Cooperative robot control method and system based on industrial internet

Abstract

The invention is suitable for the technical field of industrial equipment control, and particularly relates to a cooperative robot control method and system based on the industrial internet, and the method comprises the steps: constructing a control local area network; carrying out image acquisition on the cargo, and identifying the model and posture of the cargo based on an image acquisition result to obtain cargo state information; the working state of the collaborative robot is obtained, and a robot control instruction is generated based on the working state and the cargo state information; and encrypting the robot control instruction, sending the robot control instruction to the collaborative robot, and decrypting and executing the corresponding robot control instruction through the collaborative robot. According to the cooperative robot control method based on the industrial internet, image acquisition is performed on the goods through the control center, so that the state of the goods is recognized in a binocular distance measurement mode, the working modes of the multiple cooperative robots are adjusted according to the state of the goods, the control instructions are sent to the cooperative robots, and the production cost is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of industrial equipment control, and particularly relates to a collaborative robot control method and system based on an industrial internet. BACKGROUND

[0002] The industrial internet is a new type of infrastructure that deeply integrates modern manufacturing with advanced information technology. It realizes efficient interconnection and data sharing between devices, production lines, factories, supply chains and products through technologies such as the Internet of Things, cloud computing, big data analysis and artificial intelligence. This interconnection not only improves the automation level and intelligent decision-making ability of production, but also promotes the development of new models such as personalized customization and service transformation, aiming to improve the efficiency, flexibility and competitiveness of the entire manufacturing industry and promote the transformation and upgrading of traditional industries to digital, networked and intelligent.

[0003] As a product of the industrial internet, collaborative robots usually work together. The existing processing method is mainly to automatically identify goods by collaborative robots, which requires a high degree of intelligence of collaborative robots and high production costs. SUMMARY

[0004] The application aims to provide a collaborative robot control method based on an industrial internet, which aims to solve the problem that the existing processing method is mainly to automatically identify goods by collaborative robots, which requires a high degree of intelligence of collaborative robots and high production costs.

[0005] The application is implemented as follows. A collaborative robot control method based on an industrial internet, the method comprising:

[0006] A control local area network is constructed, which comprises a control center and a plurality of collaborative robots. The control center is provided with an image acquisition device.

[0007] The goods are image-acquired, the model and posture of the goods are identified based on the image acquisition result, and the state information of the goods is obtained.

[0008] The working state of the collaborative robot is obtained, and the robot control instruction is generated based on the working state and the state information of the goods.

[0009] The robot control instruction is encrypted and sent to the collaborative robot, and the collaborative robot decrypts and executes the corresponding robot control instruction.

[0010] Preferably, the step of image-acquiring the goods, identifying the model and posture of the goods based on the image acquisition result, and obtaining the state information of the goods comprises:

[0011] The image acquisition device acquires images of the goods from at least two angles to obtain image acquisition results, and the image acquisition results include multiple groups of images of the goods.

[0012] A binocular image group is constructed based on the goods, and a goods space model is generated through binocular image recognition.

[0013] The size information of the goods is extracted according to the goods space model, the preset goods database is queried according to the size information of the goods, the model of the goods is determined, and the goods state information is generated.

[0014] Preferably, the step of obtaining the working state of the collaborative robot and generating the robot control instruction based on the working state and the goods state information specifically comprises:

[0015] The working state of the collaborative robot is obtained, and the posture parameters of the collaborative robot at the completion of the existing instruction are extracted.

[0016] The goods state information is identified, and the operation surface of the goods is determined according to the preset goods database.

[0017] The robot control instruction is generated based on the posture parameters of the collaborative robot and the operation surface of the goods, and the robot control instruction includes a time sequence and a motion sequence.

[0018] Preferably, the step of encrypting the robot control instruction, sending it to the collaborative robot, and executing the corresponding robot control instruction through the collaborative robot decryption processing specifically comprises:

[0019] Two groups of encryption functions are randomly generated, the encryption functions are sent to the collaborative robot, and the robot control instruction is obtained.

