Guided docking methods, systems, and computer program products

Abstract

This application provides a guided docking method, system, and computer program product, relating to the field of image processing technology. The method includes: acquiring a target image; identifying a target object in the target image and determining at least one target reference point of the target object on its side; acquiring coordinate transformation data and transforming the target reference point from a camera coordinate system to a machine coordinate system based on the coordinate transformation data to obtain guidance data; calculating a correction angle based on the guidance data and the rotation reference axis of the mobile docking platform; and controlling the movement of the mobile docking platform according to the correction angle data and the guidance data, so that the mobile docking platform completes docking with the target object. This application solves the problem of low docking accuracy in automatic battery swapping processes in related technologies.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and more specifically, to a guided docking method, system, and computer program product. Background Technology

[0002] With the rapid development of new energy vehicles, range and refueling efficiency have become key factors restricting their large-scale promotion.

[0003] Currently, the mainstream energy replenishment method is charging, but it suffers from problems such as long charging times, uneven distribution of charging stations, and battery life degradation. Battery swapping, as a rapid energy replenishment method, has advantages such as short charging time (usually 3-5 minutes), centralized battery management and tiered utilization, and alleviating peak-valley pressure on the power grid, and is gradually gaining attention from the industry.

[0004] However, during automatic battery swapping, the battery pack needs to be removed and replaced from the bottom of the vehicle. Its connection interfaces are mostly precision mechanical locks and high-voltage electrical connectors, requiring extremely high precision. Even with a guidance system, parking deviations may still occur when a vehicle enters a battery swapping station.

[0005] As can be seen from the above, the problem of low docking accuracy in the automatic battery swapping process still needs to be solved. Summary of the Invention

[0006] This application provides a guiding docking method, apparatus, electronic device, and storage medium, which can solve the problem of low docking accuracy during automatic battery swapping in related technologies. The technical solutions are as follows:

[0007] According to one aspect of this application, a guided docking method is applied to a guided docking system, the system including a mobile docking platform and a target object; the method includes: acquiring a target image; the target image being obtained by the mobile docking platform capturing a side view of the target object; identifying the target object in the target image and determining at least one target reference point of the target object on the side view; acquiring coordinate transformation data, and transforming the target reference point from a camera coordinate system to a machine coordinate system based on the coordinate transformation data to obtain guidance data; calculating a correction angle based on the guidance data and the rotation reference axis of the mobile docking platform; and controlling the mobile docking platform to move according to the correction angle data and the guidance data, so that the mobile docking platform completes docking with the target object.

[0008] According to one aspect of this application, a guided docking system includes: a mobile docking platform for acquiring a target image; the target image being obtained by the mobile docking platform from a side view of a target object; identifying the target object in the target image and determining at least one target reference point of the target object on the side view; acquiring coordinate transformation data and transforming the target reference point from a camera coordinate system to a machine coordinate system based on the coordinate transformation data to obtain guidance data; calculating a correction angle based on the guidance data and the rotation reference axis of the mobile docking platform to obtain correction angle data; controlling the mobile docking platform to move according to the correction angle data and the guidance data, so that the mobile docking platform completes docking with the target object; and a target object for receiving the docking of the mobile docking platform.

[0009] According to one aspect of this application, an electronic device includes at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, implements the boot docking method as described above.

[0010] According to one aspect of this application, a storage medium having a computer program stored thereon, which, when executed by one or more processors, implements the boot docking method as described above.

[0011] According to one aspect of this application, a computer program product includes a computer program that, when executed by one or more processors, implements the boot docking method as described above.

[0012] In the above technical solution, a target image is obtained by taking a side view of the target object using a mobile docking platform. The target object in the target image is then identified, and at least one target reference point on the side of the target object is determined. By taking a side view, bottom view is avoided, reducing a large number of complex image processing operations. The target reference point is transformed from the camera coordinate system to the machine coordinate system through coordinate transformation data to obtain guidance data. Based on the guidance data and the rotation reference axis of the mobile docking platform, the correction angle data is calculated. Based on the correction angle data and the guidance data, the movement of the mobile docking platform is controlled, so that the center of the mobile docking platform can be aligned with the center of the bottom of the target object in both position and angle. This effectively solves the problem of low docking accuracy in the automatic battery swapping process in related technologies. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of a guided docking system involved in a guided docking method according to an exemplary embodiment;

[0014] Figure 2This is a schematic diagram illustrating the specific implementation of a guided docking method in an application scenario;

[0015] Figure 3 This is a flowchart illustrating a guided docking method according to an exemplary embodiment;

[0016] Figure 4 yes Figure 3 A schematic diagram illustrating a specific implementation of a target object in a corresponding embodiment;

[0017] Figure 5 yes Figure 3 A schematic diagram illustrating the specific implementation of two bottom corner points of an intermediate battery in the corresponding embodiment;

[0018] Figure 6 yes Figure 3 A flowchart of step 350 in one embodiment corresponds to the following example;

[0019] Figure 7 yes Figure 3 The steps preceding step 350 in the corresponding embodiment are shown in a flowchart of one embodiment. Detailed Implementation

[0020] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of this application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to this application are not shown or described in the specification. This is to avoid obscuring the core parts of this application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0021] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0022] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0023] As mentioned earlier, during the automatic battery swapping process, the battery pack needs to be removed from the bottom of the vehicle and replaced. Its connection interface is mostly a precision mechanical lock and a high-voltage electrical connector, which requires extremely high docking accuracy.

[0024] The automatic battery swapping system for new energy vehicles includes a battery swapping mechanism, battery compartment structure, positioning and alignment device, control system, and battery swapping process control. It can achieve efficient, safe, and automated battery swapping for new energy vehicles under conditions of no or minimal human intervention.

[0025] However, automatic battery swapping systems have several problems. First, the automation level of these systems is low, with some swapping stations still requiring manual operation, resulting in low efficiency and safety hazards. Second, due to the diverse platforms of new energy vehicles and the inconsistent battery pack structures across different brands and models, universal battery swapping is difficult to achieve. Third, because the vehicle's parking position varies each time it arrives at a swapping station, the insufficient positioning accuracy of the automatic swapping system leads to parking deviations that prevent precise docking of the swapping mechanism. Fourth, the system reliability of automatic battery swapping is low, and it is prone to mechanical jamming or communication interruptions in complex environments (rain, snow, dust). Finally, the safety protection mechanisms of automatic battery swapping systems are weak, lacking emergency handling for scenarios such as high-voltage power outages, battery status detection, and abnormal interruptions.

