CN110756462A

CN110756462A - Power adapter test method, device, system, control device and storage medium

Info

Publication number: CN110756462A
Application number: CN201910905696.5A
Authority: CN
Inventors: 李豪; 麦礼文; 马麟; 卢韶安
Original assignee: Luban's Robot (shenzhen) Co Ltd
Current assignee: Baohui Technology (Longnan) Co., Ltd; ROBOTICS ROBOTICS (SHENZHEN) Ltd.
Priority date: 2019-09-24
Filing date: 2019-09-24
Publication date: 2020-02-07
Anticipated expiration: 2039-09-24
Also published as: CN110756462B

Abstract

The embodiment of the application discloses a power adapter testing method, a power adapter testing device, a power adapter control device and a storage medium, wherein the method comprises the following steps: acquiring a first image, wherein the first image comprises a first end plug of a power adapter and/or a grabbing device; generating a first control instruction according to the first image, and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and inserting the first end plug into a socket of the test platform; acquiring a second image, wherein the second image comprises a second end plug of the power adapter and/or a grabbing device; and generating a second control instruction according to the second image, and sending the second control instruction to the gripping device, wherein the second control instruction is used for indicating the gripping device to grip a second end plug to be inserted into a socket of the test platform so as to test the power adapter, and obtaining a test result. The embodiment of the application can realize the automatic test of the power adapter, reduce the production cost and improve the production efficiency and the test accuracy.

Description

Power adapter test method, device, system, control device and storage medium

Technical Field

The present application relates to the field of testing technologies, and in particular, to a method, an apparatus, a system, a control apparatus, and a computer-readable storage medium for testing a power adapter.

Background

With the development and progress of social progress, the demand of electronic products is also sharply increased day by day.

Electronic products generally require a power adapter for charging. The power adapter is a power supply voltage conversion device for small portable electronic equipment and electronic appliances, and is commonly used in small electronic products such as mobile phones, liquid crystal displays and notebook computers. After the power adapter is produced, the power adapter can enter the market after being tested to be qualified.

At present, the test of the power adapter is generally completed manually, that is, different power test instruments are manually operated for many times, and the test result of each instrument is recorded, or a combined test instrument is manually operated, and all tests can be completed through one operation. The manual test needs to consume a large amount of labor force, has increased manufacturing cost, and in addition, the manual test easily appears misoperation, and the test accuracy is lower.

Disclosure of Invention

In view of this, embodiments of the present application provide a method, an apparatus, a system, a control apparatus, and a computer readable storage medium for testing a power adapter, so as to solve the problems of high cost and low test accuracy of the conventional power adapter test.

A first aspect of an embodiment of the present application provides a power adapter testing method, including:

acquiring a first image, wherein the first image comprises a first end plug of a power adapter and/or a grabbing device;

generating a first control instruction according to the first image, and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and inserting the first end plug into a socket of a test platform;

acquiring a second image, wherein the second image comprises a second end plug of the power adapter and/or a grabbing device;

and generating a second control instruction according to the second image, and sending the second control instruction to the grabbing device, wherein the second control instruction is used for instructing the grabbing device to grab the second end plug to be inserted into the socket of the test platform so as to test the power adapter, and a test result is obtained.

With reference to the first aspect, in a possible implementation manner, the generating a first control instruction according to the first image includes:

obtaining first target pose information according to the first image;

and generating the first control instruction according to the first target pose information.

With reference to the first aspect, in a possible implementation manner, the generating a second control instruction according to the second image includes:

obtaining second target pose information according to the second image;

and generating the second control instruction according to the second target pose information.

With reference to the first aspect, in a possible implementation manner, the obtaining first target pose information according to the first image includes:

acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

inputting the first image data into the first gesture recognition model, and outputting first target pose information;

or

Acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

inputting the first image data into the first gesture recognition model, and outputting a first recognition result of feature information associated with the first terminal plug in the image data;

and obtaining first target pose information according to the first recognition result.

With reference to the first aspect, in a possible implementation manner, the obtaining second object pose information according to the second image includes:

acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

inputting the second image data into the second gesture recognition model, and outputting second target pose information;

or

Acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

inputting the second image data into the second gesture recognition model, and outputting a second recognition result of the feature information associated with the second terminal plug in the image data;

and obtaining second target pose information according to the second recognition result.

grabbing the first end plug according to the first image and a first preset grabbing strategy;

generating a third control instruction and sending the third control instruction to the gripping device, wherein the third control instruction is used for instructing the gripping device to move the first end plug to a first preset position;

acquiring an image of the first end plug at the first preset position;

calculating first position and posture adjustment information of the first end plug according to the image of the first end plug;

and generating the first control instruction according to the first posture adjustment information.

With reference to the first aspect, in a possible implementation manner, after the capturing the first end plug, the method further includes:

judging whether the grabbing is successful;

and when the grabbing is successful, the step of generating a third control instruction and sending the third control instruction to the grabbing device is carried out.

With reference to the first aspect, in a possible implementation manner, the generating the second control instruction according to the second image includes:

grabbing the second end plug according to the second image and a second preset grabbing strategy;

generating a fourth control instruction, and sending the fourth control instruction to the gripping device, wherein the fourth control instruction is used for instructing the gripping device to move the second end plug to a second preset position;

acquiring an image of the second end plug at the second preset position;

calculating second position and posture adjustment information of the second end plug according to the image of the second end plug;

and generating the second control instruction according to the second posture adjustment information.

With reference to the first aspect, in a possible implementation manner, after grabbing the second end plug, the method further includes:

judging whether the grabbing is successful;

and when the grabbing is successful, the step of generating a fourth control instruction and sending the fourth control instruction to the grabbing device is carried out.

With reference to the first aspect, in a possible implementation manner, after the calculating first pose adjustment information of the first end plug according to the image of the first end plug, the method further includes:

judging whether the grabbing device meets a first position adjustment condition or not according to the first position adjustment information;

when the grabbing device meets the first position and posture adjusting condition, the step of generating the first control instruction according to the first position and posture adjusting information is carried out;

and when the grabbing device does not meet the first posture adjustment condition, generating a first removal control instruction, and sending the first removal control instruction to the grabbing device, wherein the first removal control instruction is used for indicating the grabbing device to release the first end plug and remove the power adapter.

With reference to the first aspect, in a possible implementation manner, after the calculating pose adjustment information of the second end plug according to the image of the second end plug, the method further includes:

judging whether the grabbing device meets a second position and posture adjusting condition or not according to the second position and posture adjusting information;

when the grabbing device meets the second position and posture adjusting condition, the step of generating a second control instruction according to the second position and posture adjusting information is carried out;

and when the grabbing device does not meet the second position and posture adjustment condition, generating a second removal control instruction, and sending the second removal control instruction to the grabbing device, wherein the second removal control instruction is used for indicating the grabbing device to release the second end plug and remove the power adapter.

