A foreign matter processing method and a vehicle

Abstract

The application is suitable for the field of wireless charging technology, and provides a foreign matter processing method and a vehicle, which comprises the following steps: acquiring an environment image of a charging area; the charging area is an area where the vehicle is located when charging; the environment image comprises first images corresponding to a plurality of sub-areas in the charging area, and different first images are obtained by shooting from different shooting angles; identifying the plurality of first images to obtain a metal foreign matter image; the metal foreign matter image is an image of a metal foreign matter in the first image; obtaining a position parameter of the metal foreign matter relative to the vehicle according to a target position and a shooting angle when a second image is collected; the target position is a position of the metal foreign matter image in the first image, and the second image is a first image in which the metal foreign matter image is located among the plurality of first images; and controlling the vehicle to travel to a position where the metal foreign matter is located to perform a foreign matter cleaning operation according to the position parameter. The foreign matter processing method provided by the application can provide charging efficiency and save the cost of manual foreign matter cleaning.

Description

Technical Field

[0001] This application belongs to the field of wireless charging technology, and in particular relates to a foreign object handling method and a vehicle. Background Technology

[0002] Most current charging technologies for new energy vehicles rely on wired charging. In wired charging, the charging gun connects the vehicle to the charging station. However, wired charging has several drawbacks, such as requiring manual operation, posing safety hazards in inclement weather, and lacking standardized protocols. In contrast, wireless charging technology offers advantages such as "no plugging or unplugging required, automatic charging, and compatibility with unmanned environments."

[0003] Wireless charging technology refers to a process where a vehicle is driven into a charging area, where a transmitter converts electrical energy into a high-frequency alternating current, generating an alternating magnetic field. The receiver on the vehicle induces a current in this alternating magnetic field, thus charging the vehicle. During this process, a large air gap exists between the transmitter and receiver, containing a strong magnetic field. If a metallic object is present within this charging area, the strong magnetic field will induce a turbine effect inside the object, causing it to heat up rapidly. This not only reduces the vehicle's charging efficiency but, in severe cases, may burn out the transmitter or receiver, damage the vehicle, or even cause a fire.

[0004] In related technologies, an electromagnetic induction coil can be deployed at the transmitting end to detect foreign objects. However, it can only determine whether there are foreign objects in the charging area. This means that once there are foreign objects in the charging area, the vehicle will be stopped from charging and will continue charging after the foreign objects are removed, resulting in low charging efficiency. Summary of the Invention

[0005] This application provides a method and apparatus for handling foreign objects, which can solve the problem of slow wireless charging efficiency for vehicles.

[0006] In a first aspect, embodiments of this application provide a foreign object handling method, comprising: acquiring an environmental image of a charging area; the charging area being the area where a vehicle is located during charging, the environmental image including first images corresponding to multiple sub-areas within the charging area, the different first images being captured from different shooting angles; identifying multiple first images to obtain a metal foreign object image; the metal foreign object image being an image of a metal foreign object in the first image; obtaining position parameters of the metal foreign object relative to the vehicle based on a target location and the shooting angle when acquiring the second image; the target location being the position of the metal foreign object image in the first image, the second image being the first image in which the metal foreign object image is located among multiple first images; and controlling the vehicle to drive to the location of the metal foreign object to perform a foreign object removal operation based on the position parameters.

[0007] Secondly, embodiments of this application provide a vehicle including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the foreign object handling method provided in the first aspect.

[0008] The beneficial effects of the embodiments of this application compared with the prior art are:

[0009] Firstly, this application can further distinguish between metallic foreign objects when foreign objects are detected. It only removes metallic foreign objects if they are detected within the charging area, rather than removing them upon detection. This has the advantage of not removing non-metallic foreign objects, allowing the vehicle to charge normally and ensuring charging efficiency; while removing metallic foreign objects prevents damage to the vehicle caused by them.

[0010] Secondly, in the previous method of detecting foreign objects using electromagnetic induction coils, the electromagnetic induction coils were subject to electromagnetic interference from the strong magnetic field in the charging area, making it impossible to accurately locate the position of the metal foreign object. However, in this application, the position parameters of the metal foreign object relative to the vehicle can be obtained based on the target position of the identified metal foreign object image in the first image and the shooting angle when the first image of the metal foreign object was captured. Thus, the position of the metal foreign object can be located and cleaned based on its position, without the need for manual cleaning, which improves the efficiency of cleaning metal foreign objects and reduces labor costs. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0013] Figure 2 This is a schematic diagram of a charging area consisting of a transmitter and a receiver according to an embodiment of this application;

[0014] Figure 3 This is a schematic diagram of a vehicle located at the center of a charging area according to an embodiment of this application;

[0015] Figure 4 This is a schematic diagram of the vehicle located at the center point of the edge of the charging area according to an embodiment of this application;

[0016] Figure 5 This is a schematic diagram showing that the acquired images of metallic foreign objects are located in different first images according to an embodiment of this application;

[0017] Figure 6 This is a schematic diagram of the target location of a metallic foreign object image provided in an embodiment of this application;

[0018] Figure 7 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0019] Figure 8 This is a diagram showing the shooting angle of the vehicle and the positional relationship between the metal foreign object image and the first image, provided in an embodiment of this application.

[0020] Figure 9 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0021] Figure 10 This is a schematic diagram showing different foreign object images in different first images provided in one embodiment of this application;

[0022] Figure 11 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0023] Figure 12 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application;

[0024] Figure 13 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0025] Figure 14 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0026] Figure 15 This is a flowchart of the steps of a foreign matter treatment method provided in an embodiment of this application;

[0027] Figure 16 This is a communication structure diagram between an edge computing unit and other units provided in an embodiment of this application. Detailed Implementation

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0029] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0030] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0031] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0032] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0033] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0034] In related technologies, an electromagnetic induction coil can be deployed at the transmitting end to detect foreign objects. However, it can only determine whether there are foreign objects in the charging area. This means that once there are foreign objects in the charging area, the vehicle will be stopped from charging and will continue charging after the foreign objects are removed, resulting in low charging efficiency.

