Charging control method and device of charging robot, storage medium and equipment

Abstract

The application discloses a charging control method and device of a charging robot, a storage medium and a computer device. The method comprises the following steps: acquiring a first image through a preset shooting device on the charging robot, and determining a first changed pose corresponding to the preset shooting device based on a first charging hole set contained in the first image; controlling the preset shooting device to reach a first target pose based on the first changed pose; acquiring a second image through the preset shooting device on the charging robot, and determining a second changed pose corresponding to the preset shooting device based on a second charging hole set contained in the second image; and controlling the preset shooting device to reach a second target pose based on the second changed pose, so that each charging hole on a charging port of the charging robot is aligned with each charging hole on a vehicle to be charged, and the charging port is controlled to charge the vehicle to be charged. The relative position of the charging port and the preset shooting device is fixed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric vehicle charging, in particular to a charging robot charging control method and device, storage medium and computer equipment. BACKGROUND

[0002] With the rapid development of the electric vehicle industry, more and more users are currently purchasing electric vehicles, and at the same time, the charging demand of electric vehicles is gradually increasing. However, in some specific areas such as open parking lots, underground parking garages, etc., due to the limited number of charging piles, the charging demand of electric vehicles cannot be met. Under this background, charging robots have emerged.

[0003] The emergence of charging robots can greatly alleviate the charging demand of parking lots, parking garages, etc. When an electric vehicle has a charging demand, a charging robot can be determined to charge the electric vehicle. The charging robot can move to the charging position of the electric vehicle and autonomously charge the electric vehicle, so it is very important to ensure the precise alignment between the charging port on the charging robot and the charging hole on the electric vehicle.

[0004] In the prior art, when the charging robot charges the electric vehicle, it usually only aligns once, that is, charges. This method is prone to alignment errors, which can cause damage to the charging port of the charging robot or the charging hole on the electric vehicle when the charging port of the charging robot is inserted into the electric vehicle. On the other hand, it is prone to misalignment, for example, for an alternating current charging hole, misalignment after rotating 45° is prone to occur. SUMMARY

[0005] Therefore, the present application provides a charging robot charging control method and device, storage medium and computer equipment, which can greatly reduce alignment errors and avoid misalignment by aligning twice, the first time using only part of the charging holes on the vehicle to be charged, and the second time using all the charging holes on the vehicle to be charged. This is conducive to ensuring the safety of charging.

[0006] According to one aspect of the present application, a charging robot charging control method is provided, comprising:

[0007] acquiring a first image through a preset shooting device on the charging robot, and determining a first change pose corresponding to the preset shooting device based on a first set of charging holes contained in the first image;

[0008] controlling the preset shooting device to reach a first target pose based on the first change pose;

[0009] acquire a second image through a preset photographing device on the charging robot, and determine a second changed pose corresponding to the preset photographing device based on a second charging hole set contained in the second image;

[0010] control the preset photographing device to reach a second target pose based on the second changed pose, so that each charging hole on a charging port of the charging robot is aligned with each charging hole on the vehicle to be charged, and control the charging port to charge the vehicle to be charged, a relative position of the charging port and the preset photographing device being fixed.

[0011] According to another aspect of the present application, a charging control device of a charging robot is provided, comprising:

[0012] a first image acquisition module, configured to acquire a first image through a preset photographing device on the charging robot, and determine a first changed pose corresponding to the preset photographing device based on a first charging hole set contained in the first image;

[0013] a first control module, configured to control the preset photographing device to reach a first target pose based on the first changed pose;

[0014] a second image acquisition module, configured to acquire a second image through the preset photographing device on the charging robot, and determine a second changed pose corresponding to the preset photographing device based on a second charging hole set contained in the second image;

[0015] a second control module, configured to control the preset photographing device to reach a second target pose based on the second changed pose, so that each charging hole on a charging port of the charging robot is aligned with each charging hole on the vehicle to be charged, and control the charging port to charge the vehicle to be charged, a relative position of the charging port and the preset photographing device being fixed.

[0016] According to still another aspect of the present application, a storage medium having a computer program stored thereon is provided, the program being executed by a processor to implement the charging control method of the charging robot.

[0017] According to yet another aspect of the present application, a computer device is provided, comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, the processor implementing the charging control method of the charging robot when executing the program.

[0018] According to still another aspect of the present application, a charging robot is provided, comprising the charging control device of the charging robot.