[0026] Currently, battery swapping methods can be divided into three types: First, the teaching method: This method relies on manual operation of a teaching pendant to control the mobile docking platform to align with the disassembly holes of the battery pack, recording the disassembly posture of the mobile docking platform, and using this posture as the disassembly posture for subsequent vehicles. Second, the teaching + visual positioning method: 1. A camera photographs the battery pack, detecting and calculating the position and angle of the guide point on the image as a reference. The guide point is generally the center coordinate of the battery. 2. The mobile docking platform is manually operated to align multiple disassembly points with the disassembly holes of the battery pack, recording the posture of the mobile docking platform at this time as a reference. 3. During the actual battery swapping process, the camera of the mobile docking platform photographs the battery pack in real time and detects and calculates the position and angle of the guide point. The difference between this and the reference value in step 1 is used to obtain the offset value. The mobile docking platform then performs the corresponding offset based on the reference value to obtain the current posture of the guided mobile docking platform. Third, the calibration method: Using a special calibration object (such as a standard sphere), the 3D image coordinate system and the mobile docking platform coordinate system are calibrated to establish the coordinate transformation relationship between the camera and the mobile docking platform.

[0027] However, while teaching-based methods are easy to understand and low-cost, requiring no external visual aids, manual teaching operations are inconvenient in certain environments (such as under a car) on large equipment. Furthermore, this method relies on the vehicle's parking position, lacks correction capabilities, and is prone to collisions. Adding visual positioning for correction based on teaching effectively addresses the lack of correction capabilities in pure teaching, but this method still requires manual teaching, posing certain safety hazards when operating under a car. Calibration-based methods can reduce a significant amount of manual operation, offering higher intelligence, improved efficiency, and safety. However, traditional vision-based methods, such as scanning the bottom of the battery, cannot guarantee image quality, posing a risk of inaccurate image detection and abnormal positioning guidance.

[0028] As can be seen from the above, the relevant technologies still suffer from low docking accuracy during automatic battery swapping.

[0029] Therefore, the guidance docking method provided in this application can effectively improve the accuracy of guidance docking during automatic battery swapping. Accordingly, the guidance docking method is applicable to guidance docking systems.

[0030] Figure 1 This is a schematic diagram of a guiding docking system involved in a guiding docking method. It should be noted that this guiding docking system is merely an example adapted to the present invention and should not be considered as providing any limitation on the scope of the present invention.

[0031] The guidance and docking system includes target object 110 and mobile docking platform 130.

[0032] The mobile docking platform 130 is used to acquire target images; the target images are obtained by the mobile docking platform from the side of the target object; the target object in the target image is identified, and at least one target reference point of the target object is determined; coordinate transformation data is acquired, and the target reference point is transformed from the camera coordinate system to the machine coordinate system based on the coordinate transformation data to obtain guidance data; the correction angle data is calculated based on the guidance data and the rotation reference axis of the mobile docking platform; the mobile docking platform is controlled to move according to the correction angle data and the guidance data, so that the mobile docking platform and the target object are docked.

[0033] Target object 110 is used to connect to the mobile connection platform.

[0034] Figure 2 This diagram illustrates a specific implementation of a guided docking system in an application scenario, such as... Figure 2As shown, the guidance and docking system includes a mobile docking platform (i.e., the RGV, Rail Guided Vehicle in the figure) and a target object (i.e., the battery at the bottom of the vehicle in the figure). The mobile docking platform has independent motion axes on both sides, which can be equipped with three-dimensional vision sensors (3D cameras in the figure) to take pictures of the side of the target object, thereby obtaining the corresponding target object.

[0035] Please see Figure 3 This application provides a guided docking method applicable to a guided docking system, which includes a mobile docking platform and a target object.

[0036] In the following method embodiments, for ease of description, the guiding docking system is used as the execution subject of each step of the method for illustration, but this does not constitute a specific limitation.

[0037] like Figure 3 As shown, the method may include the following steps:

[0038] Step 310: Obtain the target image.

[0039] The target image can be obtained by capturing the side view of the target object using a mobile 3D vision sensor. The two sides of the mobile docking platform are equipped with independent motion axes and can be configured with 3D vision sensors to capture the side view of the target object, thereby obtaining the corresponding target object.

[0040] In one embodiment, the mobile shuttle platform is equipped with a rail-guided vehicle at its core.

[0041] Regarding the target object, it refers to the object that the mobile docking platform connects to. The target object can be the battery pack at the bottom of a car, but no specific limitation is made here.

[0042] First, it should be noted that during the automated battery swapping process, the battery pack needs to be removed and replaced from the bottom of the vehicle. Its connection interfaces are mostly precision mechanical locks and high-voltage electrical connectors, requiring extremely high docking accuracy. Even with a docking guidance system, parking deviations may still occur when the vehicle enters the swapping station. The 3D vision module of the docking guidance system (such as a line laser profilometer, structured light camera, or other 3D vision sensors) uses technologies such as laser triangulation, structured light, or binocular stereo vision to acquire real-time 3D point cloud data of the vehicle chassis, accurately identifying the position and attitude of the battery compartment (including X, Y, and Z coordinates, as well as pitch, yaw, and roll angles), thereby guiding the robotic arm to perform spatial compensation.

[0043] However, when researching the docking of the mobile docking platform with the battery pack at the bottom of the car, the inventors discovered that if the mobile docking platform directly photographed the bottom of the car and extracted image features to locate the center of the battery pack, image feature extraction often failed. To avoid the inability of the mobile docking platform to accurately dock with the battery pack due to image feature extraction failure, the inventors further discovered that vehicles often have a lot of dirt, debris, and other debris that falls on top of the 3D vision sensor located at the bottom of the mobile docking platform, preventing the 3D vision sensor from forming a clear image. Furthermore, the very center of the battery pack bottom is often the dirtiest, oiliest, and most reflective area, leading to image feature extraction failure and thus preventing the mobile docking platform from docking with the battery pack.

[0044] Based on this, the inventors selected the relatively clean side of the battery pack, which is less prone to reflection, as the object to be photographed by the mobile docking platform. The target image is obtained by taking pictures of the side of the battery pack using three-dimensional vision sensors set at both ends of the guide rail of the mobile docking platform. The target image is then used to guide the mobile docking platform to dock with the target object.

[0045] Step 330: Identify the target object in the target image and determine at least one target reference point on the side of the target object.