[0035] Furthermore, the electromagnetic induction coil is not subject to electromagnetic interference from the strong magnetic field in the charging area, resulting in poor stability. It cannot pinpoint the exact location of foreign objects, requiring manual location and removal, which makes the foreign object removal operation quite troublesome for staff.

[0036] Based on this, this disclosure proposes a foreign object handling method that can be applied to a vehicle, a processor in a vehicle, or a computer program product within a processor. Please refer to [link to relevant documentation]. Figure 1 As shown, the foreign object removal method includes the following steps:

[0037] S101, acquire an environmental image of the charging area.

[0038] The charging area is the area where the vehicle is charging. This charging area can be a three-dimensional area, consisting of the transmitter on the charging ground and the receiver on the vehicle.

[0039] For example, please see Figure 2 As shown, the transmitter on the charging ground and the receiver on the vehicle combine to form a magnetic field region. This magnetic field region includes the ground where the transmitter is located and the space region formed by the transmitter and the receiver. This magnetic field region is the charging area.

[0040] The environmental image includes first images corresponding to multiple sub-regions within the charging area, each captured from a different shooting angle. Each sub-region within the charging area represents a portion of the charging area; multiple sub-regions together form the charging area, and the first images corresponding to different sub-regions constitute the complete environmental image of the charging area. The environmental image is acquired by an image acquisition device on the vehicle or by an image acquisition device independent of the vehicle.

[0041] Optionally, an image acquisition device can be installed on the vehicle to acquire environmental images of the charging area; alternatively, the vehicle can acquire environmental images of the charging area sent by an image acquisition device located outside the vehicle.

[0042] The environmental image is a complete image of the charging area obtained by combining the first images captured by the image acquisition device at a specified location from different shooting angles. The specified location can be the center point of the charging area or the center point of the edge of the charging area. The image acquisition device can acquire a complete environmental image of the charging area at the specified location using different acquisition methods.

[0043] For example, taking an image acquisition device configured on a vehicle as an example, in the first acquisition mode, the vehicle can be controlled to drive to the center of the charging area, and the image acquisition device can be controlled to take multiple first images at a preset surround view rate and at a first preset time interval until the captured range of the image acquisition device reaches the first range, and the multiple first images are combined to form an environmental image of the charging area.

[0044] For example, please see Figure 3 As shown, taking a first range of 360° as an example, the vehicle can be controlled to drive to the center of the charging area, and then the image acquisition device on the vehicle can be controlled to rotate at a speed of 30° / s, taking one first image every 2 seconds, until the image acquisition device rotates 360°. This will generate six first images from different shooting angles: 0°, 60°, 120°, 180°, 240°, 300°, and 360°. These six first images from different shooting angles are combined to form a complete environmental image of the charging area. It can be understood that since the shooting angles of 0° and 360° are the same, there are six first images from different shooting angles.

[0045] For example, taking an image acquisition device configured on a vehicle as an example, in the second acquisition mode, the vehicle can be controlled to drive to the edge center point position, and the image acquisition device can be controlled to take multiple first images at a preset surround view rate and at second preset time intervals until the captured range of the image acquisition device reaches the second range, and the multiple first images are combined to form an environmental image of the charging area.

[0046] For example, please see Figure 4 As shown, taking a second range of 180° as an example, the vehicle can be controlled to drive to the center point of the edge of the charging area, and then the shooting angle of the image acquisition device on the vehicle can be controlled to rotate at a speed of 30° / s, and a first image is captured every 1 second until the image acquisition device rotates 180°. Then, seven first images at different shooting angles of 0°, 30°, 60°, 90°, 120°, 150°, and 180° will be generated respectively. The combination of the seven first images at different shooting angles forms a complete environmental image of the charging area.

[0047] Optionally, upon receiving a detection signal, an environmental image of the charging area can be acquired. The detection signal indicates the presence of a foreign object within the charging area.

[0048] The detection signal can be sent to the vehicle by the charging pile in the charging area when it detects a foreign object in the charging area; or it can be sent to the vehicle by staff using a work computer when they scan for a foreign object in the charging area.

[0049] S102, identify multiple first images to obtain a metal foreign object image.

[0050] Among them, the metal foreign object image is the image of the metal foreign object in the first image, or it can be understood as the outline or bounding box of the metal foreign object in the first image. One metal foreign object image contains one metal foreign object.

[0051] Optionally, for each of the multiple first images, it is determined whether there is a metallic foreign object in the first image. If there is a metallic foreign object, the image of the metallic foreign object is then identified from the first image, thereby identifying the image of the metallic foreign object from the multiple first images.

[0052] For example, please see Figure 5 As shown, if six first images, from first image 1 to first image 6, are obtained, and there are metal foreign objects A and B in first image 1 and metal foreign object C in first image 6, then metal foreign object images A and B will be identified from first image 1, and metal foreign object image C will be identified from first image 6. In this case, there will be three metal foreign object images.

[0053] S103, based on the target location and the shooting angle when acquiring the second image, obtain the position parameters of the metallic foreign object relative to the vehicle.

[0054] The target location is either the position of the metal foreign object image in the first image, or the position of the center point of the metal foreign object image in the first image.

[0055] For example, please see Figure 6As shown, taking the lower left corner of the first image 1 as the origin, the center point of the metal foreign object image A is located at (20, 40) in the first image 1, so the target location is (20, 40).

[0056] The second image is the first image in which the metallic foreign object is located among multiple first images.

[0057] For example, continuing from the example in step S102, see [link to example]. Figure 5 If there are metal foreign object images A and B in the first image 1, and metal foreign object image C in the first image 6, then the first image 1 containing metal foreign object image A is the second image, the first image 1 containing metal foreign object B is also the second image, and the first image 6 containing metal foreign object image C is also the second image.

[0058] In some scenarios, where the first image 1 contains an image of a metallic foreign object A (the image of the metallic foreign object A is an image of the metallic foreign object A), and the first image is captured by an image acquisition device at a shooting angle of 30°, the position parameters of the metallic foreign object A relative to the vehicle can be obtained based on the target position of the metallic foreign object image A in the first image 1 and the shooting angle of 30° of the first image 1 captured by the image acquisition device.

