Intelligent inspection mobile robot-based charging gun identification and grabbing method and system

Abstract

The application provides a charging gun recognition and grabbing method and system based on an intelligent inspection mobile robot, which comprises the following steps: collecting image information of a charging pile area based on the intelligent inspection mobile robot, and processing the image information; guiding the intelligent inspection mobile robot to move according to the scattering position; detecting key points of the charging gun according to the processed image information, and extracting key points at both ends of the handle of the charging gun; generating a plurality of grabbing poses based on the key points at both ends of the handle, and screening an optimal grabbing pose from the plurality of grabbing poses based on collision detection; planning a motion trajectory of a mechanical arm gripper of the intelligent inspection mobile robot according to the optimal grabbing pose, and enabling the mechanical arm gripper to perform a grabbing action to grab the charging gun to a specified position. The application can grab the scattered charging gun and place it in a safe area or the original position, thereby avoiding unexpected situations.

Description

Technical Field

[0001] This invention relates to the field of robot control technology, and in particular to a method and system for identifying and grasping charging guns based on an intelligent inspection mobile robot. Background Technology

[0002] After using a charging station, many car owners fail to return the charging guns to their original positions, leaving them scattered throughout the parking area, obstructing parking and potentially damaging them. Therefore, this invention addresses this issue by using an intelligent mobile inspection robot to identify and retrieve the scattered charging guns, placing them in a safe area or their original location. Currently, no relevant technical literature has been found regarding this application scenario. Most applications of charging gun retrieval are used in automated robotic charging scenarios.

[0003] In existing technologies, the grasping of charging guns is mostly applied in robotic automatic charging scenarios, and its function is limited. Moreover, at present, there is a lack of corresponding intelligent inspection mobile robots to handle the abnormal situation of charging guns scattered on the ground. Summary of the Invention

[0004] Therefore, the purpose of this invention is to provide a charging gun identification and grasping method and system based on an intelligent inspection mobile robot, so as to solve the shortcomings of the prior art.

[0005] This invention provides the following technical solution: a method for identifying and grasping charging guns based on an intelligent inspection mobile robot, the method comprising:

[0006] The intelligent inspection mobile robot collects image information of the charging pile area and processes the image information.

[0007] The location of the scattered charging guns is identified based on the processed image information, and the intelligent inspection mobile robot is guided to move according to the location of the scattered guns.

[0008] Based on the processed image information, the key points of the charging gun are detected, and the key points at both ends of the handle of the charging gun are extracted.

[0009] Several grasping poses are generated based on the key points at both ends of the handle, and the optimal grasping pose is selected from the several grasping poses based on collision detection.

[0010] The motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot is planned according to the optimal grasping pose, and the robotic arm gripper performs a grasping action to grasp the charging gun to the designated position.

[0011] Compared with the prior art, the beneficial effects of the present invention are: by using an intelligent inspection mobile robot to inspect the parking lot, and by identifying the scattered locations of the charging guns, and determining the grasping posture based on the key points of the charging guns and the key points at both ends of the handle, and selecting the optimal grasping posture, the scattered charging guns can be grasped and placed in a safe area or in their original position to avoid accidents.

[0012] Furthermore, the step of collecting image information of the charging pile area based on the intelligent inspection mobile robot and processing the image information includes:

[0013] Acquire RGB image data of the charging gun from the RGB-D camera on the intelligent inspection mobile robot;

[0014] The RGB image data is sequentially subjected to size adjustment, normalization, color space conversion, and noise reduction.

[0015] Furthermore, the step of acquiring the RGB image data of the charging gun collected by the RGB-D camera on the intelligent inspection mobile robot includes:

[0016] Acquire distant RGB image data and near RGB image data from the RGB-D camera on the intelligent inspection mobile robot while it is in motion;

[0017] The charging gun image in the distant RGB image data is labeled, and the charging gun and key point images of the charging gun in the nearby RGB image are also labeled.

[0018] Furthermore, the step of detecting key points of the charging gun based on the processed image information includes:

[0019] Establish a YOLO-chargingGun model;

[0020] The image information is labeled, and the YOLO-chargingGun model is trained based on the labeled image information;

[0021] The key points of the charging gun in the image information are detected based on the trained YOLO-chargingGun model.