[0020] Two groups of mapping strings are generated based on the two groups of encryption functions, and a data mapping relationship table is generated based on the mapping strings.

[0021] The robot control instruction is data-converted, the converted data is encrypted through the data mapping relationship table, and the encrypted robot control instruction is sent to the corresponding collaborative robot.

[0022] Preferably, after the collaborative robot receives the encrypted robot control instruction, the encrypted robot control instruction is decrypted based on the encryption function, and the decrypted robot control instruction is subjected to validity verification.

[0023] Another object of the present application is to provide a collaborative robot control system based on an industrial internet, which comprises:

[0024] The LAN construction module is configured to construct a control LAN, wherein the control LAN comprises a control center and a plurality of collaborative robots, and the control center is provided with an image acquisition device.

[0025] The cargo information acquisition module is configured to acquire images of the cargo, identify the model and posture of the cargo based on the image acquisition result, and obtain cargo state information.

[0026] The instruction generation module is configured to acquire the working state of the collaborative robot, and generate robot control instructions based on the working state and the cargo state information.

[0027] The data encryption module is configured to encrypt the robot control instructions, send the robot control instructions to the collaborative robot, and decrypt and execute the corresponding robot control instructions by the collaborative robot.

[0028] Preferably, the cargo information acquisition module comprises:

[0029] The image acquisition unit is configured to acquire images of the cargo from at least two angles by the image acquisition device, and obtain image acquisition results, wherein the image acquisition results comprise a plurality of groups of cargo images.

[0030] The model construction unit is configured to construct a binocular image group based on the cargo, and generate a cargo space model by binocular image recognition.

[0031] The cargo identification unit is configured to extract size information of the cargo according to the cargo space model, query a preset cargo database according to the size information of the cargo, determine the model of the cargo, and generate cargo state information.

[0032] Preferably, the instruction generation module comprises:

[0033] The parameter extraction unit is configured to acquire the working state of the collaborative robot, and extract the posture parameter of the collaborative robot when the existing instructions are completed.

[0034] The operation surface identification unit is configured to identify the cargo state information, and determine the operation surface of the cargo according to the preset cargo database.

[0035] The device control unit is configured to generate robot control instructions based on the posture parameter of the collaborative robot and the operation surface of the cargo, wherein the robot control instructions comprise a time sequence and a motion sequence.

[0036] Preferably, the data encryption module comprises:

[0037] The function generation unit is configured to randomly generate two groups of encryption functions, send the encryption functions to the collaborative robot, and acquire the robot control instructions.

[0038] The mapping table generating unit is configured to generate two groups of mapping strings based on the two groups of encryption functions, and generate a data mapping relationship table based on the mapping strings.

[0039] The data conversion unit is configured to perform data conversion on the robot control instruction, encrypt the converted data through the data mapping relationship table, and send the encrypted robot control instruction to the corresponding collaborative robot.

[0040] Preferably, after receiving the encrypted robot control instruction, the collaborative robot decrypts the encrypted robot control instruction based on the encryption function, and performs validity verification on the decrypted robot control instruction.

[0041] The application provides a collaborative robot control method based on an industrial internet, which acquires images of goods through a control center, identifies the state of the goods by using a binocular distance measurement method, adjusts the working mode of a plurality of collaborative robots according to the state of the goods, and sends control instructions to the collaborative robots, thereby reducing production costs. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of a collaborative robot control method based on an industrial internet provided by the embodiment of the application is shown in the figure.

[0043] Figure 2 A flowchart of the step of acquiring images of goods, identifying the model and posture of the goods based on the image acquisition result, and obtaining the state information of the goods is shown in the figure.

[0044] Figure 3 A flowchart of the step of obtaining the working state of the collaborative robot, generating the robot control instruction based on the working state and the state information of the goods is shown in the figure.

[0045] Figure 4 A flowchart of the step of encrypting the robot control instruction, sending the encrypted robot control instruction to the collaborative robot, and decrypting and executing the corresponding robot control instruction through the collaborative robot is shown in the figure.