[0059] In other scenarios, where the first image 1 contains an image of a metallic foreign object B (the image of the metallic foreign object B is an image of the metallic foreign object B), and the first image is captured by an image acquisition device at a shooting angle of 30°, the position parameters of the metallic foreign object B relative to the vehicle can be obtained based on the target position of the metallic foreign object image B in the first image 1 and the shooting angle of 30° for the first image 1 captured by the image acquisition device.

[0060] The positional parameter of the metal foreign object relative to the vehicle can be the first deflection angle of the metal foreign object relative to the vehicle, or it can be understood as the angle between the metal foreign object and the direction directly in front of the image acquisition device on the vehicle. By controlling the image acquisition device to rotate the first deflection angle, the metal foreign object can be positioned on the center line of the acquired environmental image.

[0061] For example, if the image acquisition device is positioned directly in front of the vehicle, then the positional parameter of the metallic foreign object relative to the vehicle is the angle between the first line connecting the metallic foreign object and the image acquisition device and the front of the image acquisition device.

[0062] Optionally, obtaining a metal foreign object image by recognizing multiple first images includes: recognizing foreign object images in multiple first images; and inputting the recognized foreign object images into a metal recognition model to obtain the metal foreign object image.

[0063] For example, an image segmentation algorithm can be used to segment the environmental image into multiple first images from different shooting angles; then, a foreign object recognition algorithm can be used to select the foreign object image from the multiple first images; and then the recognized foreign object image can be input into a metal recognition model to obtain a metal foreign object image.

[0064] Among them, the image segmentation algorithm can be the Mask R-CNN (masked region convolutional neural network) instance image segmentation algorithm; the foreign object recognition algorithm can be OpenCV (open source computer vision library), Segment Anything (arbitrary segmentation), UniPixel (uniform pixel) and other foreign object recognition algorithms.

[0065] The metal recognition model can be a lightweight large model, such as the Qwen7B-Chat model. When inputting an image of a foreign object into the metal recognition model, prompt words can also be input. The prompt words are used to describe the task of the metal recognition model.

[0066] For example, the prompt could be "Analyze which of these images are metal objects and return the image number corresponding to the metal object". In this way, after inputting different foreign object images into the metal recognition model, the metal recognition model can identify that foreign object 1 is a metal key and the image number of foreign object 1 is 1.

[0067] Of course, the input prompts can also be used to instruct the metal recognition model to further subdivide the material of the metallic foreign object.

[0068] For example, the prompt could be "Analyze which of these images contain metal objects, and whether the metal objects are magnetic, and return the image number corresponding to the metal object." In this way, the metal recognition model can further determine whether the metal object is magnetic, outputting that foreign object 1 is a metal key, which is magnetic, and the image number of foreign object 1 is 1; outputting that foreign object 2 is a gold necklace, which is not magnetic, and the image number of foreign object 2 is 2.

[0069] S104, based on the location parameters, control the vehicle to drive to the location of the metal foreign object and perform the foreign object removal operation.

[0070] Optionally, the position parameters include a first deflection angle of the metal foreign object relative to the vehicle. The vehicle can be controlled to deflect the first deflection angle and then move toward the target direction where the metal foreign object is located, and the vehicle can be controlled to move toward the target direction to perform the foreign object removal operation.

[0071] Foreign object removal is a cleaning operation performed on metallic foreign objects. Different cleaning methods or cleaning mechanisms are used for different types of metallic foreign objects.

[0072] The above technical solution can achieve the following advantages:

[0073] Firstly, related technologies relying on electromagnetic induction coils can only detect the presence of foreign objects within the charging area, but cannot differentiate between metallic foreign objects. This application, however, can further differentiate between metallic and non-metallic foreign objects upon detection. It only removes metallic foreign objects when they are detected within the charging area, rather than removing them upon detection. This has the advantage of not removing non-metallic foreign objects, allowing the vehicle to charge normally and ensuring charging efficiency; and removing metallic foreign objects prevents damage to the vehicle caused by them.

[0074] Secondly, by controlling the vehicle to drive to a designated location, a complete environmental image of the charging area can be captured, which can then more comprehensively identify metallic foreign objects in the environmental image and reduce the occurrence of missed detection of metallic foreign objects.

[0075] Thirdly, in the previous method of detecting foreign objects using electromagnetic induction coils, the induction coils were subject to electromagnetic interference from the strong magnetic field in the charging area, making it impossible to accurately locate the position of the metal foreign object. However, in this application, the positional parameters of the metal foreign object relative to the vehicle can be obtained based on the target position of the identified metal foreign object image in the first image and the shooting angle when the first image of the metal foreign object was captured, thereby locating the position of the metal foreign object. Based on the position of the metal foreign object, it can be cleaned without manual cleaning, which improves the efficiency of cleaning metal foreign objects and reduces labor costs.

[0076] Figure 7 This is an exemplary embodiment involving step S103 above, which is used to interpret an exemplary scheme for obtaining the position parameters of a metallic foreign object relative to a vehicle based on the target position and the shooting angle. The position parameters of the metallic foreign object relative to the vehicle include a first deflection angle of the metallic foreign object relative to the vehicle, and includes the following steps:

[0077] S103-1, Based on the target location, obtain the horizontal distance between the center line of the metal foreign object image and the center line of the first image.

[0078] See Figure 8 As shown, taking the target position of the metal foreign object image A located in the first image 1 as an example, after knowing the target position (x1, y1) of the metal foreign object image A in the first image 1 and the coordinates (x2, y2) of the intersection point between the center line of the first image and the first image 1, the horizontal distance between the metal foreign object image and the center line of the first image can be obtained as dx_px = x2 - x1.

[0079] Optionally, after obtaining the target position, the actual physical offset on the photosensitive chip of the image acquisition device can be obtained based on the target position and the pixel size of the image acquisition device.