With reference to the first aspect, in a possible implementation manner, before the acquiring the second image, the method further includes:

judging whether the second end plug is in a static state or not;

and entering the step of acquiring a second image when the second end plug is in the static state.

With reference to the first aspect, in a possible implementation manner, after the testing the power adapter to obtain a test result, the method further includes:

obtaining the test result;

and generating a classification instruction according to the test result, wherein the classification instruction is used for instructing a classification device to classify the power adapter.

With reference to the first aspect, in a possible implementation manner, after obtaining second target pose information according to the second image, the method further includes:

judging whether the second end plug is successfully identified or not according to the second target pose information;

and when the second end plug is successfully identified, the step of generating the second control instruction according to the second target pose information is carried out.

A second aspect of the embodiments of the present application provides a power adapter testing apparatus, including:

the first image acquisition module is used for acquiring a first image, and the first image comprises a first end plug of the power adapter and/or a grabbing device;

the first control module is used for generating a first control instruction according to the first image and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and inserting the first end plug into a socket of a test platform;

the second image acquisition module is used for acquiring a second image, and the second image comprises a second end plug of the power adapter and/or a grabbing device;

and the second control module is used for generating a second control instruction according to the second image and sending the second control instruction to the grabbing device, and the second control instruction is used for indicating the grabbing device to grab the second end plug to be inserted into the socket of the test platform so as to test the power adapter and obtain a test result.

With reference to the second aspect, in a possible implementation manner, the first control module includes:

the first identification unit is used for obtaining first target pose information according to the first image;

and the first generation unit is used for generating the first control instruction according to the first target pose information.

With reference to the second aspect, in one possible implementation manner, the second control module includes:

the second identification unit is used for obtaining second target pose information according to the second image;

and the second generating unit is used for generating the second control instruction according to the second target pose information.

With reference to the second aspect, in a possible implementation manner, the first identifying unit is specifically configured to:

acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

or

Acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

With reference to the second aspect, in a possible implementation manner, the second identifying unit is specifically configured to:

acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

or

Acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

With reference to the second aspect, in a possible implementation manner, the first generating unit is specifically configured to:

grabbing the first end plug according to the first target pose information and a first preset grabbing strategy;

acquiring an image of the first end plug at the first preset position;

With reference to the second aspect, in a possible implementation manner, the first generating unit is further configured to:

judging whether the grabbing is successful;

With reference to the second aspect, in a possible implementation manner, the second generating unit is specifically configured to:

grabbing the second end plug according to the second target pose information and a second preset grabbing strategy;

acquiring an image of the second end plug at the second preset position;

With reference to the second aspect, in a possible implementation manner, the second generating unit is further specifically configured to:

judging whether the grabbing is successful;

With reference to the second aspect, in a possible implementation manner, the first generating unit is further specifically configured to:

With reference to the second aspect, in a possible implementation manner, the method further includes:

the judging module is used for judging whether the second end plug is in a static state or not;

and the entering module is used for entering the step of acquiring the second image when the second end plug is in the static state.

the test result acquisition module is used for acquiring the test result;

and the classification module is used for generating a classification instruction according to the test result, and the classification instruction is used for instructing a classification device to classify the power adapter.

With reference to the second aspect, in a possible implementation manner, the second control module further includes:

the judging unit is used for judging whether the second end plug is successfully identified or not according to the second target pose information;

and the entering unit is used for entering the step of generating the second control instruction according to the second target pose information when the second end plug is successfully identified.

A third aspect of the embodiments of the present application provides a power adapter testing system, including a control device, an image acquisition device, a gripping device, and a testing platform, where the control device is respectively in communication connection with the gripping device, the image acquisition device, and the testing platform;

the grabbing device is used for executing corresponding operation according to the control instruction of the control device;

the test platform is used for testing the power adapter; wherein the test platform comprises a socket corresponding to a plug of the power adapter;

the image acquisition device is used for acquiring images;

the control device is used for acquiring a first image, and the first image comprises a first end plug of the power adapter and/or a grabbing device; generating a first control instruction according to the first image, and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and inserting the first end plug into a socket of a test platform; acquiring a second image, wherein the second image comprises a second end plug of the power adapter and/or a grabbing device; and generating a second control instruction according to the second image, and sending the second control instruction to the grabbing device, wherein the second control instruction is used for instructing the grabbing device to grab the second end plug to be inserted into the socket of the test platform so as to test the power adapter, and a test result is obtained.

A fourth aspect of embodiments of the present invention provides a control apparatus, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of the first aspect when executing the computer program.

A fifth aspect of embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, implements the steps of the method according to any one of the first aspects.

According to the embodiment of the application, a first image control grabbing device of the power adapter grabs a first end plug of the power adapter and inserts the first end plug into the test platform; the second image control grabbing device of the power adapter grabs the second end plug and inserts the second end plug into the test platform, and finally the test is carried out to obtain a test result, so that the automatic test of the power adapter is realized, the production cost is reduced, and the production efficiency and the test accuracy are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic block diagram of an architecture of a power adapter test system according to an embodiment of the present disclosure;

FIG. 2 is a schematic block diagram illustrating a flow chart of a power adapter testing method according to an embodiment of the present disclosure;

FIG. 3 is a schematic block diagram of a process for pose identification provided by an embodiment of the present application;

FIG. 4 is a schematic block diagram of another flow of a pose identification process provided by an embodiment of the present application;

fig. 5 is a schematic block diagram of a first control instruction generation flow provided in an embodiment of the present application;

FIG. 6 is a schematic block diagram of another flow of a pose identification process provided by an embodiment of the present application;

FIG. 7 is a schematic block diagram of another flow of a pose identification process provided by an embodiment of the present application;

fig. 8 is a schematic block diagram of a second control instruction generation flow provided in an embodiment of the present application;

fig. 9 is a schematic block diagram of a process of calculating pose adjustment information according to an embodiment of the present application;

fig. 10 is a schematic block diagram of a process of determining a pose adjustment condition according to an embodiment of the present application;

FIG. 11 is a block diagram schematically illustrating a structure of a power adapter testing apparatus according to an embodiment of the present disclosure;

fig. 12 is a schematic diagram of a control device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application.

Before specifically introducing the technical solutions provided in the embodiments of the present application, an application scenario and a system architecture that may be involved in the embodiments of the present application are described as examples.

