a third threshold.

3. The method according to claim 2, wherein the determining whether the number of vehicle travel mode changes generated after the vehicle first detects the initial target object reaches a first threshold according to the vehicle operation data of the vehicle comprises: Detecting a vehicle travel mode change behavior of the vehicle according to at least one of the gear data, wheel speed sensor data, and steering wheel angle data of the vehicle; wherein, the vehicle travel mode change behavior is used to reflect that the vehicle travel mode of the vehicle has changed, and the vehicle travel mode includes at least some of a reverse travel mode, a forward travel mode, and a steering travel mode; Determining whether the number of vehicle travel mode change behaviors generated after the vehicle first detects the initial target object reaches a first threshold.

4. The method according to claim 2, wherein the determining whether the difference between the current distance between the vehicle and the initial target object and the initial distance between the vehicle and the initial target object reaches a second threshold according to the vehicle operation data of the vehicle comprises: According to the vehicle operation data of the vehicle and the target position data of the initial target object, determining the initial coordinate data of the vehicle and the initial target object in a preset coordinate system at the initial moment, and the current coordinate data of the vehicle and the initial target object in the preset coordinate system at the current moment; wherein, the initial moment is the moment when the initial target object is first detected; Calculate a target distance difference between a current distance between the vehicle and the initial target object and an initial distance between the vehicle and the initial target object according to the initial coordinate data and the current coordinate data of the vehicle and the initial target object; Determine whether the target distance difference reaches a second threshold.

5. The method according to claim 1, wherein the filtering the initial target object to obtain a filtered target object at the target parking area includes: Determine whether the size of the initial target object reaches a preset size to obtain a second determination result; If the second determination result indicates that the size of the initial target object reaches the preset size, delete the initial target object to obtain the filtered target object at the target parking area.

6. The method according to claim 5, after deleting the initial target object to obtain the filtered target object at the target parking area, further includes: Perform target detection processing on the target parking area of the vehicle to obtain a latest target object; If the latest target object has a specific target object not included in the filtered target object, when the vehicle travels in a direction approaching the target parking area, perform parking control on the vehicle according to the specific target object.

7. The method according to claim 1, before filtering the initial target object, further includes: Determine whether the vehicle is traveling in a direction away from the target parking area, and / or whether a current distance between the vehicle and the initial target object reaches a fourth threshold to obtain a third determination result; The filtering the initial target object includes: If the third determination result indicates that the vehicle is traveling in a direction away from the target parking area, and / or the current distance between the vehicle and the initial target object reaches the fourth threshold, filter the initial target object.

8. The method according to any one of claims 1-7, wherein the obtaining the initial target object existing at the target parking area of the vehicle includes: Obtain the initial target object obtained by processing the target parking area image collected by the image acquisition device; Or, Obtain the initial target object obtained by processing the target parking area perception data collected by the radar device; Or, Obtain the initial target object obtained by processing the target parking area perception data collected by the radar device and the target parking area image collected by the image acquisition device.

9. A computer program product, comprising a computer program, and when the computer program is executed, the steps of the method according to any one of claims 1-8 are implemented.

10. An electronic device, comprising: A processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the steps of the method according to any one of claims 1-8.

11. The electronic device according to claim 10, the electronic device comprising: At least one of an image acquisition device, a radar device, a parking controller, and a domain controller.

Images