[0080] For example, the formula for calculating the physical offset is as follows:

[0081] dx_phy=dx_px*s(1)

[0082] In formula (1), dx_phy is the physical offset, dx_px is the horizontal distance between the center line of the metal foreign object image and the center line of the first image, and s is the pixel size of the image acquisition device.

[0083] It is understandable that the distance between the center line of the metal foreign object image and the first image is a distance at the pixel level, while the first deflection angle when the subsequent image acquisition device acquires the first image is the actual deflection angle in the physical world. Therefore, in order to unify the coordinate systems of the two, the distance between the center line of the metal foreign object image and the first image can be converted into the physical offset of the photosensitive chip of the image acquisition device, so as to unify the physical world with the subsequent first deflection angle.

[0084] S103-2, based on the horizontal distance and the focal length when the image acquisition device acquires the first image, the second deflection angle of the metal foreign object image relative to the center line of the first image is obtained.

[0085] Optionally, the second deflection angle can be obtained based on the physical offset and the focal length when the image acquisition device acquires the first image.

[0086] like Figure 8 As shown, after obtaining the physical offset of the horizontal distance between the center line of the metal foreign object image A and the first image 1, the physical offset has the following tangent relationship with the focal length of the image acquisition device when acquiring the first image:

[0087] = (2)

[0088] After transforming formula (2), we get the following formula (3):

[0089] (3)

[0090] In formula (3), B is the second deflection angle of the metal foreign object image relative to the center line of the first image, f is the focal length of the image acquisition device when acquiring the first image, and dx_phy is the physical offset.

[0091] S103-3, the first deflection angle is obtained based on the second deflection angle and the shooting angle.

[0092] Optionally, the sum of the second deflection angle and the shooting angle can be used as the first deflection angle.

[0093] Of course, in addition to using the above method to determine the first deflection angle of the metal foreign object relative to the vehicle and then controlling the vehicle to turn to the position where the metal foreign object is located to clean the metal foreign object, a step method can also be used to control the vehicle to remove the metal foreign object.

[0094] Specifically, the process of step control for removing the metal foreign object includes the following steps:

[0095] (1) Acquire the first image. After the vehicle starts, control the front image acquisition device to initialize, acquire the first image, complete the mapping calibration between the image coordinate system and the vehicle coordinate system, that is, establish the mapping relationship between the coordinates in the image coordinate system and the coordinates in the vehicle coordinate system, and determine the image center reference coordinate; at the same time, by confirming the position of the metal foreign object in the first image, if there is no metal foreign object in two consecutive first images taken, control the vehicle to rotate in place at a preset angular velocity for a preset time to acquire multiple frames of the first image again, and confirm the position of the metal foreign object image in the first image through the foregoing image processing algorithm, and mark the center point coordinate of the metal foreign object as the target position of the metal foreign object image.

[0096] For example, refer to Figure 8 , if there is no metal foreign object in both the first image 1 and 2 taken, the vehicle rotates in place at a preset angular velocity for a preset time, acquires the first image again and confirms the position of the metal foreign object in the first image through the foregoing image processing algorithm, and marks the center point coordinate of the metal foreign object.

[0097] (2) Confirm the foreign object positioning. After it is recognized that there is a metal foreign object in the acquired first image, the image acquisition device continuously acquires the first images of the front environment at a preset frame rate (for example, 10 - 20 frames per second), performs preprocessing and metal foreign object recognition algorithm operations on each frame of the first image, frames the metal foreign object existing in the first image and marks the center point of the metal foreign object, calculates the center coordinate (x1, y1) of the metal foreign object, compares it with the image center reference coordinate (x2, y2), when x1 < x2, it is determined that the metal foreign object is located in the left area of the vehicle, and the next control is executed, that is, control the right stepping motor of the vehicle to rotate alone for a preset number of steps (for example, 5 - 10 steps), and the left stepping motor remains stationary, so as to realize a small-angle left deviation adjustment of the vehicle head.

[0098] (3) Stepping control and steering. Based on the step angle of the vehicle's stepper motor (e.g., 1.8°), wheel diameter (e.g., 60mm), and reduction ratio, the single-step forward distance (e.g., 0.64mm / step) is calculated in advance, and the total number of steps in a single step is set (e.g., 30-50 steps). The left and right stepper motors are controlled to rotate synchronously for the preset number of steps, driving the vehicle to move forward in the current direction to approach the metal foreign object. It should be noted that the image shooting process and the stepping approach process in step (2) are carried out synchronously. That is, while the vehicle is shooting the first image to determine the position of the metal foreign object, it gradually approaches the vehicle through stepping drive until the metal foreign object is located directly in front of the vehicle.

[0099] (4) Repeat the above steps (2) and (3) "foreign object location confirmation - step steering and forward movement - execute foreign object location confirmation again" cycle until the metal foreign object image is located on the center line of the first image, i.e. x1=x2. At this time, the metal foreign object is located in front of the vehicle. After the foreign object cleaning device in front of the vehicle successfully picks up the foreign object, it immediately outputs a stop forward movement command, the vehicle stops moving forward, and then exits the charging area.

[0100] The above technical solution can automatically determine the vehicle's location where the metal foreign object is located, and then control the vehicle to move along the vehicle's location to remove the metal foreign object. This provides an automated way to determine the location of metal foreign objects. The second stepping method can determine the location of the metal foreign object in real time and move to the location to remove the metal foreign object. It does not require controlling the vehicle to return to the initial position to remove the metal foreign object, making the removal of foreign objects more convenient and faster.

[0101] The following are exemplary embodiments related to step S103 above, which are used to explain different cleaning methods for cleaning metal foreign objects, including the following two exemplary embodiments.

[0102] In the first embodiment, when the metallic foreign object is magnetic, the vehicle is controlled to rotate by the first deflection angle and then travel straight; during the process of controlling the vehicle to travel straight, the magnetic metallic foreign object is cleaned by the first cleaning mechanism.

[0103] Whether a metallic foreign object is magnetic can be determined by a metal recognition model. If the metal recognition model identifies that the metallic foreign object is magnetic and determines that the magnetic metallic foreign object is the one that needs to be cleaned, the vehicle will be controlled to rotate by a first deflection angle and then move straight so as to clean the magnetic metallic foreign object through the first cleaning mechanism on the vehicle.