[0046] First, it should be noted that the target image can include both the target object and the background object. For example, if the target object is the battery pack at the bottom of a car, then the background object can include the car tires, the exhaust pipe, the mud and water reflections on the ground, etc., without limitation.

[0047] It's understandable that once the mobile docking platform enters the docking area, the target image includes not only the target object to be docked with but also background objects. Therefore, if the target object in the target image isn't identified, the mobile docking platform might misidentify the background object as the target object, preventing successful docking and potentially causing a safety accident. For example, the mobile docking platform might mistake a suspended exhaust pipe for the target object, causing its platform to crash directly into the vehicle.

[0048] Regarding the identification of target objects, target objects can be identified in target images through point cloud segmentation and clustering algorithms, model matching algorithms, deep learning detection algorithms, etc., without making specific limitations here.

[0049] The target reference point is a point used to guide the mobile docking platform to dock with the target object. The target reference point may include the bottom corner points and center coordinates of the target object, which are not limited here.

[0050] In one embodiment, step 330 may include the following steps: determining at least two bottom corner points of the target object based on the target image; calculating the center coordinates based on each bottom corner point; and obtaining each target reference point of the target object based on each bottom corner point and the center coordinates.

[0051] First, it should be noted that the bottom corner points can refer to the four vertices of the bottom surface of the target object. The bottom corner points are the unique intersection points of the bottom surface, front / back side surface, and left / right side surface of the target object. In other words, determining the bottom corner points of the target object allows us to determine its geometric dimensions, such as its length or width.

[0052] Therefore, the bottom corner points are used as guides for the mobile docking platform, thereby driving its own mechanical rotation center to align with it on the horizontal plane.

[0053] Here, the center coordinates can refer to the coordinates corresponding to the center of the bottom of the target object.

[0054] It should be noted that the mobile docking platform is a cuboid with N vertical disassembly pins on its surface, all of which are perpendicular to the platform's surface. If the target object is a battery pack, which is also a cuboid with N disassembly holes on its bottom, the disassembly pins can only align with the battery pack's disassembly holes when the center and angle of the mobile docking platform are both aligned with the center of the battery pack's bottom. This allows the mobile docking platform to connect with the battery pack and disassemble the battery.

[0055] Therefore, it is necessary to determine the center coordinates of the target object so that the center of the mobile docking platform is aligned with the center of the bottom of the target object.

[0056] In one embodiment, the two bottom corner points of the target object are respectively and Then the center coordinates .

[0057] Therefore, the reference points of the target object can be obtained by using the bottom corner points and center coordinates mentioned above.

[0058] It should be noted that if the target object is a battery pack, the outer shell of the battery pack may be metal or plastic. After long-term use, the outer shell may be subject to collisions and deformations. The center coordinates calculated directly from the bottom corners of the target object may be inaccurate, which may cause the mobile docking platform to fail to dock accurately with the target object.

[0059] In one embodiment, the target object includes multiple sub-objects; for example, if the target object is a battery pack, then the battery pack may include multiple batteries; step 330 may include the following steps: identifying each sub-object of the target object based on the target image, and selecting a sub-object that conforms to a set positional relationship as the target sub-object; determining at least two bottom corner points of the target sub-object based on the target image; calculating the center coordinates based on each bottom corner point of the target sub-object; and determining each target reference point of the target object based on the geometric relationship between the target sub-object and the target object, and based on each bottom corner point and the center coordinates.

[0060] Specifically, image recognition algorithms can be used to identify each sub-object of the target object in the target image and determine the position of each sub-object within the target object.

[0061] It is understandable that the center of the mobile connection platform needs to be aligned with the center of the bottom of the target object. Therefore, setting the positional relationship can refer to the sub-object that is located at the center of the overall spatial arrangement of the target object among multiple sub-objects, and thus the sub-object is used as the target sub-object.

[0062] In one embodiment, the sub-object located in the middle of the target object is taken as the target sub-object; based on the coordinates of each bottom corner point and the center of the target sub-object, each target reference point of the target object is obtained.

[0063] Figure 4 A schematic diagram illustrating a specific implementation of a target object is shown, such as... Figure 4 As shown, the mobile docking platform is equipped with two 3D vision sensors. The target object is a battery pack consisting of three batteries. 3D vision sensor 1 captures an image of one side of the battery pack, obtaining a target image. By identifying each battery in the target image, the middle battery located in the center of the battery pack is identified as the target sub-object. This allows for the identification of the two bottom corner points of the middle battery, thus obtaining the target reference points. Figure 5 As shown, Figure 5 The diagram shows the specific implementation of the two bottom corner points of the middle battery.

[0064] Through the above process, by identifying the sub-object located in the middle of the target object as the target sub-object, the positional deviation caused by directly calculating the center coordinates of the target object due to the deformation or tolerance of the target object's shell can be avoided, allowing the mobile docking platform to more accurately align with the center of the bottom of the target object.

[0065] It is worth mentioning that when the sub-object located in the middle of the target object has image noise in the target image, or when the surface of the sub-object has dirt, the bottom corner of the sub-object cannot be accurately identified.

[0066] Therefore, to avoid the above situation causing the mobile docking platform and the target object to fail to dock accurately, in one embodiment, if at least two bottom corner points of the target sub-object cannot be determined based on the target image, a new target sub-object is selected from among the sub-objects; the above method may also include the following steps: based on the geometric relationship between the new target sub-object and the target object, and based on the center coordinates corresponding to the new target sub-object, determine the center point of the sub-object located in the middle position among the sub-objects; based on the bottom corner points corresponding to the new target sub-object and the center point of the sub-object located in the middle position among the sub-objects, obtain the target reference point of the target object.

[0067] Specifically, when it is impossible to accurately identify the bottom corner of a sub-object located in the middle of the target object, the identified sub-objects can be dynamically switched, and any sub-object with clear surface features can be selected as the new target sub-object.

[0068] Then, the bottom corner points of the new target sub-object can be identified, and the center coordinates of the target sub-object can be calculated based on the bottom corner points. Furthermore, the center point of the target object can be determined based on the geometric relationship (e.g., relative positional relationship) between the target sub-object and the target object, thereby determining the center point of the sub-object located in the middle position among all sub-objects.

[0069] Furthermore, if the spatial dimensions of all sub-objects in the target object are the same, then based on the bottom corner points and center coordinates of each sub-object, the center point of the sub-object located in the middle position can be calculated by combining the geometric relationship between the sub-object and the target object.