The technical scheme provided by the embodiment of the application can be particularly applied to a power adapter production line, and the assembled power adapter is placed on the conveyor belt and moves along with the movement of the conveyor belt. And when a certain power adapter reaches a certain position, controlling the conveyor belt to stop. Specifically, the position of the power adapter is detected through an optical fiber sensor on the conveyor belt, or multi-system cooperative scheduling is performed through a scheduler, and the scheduler controls the conveyor belt to stop according to state information; then shooting an image of the power adapter on the conveyor belt through a camera, and identifying the pose of the power adapter according to the image; then controlling an end effector of the manipulator to grab a first end plug on the conveyor belt according to the pose of the power adapter, and inserting the first end plug into a first socket on the test platform; shooting an image of the power adapter on the test platform through a camera, and identifying the pose of the second end plug through the image; controlling an end effector of the manipulator to grab the second end plug according to the pose of the second end plug, and inserting the second end plug into a second end socket on the test rack; and finally, testing the power adapter on the test rack to obtain a test result.

Of course, the technical solution provided in the embodiment of the present application may also be applied to other scenarios, which are not limited herein. For example, in another scenario, a storage location for the power adapter is preset, the power adapter can be manually placed in the storage location, and then the manipulator picks up the power adapter from the storage location and inserts the power adapter into the test platform.

The automatic test scheme of the power adapter needs to be completed based on an automatic test system of the power adapter, which may include, but is not limited to, a manipulator, a camera, a test platform, a control device, and the like.

The power adapter generally includes a first end plug, which may be an ac end plug or a dc end plug, and a second end plug, which is a dc end plug or an ac end plug, respectively. The alternating current end plug is used for being connected with an alternating current socket, and the direct current end plug is used for being connected with a corresponding electronic product. The first end plug and the second end plug are connected through a power line. In the embodiment of the present application, the model and the type of the power adapter may be arbitrary, that is, the embodiment of the present application may test any model and any type of power adapter.

Referring to fig. 1, a schematic block diagram of an architecture of a power adapter testing system provided in an embodiment of the present application may include a control device 11, a grasping device 12, an image capturing device 13, and a testing platform 14, where the control device is in communication connection with the grasping device, the testing platform, and the image capturing device, respectively.

The image acquisition device is used for acquiring a required image; the gripping device is used for executing corresponding operations according to control instructions of the control device, and the gripping device refers to a device for executing gripping actions, and can be specifically, but not limited to, a manipulator. The test platform is used for testing the power adapter; the test platform includes a socket corresponding to the plug of the power adapter, for example, when the power adapter includes a dc terminal plug and an ac terminal plug, the test platform includes a corresponding dc terminal socket and an ac terminal socket. In addition, the test platform also comprises other instruments required by the test.

The control device is used for acquiring a first image, and the first image comprises a first end plug of the power adapter and/or the grabbing device; generating a first control instruction according to the first image, and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and inserting the first end plug into a socket of the test platform; acquiring a second image, wherein the second image comprises a second end plug of the power adapter and/or a grabbing device; and generating a second control instruction according to the second image, and sending the second control instruction to the gripping device, wherein the second control instruction is used for indicating the gripping device to grip a second end plug to be inserted into a socket of the test platform so as to test the power adapter, and obtaining a test result.

Wherein, the power adapter includes first end plug and second end plug. The first end plug may be an input end and correspondingly the second end plug is an output end; the first terminal plug may be an output terminal and correspondingly the second terminal plug an input terminal. The first end plug may include one or more plugs and the second end plug may also include one or more plugs. For example, the first end plug includes 2 plugs and the second end plug includes two plugs. Typically, there is only one of each of the first end plug and the second end plug.

The first end plug may be an ac end plug and correspondingly the second end plug is a dc end plug; the first terminal plug may also be a dc terminal plug and correspondingly the second terminal plug is an ac terminal plug.

It should be noted that, the relevant content of the workflow of the control device may also refer to other embodiments, and is not described herein again.

After the description of the scenarios and architectures that may be involved, the following describes in detail the technical solutions provided by the embodiments of the present application. In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.

Example one

Referring to fig. 2, a schematic block diagram of a flow chart of a power adapter testing method provided in an embodiment of the present application may include the following steps:

step S201, acquiring a first image, wherein the first image comprises a first end plug of a power adapter and/or a grabbing device;

it should be noted that the first image may be an image including only the first terminal plug, may be an image including only the grasping apparatus, or may be an image including both the first terminal plug and the grasping apparatus. What kind of images to collect can be selected according to the actual application requirements. Generally, the first image only comprises an image of the first terminal plug, the pose of the first terminal plug is identified through the first image, and then the grabbing device is controlled to grab the first terminal plug according to the pose.

In the case where the posture of the first terminal plug is known, for example, the first terminal plugs of the power adapter are aligned. At the moment, an image only comprising the grabbing device can be collected, the pose of the grabbing device is identified through the image, and the grabbing track is planned according to the pose of the grabbing device and the pose of the first end plug. When the first image only has the grabbing device, the pose relationship between the grabbing device and the target object needs to be known in advance.

In some cases, a first image may be captured that includes the grasping device and the first end plug, i.e., the grasping device and the first end plug are included in the first image, i.e., when the grasping device and the first end plug are located within the same picture. In this case, trajectory planning may be performed based on conventional algorithms (e.g., visual servoing, etc.) and based on learning algorithms (e.g., reinforcement learning, mock learning).

Specifically, the image of the first end plug of the power adapter is captured by an image capturing device, which may be specifically, but not limited to, an image sensor, a camera, or other equipment with an image capturing function. The placement position of the power adapter may be arbitrary, for example, the power adapter is placed on the conveyor belt. The first image may be an image captured by an image capturing device, or may be an image of a certain frame in a video, which is not limited herein.

In one embodiment, the target object can be shot through an image sensor fixed on or outside the manipulator, whether the target object is a power adapter or not is identified through a linemod algorithm, and if yes, the process is continued; if not, alarming. The target object and the manipulator can be shot through an image sensor fixed outside the manipulator, whether the target object is a power adapter or not and whether the target object is the manipulator or not are recognized through a linemod algorithm, and if the target object is the power adapter or the manipulator, the operation continues; if not, alarming. Shooting the mechanical arm by an image sensor fixed outside the mechanical arm, identifying whether the target object is the mechanical arm or not by a linemod algorithm, and if so, continuing; if not, alarming. That is, in some scenarios, for example, where a power adapter is placed on a conveyor belt, prior to capturing an image, it may be necessary to first confirm whether the object is a robot and/or power adapter, and if so, capture the corresponding image, and if not, continue the identification.

Step S202, generating a first control instruction according to the first image, and sending the first control instruction to the grabbing device, wherein the first control instruction is used for instructing the grabbing device to grab the first end plug and insert the first end plug into a socket of the test platform.

It should be noted that after the first image is acquired, the pose of the first end plug or the pose of the grabbing device can be identified according to the first image, and then the grabbing device is controlled to grab the first end plug according to the pose; and corresponding control instructions can be directly given to the manipulator based on the images through a corresponding AI algorithm to control the manipulator to grab the first end plug without identifying corresponding pose information. The direct obtaining of the manipulator control instruction according to the first image is based on image feature learning of a convolutional neural network model, and includes but is not limited to obtaining of the manipulator control instruction through reinforcement learning, supervised learning and simulation learning.