[0104] The first cleaning mechanism for cleaning magnetic metal foreign objects includes: the first cleaning mechanism adsorbing magnetic metal foreign objects, for example, the first cleaning mechanism can be an electromagnet, which adsorbs magnetic metal foreign objects.

[0105] If the electrical parameter signal output by the first cleaning mechanism is detected, it is determined that the first cleaning mechanism has completed the cleaning operation on the magnetic metal foreign object.

[0106] For example, taking the electrical parameter signal as a current signal, when the first cleaning mechanism adsorbs a magnetic metal foreign object, the current signal output by the first cleaning mechanism will change. By detecting the change in the current signal output by the first cleaning mechanism, it can be determined that the first cleaning mechanism has completed the cleaning operation on the magnetic metal foreign object.

[0107] Optionally, after the cleaning operation of the magnetic metal foreign object is completed, the vehicle will be controlled to drive to a designated location, and then the vehicle will continue to determine the next metal foreign object that needs to be cleaned.

[0108] Understandably, once the initial deflection angle of the metallic foreign object relative to the vehicle is determined, and the foreign object is magnetic, during the process of controlling the vehicle to rotate at the first deflection angle and travel straight, the first cleaning mechanism will automatically attract the magnetic metallic foreign object without needing to calculate the target distance between the magnetic metallic foreign object and the vehicle. This allows the vehicle to travel the target distance to reach the location of the metallic foreign object and clean it. When a change in the electrical parameter signal output by the first cleaning mechanism is detected, it indicates that the cleaning operation of the metallic foreign object has been completed, and the vehicle can then return to the initial designated position.

[0109] In the second embodiment, when the metal foreign object is not magnetic, the target distance between the metal foreign object and the vehicle is detected; the vehicle is controlled to rotate by the first deflection angle and travel the target distance to reach the location of the metal foreign object; and a cleaning operation is performed on the metal foreign object.

[0110] Optionally, detecting the target distance between the metallic foreign object and the vehicle includes measuring the distance between the vehicle and the metallic foreign object using an ultrasonic sensor mounted on the vehicle.

[0111] Optionally, detecting the target distance between the metallic foreign object and the vehicle includes: acquiring images of the metallic foreign object using a first image acquisition device and a second image acquisition device on the vehicle, and measuring the target distance between the metallic foreign object and the vehicle using the parallax between the first image acquisition device and the second image acquisition device, wherein the metallic foreign object is located between the first image acquisition device and the second image acquisition device. This method can also be called binocular ranging.

[0112] If it is determined that the metallic foreign object is not magnetic, a second cleaning mechanism can be used to remove the non-magnetic metallic foreign object. For example, a clamping mechanism can be used to clamp the non-magnetic metallic foreign object.

[0113] Specifically, if a pressure signal is detected from the second cleaning mechanism, it is determined that the first cleaning mechanism has completed the cleaning operation on the non-magnetic metallic foreign object. When the second cleaning mechanism detects a pressure signal, it indicates that the non-magnetic metallic foreign object is being held by the second cleaning mechanism and pressure is being generated, thus confirming that the non-magnetic metallic foreign object has been cleaned.

[0114] Understandably, once the first deflection angle of the metallic foreign object relative to the vehicle is determined, and the metallic foreign object is a non-magnetic metallic foreign object, since a non-magnetic metallic foreign object cannot be attracted, it is necessary to calculate the target distance between the metallic foreign object and the vehicle, control the vehicle to rotate the first deflection angle and travel the target distance, in order to determine that the vehicle has reached the location of the metallic foreign object, and then use the clamping mechanism to clamp the non-magnetic metallic foreign object.

[0115] The above technical solution has the following advantages:

[0116] Firstly, the method of cleaning the metallic foreign object can be determined by its material, as different materials require different cleaning mechanisms. When the metallic foreign object is magnetic, a first cleaning mechanism is used to adsorb the magnetic material, eliminating the need to clamp the object. Adsorption is faster than clamping, thus improving the efficiency of cleaning magnetic foreign objects. When the metallic foreign object is non-magnetic, a second cleaning mechanism is used to clamp the non-magnetic material, resulting in better cleaning.

[0117] Secondly, the material of the metallic foreign object can be used to determine whether to measure the target distance between the foreign object and the vehicle. If the metallic foreign object is magnetic, measuring the target distance is unnecessary because the first cleaning mechanism will automatically attract and remove the object as the vehicle moves towards it. Not calculating the target distance reduces computational effort. If the metallic foreign object is non-magnetic, measuring the target distance allows for accurate location of the object, enabling the vehicle to proceed with its removal.

[0118] Figure 9 This is an exemplary embodiment of the present disclosure, which illustrates an exemplary scheme for sequentially cleaning multiple metallic foreign objects after identifying a foreign object image, including the following steps:

[0119] S105, the identified foreign object images are sequentially input into the metal recognition model according to the image numbers corresponding to the foreign object images, to obtain the metal foreign object images and the image numbers corresponding to the metal foreign object images.

[0120] The image number corresponding to the foreign object image is used to uniquely identify a foreign object image and to represent the order of the foreign object image among multiple foreign object images.

[0121] For example, see Figure 10 As shown, after the image segmentation algorithm segments the environmental image into 6 first images, the 6 first images can be identified, and 8 foreign object images can be identified among the 6 first images. The image numbers of the 8 foreign object images are then labeled as 1 to 8 respectively. Then, the foreign object images 1 to 8 are input into the metal recognition model in the order of their image numbers, and it is found that foreign object image 1 is a metal foreign object image and its image number is 1; foreign object image 8 is a metal foreign object image and its image number is 8.

[0122] S106, according to the order of the image numbers corresponding to the metal foreign object images, traverse the metal foreign object images, and for each traversed metal foreign object image, according to the position parameters of the metal foreign object in the metal foreign object image relative to the vehicle, control the vehicle to drive to the location of the metal foreign object to perform the foreign object cleaning operation.