[0022] Furthermore, the step of generating several grasping poses based on the key points at both ends of the handle includes:

[0023] Obtain the three-dimensional coordinates of several points in the line interval connecting the key points at both ends of the handle, and use the three-dimensional coordinates of the several points as the gripping center point of the robotic arm gripper of the intelligent inspection mobile robot.

[0024] By combining the connection of key points at both ends of the handle of the charging gun and the gripping width of the charging gun, several gripping poses are generated with the gripping center point.

[0025] Secondly, the present invention also provides a charging gun identification and grasping system based on an intelligent inspection mobile robot, the system comprising:

[0026] The data acquisition and processing module is used to acquire image information of the charging pile area based on the intelligent inspection mobile robot, and to process the image information.

[0027] The identification and guidance module is used to identify the location of the scattered charging guns based on the processed image information, and guide the intelligent inspection mobile robot to move according to the location of the scattered guns.

[0028] The detection and extraction module is used to detect key points of the charging gun based on the processed image information, and extract the key points at both ends of the handle of the charging gun.

[0029] The selection generation module is used to generate several grasping poses based on the key points at both ends of the handle, and to select the optimal grasping pose from the several grasping poses based on collision detection.

[0030] The planning and grasping module is used to plan the motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot according to the optimal grasping pose, and to make the robotic arm gripper perform a grasping action to grasp the charging gun to the designated position.

[0031] Furthermore, the acquisition and processing module includes:

[0032] The first acquisition unit is used to acquire RGB image data of the charging gun collected by the RGB-D camera on the intelligent inspection mobile robot;

[0033] The processing unit is used to sequentially perform size adjustment, normalization, color space conversion, and noise reduction on the RGB image data.

[0034] Furthermore, the first acquisition unit includes:

[0035] The acquisition subunit is used to acquire distant RGB image data and near RGB image data collected by the RGB-D camera on the intelligent inspection mobile robot in the moving state, respectively.

[0036] The annotation subunit is used to annotate the charging gun image in the distant RGB image data, and to annotate the charging gun and key point images of the charging gun in the nearby RGB image.

[0037] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described charging gun identification and grasping method based on an intelligent inspection mobile robot.

[0038] Fourthly, the present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for identifying and grasping charging guns based on an intelligent inspection mobile robot. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart of the charging gun identification and grasping method based on an intelligent inspection mobile robot in the first embodiment of the present invention.

[0041] Figure 2 This is a structural block diagram of the charging gun identification and grasping system based on an intelligent inspection mobile robot according to the second embodiment of the present invention.

[0042] Figure 3 This is a schematic diagram of the structure of the electronic device in the third embodiment of the present invention.

[0043] Explanation of key component symbols:

[0044] 10. Data Acquisition and Processing Module; 20. Recognition and Guidance Module; 30. Detection and Extraction Module; 40. Selection Generation Module; 50. Planning and Grabbing Module;

[0045] 60. Bus; 61. Processor; 62. Memory; 63. Communication interface.

[0046] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0048] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] Example 1

[0051] Please see Figure 1 The figure shows a charging gun identification and grasping method based on an intelligent inspection mobile robot according to the first embodiment of the present invention. The method includes steps S1 to S5:

[0052] S1, Based on the intelligent inspection mobile robot, image information of the charging pile area is collected and the image information is processed;

[0053] Specifically, step S1 includes steps S11 to S12:

[0054] S11, acquire the RGB image data of the charging gun collected by the RGB-D camera on the intelligent inspection mobile robot;

[0055] Furthermore, step S11 includes steps S111 to S112:

[0056] S111, respectively acquire the distant RGB image data and the near RGB image data collected by the RGB-D camera on the intelligent inspection mobile robot in the moving state;

[0057] S112, label the charging gun image in the distant RGB image data, and label the charging gun and key point images of the charging gun in the nearby RGB image;

[0058] S12, the RGB image data is sequentially subjected to size adjustment, normalization, color space conversion and noise reduction processing;

[0059] It should be noted that a large amount of RGB image data of the charging gun was collected using an RGB-D camera from both near and far distances. For images of the charging gun collected from a distance, only the target bounding box was marked. For images of the charging gun collected from a distance, in addition to marking the target bounding box, the key points also needed to be marked.