[0070] For example, suppose the target object is a large battery pack with its internal array arranged in 3 rows and 1 column, and the three sub-objects (battery modules) within it have identical spatial dimensions. If the mobile docking platform only extracts the bottom corner points of the first sub-object located at the edge (e.g., the leftmost one), then the length, width, and center coordinates of this target sub-object are first calculated. Subsequently, on the one hand, by multiplying the length and width of the target sub-object by the number of rows and columns of the array (3×1), the spatial dimensions of the entire target object can be calculated, defining the boundaries for the mobile docking platform; on the other hand, based on the geometric relationship between the target sub-objects and the target object, starting from the center coordinates of the leftmost target sub-object, a spatial translation is performed according to a known step size, which allows for a highly accurate calculation of the center coordinates of the entire target object (i.e., the center point of the sub-object considered to be in the middle position among the sub-objects).

[0071] Through the above embodiments, even when the bottom corner points of the sub-objects located in the middle of the target object cannot be accurately identified, the center point of the sub-object located in the middle of each sub-object can be calculated by using the bottom corner points and center coordinates of any sub-object, combined with the geometric relationship between the target sub-object and the target object. This enables better docking between the mobile docking platform and the target object in different environments.

[0072] Step 350: Obtain coordinate transformation data, and based on the coordinate transformation data, transform the target reference point from the camera coordinate system to the machine coordinate system to obtain guidance data.

[0073] Among them, coordinate transformation data can be used to transform the target reference point in the camera coordinate system to the machine coordinate system; guidance data can refer to the data used to guide the mobile docking platform to the position where it docks with the target object.

[0074] It is understandable that the target reference point obtained by the 3D vision sensor is based on the spatial coordinates of the 3D vision sensor itself, while the mobile docking platform needs to perform movement based on its own mechanical center. Since the two references are different, coordinate transformation is required to map the target reference point into physical displacement and attitude deflection amounts that the mobile docking platform can directly read, thereby guiding the mobile docking platform to accurately dock with the target object.

[0075] In one embodiment, such as Figure 6 As shown, step 350 may also include the following steps:

[0076] Step 351: Perform plane fitting processing based on each target reference point to obtain the target plane.

[0077] It is understandable that multiple target reference points provide spatial coordinates. By performing plane fitting processing using these target reference points, the scattered position points of the target object can be transformed into a surface representing the overall tilt state of the target object.

[0078] Step 353: Convert each target reference point into the machine coordinate system using coordinate transformation data to obtain each target reference point in the machine coordinate system.

[0079] It is understandable that by converting the target reference points in the camera coordinate system to the mechanical coordinate system, the mobile docking platform and the target object can be placed under a unified spatial reference.

[0080] Step 355 involves projecting each target reference point in the mechanical coordinate system onto the target plane to obtain the corresponding projected coordinate points.

[0081] It should be noted that due to depth measurement errors, the target reference points in the camera coordinate system are often not absolutely coplanar. Similarly, since the target reference points in the machine coordinate system are derived from the target reference points in the camera coordinate system using coordinate transformation data, the target reference points in the machine coordinate system also exhibit unevenness in 3D space. By projecting each target reference point onto the fitted target plane, the noise generated by the depth measurement of the 3D vision sensor can be eliminated.

[0082] Step 357: Select a projection coordinate point that meets the set conditions from the projection coordinate points, and calculate the projection center point based on the selected projection coordinate point.

[0083] Step 359: Obtain guidance data based on the projection center point.

[0084] As mentioned earlier, the center of the mobile docking platform needs to be aligned with the center of the bottom of the target object. Based on this, the setting condition can refer to selecting the projection coordinate point of the center position from each of the projection coordinate points. Then, the projection center point can be calculated through the selected projection coordinate point, thereby determining the center of the bottom of the target object.

[0085] Since the projection center point is in the mechanical coordinate system, the mobile docking platform can move according to the guidance data, so that the center of the mobile docking platform needs to be aligned with the center of the bottom of the target object.

[0086] Step 370: Calculate the correction angle data based on the guidance data and the rotation reference axis of the mobile docking platform.

[0087] First, it should be noted that during vehicle battery swapping, due to inconsistent tire pressure and ground looseness, the vehicle will have tilt angles at the front and rear (front and rear, such as the front wheels concave) and left and right (sides of the vehicle, such as the right wheels concave). At the same time, the vehicle is also parked at an angle. Therefore, in addition to center point alignment, tilt angle alignment is also required. Based on this, the tilt angle alignment can be achieved by controlling the center of the mobile docking platform with the center of the target object through the correction angle data.

[0088] The rotation reference axis can refer to the central axis of the mechanical structure of the mobile docking platform, and the correction angle data can refer to the data used to guide the mobile docking platform to the angle of docking with the target object.

[0089] In one embodiment, the guiding data includes the target normal vector; after step 351, the following steps may also be included: calculating the target normal vector based on the target plane.

[0090] Among them, the target normal vector can reflect the tilt state of the target object in three-dimensional space.

[0091] In one embodiment, the rotation reference axis includes at least one of the X-axis rotation axis, the Y-axis rotation axis, and the Z-axis rotation axis; step 370 may include the following steps: obtaining the target normal vector; calculating the angles between the target normal vector and the X-axis rotation axis, the Y-axis rotation axis, and the Z-axis rotation axis respectively to obtain the corresponding correction angles; and obtaining correction angle data based on each correction angle.

[0092] It is understandable that since the target normal vector can indicate the tilt state of the target object in three-dimensional space, the angle between different rotation reference axes and the target normal vector can reflect the angle adjustment of the mobile docking platform, thereby obtaining the corresponding correction angle data.

[0093] Step 390: Based on the correction angle data and guidance data, control the movement of the mobile docking platform so that the mobile docking platform can dock with the target object.

[0094] As mentioned earlier, guidance data can refer to data used to guide the mobile docking platform to the position where it docks with the target object, and correction angle data can refer to data used to guide the mobile docking platform to the angle at which it docks with the target object. Therefore, by controlling the movement of the mobile docking platform based on the correction angle data and guidance data, the center of the mobile docking platform can be aligned with the center of the bottom of the target object in both position and angle, thereby enabling the mobile docking platform to dock with the target object.