It should be noted that the test platform may be embodied as a test rack, and the platform includes related instruments and functions for implementing the power adapter test. For example, a first socket corresponding to a first end plug of the power adapter, and a second socket corresponding to a second end plug.

In some embodiments, the specific process of generating the first control instruction according to the first image may include: obtaining first target pose information according to the first image; and generating a first control instruction according to the first target pose information.

It is understood that the first target pose information of the power adapter includes information such as the position and posture of the first terminal plug.

In specific applications, the pose recognition mode includes, but is not limited to, image feature recognition, template matching recognition and linemod algorithm recognition, where the image feature recognition may include gradient feature and contour feature recognition, color feature and contour feature recognition and other feature recognition (for example, SIFT, SURF, etc.).

The process based on gradient and contour feature identification may specifically include: when the image is collected, different light sources and different lighting schemes are used for lighting, so that the power adapter presents clear edges in the image, then edge information in the image is extracted based on methods such as a Canny operator, the outline of the power adapter is obtained according to the edge information, and then the power adapter is identified by using the geometric characteristics of the power adapter, such as angular points, inflection points and the like. The process based on color feature and contour feature identification may specifically include: when the image is collected, different light sources and different lighting schemes are used for lighting, so that the power adapter presents different colors on the image from the background, then binarization processing is carried out in a color space, the outline of the power adapter is extracted, and then the power adapter is identified based on the outline of the power adapter.

The process of identifying based on template matching may specifically include: the power adapter profile is obtained using different light sources and lighting schemes and then matched based on a pre-defined power adapter template to identify the power adapter. And the template can be given manually or can be automatically generated by using a 3D model of the power adapter and a 3D model of the camera. The process of identifying based on the linemod algorithm may specifically include: the method comprises the steps of collecting a 3D model of the power adapter in advance, identifying position information of the power adapter through a linemod algorithm, generating a corresponding template through the 3D model of the power adapter, and identifying the pose of the power adapter based on the template.

In some embodiments, referring to the schematic flow diagram of the pose identification process shown in fig. 3, the specific process of obtaining the pose information of the first object from the first image may include:

and S301, acquiring image data of the first terminal plug.

It is understood that the image data of the first terminal plug may be image data acquired by an image sensor and transmitted in real time, or image data acquired from a memory or a server.

In one embodiment, the image data may be image data including a first terminal plug and a complex background; in addition, in another embodiment, the image data may be image data including only the first terminal plug, or including the first terminal plug and a single background (i.e., a background including a single color or pattern in addition to the first terminal plug), and the image data may be various types of 2D image data (e.g., RGB image, grayscale or black-and-white image). Image sensors may include, but are not limited to: cameras, video cameras, scanners or other devices with associated functions (cell phones, computers), etc.

And step S302, acquiring a posture recognition model of the first terminal plug.

The posture recognition model of the first terminal plug is a model obtained by acquiring a posture recognition model trained in advance from a memory, a server, or the like, that is, the posture recognition model is a model established in advance and trained in advance. The gesture recognition model can be trained by using existing or future developed training methods such as supervised learning, semi-supervised learning or unsupervised learning, and the like, and the detailed description is omitted here.

The network model of the gesture recognition model may include, but is not limited to, a Convolutional Neural Network (CNN), and in the embodiment of the present application, the type of the CNN model may be arbitrary. Common CNN models may include, but are not limited to: le Net, AlexNet, ZF Net, VGG, Google Net, Residual Net, Dense Net, R-CNN, SPP-NET, Fast-RCNN, YOLO, SSD, BB8, YOLO-6D, Deep-6dPose, Pose CNN, Hourglass, CPN and other now known or later developed network model structures.

And step S303, inputting the image data into the gesture recognition model, and outputting the first target pose information.

It should be noted that the first target pose information includes, but is not limited to: the first-end plug comprises one or more of overall pose information of the first-end plug, local pose information of the first-end plug, pose information associated with global features of the first-end plug, pose information associated with local features of the first-end plug and the like, which meet preset grabbing requirements.

The overall or local pose information of the first end plug meeting the preset grabbing requirement can be obtained according to the pose information associated with the global feature of the first end plug, and the local pose information of the first end plug meeting the preset grabbing requirement can be obtained according to the pose information associated with the local feature of the first end plug. For example, the first end plug meeting the preset grabbing requirement is suitable for grabbing the pose information of the grabbing point; or the first end plug meeting the preset grabbing requirement is suitable for grabbing the associated pose information of the grabbing points, and the pose information of the grabbing points can be obtained through the associated pose information of the grabbing points suitable for grabbing.

In one embodiment, the recognition result output by the gesture recognition model is the first target pose information, that is, the gesture recognition result of the first terminal plug meeting the preset grabbing requirement is directly output by the gesture recognition model, that is, the recognition result may be directly the three-dimensional pose information of the first terminal plug.

The recognition result output by the gesture recognition model can comprise first target pose information; a first recognition result of characteristic information associated with the first end plug in the image data may also be included.

When the recognition result output by the posture recognition model is the first recognition result, after the first recognition result is obtained, the posture information of the first target position is further obtained according to the first recognition result.

Referring to the schematic flow diagram of the pose identification process shown in fig. 4, the specific process of obtaining the pose information of the first object from the first image may include:

step S401, acquiring image data of the first terminal plug.

And S402, acquiring a posture recognition model of the first terminal plug.

Step S403 is to input the image data into the gesture recognition model, and output a first recognition result of the feature information associated with the first terminal plug in the image data.

It should be noted that, similar contents in the above steps S401 to S403 to those of the corresponding embodiment in fig. 3 may refer to the above corresponding contents, and are not described again here.

The characteristic information associated with the first end plug may include, but is not limited to: keypoints and/or keypoints (where a keypoint can be viewed as a combination of multiple consecutive keypoints). The key point may be a key point on the home first-end plug; or a key point to a bounding box that encloses the first end plug.

In one embodiment, the first recognition result of the feature information associated with the first terminal plug in the image data may include a category, a mask, and the like of the target object in the image in addition to the result related to the gesture recognition described above. Such as: the category of the object is what the object is specific to, and the mask is typically the area of interest to the user in the image.

And S404, obtaining first target pose information according to the first recognition result.

Specifically, after obtaining the recognition result of the feature information associated with the first terminal plug in the image data, the first target pose information is generated through some algorithm, for example, to minimize a reprojection error of the 3D model of the first terminal plug in the photo.

When the recognition result includes a first recognition result of feature information associated with the first terminal plug in the image data, further processing is required (for example, by combining a 3D model of the first terminal plug) to obtain the first target pose information according to the two-dimensional feature information result in the image.