[0019] By the technical scheme, the charging control method and device of the charging robot, the storage medium and the computer device provided by the application can capture the charging hole part of the vehicle to be charged through the preset shooting device arranged on the charging robot, so that the first image can be correspondingly obtained, and the first charging hole set can be included in the first image. Then, the first change pose corresponding to the preset shooting device can be determined according to the first charging hole set included in the first image. After the first change pose is determined, the preset shooting device can be controlled to reach the first target pose. Then, the charging hole part of the vehicle to be charged can be captured again through the preset shooting device, so that the second image can be correspondingly obtained. Here, the second charging hole set can be included in the second image, and the second charging hole set can be all charging holes. According to the second charging hole set in the second image, the second change pose corresponding to the preset shooting device at this time can be determined. After the second change pose corresponding to the preset shooting device is determined, the preset shooting device can be controlled to reach the second target pose. When the preset shooting device reaches the second target pose, the charging holes on the charging port and the charging holes on the vehicle to be charged have been accurately aligned one by one, and only a preset distance is left in the preset direction. The embodiment of the application aligns twice, the first time only uses part of the charging holes on the vehicle to be charged to align, and the second time uses all the charging holes on the vehicle to be charged to align, which not only greatly reduces the alignment error, but also avoids the misalignment, and is beneficial to ensuring the safety of charging.

[0020] The above description is only a summary of the technical scheme of the application. In order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0021] The drawings described herein are used to provide further understanding of the application, and form a part of the application. The schematic embodiments of the application and their descriptions are used to explain the application, and do not constitute an improper limitation on the application. In the drawings:

[0022] Figure 1 A flowchart of a charging control method of a charging robot provided by an embodiment of the application is shown;

[0023] Figure 2 A connection relationship between a charging port and a preset shooting device provided by an embodiment of the application is shown;

[0024] Figure 3 A schematic view of a charging hole in a charging port provided by an embodiment of the application is shown;

[0025] Figure 4A flowchart of a charging control method of a charging robot is shown;

[0026] Figure 5 A schematic diagram of a first output result is shown;

[0027] Figure 6 A schematic diagram of a first point cloud template is shown;

[0028] Figure 7 A schematic diagram of a second point cloud template is shown;

[0029] Figure 8 A structural schematic diagram of a charging control device of a charging robot is shown. DETAILED DESCRIPTION

[0030] Hereinafter, the present application will be described in detail with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0031] A charging control method of a charging robot is provided in the present embodiment, as shown in the figure, the method comprises: Figure 1

[0032] In step 101, a first image is obtained by a preset shooting device on the charging robot, and a first change pose corresponding to the preset shooting device is determined based on a first set of charging holes contained in the first image.

[0033] The charging control method of the charging robot provided in the present application can be applied to a mobile charging robot, for example, it can be used in the application scenario where the mobile charging robot charges an electric vehicle. The charging robot can be provided with a preset shooting device, a mechanical arm, a charging port, etc. The charging holes on the charging port are arranged in the same way as the charging holes of the vehicle to be charged. The preset shooting device can be a depth camera, and images can be obtained through the preset shooting device. The relative position between the preset shooting device and the charging port can be fixed, for example, the preset shooting device and the charging port can be fixed on a target component, as shown in the figure, the target component can be fixed on the mechanical arm, and the synchronous movement of the preset shooting device and the charging port is controlled by the mechanical arm. Figure 2

[0034] ​​When the charging robot moves to the vicinity of the charging position of the vehicle to be charged, the charging cover corresponding to the charging position of the vehicle to be charged can be automatically opened under the control of the cloud or the charging robot. Then, the charging hole position of the vehicle to be charged can be photographed by the preset photographing device arranged on the charging robot, so that the first image can be correspondingly obtained, and the first image can include the first charging hole set. Generally, the charging hole arrangement of the vehicle to be charged can be composed of seven charging holes as shown in Figure 3 The present application adopts twice alignment. In the first alignment, a part of the seven charging holes can be selected for alignment, and in the second alignment, the seven charging holes are selected for alignment. Twice alignment can realize accurate alignment between the charging port of the charging robot and the charging hole on the electric vehicle. The first charging hole set can be a set composed of a part of the seven charging holes of the vehicle to be charged. After obtaining the first image, the first change pose corresponding to the preset photographing device can be determined according to the first charging hole set contained in the first image.

[0035] Step 102, based on the first change pose, control the preset photographing device to reach the first target pose;

[0036] In this embodiment, the first target pose can be known, that is, the target pose set when the preset photographing device is aligned for the first time. After determining the first change pose, the preset photographing device can be controlled to reach the first target pose. Specifically, the mechanical arm on the charging robot can be controlled to move the preset photographing device from the first change pose to the first target pose. The first change pose can be a pose relative to the first target pose, and the pose change between the current pose and the first target pose can be determined from the first change pose.