[0095] Through the above process, the target image is obtained by taking a side view of the target object using a mobile docking platform. The target object in the image is then identified, and at least one target reference point on the side of the target object is determined. By taking a side view, bottom view is avoided, reducing a large number of complex image processing operations. The target reference point is transformed from the camera coordinate system to the machine coordinate system through coordinate transformation data to obtain guidance data. Based on the guidance data and the rotation reference axis of the mobile docking platform, the correction angle data is calculated. Based on the correction angle data and the guidance data, the movement of the mobile docking platform is controlled, so that the center of the mobile docking platform can be aligned with the center of the bottom of the target object in both position and angle. This effectively reduces a large number of complex manual teaching operations, improves the timeliness and safety of the operation, and improves the docking accuracy in the automatic battery swapping process.

[0096] Please see Figure 7 In an exemplary embodiment, prior to step 350, the method may further include the following steps:

[0097] Step 410: By controlling the mobile docking platform to rotate around the spatial coordinate axis to scan the calibration sphere, the center coordinates of the mobile docking platform in the camera coordinate system are determined.

[0098] It can be understood that by controlling the mobile docking platform to rotate around the spatial coordinate axis to scan the fixed calibration ball, and extracting the spatial circular trajectory of the calibration ball under multiple rotation poses, the origin offset coordinates of the center of the mobile docking platform in the camera coordinate system can be calculated, which can be regarded as the center coordinates of the center of the mobile docking platform in the camera coordinate system.

[0099] In a practical example, step 410 may further include the following steps: controlling the mobile docking platform to rotate and scan the calibration sphere around different spatial coordinate axes to obtain multiple sphere center coordinates corresponding to the calibration sphere on different spatial coordinate axes; fitting spatial circles based on the multiple sphere center coordinates corresponding to different spatial coordinate axes to obtain spatial circles corresponding to each spatial coordinate axis; determining the corresponding rotation reference axis based on the center of the spatial circle corresponding to each spatial coordinate axis; and determining the center coordinates of the center of the mobile docking platform in the camera coordinate system according to the intersection of each rotation reference axis.

[0100] The spatial coordinate axes can include the X-axis, Y-axis, and Z-axis.

[0101] Taking the Z-axis as an example, the calibration sphere is placed on a mobile docking platform, which is then rotated around the Z-axis. Simultaneously, the 3D vision sensor on the platform scans the calibration sphere. By rotating it at multiple different angles, multiple center coordinates are fitted, and a spatial circle is then fitted using these center coordinates. The center of this circle and the normal vector of the fitted circle plane are the Z-axis of rotation, respectively. A point P on the plane and the unit normal vector : Where d is the actual parameter, which is any non-zero real number, and P is a known point on the line. It is the normal vector of the line. Accordingly, the X-axis of rotation is obtained using the method described above. and Y-axis of rotation .

[0102] Then, by sequentially controlling the mobile docking platform to move around its multiple spatial coordinate axes, corresponding rotation reference axes are constructed in the camera coordinate system. The intersection point of these multiple rotation reference axes in three-dimensional space corresponds to the center of the mobile docking platform. Based on the coordinates of this intersection point, the center coordinates of the mobile docking platform in the camera coordinate system can be determined.

[0103] It should be noted that, since the intersection points of the above-mentioned multiple rotation reference axes in three-dimensional space may not actually intersect, in one embodiment, step 417 may also include the following steps: using the minimum spatial distance deviation from the spatial coordinate point to each rotation reference axis as a constraint, determine the optimal spatial intersection point of the multiple rotation reference axes, and obtain the center coordinates of the center of the mobile docking platform in the camera coordinate system.

[0104] Specifically, the center of the mobile docking platform is calculated by taking the intersection of the three rotation reference axes. ,in, , , These are the coordinates of the center on the X, Y, and Z axes, respectively. The center coordinates can be optimized by minimizing the sum of the squared distances from the point to these three lines. No specific restrictions are imposed here; however, it should be noted that... It is in the camera coordinate system.

[0105] Step 420: The calibration sphere is spatially scanned using a mobile docking platform to calibrate the positional relationship between the camera coordinate system and the machine coordinate system, thereby obtaining the first transformation matrix.

[0106] The first transformation matrix can be used to calibrate the positional relationship between the camera coordinate system and the machine coordinate system.

[0107] In one embodiment, step 420 may further include the following steps: scanning the calibration sphere with spatial points according to a set three-dimensional spatial trajectory using a mobile docking platform, and recording the mechanical coordinate point set of the mobile docking platform during the spatial point scanning process; during the spatial point scanning process, fitting and calculating the center coordinates of the calibration sphere at each scanning point to generate a camera coordinate point set; and registering the mechanical coordinate point set with the camera coordinate point set to obtain a first transformation matrix.

[0108] The defined three-dimensional spatial trajectory can refer to the scanning trajectory of the calibration ball.

[0109] Specifically, before the spatial point scanning, the rotation angles α, β, and γ of the mobile docking platform are all zeroed. The calibration sphere is placed on the mobile docking platform, and spatial point scanning is performed through a cube of points (9 points per layer, three layers in total, for a total of 27 points). The coordinates of the center of the calibration sphere at each scanning point are calculated by fitting, generating a set of camera coordinate points. The set of mechanical coordinate points during the spatial point scanning process of the mobile docking platform Calibration is performed, including the camera coordinate point set. With mechanical coordinate point set Correspondingly; furthermore, the first transformation matrix can be obtained through iterative closest point (ICP) registration. .

[0110] Step 430: Obtain the coordinates of the reference center of the calibration ball at any position.

[0111] Step 440: Based on the first transformation matrix, the center coordinates, and the reference sphere center coordinates, the offset is calculated to obtain the offset value.

[0112] As mentioned earlier, the three rotation reference axes of the mobile docking platform in the camera coordinate system are respectively , and The intersection of the three rotational reference axes is .

[0113] Furthermore, the calibration ball is placed at any position on the mobile docking platform (captured by the 3D vision sensor). Therefore, the center of the calibration ball has a fixed offset value from the actual center of the mobile docking platform. This offset value is... ,in, These are the calibration ball centers Coordinates along the X, Y, and Z axes based on the machine coordinate system.

[0114] So, Transformed to the machine coordinate system using the first transformation matrix, the result is... At this time It should be (0, 0, 0), but because the calibration sphere center has a fixed offset from the center of the RGV platform, therefore... It is not (0, 0, 0), and its coordinate value is the offset value.

[0115] Step 450: Calculate the second transformation matrix based on the first transformation matrix and the offset.

[0116] It is understandable that the first transformation matrix can be compensated by the offset, thereby obtaining a second transformation matrix with higher accuracy. The second transformation matrix eliminates the influence of the fixed offset.