It should be noted that the image data obtaining and subsequent processing may be one or more of the following image processing methods based on deep learning, such as image classification, object localization, object detection, image segmentation, such as semantic segmentation, instance segmentation, and panoramic segmentation, which are developed now or in the future. For example, based on image-level prediction of image classification, outputting image data of a first terminal plug meeting a preset grabbing requirement in the image data; or framing the position of the first end plug meeting the preset grabbing requirement in the image in a surrounding box form in the first image based on target detection, and obtaining the characteristic information of the first end plug based on the coordinates of 8 vertexes and a midpoint of the surrounding box; or outputting the characteristic information of the first end plug which meets the preset grabbing requirement in the image data based on the pixel-level prediction of semantic segmentation. Of course, the pose recognition mode may also be other modes, for example, the pose of the power adapter is recognized by using the point cloud data, which is not limited herein. It should be noted that the pose identification mode may be selected according to a specific application scenario and a requirement.

Optionally, after the first target pose information is identified, the power adapter may be tracked by the grasping device according to the pose of the first end plug and a preset grasping pose, whether the manipulator is graspable is determined, and if the manipulator is graspable, the power adapter may be grasped by the grasping device according to the first target pose information.

Further, referring to the schematic block diagram of the first control instruction generation flow shown in fig. 5, the specific process of generating the first control instruction according to the first image may include:

step S501, capturing a first terminal plug according to the first image and a first preset capturing strategy.

It should be noted that the first preset grabbing strategy refers to a grabbing rule formulated according to pre-calibrated eye-hand information, the degree of freedom of the manipulator and a collision test. Wherein, the collision test needs to input a rough mechanical model of the test platform and correct the assembly error by using the auxiliary script. And then specifically calculating the minimum distance between the mechanical arm and the end effector and the test platform, and excluding attitude information which is less than a certain distance and is possible to collide.

Optionally, step S502 of determining whether the grabbing is successful may be further included. When the capturing is successful, the process proceeds to step S504, and otherwise, the process proceeds to step S503.

It is understood that in some other embodiments, step S502 may be omitted, that is, after the grabbing action is performed, whether grabbing is successful is not determined, and step S504 is directly entered.

And S503, repeatedly grabbing according to the preset grabbing angle range.

It can be understood that when grabbing fails, according to a preset grabbing angle, grabbing is iterated within a certain angle range, if grabbing succeeds, the step S504 is entered, and if grabbing fails again, pose recognition can be performed on the second-end plug again.

And S504, generating a third control instruction, and sending the third control instruction to the grabbing device, wherein the third control instruction is used for indicating the grabbing device to move the first end plug to a first preset position.

And step S505, acquiring an image of the first end plug at the first preset position.

Specifically, after the first end plug is moved to a preset position, an image of the first end plug can be acquired through a point cloud camera, and then a depth map and 3D point cloud information of the first end plug are generated through laser spots. And then calculating a space conversion relation, and calculating the posture state adjustment information of the first end plug according to the space conversion relation.

Step S506, calculating first posture adjustment information of the first terminal plug according to the image of the first terminal plug.

Specifically, a depth map and 3D point cloud information of the first end plug are generated according to the image of the first end plug. And calculating the spatial conversion relation between the first terminal plug and a preset first terminal plug model according to the depth map and the 3D point cloud information. Carrying out coarse matching by using the depth map, wherein the coarse matching process specifically comprises the following steps: approximating a polygon (e.g. a quadrangle) by using a first end plug of the depth map, then taking a plurality of points (e.g. two points) at the left and right lower corners of the polygon, and calculating the middle point of the plurality of points and the inclination angle around the z-axis of the camera; and performing point-to-surface ICP space conversion relation point cloud registration according to the information obtained by the rough matching, and performing point-to-point ICP registration again to obtain a space conversion relation between the first terminal plug and a preset first terminal plug model.

In some embodiments, after the calculating the first posture adjustment information of the first terminal plug according to the image of the first terminal plug, the method further includes: judging whether the grabbing device meets a first position adjustment condition or not according to the first position adjustment information; when the grabbing device meets the first position and posture adjusting condition, the step of generating a first control instruction according to the first position and posture adjusting information is carried out; and when the grabbing device does not meet the first posture adjustment condition, generating a first removal control instruction, and sending the first removal control instruction to the grabbing device, wherein the first removal control instruction is used for indicating the grabbing device to release the first end plug and remove the power adapter.

The first position adjustment condition may be a degree of freedom of the robot arm. When the mechanical arm has enough freedom degree to complete the adjustment and insertion of the second end plug, the mechanical arm meets the first position and posture adjustment condition, otherwise, if the mechanical arm does not have enough freedom degree to complete the adjustment and insertion of the first end plug, the mechanical arm does not meet the first position and posture adjustment condition.

Removing the power adapter refers to controlling the mechanical arm to pull out the plug and placing the power adapter in the corresponding area.

It will be appreciated that the path of the robotic arm to insert the first end plug into the socket may be fixed or random. The grabbing tracks of the first-end plugs in different postures are correspondingly different.

And step S507, generating a first control instruction according to the first posture adjustment information.

After the first end plug is grabbed and inserted into the socket of the test platform, the image of the power adapter on the test platform can be acquired, so that the second end plug is grabbed and inserted into the socket of the test platform according to the acquired image.

And S203, acquiring a second image, wherein the second image comprises a second end plug of the power adapter and/or the grabbing device.

It will be appreciated that after the gripping device grips the first plug of the power adapter and inserts into the first socket on the testing platform, the other plugs of the power adapter are generally suspended and are located at any position, and these plugs are not inserted into the corresponding sockets. At the moment, the image acquisition device acquires an image of the power adapter on the test platform, and second target pose information of the second end plug is identified according to the image.

After the first terminal plug is inserted into the socket, the other terminal plug of the power adapter may be in a static state, but in most cases, the other terminal plug is first shaken for a period of time and then stands still. And the pose identification needs the plugs at other ends to be in a static state, so that the identified pose and the actual pose are not different due to the shaking of the plugs, and the current identified pose and the actual pose are ensured to be the same. In some embodiments, before the acquiring the second image, the method may further include: judging whether the second end plug is in a static state or not; and when the second end plug is in a static state, entering a step of acquiring a second image. Otherwise, if the second end plug is not in the static state, returning to the step of continuously judging whether the second end plug is in the static state.

Generally, when the power adapter comprises an alternating current end plug and a direct current end plug, the alternating current end plug of the power adapter is generally larger than the direct current end plug in size and heavier in weight, and the alternating current end plug with the larger size can be grabbed firstly, so that after the alternating current end plug is inserted into the alternating current end socket, the shaking amplitude of the direct current end plug is possibly smaller, and the power adapter can enter a static state in a shorter time. Therefore, the plug at the alternating current end can be firstly grabbed and inserted on the alternating current socket, and then the plug at the direct current end can be grabbed and inserted on the direct current socket. Preferably, the first terminal plug is an ac terminal plug, and the second terminal plug is a dc terminal plug.