[0037] Step 103, obtaining a second image by the preset photographing device on the charging robot, and determining a second change pose corresponding to the preset photographing device based on a second charging hole set contained in the second image;

[0038] In this embodiment, after the preset photographing device reaches the first target pose, the charging hole position of the vehicle to be charged can be photographed again by the preset photographing device, so that the second image can be correspondingly obtained. Here, the second image can include the second charging hole set, and the second charging hole set can be all charging holes. Then, the second change pose corresponding to the preset photographing device at this time can be determined according to the second charging hole set in the second image.

[0039] In step 104, based on the second changed pose, the preset shooting device is controlled to reach a second target pose, so that each charging hole on the charging port of the charging robot is aligned with each charging hole on the vehicle to be charged, and the charging port is controlled to charge the vehicle to be charged, and the relative position between the charging port and the preset shooting device is fixed.

[0040] In this embodiment, the second target pose can also be a target pose set when the preset shooting device is aligned for the second time. After the second changed pose corresponding to the preset shooting device is determined, the preset shooting device can be controlled to reach the second target pose. The second changed pose can be a pose relative to the second target pose, and from the second changed pose, the change in pose between the current pose and the second target pose can be determined. It should be noted that when the preset shooting device reaches the second target pose, the charging holes on the charging port and the charging holes on the vehicle to be charged have been precisely aligned one by one, and only a preset distance is left in the preset direction. Here, the preset direction can be the direction of the line between the charging holes on the charging port and the charging holes on the vehicle to be charged.

[0041] By applying the technical solution of the present embodiment, the charging hole part of the vehicle to be charged can be photographed by the preset shooting device arranged on the charging robot, so that the first image can be correspondingly obtained, and the first charging hole set can be included in the first image. Then, the first changed pose corresponding to the preset shooting device can be determined according to the first charging hole set included in the first image. After the first changed pose is determined, the preset shooting device can be controlled to reach the first target pose. Then, the charging hole part of the vehicle to be charged can be photographed again by the preset shooting device, so that the second image can be correspondingly obtained. Here, the second image can include the second charging hole set, and the second charging hole set can be all charging holes. According to the second charging hole set in the second image, the second changed pose corresponding to the preset shooting device at this time can be determined. After the second changed pose corresponding to the preset shooting device is determined, the preset shooting device can be controlled to reach the second target pose. When the preset shooting device reaches the second target pose, the charging holes on the charging port and the charging holes on the vehicle to be charged have been precisely aligned one by one, and only a preset distance is left in the preset direction. The present embodiment uses part of the charging holes on the vehicle to be charged for alignment in the first alignment and uses all the charging holes on the vehicle to be charged for alignment in the second alignment, which not only greatly reduces the alignment error, but also avoids the situation of false matching, and is conducive to ensuring the safety of charging.

[0042] Further, as a refinement and expansion of the above embodiment, in order to completely describe the specific implementation process of the present embodiment, another charging control method of a charging robot is provided, as shown in Figure 4 The method comprises:

[0043] Step 201, acquiring a first image through a preset shooting device on the charging robot;

[0044] In this embodiment, when the charging robot moves to the vicinity of the charging position of the vehicle to be charged, the charging cover corresponding to the charging position of the vehicle to be charged can be automatically opened under the control of the cloud or the charging robot. Then, the charging hole position of the vehicle to be charged can be photographed through the preset shooting device arranged on the charging robot, so that the first image can be correspondingly acquired, and the first image can include the first charging hole set.

[0045] Step 202, inputting the first color image into a preset recognition model, and determining the first charging hole set based on a first output result of the preset recognition model;

[0046] In this embodiment, the first image includes a first color image and a first depth image. A preset recognition model can be constructed in advance, which can be a deep learning model, and specifically can be a yolo (You Only Look Once) detection model. The Yolo detection model is an object recognition and positioning algorithm model based on a deep neural network, and its biggest feature is fast running speed, which can be used in real-time systems. Before using the preset recognition model, the initial recognition model can be trained. Before training the initial recognition model, a plurality of training samples can be acquired, each of which can include a sample image containing all charging holes of an electric vehicle photographed under different conditions, and the different conditions can include different light, different weather, different angles, etc. In this way, the acquired sample images are more comprehensive, and the training effect is better. Then, each sample image can be classified and labeled. The outer contour of all charging holes is labeled as a first class, a large square is labeled, a part of the charging holes is labeled as a second class, and each charging hole is labeled with a small square. The charging hole labeled with a small square is included in the first charging hole set to be recognized subsequently. When the model error of the initial recognition model after training reaches an acceptable error, the initial recognition model at this time can be used as the preset recognition model.