[0046] Figure 5 An architecture diagram of a collaborative robot control system based on an industrial internet provided by the embodiment of the application is shown in the figure.

[0047] Figure 6 An architecture diagram of a goods information acquisition module provided by the embodiment of the application is shown in the figure.

[0048] Figure 7 An architecture diagram of an instruction generation module provided by the embodiment of the application is shown in the figure.

[0049] Figure 8A structural diagram of a data encryption module provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0051] As shown in Figure 1 A flowchart of a collaborative robot control method based on an industrial internet provided by an embodiment of the present application, the method comprises:

[0052] S100, a control local area network is constructed, the control local area network comprises a control center and a plurality of collaborative robots, and the control center is provided with an image acquisition device.

[0053] In this step, a control local area network is constructed, in order to be able to collaboratively control all the collaborative robots, all the collaborative robots are connected to construct a local control network, a control center is arranged in the local control network, the control center is directly or indirectly connected with all the other collaborative robots, the devices in the local control network can be connected through a wired connection, and any form of wireless connection can be used, as long as the timeliness of data transmission can be met, and an image acquisition device is arranged on the control center, specifically, the image acquisition device is a binocular camera, which can simultaneously acquire images from two angles, and subsequent binocular distance measurement algorithm can identify the positions of each pixel point in the picture to construct a three-dimensional model of the goods.

[0054] S200, image acquisition is performed on the goods, the model and the posture of the goods are identified based on the image acquisition result to obtain the state information of the goods.

[0055] In this step, image acquisition is performed on the goods, since the image acquisition device is a binocular camera, image acquisition can be simultaneously performed on the goods from different angles, binocular images are acquired, the positions of each pixel point in the binocular images are identified by using binocular recognition technology, the positions of all objects in the picture are identified by identification, and each pixel point is mapped to a three-dimensional coordinate system by constructing a three-dimensional coordinate system, so that a model of the goods is constructed, and the model of the goods is extracted to obtain the model and the posture of the goods, that is, the state information of the goods.

[0056] S300, the working state of the collaborative robot is acquired, and robot control instructions are generated based on the working state and the state information of the goods.

[0057] In this step, the working state of the collaborative robot is obtained, and the collaborative robot is finally in a certain state when completing the last round of task. For a five-axis robot, the rotation angle of each axis can be directly obtained when it is in a certain state. According to the working state of the collaborative robot, the current action of the robot can be determined, and according to the cargo state information, the attitude of the cargo in space can be known. According to this, the robot control instruction is generated. The robot control instruction is used to control the collaborative robot to operate, and the collaborative robot is used to carry or move the cargo.

[0058] S400, the robot control instruction is encrypted and sent to the collaborative robot, and the collaborative robot decrypts and executes the corresponding robot control instruction.

[0059] In this step, the robot control instruction is encrypted. When encrypting, two sets of encryption functions are generated by a random algorithm, and random numbers are generated by using the encryption functions. Specifically, since the encryption functions are randomly generated, the generated calculation values are also random when a preset natural number is imported into the encryption functions. A data mapping relationship table is constructed based on the randomly generated calculation values, and the data mapping relationship table is used to convert the data of the robot control instruction. At this time, data transmission can avoid data leakage and ensure the security of the instruction. After the collaborative robot receives the above data, it can execute the decryption to complete the processing of the cargo, such as clamping or carrying.

[0060] As shown in Figure 2 As shown in

[0061] S201, image acquisition device acquires images of the cargo from at least two angles to obtain image acquisition results, and the image acquisition results contain multiple groups of cargo images.

[0062] In this step, the image acquisition device acquires images of the cargo from at least two angles. When acquiring, at least two angles are needed, such as placing the cargo on the conveyor belt. The image acquisition direction of the image acquisition device can be adjusted, and the image acquisition device can be acquired from the front and rear of the cargo when the cargo passes through the image acquisition device. Specifically, the direction of the cargo advancing is regarded as the front, and the opposite side of the front is regarded as the rear.