It should be noted that, images of other plugs of multiple power adapters that are continuous in time may be collected, and whether the other plugs are in a static state may be determined according to the degree of distinction between the multiple images. Specifically, the positions of the plugs at the other ends in each image can be identified, and whether the plugs at the other ends are static or not can be judged according to the position change of the plugs at the other ends in each image. And whether other plugs are static or not can be judged according to the posture changes of the first end plug which are continuously carried out twice by identifying the three-dimensional poses of the first end plug. And when the other end plugs are in a static state, acquiring a second image, and controlling the mechanical arm to grab the second end plug of the power adapter according to the second image.

And S204, generating a second control instruction according to the second image, and sending the second control instruction to the grabbing device, wherein the second control instruction is used for indicating the grabbing device to grab a second end plug to be inserted into a socket of the test platform so as to perform communication test on the power adapter, and obtain a test result.

It should be noted that the power adapter test includes performing tests on various product specifications of the power adapter, including but not limited to one or more of output voltage, output current, output power, power factor, output voltage, output current, output power, efficiency, tip voltage, output voltage ripple, startup time, hold time, average efficiency, frequency, overcurrent protection, overvoltage protection, and the like.

After the second image is acquired, the pose of the second end plug can be identified according to the second image, and then the manipulator is controlled to capture the second end plug according to the pose; and corresponding control instructions can be directly given to the manipulator based on the images through corresponding AI algorithms to control the manipulator to grab the second end plug without identifying corresponding pose information. The direct obtaining of the manipulator control instruction according to the second image is based on image feature learning of a convolutional neural network model, and includes but is not limited to obtaining of the manipulator control instruction through reinforcement learning, supervised learning and simulation learning.

In some embodiments, the specific process of generating the second control instruction according to the second image may include: obtaining second target pose information according to the second image; and generating a second control instruction according to the second target pose information.

Specifically, the second image is subjected to binarization processing, profile information of a second end plug is extracted, and then the interference of a background is eliminated according to a preset ROI (region of interest); performing linmod algorithm detection, wherein linemod can be used for performing monocular detection for one time through two cameras to obtain a preliminary matching result, and then optimizing according to the space attitude and ICP (iterative closest Point) to obtain the 3D position and attitude information of the second end plug; and then, performing monocular optimization detection on the detection results through the two cameras, and further optimizing the results according to binocular information to obtain more accurate 3d position and posture information.

In some embodiments, referring to the schematic flow diagram of the pose identification process shown in fig. 6, the specific process of obtaining the pose information of the second object from the second image may include:

and step S601, acquiring second image data of the second terminal plug.

And step S602, acquiring a second gesture recognition model of the second terminal plug.

And step S603, inputting the second image data into a second gesture recognition model, and outputting second target pose information.

The recognition result output by the gesture recognition model can comprise first target pose information; a first recognition result of characteristic information associated with the first end plug in the image data may also be included. When the recognition result output by the posture recognition model is the first recognition result, after the first recognition result is obtained, the posture information of the first target position needs to be further obtained according to the first recognition result, which will be described below with reference to fig. 7.

Referring to the schematic flow chart of the pose identification process shown in fig. 7, the specific process of obtaining the pose information of the second object according to the second image may include:

and step S701, acquiring second image data of the second terminal plug.

And step S702, acquiring a second gesture recognition model of the second terminal plug.

And step S703, inputting the second image data into the second gesture recognition model, and outputting a second recognition result of the feature information associated with the second terminal plug in the image data.

And step S704, obtaining second target pose information according to the second recognition result.

It should be noted that the process of identifying the second target pose information of the second terminal plug is similar to the process of identifying the first target pose information of the first terminal plug, and related descriptions may refer to related contents of the embodiments corresponding to fig. 3 and fig. 4, and are not described herein again.

In some embodiments, after the pose of the second end plug is derived, it may be further determined whether the identification was successful. That is, after obtaining the second object pose information from the second image, the method may further include: judging whether the second end plug is successfully identified or not according to the second target pose information; and when the second end plug is successfully identified, generating a second control instruction according to the second target pose information. Otherwise, if the identification is not successful, the image is collected again, and the pose identification is carried out again.

Specifically, the judgment condition for successful identification includes, but is not limited to: according to the pose of the second end plug, two groups of characteristic points of a plurality of second ends can be obtained, and then whether the two groups meet the limit error or not is judged by utilizing the relationship information between the two eyes; and calculating the three-dimensional distance between the plurality of characteristic points according to the two groups of characteristic points of the second end and the binocular information, and judging whether the three-dimensional distance meets the actual error. And if and only if the relation information conforms to the limit error and the three-dimensional distance conforms to the actual error, the identification is successful, otherwise, if the relation information does not conform to the limit error and/or the three-dimensional distance does not conform to the actual error, the identification is unsuccessful.

After second target pose information of the second end plug is identified, the end effector of the manipulator can be controlled to grab the second end plug according to a preset grabbing strategy; and then judging whether the grabbing is successful or not according to the feedback of the sensor on the end effector, and after the grabbing is successful, inserting the second end plug into a socket of the test platform after adjusting the pose of the second end plug. And when the grabbing is unsuccessful, the grabbing can be repeated for multiple times within a certain preset grabbing angle range, and if the grabbing fails again, the pose of the second end plug is identified again.

After the first end plug and the second end plug of the power adapter are inserted into the corresponding sockets, the test platform can be controlled to perform testing. Firstly, whether a power adapter is tested or not can be judged, if yes, the power adapter is removed after the test is finished, and then a test instruction is sent to test the current power adapter; and judging whether the test result can be received or not, and if the test result is received, indicating that the test is finished. If the test result is not received and the time for not receiving the test result continuously exceeds the preset time threshold, the system can be controlled to stop working, and relevant personnel are informed to carry out manual investigation.

After the test result is obtained, whether the test passes or not can be judged according to the test result, if the test passes, the power adapter is good, and if the test fails, the power adapter is possibly bad.

Optionally, after the performing the communication test on the power adapter to obtain the test result, the method may further include:

and S205, obtaining a test result, generating a classification instruction according to the test result, and sending the classification instruction to a classification device, wherein the classification instruction is used for instructing the classification device to classify the power adapter.

It can be understood that the categories of the power adapter include good and bad, and a good is a good when the test is passed, and a bad is a bad when the test is not passed. Specifically, whether the test is passed or not is judged according to the test result, and when the test is passed, the manipulator is controlled to pull out the first end plug and the other end plugs, and then the power adapter is placed in a good product area; and when the test fails, controlling the manipulator to pull out the first end plug and the second end plug, and then placing the power adapter into a defective area. The sorting device is a device for sorting the power adapters, and may be, but is not limited to, a robot.