[0047] After acquiring the first image, the first color image in the first image can be input into the preset recognition model, and the first output result output from the preset recognition model can include two types of recognition results. The first type is a global recognition result, which includes all seven charging holes; the second type is a local recognition result, which includes a part of the charging holes. For example, Figure 5As shown, the first output result of the preset recognition model can be obtained, where the first type is indicated by a large square, and the second type is indicated by three small squares. Specifically, the large square can be one color, and the three small squares can be another color. The three charging holes corresponding to the three small squares can constitute the first charging hole set, that is, the identification of the first charging hole set is completed.

[0048] In step 203, based on the first charging hole set, the first position coordinates corresponding to each point cloud point in the first charging hole set are determined from the first depth image.

[0049] In this embodiment, the first depth image can include the depth distance corresponding to each pixel point. Since the first color image and the first depth image are completely corresponding, the depth distance of each point cloud point included in the first charging hole set can be determined in the first depth image through the first charging hole set identified in the first color image. Then, the first position coordinates corresponding to each point cloud point in the first charging hole set can be obtained by combining the intrinsic parameters of the preset shooting device.

[0050] In step 204, the first change pose corresponding to the preset shooting device is determined according to the first position coordinates corresponding to each point cloud point and the first point cloud template.

[0051] In this embodiment, the first point cloud template can be pre-set, and the first point cloud template can be obtained by shooting processing of the preset shooting device at the first target pose. The first point cloud template also includes data corresponding to point cloud points in the first charging hole set. When the charging holes included in the first charging hole set are the three charging holes in the middle row, the first point cloud template can be as shown. Figure 6 After determining the first position coordinates corresponding to each point cloud point in the first charging hole set, the change of the preset shooting device relative to the first target pose when the preset shooting device obtains the first image can be calculated according to the first point cloud template, and the first change pose is obtained.

[0052] In step 205, the first target pose is reached by controlling the preset shooting device based on the first change pose.

[0053] In step 206, the second image is obtained by the preset shooting device on the charging robot.

[0054] In this embodiment, after the first change pose is determined, the preset shooting device can be controlled to reach the first target pose. Then, the charging hole part of the vehicle to be charged can be photographed again by the preset shooting device, so that the second image can be obtained. Here, the second image can include a second charging hole set, and the second charging hole set can be all charging holes.

[0055] In step 207, the second color image is input to a preset recognition model, and a second output result of the preset recognition model is used to determine the second charging hole set;

[0056] In step 208, based on the second charging hole set, a second position coordinate corresponding to each point cloud point in the second charging hole set is determined from the second depth image;

[0057] In step 209, based on the second position coordinate corresponding to each point cloud point and the second point cloud template, a second change pose corresponding to the preset shooting device is determined.

[0058] In this embodiment, the process of determining the second change pose corresponding to the preset shooting device based on the second color image and the second depth image in steps 207-209 is similar to the process of steps 202-204, wherein the second charging hole set can include all seven charging holes, and the second output result can also include two types of recognition results. The first type is a global recognition result, that is, the first type includes all seven charging holes. The second type is a local recognition result, that is, the second type includes a part of the charging holes. The first type is indicated by a large square, and then the charging holes in the large square can be directly determined as the second charging hole set. When the second charging hole set includes seven charging holes, the second point cloud template can be specifically as shown in Figure 7

[0059] In step 210, based on the second change pose, the preset shooting device is controlled to reach a second target pose, so that each charging hole on the charging port of the charging robot is aligned with each charging hole on the vehicle to be charged, and the charging port is controlled to move a preset distance in a preset direction to the vehicle to be charged, so that the charging port charges the vehicle to be charged.

[0060] In this embodiment, after the second change pose corresponding to the preset shooting device is determined, the preset shooting device can be further moved to the second target pose by the mechanical arm. After the preset shooting device is moved to the second target pose, the charging port can be moved to the vehicle to be charged in a preset direction by the mechanical arm again, and specifically, the charging port can be moved a preset distance, so that the vehicle to be charged can be safely and accurately charged.

[0061] In the embodiments of the present application, step 203 can optionally include:

[0062] In step 203-1, based on the first classification box corresponding to each first charging hole in the first charging hole set, a point cloud corresponding to each first classification box is determined from the first depth image, and the point clouds corresponding to the first classification boxes are aggregated.

[0063] ​In this embodiment, the first charging hole set can include a plurality of first charging holes, and each first charging hole corresponds to a first classification box. Since the first classification box can be a rectangular classification box, when determining the point cloud from the first depth image according to the first classification box, the corresponding point cloud in the first classification box is not all the point cloud corresponding to the charging hole. At this time, the corresponding point cloud in each first classification box can be aggregated to obtain all the point cloud corresponding to the first classification box, which must include all the point cloud corresponding to the first charging hole set.