[0063] S202, based on the cargo, a binocular image group is constructed, and a cargo space model is generated by binocular image recognition.

[0064] In this step, based on the goods, a binocular image group is constructed. If the image acquisition device is a monocular camera, the binocular image cannot be directly acquired, and the image acquisition device can be used to acquire images with a small angle difference. For example, the image acquisition device can continuously capture two groups of images with a 50ms interval during the movement of the goods. Then, the two groups of images are used as the binocular image group. According to the conveying speed of the goods and the image acquisition interval, the position difference between the two times of shooting can be calculated. The goods in the recognition picture are recognized by using binocular recognition, so as to construct a three-dimensional coordinate system and obtain the model of the goods, that is, the spatial model of the goods.

[0065] In this step, the size information of the goods is extracted according to the spatial model of the goods. After the spatial model of the goods is constructed, the appearance size of the goods, such as the length, width and height of the goods, is read from the spatial model of the goods. If the goods are special-shaped goods, the edges thereof are extracted and compared with the goods database. The model data of the goods are recorded in the goods database. Through comparison, the type and corresponding size information of the goods can be determined, and the posture of the goods, such as whether the front face is upward or not, whether rotation occurs or not, etc., can be recognized.

[0066] In this step, the size information of the goods is extracted according to the spatial model of the goods. After the spatial model of the goods is constructed, the appearance size of the goods, such as the length, width and height of the goods, is read from the spatial model of the goods. If the goods are special-shaped goods, the edges thereof are extracted and compared with the goods database. The model data of the goods are recorded in the goods database. Through comparison, the type and corresponding size information of the goods can be determined, and the posture of the goods, such as whether the front face is upward or not, whether rotation occurs or not, etc., can be recognized.

[0067] As shown in Figure 3 As a preferred embodiment of the present application, the step of acquiring the working state of the collaborative robot and generating the robot control instruction based on the working state and the goods state information comprises the following steps:

[0068] S301, acquiring the working state of the collaborative robot, and extracting the posture parameter of the collaborative robot when the existing instruction is completed.

[0069] In this step, the working state of the collaborative robot is acquired. Taking a five-axis robot as an example, the rotation angle of each axis of the five-axis robot is acquired. If the collaborative robot is equipped with a gripper, the opening angle of the gripper is recognized to obtain the posture parameter of the collaborative robot.

[0070] S302, recognizing the goods state information, and determining the operation surface of the goods according to the preset goods database.

[0071] In this step, the goods state information is recognized. The size information of the goods is recorded in the goods database, and the orientation and attribute of each surface of the goods are labeled. For example, the goods A is a cuboid, which includes six surfaces, namely a, b, c, d, e and f. The surface a is the top surface, the surface c is the bottom surface, and the surfaces b and d are used for clamping. Therefore, the surfaces b and d are the operation surfaces.

[0072] S303: Generate robot control instructions based on the posture parameters of the collaborative robot and the operation surface of the goods. The robot control instructions include a time sequence and an action sequence.

[0073] In this step, robot control instructions are generated based on the posture parameters of the collaborative robot and the operating surface of the goods. According to the status of the goods and the status of the collaborative robot, the actions that the collaborative robot needs to perform in the process of clamping the goods can be determined, and corresponding instructions are generated based on the actions, that is, robot control instructions are obtained. The time series records the time when each action is executed.

[0074] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of encrypting the robot control instruction, sending it to the collaborative robot, and decrypting and executing the corresponding robot control instruction by the collaborative robot specifically include:

[0075] S401, randomly generate two sets of encryption functions, send the encryption functions to the collaborative robot, and obtain robot control instructions.

[0076] In this step, two sets of encryption functions are randomly generated. Specifically, the type of encryption function is fixed, which is a one-dimensional multi-function, such as f(x)=a+bx+cx 2 +dx 3 , the constant term of the function is generated by a random algorithm, thereby obtaining two sets of encryption functions, namely f1 and f2, and sending the encrypted functions to the collaborative robot.