[0060] S2, based on the processed image information, identify the location where the charging guns are scattered, and guide the intelligent inspection mobile robot to move according to the location where they are scattered;

[0061] It should be noted that the intelligent inspection mobile robot is guided to move based on the location of the charging guns scattered on the ground in the image information, and moves to the vicinity of the scattered charging guns.

[0062] It is worth noting that the intelligent inspection mobile robot will continuously collect image information while moving, and can detect, identify and report abnormal situations such as goods piled up in the parking lot, two-wheeled vehicles illegally parked, and car windows not closed.

[0063] S3, detect the key points of the charging gun based on the processed image information, and extract the key points at both ends of the handle of the charging gun.

[0064] Specifically, step S3 includes steps S31 to S33:

[0065] S31, Establish the YOLO-chargingGun model;

[0066] S32, annotate the image information, and train the YOLO-chargingGun model based on the annotated image information;

[0067] S33, Detect the key points of the charging gun in the image information based on the trained YOLO-chargingGun model;

[0068] It should be noted that the charging gun in the distant RGB image data and the charging gun in the nearby RGB image data are regarded as two types of targets. A YOLO-chargingGun algorithm model that can detect and identify both types of targets is constructed. The algorithm model is trained with labeled data and outputs an algorithm model with good convergence.

[0069] S4, generate several grasping poses based on the key points at both ends of the handle, and select the optimal grasping pose from the several grasping poses based on collision detection.

[0070] Specifically, step S4 includes steps S41 to S42:

[0071] S41, obtain the three-dimensional coordinates of several points in the line interval connecting the key points at both ends of the handle, and use the three-dimensional coordinates of the several points as the gripping center point of the mechanical arm gripper of the intelligent inspection mobile robot.

[0072] S42, combining the connection of key points at both ends of the handle of the charging gun and the gripping width of the charging gun, and generating several gripping poses with the gripping center point;

[0073] It should be noted that the key points at both ends of the handle are obtained by the YOLO-chargingGun model detection and recognition algorithm after training. The three-dimensional coordinates of the midpoint of the line connecting the key points at both ends of the handle are obtained by the RGB-D camera and used as the gripping center point of the robotic arm gripper. The opening and closing direction of the two-finger gripper is perpendicular to the line connecting the key points at both ends of the handle. Combined with the actual gripping width of the charging gun handle, several approximately perpendicular gripping poses are generated.

[0074] S5, based on the optimal grasping pose, plan the motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot, and make the robotic arm gripper perform a grasping action to grasp the charging gun to the designated position;

[0075] It should be noted that collision detection is performed on the generated grasping pose to select the optimal grasping pose. Based on the optimal grasping pose, the motion trajectory of the robotic arm gripper is planned, and the robotic arm performs the grasping action to place the charging gun behind the car's stop lever / stopper.

[0076] In summary, the charging gun identification and grasping method based on an intelligent inspection mobile robot in the above embodiments of the present invention uses an intelligent inspection mobile robot to inspect parking lots, identifies the scattered locations of charging guns, determines the grasping posture based on key points of the charging guns and the key points at both ends of the handle, and selects the optimal grasping posture. This allows the scattered charging guns to be grasped and placed in a safe area or their original location, avoiding accidents. In addition to detecting and identifying daily environmental anomalies in parking lots, the intelligent inspection mobile robot can also handle the anomaly of charging guns scattered on the ground. Compared with grasping posture estimation algorithms such as AnyGrasp, GraspNet, and Contact GraspNet, which do not limit the grasping target, this method can greatly improve the grasping success rate and shorten the grasping response time.

[0077] Example 2

[0078] The second embodiment of the present invention also provides a charging gun identification and grasping system based on an intelligent inspection mobile robot. Please refer to [link to relevant documentation]. Figure 2 The figure shows a charging gun identification and grasping system based on an intelligent inspection mobile robot according to the second embodiment of the present invention. The system includes:

[0079] The data acquisition and processing module 10 is used to acquire image information of the charging pile area based on the intelligent inspection mobile robot, and to process the image information.

[0080] The identification and guidance module 20 is used to identify the location of the scattered charging guns based on the processed image information, and guide the intelligent inspection mobile robot to move according to the location of the scattered charging guns.

[0081] The detection and extraction module 30 is used to detect the key points of the charging gun based on the processed image information, and extract the key points at both ends of the handle of the charging gun.