[0064] In step 203-2, the aggregated point cloud is subjected to plane fitting processing to obtain a first target point cloud corresponding to the first charging hole set, and a first position coordinate corresponding to each point cloud point in the first target point cloud is determined.

[0065] In this embodiment, since the surfaces of the charging holes are on the same plane according to the national standard, in order to ensure the accuracy of the point cloud corresponding to the first charging hole set, the aggregated point cloud can be subjected to plane fitting processing, and then the first target point cloud corresponding to the first charging hole set can be obtained. The point cloud points in the first target point cloud are accurate point cloud points corresponding to the first charging hole set. Then, the first position coordinate corresponding to each point cloud point in the first target point cloud can be determined, that is, the first position coordinate corresponding to each point cloud point in the first charging hole set.

[0066] In the embodiments of the present application, step 204 can optionally include:

[0067] In step 204-1, each point cloud point is matched with the first point cloud template based on the first position coordinate corresponding to the point cloud point to obtain a target matching result.

[0068] In this embodiment, the point cloud point and the first point cloud template can be matched according to the first position coordinate corresponding to each point cloud point. In the matching process, the ICP matching algorithm can be used, that is, point-to-point matching, so that a pose can be calculated correspondingly. Finally, the target matching result can be obtained according to each pose.

[0069] In step 204-2, when the target matching result satisfies a target preset condition, a first change pose corresponding to the preset shooting device is calculated based on the target matching result.

[0070] In this embodiment, it can be determined in advance whether the target matching result satisfies the target preset condition. Here, the target preset condition can be a positive correct matching, that is, the horizontal rotation angle of the pose is less than 90°. If the target matching result satisfies the target preset condition, then the first change pose corresponding to the preset shooting device can be directly calculated based on the target matching result.

[0071] Step 204-3, when the target matching result does not satisfy the target preset condition, performing coordinate transformation processing based on the target matching result, and calculating the first changed pose corresponding to the preset shooting device according to the matching result after the coordinate transformation processing.

[0072] In this embodiment, if the target matching result does not satisfy the target preset condition, it can be generally divided into the following three cases. The first case is forward matching, but the horizontal rotation angle of the pose is greater than 90°. The second case is reverse matching, and the horizontal rotation angle of the pose is less than 90°, that is, the point cloud point and the first point cloud template are matched back to back. The third case is reverse and rotation matching, that is, the point cloud point and the first point cloud template are matched back to back, and the horizontal rotation angle of the pose is greater than 90°. No matter which of the above three cases, the first changed pose cannot be directly calculated, and the first changed pose corresponding to the preset shooting device needs to be calculated based on the matching result after the coordinate transformation processing.

[0073] When judging which of the above cases the target matching result belongs to, the following method can be used for judgment. First, according to the normal vector of the plane where the first target point cloud is located, and in combination with the calculated pose, it is calculated whether the direction of the normal vector is reversed after the transformation according to the pose, for example, the original z value of the normal vector is greater than 0, and after the transformation, it becomes less than 0, which means that the reverse matching is performed. At the same time, a vector on the x axis is selected, such as (100, 0, 0), and the vector after the transformation of the vector according to the above pose is calculated, so as to judge whether the horizontal rotation exceeds 90 degrees. If the x value after the rotation becomes negative, such as -80, it means that the rotation exceeds 90 degrees. According to the two conditions, it can be judged whether the target matching result satisfies the target preset condition, and if the target preset condition is not satisfied, which of the three cases it belongs to. According to the coordinate transformation processing, the correct pose, that is, the first changed pose, can be calculated for subsequent calculation.

[0074] In the embodiment of the application, step 208 can optionally include:

[0075] Step 208-1, determining, from the second depth image, a point cloud corresponding to the second classification frame based on the second classification frame corresponding to the second charging hole set;

[0076] Step 208-2, performing plane fitting processing on the point cloud corresponding to the second classification frame to obtain a second target point cloud corresponding to the second charging hole set, and determining a second position coordinate corresponding to each point cloud point in the second target point cloud.

[0077] In this embodiment, in order to ensure the accuracy of the point cloud corresponding to the second set of charging holes, the corresponding point cloud in the second classification frame can also be subjected to plane fitting processing. Since the seven charging holes are all on the same plane, the second target point cloud corresponding to the second set of charging holes can be accurately determined through plane fitting processing.

[0078] Further, as Figure 1 The specific implementation of the method, the embodiment of the application provides a charging control device of a charging robot, as Figure 8 shown, the device comprises:

[0079] A first image acquisition module is configured to acquire a first image through a preset shooting device on the charging robot, and determine a first change pose corresponding to the preset shooting device based on a first set of charging holes contained in the first image.