[0123] Continuing with the example in step S105, see [link to example]. Figure 10 As shown, since the image number of metal foreign object image 1 precedes that of metal foreign object image 8, the vehicle can be controlled to first travel to the location of the metal foreign object in metal foreign object image 1 to perform the foreign object removal operation, and then the vehicle can be controlled to travel to the location of the metal foreign object in metal foreign object image 8 to perform the foreign object removal operation. By setting the order of the image numbers, the cleaning mechanism on the vehicle can sequentially clean the metal foreign objects that have appeared in the charging area according to the order of the image numbers, thereby ensuring that each metal foreign object can be cleaned and reducing the chance of missing any metal foreign objects.

[0124] Optionally, when the first metal foreign object image is encountered, the vehicle is controlled to travel from a designated location to the location of the first metal foreign object based on the position parameters of the first metal foreign object in the first metal foreign object image relative to the vehicle to perform a cleaning operation; the designated location is the location where the vehicle was when it acquired the environmental image; after the vehicle completes the cleaning operation on the first metal foreign object, the vehicle is controlled to return to the designated location and a second metal foreign object image located after the image number of the first metal foreign object image is determined; based on the position parameters of the second metal foreign object in the second metal foreign object image relative to the vehicle, the vehicle is controlled to travel from the designated location to the location of the second metal foreign object to perform a cleaning operation.

[0125] The traversed metal foreign object images include a first metal foreign object image and a second metal foreign object image. The first metal foreign object image and the second metal foreign object image are two metal foreign object images among the traversed metal foreign object images. The image number corresponding to the second metal foreign object image is located after the image number corresponding to the first metal foreign object image.

[0126] For example, see Figure 10 As shown, taking the first metal foreign object image as metal foreign object image 1 and the second metal foreign object image as metal foreign object image 8 as an example, the image number of metal foreign object image 1 is located before the image number of metal foreign object image 8. During traversal, metal foreign object image 1 will be traversed first to determine the target position of metal foreign object image 1 in the first image 1 and the shooting angle when the image acquisition device acquires the first image 1 at a specified position (such as the edge center point of the charging area shown in 4). The first deflection angle of the metal foreign object in metal foreign object image 1 relative to the vehicle is obtained. Then, the vehicle is controlled to rotate at the specified position by the first deflection angle and then driven to the position of the metal foreign object in metal foreign object image 1 to process the metal foreign object.

[0127] After the metal foreign object is removed, the vehicle is controlled to return to the previously designated position, and then the metal foreign object image 8 is traversed to determine the target position of the metal foreign object image 8 in the first image 6 and the shooting angle of the image acquisition device when acquiring the first image 6 at the designated position. The first deflection angle of the metal foreign object in the metal foreign object image 8 relative to the vehicle is obtained. The vehicle is then controlled to rotate at the current designated position by the first deflection angle, and then travels to the location of the metal foreign object in the metal foreign object image 8 to process the metal foreign object. This process is repeated. After each metal foreign object is removed, the vehicle is controlled to return to the designated position to remove the next metal foreign object.

[0128] The above technical solution has the following advantages:

[0129] Firstly, by setting the order of image numbers, the cleaning mechanism on the vehicle can clean up any metal foreign objects that have appeared in the charging area in sequence according to the order of the image numbers, thereby ensuring that all metal foreign objects can be cleaned and reducing the chance of missing any metal foreign objects.

[0130] Secondly, after each metal object is removed, the vehicle is controlled to return to a designated position to re-determine the initial deflection angle of the next metal object relative to the vehicle. This is because the initial deflection angle of each metal object relative to the vehicle is calculated based on the vehicle's position at the designated location. After removing the previous metal object, the vehicle is no longer at the designated location but at the current location where the previous metal object was. If the vehicle were still controlled based on the initial deflection angle calculated from the designated location, it would deflect the vehicle at the current position, causing it to move away from the next metal object and thus preventing it from reaching its destination. Therefore, the vehicle needs to return to the designated position and deflect the initial deflection angle before it can proceed to the location of the next metal object.

[0131] Figure 11 This is an exemplary embodiment involving step S101 above, which is an exemplary scheme for interpreting the acquisition of an environmental image of the charging area, including the following steps:

[0132] S101-1, If ​​the light intensity of the charging area is detected to be lower than the preset intensity, the lighting device is activated.

[0133] The light intensity in the charging area can be detected by a light intensity detection device. When the light intensity in the charging area is lower than the preset intensity, it indicates that the light intensity in the charging area is low.

[0134] The lighting device is used to supplement the lighting of the charging area; for example, please refer to [link to relevant documentation]. Figure 12 As shown, it is possible to install such as on the vehicle. Figure 12 The lighting device 6 in the middle provides additional lighting to the charging area.

[0135] S101-2, when the lighting device is activated and the vehicle moves to the designated position, an environmental image of the charging area is acquired.

[0136] The step of activating the lighting device can occur either before or after the vehicle moves to the designated location.

[0137] With the lighting activated and the vehicle moved to the designated location, the image acquisition device on the vehicle can capture a complete environmental image of the charging area under sufficient lighting.

[0138] Alternatively, if the acquired environmental image has uneven brightness, an adaptive histogram equalization algorithm (such as CLAHE) can be used to perform brightness equalization on the environmental image, reducing image deviation caused by uneven lighting.

[0139] In related technologies, in dimly lit environments such as underground parking lots, if the collected images of foreign objects are input into a metal foreign object model, it is difficult to identify whether the metal foreign object has magnetism because some of the metal foreign objects are made of similar materials and the metal foreign object model cannot distinguish between metal foreign objects of different materials in dim light.

[0140] The above technical solution can activate the lighting device to supplement the lighting of the entire charging area. In this way, the foreign object image captured by the image acquisition device will not be too dark, and the material of each metal foreign object can be better identified by the metal foreign object model. This allows for accurate identification of the material of different metal foreign objects, which facilitates the subsequent precise use of different cleaning mechanisms to clean metal foreign objects of different materials.

[0141] Figure 13 This is an exemplary embodiment involving step S101 above, which is an exemplary scheme for interpreting the acquisition of an environmental image of the charging area, including the following steps:

[0142] S101-3, when the vehicle moves to the designated location, acquire an environmental image of the charging area.