[0077] S402: Generate two sets of mapping strings based on the two sets of encryption functions, and generate a data mapping relationship table based on the mapping strings.

[0078] In this step, two sets of mapping strings are generated based on the two sets of encryption functions, and a preset natural number sequence is input into the two sets of encryption functions at the same time, such as importing natural numbers 1, 2, 3, 4, 5..., and the two sets of encryption functions generate corresponding calculation values. The calculation values ​​are spliced ​​to obtain two sets of decimal strings, and the decimal strings are converted into binary strings, and then converted into hexadecimal strings. The correspondence between the characters in the hexadecimal strings is extracted in sequence. The two sets of hexadecimal strings are the first string and the second string, and the number of hexadecimal characters is sixteen. Each time, a character is intercepted from the starting position of the first string and the second string to construct a set of mapping relationships, such as A2382F7 and BD26134, then A corresponds to B, 2 corresponds to D, and 3 corresponds to 2 (if it conflicts with the previous mapping relationship, it will be discarded), until sixteen sets of mapping relationships are obtained, and a data mapping relationship table is constructed.

[0079] S403, data conversion is performed on the robot control instruction, the converted data is encrypted through the data mapping relationship table, and the encrypted robot control instruction is sent to the corresponding collaborative robot.

[0080] In this step, the robot control instruction is directly converted into hexadecimal, and then data conversion is performed according to the data mapping relationship table to obtain converted data, which is the encrypted robot control instruction. The converted data is sent to the corresponding collaborative robot. Since the collaborative robot also has a corresponding encryption function, it can decrypt the data mapping relationship table to obtain the corresponding robot control instruction. The collaborative robot receives the encrypted robot control instruction, decrypts it based on the encryption function, and performs validity check on the decrypted robot control instruction. If the check fails, it is determined that the instruction is abnormal, and an alarm is issued.

[0081] As shown in Figure 5 , a collaborative robot control system based on an industrial internet is provided, which comprises:

[0082] A local area network construction module 100 is used to construct a control local area network, which comprises a control center and a plurality of collaborative robots, and the control center is provided with an image acquisition device.

[0083] In the system, the local area network construction module 100 constructs a control local area network. In order to be able to collaboratively control all collaborative robots, all collaborative robots are connected to construct a local control network. A control center is arranged in the local control network, and the control center is directly or indirectly connected with all other collaborative robots. The devices in the local control network can be connected through wired connection, and any form of wireless connection can be used, as long as the timeliness of data transmission can be met. An image acquisition device is arranged on the control center. Specifically, the image acquisition device is a binocular camera, which can simultaneously acquire images from two angles. Subsequently, the positions of each pixel point in the picture can be recognized by using a binocular distance measuring algorithm to construct a three-dimensional model of the goods.

[0084] A goods information acquisition module 200 is used to acquire images of the goods, recognize the model and posture of the goods based on the image acquisition result, and obtain the goods state information.

[0085] In the system, the cargo information acquisition module 200 collects images of the cargo. Since the image collection device is a binocular camera, the cargo can be collected from different angles at the same time, and binocular images can be collected. By using binocular recognition technology, the positions of each pixel point in the binocular images can be recognized, and the positions of all objects in the picture can be recognized. By constructing a three-dimensional coordinate system, each pixel point can be mapped to the three-dimensional coordinate system, thereby constructing a model of the cargo. According to the model of the cargo, the model and the attitude of the cargo can be extracted, that is, the cargo state information can be obtained.

[0086] The instruction generation module 300 is configured to acquire the working state of the collaborative robot, and generate a robot control instruction based on the working state and the cargo state information.