[0080] A first control module is configured to control the preset shooting device to reach a first target pose based on the first change pose.

[0081] A second image acquisition module is configured to acquire a second image through the preset shooting device on the charging robot, and determine a second change pose corresponding to the preset shooting device based on a second set of charging holes contained in the second image.

[0082] A second control module is configured to control the preset shooting device to reach a second target pose based on the second change pose, so that each charging hole on a charging port of the charging robot is aligned with each charging hole on a vehicle to be charged, and the charging port is controlled to charge the vehicle to be charged. The relative position between the charging port and the preset shooting device is fixed.

[0083] Optionally, the first image comprises a first color image and a first depth image; and the first image acquisition module comprises:

[0084] A first set of charging hole determination unit is configured to input the first color image into a preset recognition model, and determine the first set of charging holes based on a first output result of the preset recognition model.

[0085] A first position coordinate determination unit is configured to determine a first position coordinate corresponding to each point cloud point in the first set of charging holes from the first depth image based on the first set of charging holes.

[0086] A first change pose determination unit is configured to determine the first change pose corresponding to the preset shooting device according to the first position coordinate corresponding to each point cloud point and a first point cloud template.

[0087] Optionally, the first position coordinate determination unit is configured to:

[0088] determine, based on the first classification box corresponding to each first charging hole in the first set of charging holes, a point cloud corresponding to each first classification box from the first depth image, and aggregate the point cloud corresponding to each first classification box; perform plane fitting processing on the aggregated point cloud to obtain a first target point cloud corresponding to the first set of charging holes, and determine a first position coordinate corresponding to each point cloud point in the first target point cloud.

[0089] Optionally, the first change pose determination unit is configured to:

[0090] match the point cloud point with the first point cloud template based on the first position coordinate corresponding to each point cloud point to obtain a target matching result; when the target matching result satisfies a target preset condition, calculate a first change pose corresponding to the preset photographing device based on the target matching result; when the target matching result does not satisfy the target preset condition, perform coordinate transformation processing based on the target matching result, and calculate the first change pose corresponding to the preset photographing device according to the matching result after the coordinate transformation processing.

[0091] Optionally, the second image includes a second color image and a second depth image; and the second image acquisition module includes:

[0092] a second charging hole set determination unit configured to input the second color image into a preset recognition model, and determine a second set of charging holes based on a second output result of the preset recognition model;

[0093] a second position coordinate determination unit configured to determine, based on the second set of charging holes, a second position coordinate corresponding to each point cloud point in the second set of charging holes from the second depth image;

[0094] a second change pose determination unit configured to determine, according to the second position coordinate corresponding to each point cloud point and a second point cloud template, a second change pose corresponding to the preset photographing device.

[0095] Optionally, the second position coordinate determination unit is configured to:

[0096] determine, based on a second classification box corresponding to the second set of charging holes, a point cloud corresponding to the second classification box from the second depth image; and perform plane fitting processing on the point cloud corresponding to the second classification box to obtain a second target point cloud corresponding to the second set of charging holes, and determine a second position coordinate corresponding to each point cloud point in the second target point cloud.

[0097] Optionally, the second control module is further configured to control the charging port to move a preset distance in a preset direction towards the vehicle to be charged, so that the charging port charges the vehicle to be charged.

[0098] It should be noted that other corresponding descriptions of the functions of the charging control device of the charging robot provided in the embodiments of the present application can be referred to the corresponding descriptions in the methods, which will not be repeated here. Figures 1 to 7

[0099] Further, the embodiments of the present application provide a charging robot, comprising the charging control device of the charging robot according to any one of the above.

[0100] Based on the above method as shown in Figures 1 to 7 Accordingly, the embodiments of the present application also provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the charging control method of the charging robot as shown in Figures 1 to 7

[0101] Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present application.

[0102] Based on the above method as shown in Figures 1 to 7 and Figure 8 The virtual device embodiment, in order to achieve the above purpose, the embodiments of the present application also provide a computer device, which can be a personal computer, a server, a network device, etc., the computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to realize the charging control method of the charging robot as shown in Figures 1 to 7

[0103] Optionally, the computer device can also include a user interface, a network interface, a camera, a radio frequency (Radio Frequency, RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface can include a display screen (Display), an input unit such as a keyboard (Keyboard), etc. The optional user interface can also include a USB interface, a card reader interface, etc. The network interface can optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0104] Those skilled in the art can understand that the structure of the computer device provided in the embodiments of the present application does not constitute a limitation on the computer device, which can include more or fewer components, or combine certain components, or different component arrangements.