[0082] The selection module 40 is used to generate several grasping poses based on the key points at both ends of the handle, and to select the optimal grasping pose from the several grasping poses based on collision detection.

[0083] The planning and grasping module 50 is used to plan the motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot according to the optimal grasping pose, and to make the robotic arm gripper perform a grasping action to grasp the charging gun to the designated position.

[0084] Specifically, in some optional embodiments, the acquisition and processing module 10 includes:

[0085] The first acquisition unit is used to acquire RGB image data of the charging gun collected by the RGB-D camera on the intelligent inspection mobile robot;

[0086] The processing unit is used to sequentially perform size adjustment, normalization, color space conversion, and noise reduction on the RGB image data.

[0087] Specifically, in some optional embodiments, the first acquisition unit includes:

[0088] The acquisition subunit is used to acquire distant RGB image data and near RGB image data collected by the RGB-D camera on the intelligent inspection mobile robot in the moving state, respectively.

[0089] The annotation subunit is used to annotate the charging gun image in the distant RGB image data, and to annotate the charging gun and key point images of the charging gun in the nearby RGB image.

[0090] Specifically, in some optional embodiments, the detection and extraction module 30 includes:

[0091] Establish a unit for building the YOLO-chargingGun model;

[0092] The annotation unit is used to annotate the image information and train the YOLO-chargingGun model based on the annotated image information;

[0093] The detection unit is used to detect key points of the charging gun in the image information based on the trained YOLO-chargingGun model.

[0094] Specifically, in some optional embodiments, the selection generation module 40 includes:

[0095] The second acquisition unit is used to acquire the three-dimensional coordinates of several points in the line interval connecting the key points at both ends of the handle, and to use the three-dimensional coordinates of the several points as the gripping center point of the mechanical arm gripper of the intelligent inspection mobile robot.

[0096] The combined generation unit is used to combine the connection of key points at both ends of the handle of the charging gun and the gripping width of the charging gun, and generate several gripping poses with the gripping center point.

[0097] The functions or operation steps implemented by the above modules and units are largely the same as those in the above method embodiments, and will not be repeated here.

[0098] The charging gun identification and grasping system based on an intelligent inspection mobile robot provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0099] Example 3

[0100] The third embodiment of the present invention also proposes an electronic device, please refer to [link / reference]. Figure 3 The image shows an electronic device according to a third embodiment of the present invention.

[0101] The electronic device may include a processor 61 and a memory 62 storing computer program instructions.

[0102] Specifically, the processor 61 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the present application.

[0103] The memory 62 may include a large-capacity storage device for data or instructions. For example, and not limitingly, the memory 62 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 62 may include removable or non-removable (or fixed) media. Where appropriate, the memory 62 may be internal or external to a data processing device. In a particular embodiment, the memory 62 is non-volatile memory. In a particular embodiment, the memory 62 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0104] The memory 62 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 61.

[0105] The processor 61 reads and executes the computer program instructions stored in the memory 62 to implement the charging gun identification and grasping method based on the intelligent inspection mobile robot described in Embodiment 1.

[0106] In some embodiments, the electronic device may further include a communication interface 63 and a bus 60. For example, Figure 3 As shown, the processor 61, memory 62, and communication interface 63 are connected through bus 60 and complete communication with each other.

[0107] The communication interface 63 is used to enable communication between the various modules, devices, units, and / or equipment in this application. The communication interface 63 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0108] Bus 60 includes hardware, software, or both, that couples components of a device together. Bus 60 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 60 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 60 may include one or more buses. Although this application describes and illustrates a specific bus, this application considers any suitable bus or interconnection.

[0109] The electronic device can acquire the charging gun identification and grasping system based on the intelligent inspection mobile robot and execute the charging gun identification and grasping method based on the intelligent inspection mobile robot in this embodiment.

[0110] Furthermore, in conjunction with the charging gun identification and grasping method based on an intelligent inspection mobile robot in Embodiment 1 above, this application can provide a storage medium for implementation. This storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the charging gun identification and grasping method based on an intelligent inspection mobile robot in Embodiment 1 above.