It should be noted that, in the embodiment of the present application, the first end plug of the power adapter may be inserted into the socket first, and then the second end plug may be inserted into the corresponding socket. In practical applications, the second end plug may be inserted into the socket first, and then the first end plug of the power adapter may be inserted into the socket. Of course, the second terminal plug may be inserted into the socket at the same time, and the first terminal plug of the power adapter may be inserted into the socket.

According to the embodiment of the application, a first image control grabbing device of the power adapter grabs a first end plug of the power adapter and inserts the first end plug into the test platform; the second image control grabbing device of the power adapter grabs other end plugs to be inserted into the test platform, and finally the test is carried out to obtain a test result, so that the automatic test of the power adapter is realized, the production cost is reduced, and the production efficiency and the test accuracy are improved.

Example two

Based on the first embodiment, referring to fig. 8, the specific process of generating the second control instruction according to the second image may include:

and step S801, capturing the second terminal plug according to the second image and a second preset capturing strategy.

It should be noted that the second preset grabbing strategy refers to a grabbing rule formulated according to pre-calibrated eye-hand information, the degree of freedom of the manipulator and a collision test. Wherein, the collision test needs to input a rough mechanical model of the test frame and correct the assembly error by using the auxiliary script. And then specifically calculating the minimum distance between the mechanical arm and the end effector and the test rack, and excluding attitude information which is less than a certain distance and is possible to collide.

Optionally, the method may further include step S802 of determining whether the grabbing is successful; when the grabbing is unsuccessful, the process proceeds to step S803, whereas when the grabbing is successful, the process proceeds to step S804.

It is understood that in some other embodiments, step S802 may be omitted, that is, after the grabbing action is performed, whether grabbing is successful is not determined, and step S804 is directly entered.

And S803, repeatedly grabbing according to a preset grabbing angle range.

When grabbing fails, according to a preset grabbing angle, iterative grabbing is performed within a certain angle range, if grabbing succeeds, the step S804 is executed, and if grabbing fails again, pose recognition can be performed on the second end plug again.

And step S804, generating a fourth control instruction, and sending the fourth control instruction to the gripping device, wherein the fourth control instruction is used for indicating the gripping device to move the second end plug to a second preset position.

It should be noted that the second preset position is preset, and the second end plug is moved to the preset position, so that subsequent pose adjustment information identification can be facilitated.

And step S805, acquiring an image of the second end plug at the second preset position.

Step 806, calculating second position and posture adjustment information of the second terminal plug according to the image of the second terminal plug.

Specifically, after the second end plug is moved to a preset position, an image of the second end plug can be acquired through a point cloud camera, and then a depth map and 3D point cloud information of the second end plug are generated through laser spots. And then calculating a space conversion relation, and calculating the posture state adjustment information of the second end plug according to the space conversion relation.

Further, referring to a schematic flow chart of the pose adjustment information calculation process shown in fig. 9, the specific process of calculating the pose adjustment information of the second terminal plug according to the image of the second terminal plug may include:

step S901, generating a depth map and 3D point cloud information of the second header according to the image of the second header.

And S902, calculating a spatial conversion relation between the second end plug and a preset second end plug model according to the depth map and the 3D point cloud information.

Specifically, the depth map is used for rough matching, and the rough matching process specifically includes: approximating a polygon (e.g., a quadrangle) by using the second end plug of the depth map, then taking a plurality of points (e.g., two points) at the left and right lower corners of the polygon, and calculating the middle point of the plurality of points and the inclination angle around the z-axis of the camera; and performing point-to-surface ICP space conversion relation point cloud registration according to the information obtained by the rough matching, and performing point-to-point ICP registration again to obtain a space conversion relation between the second end plug and a preset second end plug model.

And step S903, calculating the pose adjustment information of the second end plug according to the space conversion relation and the pre-calibrated eye-hand information.

It should be noted that the pose adjustment information controls the mechanical arm to rotate by a certain degree of freedom, the position and the posture of the second end plug are adjusted, and then the second end plug is inserted into the second socket. The mechanical arm needs to have enough freedom degree to complete posture adjustment, so that after pose adjustment information is calculated, whether the freedom degree of the mechanical arm meets the adjustment requirement or not can be further judged.

In some embodiments, referring to the schematic flow chart of the pose adjustment condition determination process shown in fig. 10, after the above-described calculation of the pose adjustment information of the second terminal plug from the image of the second terminal plug, the method may further include:

step S1001, judging whether the grabbing device meets a second position adjustment condition or not according to the second position adjustment information; when the gripping device satisfies the second posture adjustment condition, the process proceeds to step S1002, whereas when the gripping device does not satisfy the second posture adjustment condition, the process proceeds to step S1003.

The second position and orientation adjustment condition may be a degree of freedom of the mechanical arm. When the mechanical arm has enough freedom degree to complete the adjustment and the insertion of the second end plug, the mechanical arm meets the second position and posture adjustment condition, otherwise, if the mechanical arm does not have enough freedom degree to complete the adjustment and the insertion of the second end plug, the mechanical arm does not meet the second position and posture adjustment condition.

Step S1002, a step of generating a second control command according to the second posture adjustment information is performed.

And S1003, generating a second removal control instruction, and sending the second removal control instruction to the gripping device, wherein the removal control instruction is used for indicating the gripping device to release the second end plug and remove the power adapter.

Wherein, removing the power adapter means controlling the mechanical arm to pull out the first end plug and placing the power adapter in the corresponding area.

Step S1004, a second control instruction is generated according to the second posture adjustment information.

It will be appreciated that the path of the robotic arm to insert the second end plug into the socket may be fixed or random. The grabbing track of the second-end plug with different postures is correspondingly different.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

EXAMPLE III

Referring to fig. 11, a schematic block diagram of a power adapter testing apparatus according to an embodiment of the present disclosure is shown, where the apparatus may include:

a first image obtaining module 111, configured to obtain a first image, where the first image includes a first terminal plug of the power adapter and/or a grasping apparatus;

the first control module 112 is configured to generate a first control instruction according to the first image, and send the first control instruction to the grasping device, where the first control instruction is used to instruct the grasping device to grasp a first end plug and insert the first end plug into a socket of the test platform;

a second image obtaining module 113, configured to obtain a second image, where the second image includes a second terminal plug of the power adapter and/or a grasping device;

and the second control module 114 is configured to generate a second control instruction according to the second image, and send the second control instruction to the gripping device, where the second control instruction is used to instruct the gripping device to grip that the second end plug is inserted into a socket of the test platform, so as to test the power adapter, and obtain a test result.

In one possible implementation, the first control module includes:

and the first generation unit is used for generating a first control instruction according to the first target pose information.

In one possible implementation, the second control module includes:

and the second generating unit is used for generating a second control instruction according to the second target pose information.