[0105] ​​​The storage medium can further include an operating system and a network communication module. The operating system is a program for managing and saving hardware and software resources of a computer device and supports the running of an information processing program and other software and / or programs. The network communication module is used to realize communication between components in the storage medium and communication with other hardware and software in the entity device.

[0106] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and a necessary general hardware platform, or by hardware. The charging hole part of the vehicle to be charged can be photographed by the preset photographing device arranged on the charging robot, so that the first image can be correspondingly obtained, and the first charging hole set can be included in the first image. Then, the first change pose corresponding to the preset photographing device can be determined according to the first charging hole set included in the first image. After determining the first change pose, the preset photographing device can be controlled to reach the first target pose. Then, the charging hole part of the vehicle to be charged can be photographed again by the preset photographing device, so that the second image can be correspondingly obtained, and the second charging hole set can be included in the second image, and the second charging hole set can be all charging holes. According to the second charging hole set in the second image, the second change pose corresponding to the preset photographing device at this time can be determined. After determining the second change pose corresponding to the preset photographing device, the preset photographing device can be controlled to reach the second target pose. When the preset photographing device reaches the second target pose, the charging holes on the charging port and the charging holes on the vehicle to be charged have been accurately aligned one by one, and only a preset distance is left along the preset direction. The embodiments of the present application align twice, the first time only using part of the charging holes on the vehicle to be charged for alignment, and the second time using all the charging holes on the vehicle to be charged for alignment, which not only greatly reduces the alignment error, but also avoids the situation of mis-matching, and is conducive to ensuring the safety of charging.

[0107] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or flows in the drawings are not necessarily required for implementing the present application. Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be changed and located in one or more devices different from the implementation scenario. The modules of the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0108] The above application serial numbers are only for description, and do not represent the advantages and disadvantages of the implementation scenario. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any changes that can be thought of by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A charging control method for a charging robot, characterized in that, include: The first image is acquired by a preset shooting device on the charging robot, and the first changed pose corresponding to the preset shooting device is determined based on the first set of charging holes contained in the first image. The first set of charging holes is a collection of a portion of the charging holes of the vehicle to be charged. Based on the first changed pose, control the preset shooting device to reach the first target pose; The second image is acquired by a preset shooting device on the charging robot, and the second changing pose corresponding to the preset shooting device is determined based on the second charging hole set contained in the second image, wherein the second charging hole set is all the charging holes of the vehicle to be charged. Based on the second changed pose, the preset shooting device is controlled to reach the second target pose so that each charging port on the charging port of the charging robot is aligned with each charging port on the vehicle to be charged, and the charging port is controlled to charge the vehicle to be charged. The relative position of the charging port and the preset shooting device is fixed. The first image includes a first color image and a first depth image; determining the first changing pose corresponding to the preset shooting device based on the first charging port set contained in the first image includes: The first color image is input into a preset recognition model, and the first charging port set is determined based on the first output result of the preset recognition model. Based on the first charging hole set, determine the first position coordinates corresponding to each point cloud point in the first charging hole set from the first depth image; Based on the first position coordinates corresponding to each point cloud point and the first point cloud template, the first change pose corresponding to the preset shooting device is determined.

2. The method according to claim 1, characterized in that, The step of determining the first position coordinates corresponding to each point cloud point in the first charging port set from the first depth image based on the first charging port set includes: Based on the first classification box corresponding to each first charging hole in the first charging hole set, the point cloud corresponding to each first classification box is determined from the first depth image, and the point clouds corresponding to each first classification box are aggregated. The point cloud after aggregation is subjected to plane fitting to obtain the first target point cloud corresponding to the first charging hole set, and the first position coordinates corresponding to each point cloud point in the first target point cloud are determined.

3. The method according to claim 1, characterized in that, The step of determining the first changed pose corresponding to the preset shooting device based on the first position coordinates corresponding to each point cloud point and the first point cloud template includes: Based on the first position coordinates corresponding to each point cloud point, the point cloud points are matched with the first point cloud template to obtain the target matching result; When the target matching result meets the target preset conditions, the first changed pose corresponding to the preset shooting device is calculated based on the target matching result; When the target matching result does not meet the target preset conditions, coordinate transformation processing is performed based on the target matching result, and the first changed pose corresponding to the preset shooting device is calculated based on the matching result after coordinate transformation processing.

4. The method according to claim 1, characterized in that, The second image includes a second color image and a second depth image; determining the second changing pose corresponding to the preset shooting device based on the second charging port set contained in the second image includes: The second color image is input into a preset recognition model, and the second charging port set is determined based on the second output result of the preset recognition model; Based on the second charging hole set, determine the second position coordinates corresponding to each point cloud point in the second charging hole set from the second depth image; Based on the second position coordinates corresponding to each point cloud point and the second point cloud template, the second change pose corresponding to the preset shooting device is determined.