[0117] Specifically, the second transformation matrix can be represented as:

[0118] ,

[0119] in, This is the first transformation matrix, with a size of 4×4. It is an identity matrix with a size of 3×3. The offset value vector is 3×1, and 0 is represented as a 1×3 (0, 0, 0) vector.

[0120] Step 460: Based on the second transformation matrix, obtain the coordinate transformation data.

[0121] Under the above embodiments, by scanning the calibration sphere in space, the mechanical coordinate system and camera coordinate system of the mobile docking platform are calibrated. The coordinate transformation data obtained from the calibration is used to realize the coordinate transformation of the target reference point, which facilitates the control of the mobile docking platform through the target image in the future.

[0122] In one exemplary embodiment, the target image includes a first target image and a second target image; the first target image corresponds to a first side of the target object, and the second target image corresponds to a second side of the target object; wherein the first side and the second side are parallel.

[0123] Step 330 may further include the following steps: identifying target objects in the first target image and the second target image respectively, determining each first target reference point corresponding to the target object on the first side and each second target reference point corresponding to the target object on the second side; setting multiple regions of interest in the first target image and the second target image respectively to obtain target points corresponding to the first side and the second side respectively; performing plane fitting based on the target points corresponding to the first side and the second side respectively to obtain the first target plane corresponding to the first side and the second target plane corresponding to the second side; calculating based on each first target reference point and the first target plane to obtain the coordinates of each first target reference point on the Z-axis, and updating each first target reference point; calculating based on each second target reference point and the second target plane to obtain the coordinates of each second target reference point on the Z-axis, and updating each second target reference point.

[0124] First, it should be noted that three-dimensional vision sensors can be installed on the guide rails on both sides of the mobile docking platform to capture images of the first and second sides of the target object, thereby obtaining the first target image and the second target image. By identifying the first target reference points corresponding to the first side of the target object and the second target reference points of the target object on the second side, the coordinates of the bottom corner points of the target object on the first side corresponding to the X and Y axes (i.e., the first target reference points) and the coordinates of the bottom corner points of the target object on the second side corresponding to the X and Y axes (i.e., the second target reference points) can be determined.

[0125] Specifically, firstly, after acquiring the first target image and the second target image of the target object, regions of interest (ROIs) including the first side features and the second side features of the target can be set in the first target image and the second target image, respectively; then, a feature extraction algorithm is executed within the range defined by the ROI to identify and acquire the target points corresponding to the first side and the target points corresponding to the second side of the target object.

[0126] Based on this, background objects can be removed from the first target image and the second target image by using the region of interest.

[0127] For example, in addition to the first and second side views, the first and second target images may also include background objects such as tires, exhaust pipes, ground, and chassis supports. In this case, the first and second side views can be divided by the region of interest in the first and second target images.

[0128] Furthermore, by taking points in the regions of interest of the first and second target images respectively, the target points corresponding to the first side and the second side can be obtained. Then, plane fitting can be performed based on the target points corresponding to the first and second sides respectively to obtain the corresponding first target plane and second target plane.

[0129] Then, by calculating the X and Y coordinates of the bottom corner point of the target object on the first side obtained from the above steps with the first target plane, the Z coordinate of the bottom corner point of the target object on the first side can be obtained. By calculating the X and Y coordinates of the bottom corner point of the target object on the second side with the second target plane, the Z coordinate of the bottom corner point of the target object on the second side can be obtained. Based on the X, Y, and Z coordinates of the bottom corner point of the target object on the first side, the center coordinates of the target object on the first side are calculated. Based on the X, Y, and Z coordinates of the bottom corner point of the target object on the second side, the center coordinates of the target object on the second side are calculated. Thus, the coordinate update of each first target reference point and each second target reference point is completed.

[0130] In one embodiment, the target object is a battery pack, and the bottom corner of the first side of the battery pack is... and Calculate the center coordinates Similarly, the bottom corner points of the second side of the battery pack can be obtained. , and midpoint .

[0131] In one embodiment, the coordinate transformation data includes first coordinate transformation data corresponding to the first side and second coordinate transformation data corresponding to the second side;

[0132] Step 350 may further include the following steps: converting each updated first target reference point into a mechanical coordinate system using first coordinate transformation data to obtain each first target reference point in the mechanical coordinate system; converting each updated second target reference point into a mechanical coordinate system using second coordinate transformation data to obtain each second target reference point in the mechanical coordinate system; performing plane fitting based on each first target reference point and each second target reference point in the mechanical coordinate system to obtain the bottom plane of the target object; projecting each first target reference point and each second target reference point in the mechanical coordinate system onto the bottom plane to obtain corresponding first projection coordinate points and second projection coordinate points; selecting first projection coordinate points and second projection coordinate points that meet set conditions from each first projection coordinate point and each second projection coordinate point, and calculating the projection center point based on the selected first projection coordinate points and second projection coordinate points; obtaining guidance data based on the projection center point.

[0133] It should be noted that the updated first target reference points and second target reference points are in the camera coordinate system. In order to control the mobile docking platform based on the first target reference points and second target reference points, they need to be converted to the machine coordinate system.

[0134] Based on this, the updated first target reference points can be converted into the machine coordinate system using the first coordinate transformation data, and the updated second target reference points can be converted into the machine coordinate system using the second coordinate transformation data.

[0135] It should be understood that, ideally, the first target reference points and the second target reference points after the above transformation are on the same plane (the bottom surface of the target object). In reality, due to detection / calibration errors, they are not on the same plane. Therefore, the first target reference points and the second target reference points on the mechanical coordinate system are projected onto the bottom plane to obtain the corresponding first projected coordinate points and second projected coordinate points, thereby eliminating the error.

[0136] It is understandable that, since the center of the mobile docking platform needs to be aligned with the center of the target object, the setting condition can refer to selecting the first projection coordinate point and the second projection coordinate point located at the center position among each first projection coordinate point and each second projection coordinate point, and then calculating the projection center point based on the selected first projection coordinate point and the second projection coordinate point, which can be regarded as the center of the target object.

[0137] In one embodiment, , , and , , Data transformed using the first coordinate system respectively Second coordinate transformation data Transform to the machine coordinate system and use , , and , , Fit the bottom plane M and its target normal vector using six points. Where a, b, and c are the target normal vectors. Coordinates along the X, Y, and Z axes; respectively , , and , , Projecting onto the bottom plane M, we obtain its projected coordinates in the machine coordinate system. , , , , , All points are coplanar, and this bottom plane serves as the bottom surface of the target object. and The projection center point is the guiding data: .