[0087] In the system, the instruction generation module 300 acquires the working state of the collaborative robot. When the collaborative robot completes the last task, it will be in a certain state. For a five-axis robot, the rotation angle of each axis can be directly obtained when it is in the state. According to the working state of the collaborative robot, the current action of the robot can be determined, and according to the cargo state information, the attitude of the cargo in space can be known. Accordingly, the robot control instruction is generated. The robot control instruction is used to control the collaborative robot to operate, and the collaborative robot is used to carry or move the cargo.

[0088] The data encryption module 400 is configured to encrypt the robot control instruction and send it to the collaborative robot. The collaborative robot decrypts and executes the corresponding robot control instruction.

[0089] In the system, the data encryption module 400 encrypts the robot control instruction. When encrypting, two sets of encryption functions are generated by a random algorithm, and random numbers are generated by using the encryption functions. Specifically, since the encryption functions are randomly generated, the generated calculation values are also random when a preset natural number is imported into the encryption functions. A data mapping relationship table is constructed based on the randomly generated calculation values, and the data mapping relationship table is used to convert the data of the robot control instruction. At this time, data transmission can avoid data leakage, ensuring the security of the instruction. After the collaborative robot receives the above data, it can execute the instruction after decryption, thereby completing the processing of the cargo, such as clamping or carrying.

[0090] As shown in Figure 6 As a preferred embodiment of the present application, the cargo information acquisition module 200 includes:

[0091] The image collection unit 201 is configured to collect images of the cargo from at least two angles by using an image collection device, and obtain an image collection result. The image collection result includes multiple groups of cargo images.

[0092] In this module, the image acquisition unit 201 uses an image acquisition device to capture images of the goods from at least two angles. When capturing images, it is necessary to capture images from at least two angles. For example, if the goods are placed on a conveyor belt, the image acquisition direction of the image acquisition device can be adjusted. When the goods pass through the image acquisition device, an image is captured from the front and the rear of the goods respectively. Specifically, the direction in which the goods move forward is considered to be the front, and the opposite side of the front is considered to be the rear.

[0093] The model building unit 202 is configured to build a binocular image group based on the cargo and generate a cargo space model through binocular image recognition.

[0094] In this module, the model construction unit 202 constructs a binocular image group based on the cargo. If the image acquisition device is a monocular camera and cannot directly move the binocular image, it can capture images with a slight angle difference. For example, when the cargo is moving, the image acquisition device continuously captures two sets of images at an interval of 50ms. These two sets of images are then used as a binocular image group. The position difference between the two shots can be calculated based on the cargo conveying speed and the image acquisition interval. Binocular recognition is used to complete the identification of the cargo in the picture, thereby constructing a three-dimensional coordinate system and obtaining a model of the cargo, which is the cargo space model.

[0095] The cargo identification unit 203 is used to extract the size information of the cargo according to the cargo space model, query a preset cargo database according to the size information of the cargo, determine the model of the cargo, and generate cargo status information.

[0096] In this module, the cargo identification unit 203 extracts the cargo's dimensional information based on the cargo space model. After constructing the cargo space model, it reads the cargo's external dimensions, such as its length, width, and height, from the cargo space model. If the cargo is irregularly shaped, its edges are extracted and compared with the cargo database, which records the cargo model data. This comparison can determine the cargo model and corresponding dimensional information, and identify the cargo's posture, such as whether the front is facing up or whether it is rotated.

[0097] like Figure 7 As shown, as a preferred embodiment of the present invention, the instruction generation module 300 includes:

[0098] The parameter extraction unit 301 is used to obtain the working status of the collaborative robot and extract the posture parameters of the collaborative robot when the existing instructions are completed.

[0099] In this module, the parameter extraction unit 301 obtains the working status of the collaborative robot. Taking a five-axis robot as an example, the rotation angle of each axis of the five-axis robot is obtained. If the collaborative robot is equipped with a gripper, the opening angle of the gripper is identified to obtain the posture parameters of the collaborative robot.

[0100] The operation surface identification unit 302 is used to identify cargo status information and determine the operation surface of the cargo according to a preset cargo database.