5. The method according to claim 4, characterized in that, The step of determining the second position coordinates corresponding to each point cloud point in the second charging hole set from the second depth image based on the second charging hole set includes: Based on the second classification box corresponding to the second charging hole set, the point cloud corresponding to the second classification box is determined from the second depth image; The point cloud corresponding to the second classification box is subjected to planar fitting processing to obtain the second target point cloud corresponding to the second charging hole set, and the second position coordinates corresponding to each point cloud point in the second target point cloud are determined.

6. The method according to claim 1, characterized in that, The control of the charging port to charge the vehicle to be charged includes: The charging port is controlled to move a preset distance toward the vehicle to be charged in a preset direction, so that the charging port can charge the vehicle to be charged.

7. A charging control device for a charging robot, characterized in that, include: The first image acquisition module is used to acquire a first image through a preset shooting device on the charging robot, and determine a first changed pose corresponding to the preset shooting device based on the first charging hole set contained in the first image, wherein the first charging hole set is a set of a portion of the charging holes of the vehicle to be charged. The first control module is used to control the preset shooting device to reach the first target pose based on the first changed pose. The second image acquisition module is used to acquire a second image through a preset shooting device on the charging robot, and determine a second changed pose corresponding to the preset shooting device based on the second charging hole set contained in the second image, wherein the second charging hole set is all the charging holes of the vehicle to be charged; The second control module is used to control the preset shooting device to reach the second target pose based on the second changed pose, so that each charging port on the charging port of the charging robot is aligned with each charging port on the vehicle to be charged, and to control the charging port to charge the vehicle to be charged. The relative position of the charging port and the preset shooting device is fixed. The first image includes a first color image and a first depth image; the first image acquisition module includes: The first charging port set determination unit is used to input the first color image into a preset recognition model and determine the first charging port set based on the first output result of the preset recognition model. The first position coordinate determination unit is used to determine the first position coordinates corresponding to each point cloud point in the first charging hole set from the first depth image based on the first charging hole set. The first pose change determination unit is used to determine the first pose change corresponding to the preset shooting device based on the first position coordinates corresponding to each point cloud point and the first point cloud template.

8. The apparatus according to claim 7, characterized in that, The first position coordinate determination unit is used for: Based on the first classification box corresponding to each first charging hole in the first charging hole set, the point cloud corresponding to each first classification box is determined from the first depth image, and the point clouds corresponding to each first classification box are aggregated. The point cloud after aggregation is subjected to plane fitting to obtain the first target point cloud corresponding to the first charging hole set, and the first position coordinates corresponding to each point cloud point in the first target point cloud are determined.

9. The apparatus according to claim 7, characterized in that, The first pose change determination unit is used for: Based on the first position coordinates corresponding to each point cloud point, the point cloud points are matched with the first point cloud template to obtain a target matching result; when the target matching result meets the target preset conditions, the first change pose corresponding to the preset shooting device is calculated based on the target matching result. When the target matching result does not meet the target preset conditions, coordinate transformation processing is performed based on the target matching result, and the first changed pose corresponding to the preset shooting device is calculated based on the matching result after coordinate transformation processing.

10. The apparatus according to claim 7, characterized in that, The second image includes a second color image and a second depth image; The second image acquisition module includes: The second charging port set determination unit is used to input the second color image into a preset recognition model and determine the second charging port set based on the second output result of the preset recognition model. The second position coordinate determination unit is used to determine the second position coordinates corresponding to each point cloud point in the second charging hole set from the second depth image based on the second charging hole set. The second pose determination unit is used to determine the second pose corresponding to the preset shooting device based on the second position coordinates corresponding to each point cloud point and the second point cloud template.

11. The apparatus according to claim 10, characterized in that, The second position coordinate determination unit is used for: Based on the second classification box corresponding to the second charging hole set, the point cloud corresponding to the second classification box is determined from the second depth image; The point cloud corresponding to the second classification box is subjected to planar fitting processing to obtain the second target point cloud corresponding to the second charging hole set, and the second position coordinates corresponding to each point cloud point in the second target point cloud are determined.

12. The apparatus according to claim 7, characterized in that, The second control module is also used to control the charging port to move a preset distance toward the vehicle to be charged in a preset direction, so that the charging port can charge the vehicle to be charged.

13. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

14. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

15. A charging robot, characterized in that, The charging control device includes the charging robot according to any one of claims 7 to 12.

Images