[0143] S101-4, if the visibility of the charging area is detected to be less than the preset visibility, the environmental image is dehazed to obtain the environmental image.

[0144] The fact that the visibility of the charging area is less than the preset visibility indicates that the collected environmental image may be blurry.

[0145] The visibility of the charging area can be detected by a visibility detection device. When the charging area is in an environment with low visibility, such as heavy wind, sand, dust, rain, or fog, the collected environmental images may be blurry.

[0146] Optionally, for environmental images acquired in environments with heavy rainfall or fog, the first defogging algorithm can be used to process the environmental image to obtain a defogging environmental image.

[0147] The first dehazing algorithm can be a neighboring frame compensation algorithm or a dark channel prior dehazing algorithm. For example, it can copy the clear pixels of the previous and next frames in the acquired environmental image to the pixels containing raindrops, and then perform light smoothing to remove the raindrops displayed in the environmental image. Alternatively, it can be Gaussian filtering to denoise the acquired environmental image to reduce noise interference such as fine dust in the parking lot.

[0148] Optionally, for environmental images collected in environments with high dust and sandstorms, a second dehazing algorithm can be used to process the environmental images to obtain dehazed environmental images.

[0149] The second dehazing algorithm can be a Laplacian sharpening algorithm, which can first use white balance correction to bring the yellowish-gray tone caused by dust in the acquired environmental image back to the normal level, and then use sharpening processing to sharpen and enhance the entire image, making the environmental image appear brighter.

[0150] In related technologies, in low-visibility environments, if the image of a foreign object in the first captured image is input into a metal foreign object model, the model cannot distinguish between metal foreign objects of different materials because some of the metal foreign objects are of similar material and are obscured in low-visibility scenarios. This makes it difficult to identify whether the metal foreign object is magnetic.

[0151] The above technical solution can be used to defog environmental images collected in low-visibility environments. As a result, the clarity of metallic foreign objects in each environmental image after defogging will be higher, and the material of each metallic foreign object can be better identified by the metallic foreign object model. This allows for accurate identification of the material of different metallic foreign objects, which facilitates the subsequent precise use of different cleaning mechanisms to clean metallic foreign objects of different materials.

[0152] Figure 14 This is an exemplary embodiment involving step S101 above, which is an exemplary scheme for interpreting the acquisition of an environmental image of the charging area, including the following steps:

[0153] S101-5, when the vehicle moves to the designated position, controls the image acquisition device to acquire environmental images of the charging area at a preset surround view rate.

[0154] The preset panoramic rate is the angle that the image acquisition device rotates per unit time. For example, the shooting angle of the image acquisition device rotates at a speed of 30° / s.

[0155] S101-6, when the image acquisition device detects a foreign object, the image acquisition device is controlled to reduce the preset surround view rate to acquire environmental images of the charging area at a surround view rate lower than the preset surround view rate.

[0156] For example, if the image acquisition device rotates at a speed of 30° / s, it can rotate at a speed of 25° / s when it detects a foreign object.

[0157] By using the above technical solution, when a foreign object is detected, the panning rate of the image acquisition device can be controlled to decrease, thereby acquiring environmental images with the presence of foreign objects at a lower panning rate, so as to ensure that the image portion containing foreign objects is clearer.

[0158] Figure 15This is an exemplary embodiment involving step S101 above, which is an exemplary scheme for interpreting the acquisition of an environmental image of the charging area, including the following steps:

[0159] S101-7, when the vehicle moves to the designated position, determine the distance between the vehicle chassis and the ground of the charging area.

[0160] S101-8, when the distance is less than a first preset distance, control the image acquisition device for acquiring the environmental image to move towards the direction closer to the ground.

[0161] When the distance between the vehicle chassis and the charging area is less than the first preset distance, it means that the vehicle chassis is close to the ground of the charging area. At this time, the field of view of the image acquisition device on the vehicle may be blocked by the vehicle chassis, and it will be unable to acquire a complete environmental image of the charging area. Therefore, the image acquisition device can be controlled to move towards the ground.

[0162] S101-9, when the distance between the image acquisition device and the ground is less than a second preset distance, the environmental image of the charging area acquired by the image acquisition device is obtained.

[0163] The second preset distance is less than the first preset distance. When the image acquisition device moves closer to the ground until the distance between the image acquisition device and the ground is less than the second preset distance, it means that the image acquisition device is closer to the ground than the vehicle chassis. Therefore, the field of view of the image acquisition device is no longer blocked by the vehicle chassis, thus acquiring a complete environmental image of the charging area.

[0164] The above technical solution can determine the relationship between the distance between the image acquisition device and the ground, and the distance between the vehicle chassis and the ground. When the distance between the vehicle chassis and the ground is less than the distance between the image acquisition device and the ground, the image acquisition device can be controlled to move closer to the ground until the distance between the image acquisition device and the ground is less than the distance between the vehicle chassis and the ground, thereby avoiding the vehicle chassis from obstructing the image acquisition device's field of view.

[0165] Figure 12 This is a structural schematic diagram of the foreign object handling device on the vehicle involved in this disclosure. Please refer to [link / reference]. Figure 12 As shown, the vehicle is equipped with an image acquisition device 1, an edge computing unit 2, a communication and navigation module 3, a vehicle power supply 4, vehicle wheels 5, and a lighting device 6.

[0166] The edge computing unit 2 is used to process the environmental images acquired by the image acquisition device 1, such as performing Gaussian filtering for noise reduction and brightness equalization to reduce external environmental interference such as ambient light and ground stains. It can also use image segmentation algorithms to identify multiple foreign object images from the environmental images and select the outlines of various foreign objects in the environmental images.

[0167] Of course, if the computing power of the edge computing unit 2 on the vehicle is insufficient, the vehicle can also transmit the collected environmental images to a centralized processing unit that is independent of the vehicle through the communication and navigation module 3, and the centralized processing unit will complete the image segmentation operation.