[0138] It should be noted that the target normal vector of the bottom surface of the battery was obtained above. By calculating the angles between the target normal vector and each rotation reference axis of the mobile docking platform, the correction angles α of the X-axis rotation axis, β of the Y-axis rotation axis, and γ of the Z-axis rotation axis can be obtained, thereby guiding the center of the mobile docking platform to be in the same tilt state as the center of the target object.

[0139] The calculation process is shown in the following formula:

[0140] , ;

[0141] Therefore, the rotation axes α, β, and γ in the X direction are calculated as follows:

[0142] .

[0143] Under the above embodiments, the mobile docking platform can scan two parallel sides of the target object to obtain a first target image and a second target image. Based on the first target image and the second target image, guidance data can be calculated. By determining the center of the target object, the center of the mobile docking platform can be guided to align with the center of the target object, thereby accurately completing the docking.

[0144] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0145] This document describes various exemplary embodiments with reference to them. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope of this document. For example, various operational steps and components for performing operational steps can be implemented in different ways depending on the specific application or considering any number of cost functions associated with the operation of the system (e.g., one or more steps can be deleted, modified, or combined with other steps).

[0146] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.

[0147] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. Furthermore, as those skilled in the art will understand, the principles herein can be reflected in a computer program product on a computer-readable storage medium pre-loaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions can be loaded onto a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to form a machine, such that instructions executing on the computer or other programmable data processing apparatus can generate means for performing a specified function. These computer program instructions can also be stored in a computer-readable storage medium that can instruct the computer or other programmable data processing apparatus to operate in a particular manner, such that instructions stored in the computer-readable storage medium can form an article of manufacture including means for implementing the specified function. The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable apparatus to produce a computer-implemented process, such that instructions executing on the computer or other programmable apparatus can provide steps for implementing the specified function.

[0148] While the principles herein have been illustrated in various embodiments, numerous modifications to the structure, arrangement, proportions, elements, materials, and components, particularly suited to specific environmental and operational requirements, may be used without departing from the principles and scope of this disclosure. These modifications and other alterations or alterations will be included within the scope of this document.

[0149] The foregoing specific descriptions have been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of this disclosure. Therefore, considerations for this disclosure are to be illustrative rather than restrictive, and all such modifications are to be included within its scope. Similarly, advantages, other advantages, and solutions to problems with respect to various embodiments have been described above. However, benefits, advantages, solutions to problems, and any elements that produce these, or make them more explicit, should not be construed as critical, essential, or necessary. The term “comprising” and any other variations thereof as used herein are non-exclusive inclusion, meaning that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed or not part of the process, method, system, article, or apparatus. Furthermore, the term “coupled” and any other variations thereof as used herein refer to physical connections, electrical connections, magnetic connections, optical connections, communication connections, functional connections, and / or any other connections.

[0150] Those skilled in the art will recognize that many changes can be made to the details of the above embodiments without departing from the basic principles of the invention. Therefore, the scope of the invention should be determined only by the claims.

Claims

1. A guided docking method, characterized in that, This is applied to a guided docking system, which includes a mobile docking platform and a target object. The method includes: Acquire a target image; the target image is obtained by the mobile docking platform capturing a side view of the target object. The target object in the target image is identified, and at least one target reference point of the target object on the side is determined; Acquire coordinate transformation data, and based on the coordinate transformation data, transform the target reference point from the camera coordinate system to the machine coordinate system to obtain guidance data; The correction angle data is obtained by calculating based on the guidance data and the rotation reference axis of the mobile docking platform; Based on the correction angle data and the guidance data, the mobile docking platform is controlled to move, so that the mobile docking platform can dock with the target object.

2. The method as described in claim 1, characterized in that, The step of identifying the target object in the target image and determining at least one target reference point of the target object includes: Based on the target image, at least two bottom corner points of the target object are determined; Calculate the center coordinates based on each of the bottom corner points; Based on the coordinates of each of the bottom corner points and the center, the target reference points of the target object are obtained.

3. The method as described in claim 1, characterized in that, The target object includes multiple sub-objects; The step of identifying the target object in the target image and determining at least one target reference point of the target object includes: Based on the target image, identify each of the sub-objects of the target object, and select the sub-object that conforms to the set positional relationship as the target sub-object; Based on the target image, at least two bottom corner points of the target sub-object are determined; Calculate the center coordinates based on each of the bottom corner points of the target sub-object; Based on the geometric relationship between the target sub-object and the target object, and based on the coordinates of each bottom corner point and the center point, determine each target reference point of the target object.

4. The method as described in claim 3, characterized in that, The step of identifying each sub-object of the target object based on the target image, and selecting a sub-object that conforms to a set positional relationship as the target sub-object, includes: The sub-object located in the middle of the target object is taken as the target sub-object; The step of determining each of the target reference points of the target object based on the geometric relationship between the target sub-object and the target object, and based on the coordinates of each of the bottom corner points and the center, includes: Based on the bottom corner points and center coordinates of the target sub-object, the target reference points of the target object are obtained.

5. The method as described in claim 4, characterized in that, After selecting the sub-object located in the middle of the target object as the target sub-object, the method further includes: If at least two bottom corner points of the target sub-object cannot be determined based on the target image, then a new target sub-object is selected from among the sub-objects. The step of determining each of the target reference points of the target object based on the geometric relationship between the target sub-object and the target object, and based on the coordinates of each of the bottom corner points and the center, includes: Based on the geometric relationship between the new target sub-object and the target object, and based on the center coordinates corresponding to the new target sub-object, determine the center point of the sub-object located in the middle position among all the sub-objects; Based on the bottom corner points corresponding to the new target sub-object and the center point of the sub-object located in the middle position, the target reference point of the target object is obtained.

6. The method as described in claim 1, characterized in that, The process of acquiring coordinate transformation data and transforming the target reference point from the camera coordinate system to the machine coordinate system based on the coordinate transformation data to obtain guidance data includes: Based on each of the target reference points, a plane fitting process is performed to obtain the target plane; The target reference points are converted into a mechanical coordinate system using the coordinate transformation data, thereby obtaining the target reference points in the mechanical coordinate system. Each of the target reference points in the mechanical coordinate system is projected onto the target plane to obtain the corresponding projected coordinate points; Select a projection coordinate point that meets the set conditions from each of the projection coordinate points, and calculate the projection center point based on the selected projection coordinate point. The guidance data is obtained based on the projection center point.