In a possible implementation manner, the first identification unit is specifically configured to:

acquiring first image data of a first end plug;

acquiring a first posture identification model of a first terminal plug;

inputting first image data into a first gesture recognition model, and outputting first target pose information;

or

Acquiring first image data of a first end plug;

acquiring a first posture identification model of a first terminal plug;

inputting the first image data into a first gesture recognition model, and outputting a first recognition result of feature information associated with the first terminal plug in the image data;

In a possible implementation manner, the second identification unit is specifically configured to:

acquiring second image data of a second end plug;

acquiring a second posture identification model of the second end plug;

inputting second image data into a second gesture recognition model, and outputting second target pose information;

or

Acquiring second image data of a second end plug;

acquiring a second posture identification model of the second end plug;

inputting second image data into a second gesture recognition model, and outputting a second recognition result of feature information associated with the second terminal plug in the image data;

In a possible implementation manner, the first generating unit is specifically configured to:

generating a third control instruction, and sending the third control instruction to the grabbing device, wherein the third control instruction is used for indicating the grabbing device to move the first end plug to a first preset position;

acquiring an image of a first end plug at a first preset position;

and generating a first control instruction according to the first posture adjustment information.

In a possible implementation manner, the first generating unit is further configured to:

judging whether the grabbing is successful;

and when the grabbing is successful, generating a third control instruction and sending the third control instruction to the grabbing device.

In a possible implementation manner, the second generating unit is specifically configured to:

capturing a second end plug according to the second target pose information and a second preset capturing strategy;

acquiring an image of a second end plug at a second preset position;

and generating a second control instruction according to the second posture adjustment information.

In a possible implementation manner, the second generating unit is further specifically configured to:

judging whether the grabbing is successful;

and when the grabbing is successful, generating a fourth control instruction and sending the fourth control instruction to the grabbing device.

In a possible implementation manner, the first generating unit is further specifically configured to:

when the grabbing device meets the first position and posture adjusting condition, the step of generating a first control instruction according to the first position and posture adjusting information is carried out;

and when the gripping device does not meet the second position and posture adjustment condition, generating a second removal control instruction, and sending the second removal control instruction to the gripping device, wherein the second removal control instruction is used for indicating the gripping device to release the second end plug and remove the power adapter.

In one possible implementation manner, the method further includes:

and the entering module is used for entering the step of acquiring the second image when the second end plug is in a static state.

In one possible implementation manner, the method further includes:

the test result acquisition module is used for acquiring a test result;

and the classification module is used for generating a classification instruction according to the test result, and the classification instruction is used for indicating the classification device to classify the power adapter.

In one possible implementation, the second control module further includes:

and the entering unit is used for entering the step of generating a second control instruction according to the second target pose information when the second end plug is successfully identified.

It should be noted that the power adapter testing apparatus provided in this embodiment corresponds to each of the power adapter testing methods described above, and for related description, reference is made to the above corresponding contents, which are not described herein again.

The embodiment can realize the automatic test of the power adapter, reduce the production cost and improve the production efficiency and the test accuracy.

Example four

Fig. 12 is a schematic diagram of a control device according to an embodiment of the present application. As shown in fig. 12, the control device 12 of this embodiment includes: a processor 120, a memory 121, and a computer program 122 stored in the memory 121 and executable on the processor 120. The processor 120, when executing the computer program 122, implements the steps in the various power adapter testing method embodiments described above. Alternatively, the processor 120 implements the functions of the modules/units in the above device embodiments when executing the computer program 122.

Illustratively, the computer program 122 may be partitioned into one or more modules/units that are stored in the memory 121 and executed by the processor 120 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 122 in the control device 12. For example, the computer program 122 may be segmented into a first image acquisition module, a first control module, a second image acquisition module, and a second control module:

the control device may include, but is not limited to, a processor 120, a memory 121. It will be understood by those skilled in the art that fig. 12 is merely an example of the control apparatus 12, and does not constitute a limitation of the control apparatus 12, and may include more or less components than those shown, or combine some components, or different components, for example, the control apparatus may further include input-output devices, network access devices, buses, and the like.

The Processor 120 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 121 may be an internal storage unit of the control device 12, such as a hard disk or a memory of the control device 12. The memory 121 may also be an external storage device of the control apparatus 12, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the control apparatus 12. Further, the memory 121 may also include both an internal storage unit and an external storage device of the control apparatus 12. The memory 121 is used to store the computer program and other programs and data required by the control device. The memory 121 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus, control apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus and the control apparatus are merely illustrative, and for example, the division of the modules or units is only one logical function division, and there may be other division manners in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for testing a power adapter, comprising:

2. The power adapter testing method of claim 1, wherein said generating a first control instruction from the first image comprises:

obtaining first target pose information according to the first image;

3. The power adapter testing method of claim 1, wherein said generating a second control instruction from the second image comprises:

obtaining second target pose information according to the second image;

4. The power adapter testing method of claim 2, wherein said deriving first target pose information from the first image comprises:

acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

or

Acquiring first image data of the first end plug;

acquiring a first posture identification model of the first terminal plug;

5. The power adapter testing method of claim 3, wherein said deriving second target pose information from the second image comprises:

acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

or

Acquiring second image data of the second end plug;

acquiring a second posture identification model of the second terminal plug;

6. The power adapter testing method of claim 1, wherein said generating a first control instruction from the first image comprises:

acquiring an image of the first end plug at the first preset position;

7. The power adapter testing method of claim 6, further comprising, after grabbing the first end plug:

judging whether the grabbing is successful;

8. The power adapter testing method of claim 1, wherein said generating the second control command from the second image comprises:

acquiring an image of the second end plug at the second preset position;

9. The power adapter testing method of claim 1, further comprising, after grabbing the second end plug:

judging whether the grabbing is successful;

10. The method for testing a power adapter according to claim 6, further comprising, after the calculating the first posture adjustment information of the first terminal plug from the image of the first terminal plug:

11. The power adapter testing method according to claim 8, further comprising, after said calculating pose adjustment information of the second end plug from the image of the second end plug:

12. The power adapter testing method of claim 1, further comprising, prior to said acquiring a second image:

judging whether the second end plug is in a static state or not;

13. The power adapter testing method according to any one of claims 1 to 12, further comprising, after the testing the power adapter to obtain a test result:

obtaining the test result;

and generating a classification instruction according to the test result, and sending the classification instruction to a classification device, wherein the classification instruction is used for instructing the classification device to classify the power adapter.

14. The power adapter testing method of claim 3, further comprising, after said deriving second target pose information from said second image:

15. A power adapter testing apparatus, comprising:

16. A power adapter test system is characterized by comprising a control device, an image acquisition device, a grabbing device and a test platform, wherein the control device is respectively in communication connection with the grabbing device, the image acquisition device and the test platform;

the image acquisition device is used for acquiring images;

17. A control device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 14 are implemented when the computer program is executed by the processor.

18. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 14.