[0168] Furthermore, a metal recognition model can be deployed on the edge computing unit 2 to ensure that the edge computing unit 2 has the ability to recognize metal foreign objects.

[0169] Of course, for scenarios where multiple vehicles are charging simultaneously, this metal recognition model can also be deployed on a high-performance edge computing unit 2 to accommodate simultaneous charging of multiple vehicles. For example, the edge computing unit with the highest computing power can be selected from multiple vehicles and used to identify metallic foreign objects within the entire charging area.

[0170] Among them, see Figure 16 As shown, the communication and navigation module 3 includes a communication module and a navigation module. The communication module, navigation module, foreign object removal control unit, image acquisition unit, image preprocessing unit, image segmentation unit, and large model calling unit all communicate with a certain edge computing unit.

[0171] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0172] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0173] This application also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0174] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0175] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0176] If the integrated unit 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0177] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0178] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Python, Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0179] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0180] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0181] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0182] The units described as separate components may or may not be physically separate. The 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for handling foreign objects, characterized in that, include: Acquire an environmental image of the charging area; the charging area is the area where the vehicle is located when it is charging, and the environmental image includes first images corresponding to multiple sub-areas within the charging area, with different first images being captured from different shooting angles; Multiple first images are identified to obtain a metallic foreign object image; the metallic foreign object image is an image of the metallic foreign object in the first images. Based on the target location and the shooting angle when acquiring the second image, the position parameters of the metallic foreign object relative to the vehicle are obtained; the target location is the position of the metallic foreign object image in the first image, and the second image is the first image in which the metallic foreign object image is located among multiple first images; Based on the location parameters, the vehicle is controlled to travel to the location of the metallic foreign object and perform a foreign object removal operation; The position parameters include the first deflection angle of the metallic foreign object relative to the vehicle; The step of obtaining the position parameters of the metallic foreign object relative to the vehicle based on the target location and the shooting angle when acquiring the second image includes: Based on the target location, the horizontal distance between the center line of the metal foreign object image and the center line of the first image is obtained; Based on the horizontal distance and the focal length when the image acquisition device acquires the first image, the second deflection angle of the metal foreign object image relative to the center line of the first image is obtained. The first deflection angle is obtained based on the second deflection angle and the shooting angle; The step of controlling the vehicle to drive to the location of the metallic foreign object and performing a foreign object removal operation based on the location parameters includes: When the metallic foreign object is magnetic, the vehicle is controlled to rotate by the first deflection angle and then proceed straight; during the process of controlling the vehicle to proceed straight, the magnetic metallic foreign object is cleaned by the first cleaning mechanism; wherein, when the electrical parameter signal output by the first cleaning mechanism is detected, it is determined that the first cleaning mechanism has completed the cleaning operation on the magnetic metallic foreign object. If the metal foreign object is not magnetic, detect the target distance between the metal foreign object and the vehicle; control the vehicle to rotate by the first deflection angle and travel the target distance to reach the location of the metal foreign object; and perform a cleaning operation on the metal foreign object.

2. The method as described in claim 1, characterized in that, The step of identifying multiple first images to obtain a metallic foreign object image includes: Multiple images of foreign objects in the first image were identified; The identified foreign object image is input into the metal recognition model to obtain the metal foreign object image.

3. The method as described in claim 2, characterized in that, The identified foreign object images each have their own image number; the step of inputting the identified foreign object images into a metal recognition model to obtain the metal foreign object image includes: The identified foreign object images are sequentially input into the metal recognition model according to the image numbers corresponding to the foreign object images to obtain the metal foreign object images and the image numbers corresponding to the metal foreign object images. The step of controlling the vehicle to drive to the location of the metallic foreign object and performing a foreign object removal operation based on the location parameters includes: According to the order of the image numbers corresponding to the metal foreign object images, the metal foreign object images are traversed. For each traversed metal foreign object image, based on the position parameters of the metal foreign object in the metal foreign object image relative to the vehicle, the vehicle is controlled to drive to the location of the metal foreign object to perform the foreign object removal operation.

4. The method as described in claim 3, characterized in that, The traversed metal foreign object images include a first metal foreign object image and a second metal foreign object image, wherein the image number corresponding to the second metal foreign object image is located after the image number corresponding to the first metal foreign object image; the step of traversing the metal foreign object images according to the order of their corresponding image numbers, and for each traversed metal foreign object image, controlling the vehicle to drive to the location of the metal foreign object and performing a foreign object removal operation based on the position parameters of the metal foreign object in the metal foreign object image relative to the vehicle, includes: When the first metal foreign object image is encountered, the vehicle is controlled to travel from a designated location to the location of the first metal foreign object to perform a cleaning operation based on the position parameters of the first metal foreign object in the first metal foreign object image relative to the vehicle; the designated location is the location where the vehicle was when it acquired the environmental image. When the vehicle completes the cleaning operation of the first metallic foreign object, the vehicle is controlled to return to the designated position, and a second metallic foreign object image is determined after the image number of the first metallic foreign object image. Based on the position parameters of the second metal foreign object in the second metal foreign object image relative to the vehicle, the vehicle is controlled to travel from the designated location to the location of the second metal foreign object to perform a cleaning operation.

5. The method as described in claim 1, characterized in that, The acquisition of the environmental image of the charging area includes: If the light intensity in the charging area is detected to be lower than a preset intensity, the lighting device is activated; the lighting device is used to provide illumination to the charging area. When the lighting device is activated and the vehicle moves to a designated location, an environmental image of the charging area is captured; the designated location is a location where the complete environmental image of the charging area can be captured.

6. The method as described in claim 1, characterized in that, The acquisition of the environmental image of the charging area includes: When the vehicle moves to a designated location, the distance between the vehicle's chassis and the ground of the charging area is determined; the designated location is one where the complete environmental data of the charging area can be captured. When the distance is less than a first preset distance, the image acquisition device for acquiring the environmental image is controlled to move towards the direction closer to the ground; When the distance between the image acquisition device and the ground is less than a second preset distance, the image acquisition device acquires an environmental image of the charging area; the second preset distance is less than the first preset distance.

7. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 6.

Images