[0111] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0112] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for identifying and grasping charging guns based on an intelligent inspection mobile robot, characterized in that, The method includes: The intelligent inspection mobile robot collects image information of the charging pile area and processes the image information. The location of the scattered charging guns is identified based on the processed image information, and the intelligent inspection mobile robot is guided to move according to the location of the scattered guns. Based on the processed image information, the key points of the charging gun are detected, and the key points at both ends of the handle of the charging gun are extracted. Several grasping poses are generated based on the key points at both ends of the handle, and the optimal grasping pose is selected from the several grasping poses based on collision detection. The motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot is planned according to the optimal grasping pose, and the robotic arm gripper performs a grasping action to grasp the charging gun to the designated position.

2. The charging gun identification and grasping method based on an intelligent inspection mobile robot according to claim 1, characterized in that, The steps of collecting image information of the charging pile area based on the intelligent inspection mobile robot and processing the image information include: Acquire RGB image data of the charging gun from the RGB-D camera on the intelligent inspection mobile robot; The RGB image data is sequentially subjected to size adjustment, normalization, color space conversion, and noise reduction.

3. The charging gun identification and grasping method based on an intelligent inspection mobile robot according to claim 2, characterized in that, The step of acquiring the RGB image data of the charging gun based on the RGB-D camera on the intelligent inspection mobile robot includes: Acquire distant RGB image data and near RGB image data from the RGB-D camera on the intelligent inspection mobile robot while it is in motion; The charging gun image in the distant RGB image data is labeled, and the charging gun and key point images of the charging gun in the nearby RGB image are also labeled.

4. The charging gun identification and grasping method based on an intelligent inspection mobile robot according to claim 1, characterized in that, The step of detecting key points of the charging gun based on the processed image information includes: Establish a YOLO-chargingGun model; The image information is labeled, and the YOLO-chargingGun model is trained based on the labeled image information; The key points of the charging gun in the image information are detected based on the trained YOLO-chargingGun model.

5. The charging gun identification and grasping method based on an intelligent inspection mobile robot according to claim 1, characterized in that, The step of generating several grasping poses based on key points at both ends of the handle includes: Obtain the three-dimensional coordinates of several points in the line interval connecting the key points at both ends of the handle, and use the three-dimensional coordinates of the several points as the gripping center point of the robotic arm gripper of the intelligent inspection mobile robot. By combining the connection of key points at both ends of the handle of the charging gun and the gripping width of the charging gun, several gripping poses are generated with the gripping center point.

6. A charging gun identification and grasping system based on an intelligent inspection mobile robot, characterized in that, The system includes: The data acquisition and processing module is used to acquire image information of the charging pile area based on the intelligent inspection mobile robot, and to process the image information. The identification and guidance module is used to identify the location of the scattered charging guns based on the processed image information, and guide the intelligent inspection mobile robot to move according to the location of the scattered guns. The detection and extraction module is used to detect key points of the charging gun based on the processed image information, and extract the key points at both ends of the handle of the charging gun. The selection generation module is used to generate several grasping poses based on the key points at both ends of the handle, and to select the optimal grasping pose from the several grasping poses based on collision detection. The planning and grasping module is used to plan the motion trajectory of the robotic arm gripper of the intelligent inspection mobile robot according to the optimal grasping pose, and to make the robotic arm gripper perform a grasping action to grasp the charging gun to the designated position.

7. The charging gun identification and grasping system based on an intelligent inspection mobile robot according to claim 6, characterized in that, The acquisition and processing module includes: The first acquisition unit is used to acquire RGB image data of the charging gun collected by the RGB-D camera on the intelligent inspection mobile robot; The processing unit is used to sequentially perform size adjustment, normalization, color space conversion, and noise reduction on the RGB image data.

8. The charging gun identification and grasping system based on an intelligent inspection mobile robot according to claim 7, characterized in that, The first acquisition unit includes: The acquisition subunit is used to acquire distant RGB image data and near RGB image data collected by the RGB-D camera on the intelligent inspection mobile robot in the moving state, respectively. The annotation subunit is used to annotate the charging gun image in the distant RGB image data, and to annotate the charging gun and key point images of the charging gun in the nearby RGB image.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the charging gun identification and grasping method based on the intelligent inspection mobile robot as described in any one of claims 1 to 5.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the charging gun identification and grasping method based on the intelligent inspection mobile robot as described in any one of claims 1 to 5.

Images