7. The method as described in claim 6, characterized in that, The guiding data includes the target normal vector; After obtaining the target plane by performing plane fitting processing based on each of the target reference points, the method further includes: calculating the target normal vector based on the target plane.

8. The method as described in claim 1, characterized in that, The rotation reference axis includes at least one of the X-axis rotation axis, the Y-axis rotation axis, and the Z-axis rotation axis; The step of calculating the correction angle data based on the guidance data and the rotation reference axis of the mobile docking platform includes: Obtain the target normal vector; Calculate the angles between the target normal vector and the X-axis, Y-axis, and Z-axis rotation axes respectively to obtain the corresponding correction angles; The correction angle data is obtained based on each of the correction angles.

9. The method according to any one of claims 1 to 8, characterized in that, Before acquiring coordinate transformation data and transforming the target reference point from the camera coordinate system to the machine coordinate system based on the coordinate transformation data to obtain guidance data, the method further includes: By controlling the mobile docking platform to rotate around the spatial coordinate axis to scan the calibration sphere, the center coordinates of the mobile docking platform in the camera coordinate system are determined; The calibration sphere is spatially scanned using the mobile docking platform to calibrate the positional relationship between the camera coordinate system and the machine coordinate system, thereby obtaining the first transformation matrix. Obtain the reference center coordinates of the calibration sphere at any position; Based on the first transformation matrix, the center coordinates, and the reference sphere center coordinates, an offset value is obtained by calculating the offset. The second transformation matrix is ​​obtained by calculating based on the first transformation matrix and the offset; The coordinate transformation data is obtained based on the second transformation matrix.

10. The method as described in claim 9, characterized in that, The step of determining the center coordinates of the mobile docking platform in the camera coordinate system by controlling the mobile docking platform to rotate and scan the calibration sphere around the spatial coordinate axis includes: The mobile docking platform is controlled to rotate and scan the calibration sphere around different spatial coordinate axes to obtain multiple center coordinates of the calibration sphere on different spatial coordinate axes. Based on the coordinates of multiple sphere centers corresponding to the different spatial coordinate axes, spatial circles are fitted to obtain spatial circles corresponding to each of the spatial coordinate axes. Based on the center of the spatial circle corresponding to each of the aforementioned spatial coordinate axes, determine the corresponding rotation reference axis; The center coordinates of the mobile docking platform in the camera coordinate system are determined based on the intersection of the rotation reference axes.

11. The method as described in claim 10, characterized in that, Determining the center coordinates of the mobile docking platform in the camera coordinate system based on the intersection of each of the rotation reference axes includes: Using the minimum spatial distance deviation from the spatial coordinate point to each of the rotation reference axes as a constraint, the optimal spatial intersection point of the multiple rotation reference axes is determined, and the center coordinates of the center of the mobile docking platform in the camera coordinate system are obtained.

12. The method as described in claim 9, characterized in that, The step of performing a spatial scan of the calibration sphere using the mobile docking platform to calibrate the positional relationship between the camera coordinate system and the machine coordinate system, and obtaining a first transformation matrix, includes: The mobile docking platform scans the calibration ball according to a set three-dimensional spatial trajectory, and records the set of mechanical coordinate points of the mobile docking platform during the spatial point scanning process. During the spatial point scanning process, the center coordinates of the calibration sphere at each scanning point are calculated to generate a set of camera coordinate points. The first transformation matrix is ​​obtained by registering the mechanical coordinate point set with the camera coordinate point set.

13. The method according to any one of claims 1 to 8, characterized in that, The target image includes a first target image and a second target image; the first target image corresponds to a first side of the target object, and the second target image corresponds to a second side of the target object; wherein the first side and the second side are parallel. The step of identifying the target object in the target image and determining at least one target reference point of the target object includes: The target objects in the first target image and the second target image are identified respectively, and the first target reference points corresponding to the target objects on the first side and the second target reference points corresponding to the target objects on the second side are determined. Multiple regions of interest are set in the first target image and the second target image respectively to obtain target points corresponding to the first side and target points corresponding to the second side. Plane fitting is performed based on the target points corresponding to the first side and the target points corresponding to the second side to obtain the first target plane corresponding to the first side and the second target plane corresponding to the second side. Based on the first target reference point and the first target plane, the coordinates of each first target reference point on the Z-axis are obtained, and each first target reference point is updated. The coordinates of each second target reference point on the Z-axis are obtained by calculating based on each second target reference point and the second target plane, and then each second target reference point is updated.

14. The method as described in claim 13, characterized in that, The coordinate transformation data includes first coordinate transformation data corresponding to the first side and second coordinate transformation data corresponding to the second side; The process of acquiring coordinate transformation data and transforming the target reference point from the camera coordinate system to the machine coordinate system based on the coordinate transformation data to obtain guidance data includes: The updated first target reference points are converted into a mechanical coordinate system using the first coordinate transformation data to obtain each first target reference point in the mechanical coordinate system. The updated second target reference points are converted into the machine coordinate system using the second coordinate transformation data, resulting in the second target reference points in the machine coordinate system. The bottom plane of the target object is obtained by performing plane fitting between each of the first target reference points and each of the second target reference points on the machine coordinate system. The first target reference point and the second target reference point on the mechanical coordinate system are projected onto the bottom plane to obtain the corresponding first projection coordinate point and second projection coordinate point. Select a first projection coordinate point and a second projection coordinate point that meet the set conditions from each of the first projection coordinate points and each of the second projection coordinate points respectively, and calculate the projection center point based on the selected first projection coordinate points and second projection coordinate points; The guidance data is obtained based on the projection center point.

15. A guiding docking system, characterized in that, include: A mobile connection platform used to acquire target images; The target image is obtained by the mobile shuttle platform taking a picture of the side view of the target object; The target object in the target image is identified, and at least one target reference point of the target object on the side is determined; coordinate transformation data is acquired, and the target reference point is transformed from the camera coordinate system to the machine coordinate system based on the coordinate transformation data to obtain guidance data; correction angle data is calculated based on the guidance data and the rotation reference axis of the mobile docking platform; the mobile docking platform is controlled to move according to the correction angle data and the guidance data, so that the mobile docking platform completes docking with the target object; The target object is used to connect to the mobile docking platform.

16. A computer-readable storage medium, characterized in that, The medium stores a computer program that can be executed by a processor to implement the method as described in any one of claims 1-14.

Images