[0101] In this module, the operating surface identification unit 302 identifies the cargo status information, records the cargo size information in the cargo database, and marks the orientation and attributes of each surface of the cargo. For example, if cargo A is a rectangular parallelepiped with six surfaces, namely a, b, c, d, e, and f, where surface a is the top surface, surface c is the bottom surface, and surfaces b and d are used for clamping, then surfaces b and d are operating surfaces.

[0102] The device control unit 303 is used to generate robot control instructions based on the posture parameters of the collaborative robot and the operation surface of the goods. The robot control instructions include a time sequence and an action sequence.

[0103] In this module, the device control unit 303 generates robot control instructions based on the posture parameters of the collaborative robot and the operating surface of the goods. According to the state of the goods and the state of the collaborative robot, it can determine the actions that the collaborative robot needs to perform in the process of clamping the goods, and generate corresponding instructions based on the actions, that is, obtain robot control instructions. The time series records the time when each action is executed.

[0104] like Figure 8 As shown, as a preferred embodiment of the present invention, the data encryption module 400 includes:

[0105] The function generation unit 401 is used to randomly generate two sets of encryption functions, send the encryption functions to the collaborative robot, and obtain robot control instructions.

[0106] In this module, the function generation unit 401 randomly generates two sets of encryption functions. Specifically, the type of the encryption function is fixed, which is a one-dimensional multi-function, such as f(x)=a+bx+cx 2 +dx 3 , the constant term of the function is generated by a random algorithm, thereby obtaining two sets of encryption functions, namely f1 and f2, and sending the encrypted functions to the collaborative robot.

[0107] The mapping table generating unit 402 is configured to generate two sets of mapping strings based on the two sets of encryption functions, and generate a data mapping relationship table based on the mapping strings.

[0108] In the module, the mapping table generating unit 402 generates two groups of mapping strings based on two groups of encryption functions, and inputs a preset natural number sequence into the two groups of encryption functions, such as importing natural numbers 1, 2, 3, 4, 5, and the two groups of encryption functions generate corresponding calculation values, the calculation values are spliced to obtain two groups of decimal strings, the decimal strings are converted into binary strings, and then the binary strings are converted into hexadecimal strings, the corresponding relationship between characters in the hexadecimal strings is extracted in sequence, the two groups of hexadecimal strings are a first string and a second string, the number of hexadecimal characters is sixteen, one character is extracted from the starting position of the first string and the second string each time, and a group of mapping relationships, such as A2382F7 and BD26134, are constructed to obtain that A corresponds to B, 2 corresponds to D, and 3 corresponds to 2 (if the mapping relationship conflicts with the previous mapping relationship, the mapping relationship is discarded), until sixteen groups of mapping relationships are obtained, and a data mapping relationship table is constructed.

[0109] The data converting unit 403 is configured to perform data conversion on the robot control instruction, encrypt the converted data by using the data mapping relationship table, and send the encrypted robot control instruction to the corresponding collaborative robot.

[0110] In the module, the data converting unit 403 converts the robot control instruction into hexadecimal, and then converts the data according to the data mapping relationship table to obtain converted data, which is the encrypted robot control instruction, and sends the converted data to the corresponding collaborative robot. Since the collaborative robot also has a corresponding encryption function, it can decrypt the converted data according to the constructed data mapping relationship table to finally execute the corresponding robot control instruction. After receiving the encrypted robot control instruction, the collaborative robot decrypts the encrypted robot control instruction based on the encryption function, and performs validity verification on the decrypted robot control instruction. If the verification fails, it is determined that the instruction is abnormal, and an alarm is issued.

[0111] The above only describes the preferred embodiments of the present application and should not be used to limit the present application. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A collaborative robot control method based on the Industrial Internet, characterized in that: The method comprises: Construct a control local area network, which consists of a control center and multiple collaborative robots. The control center is equipped with an image acquisition device. Capture images of the goods, identify the model and posture of the goods based on the image acquisition results, and obtain the goods status information; Obtain the working status of the collaborative robot and generate robot control instructions based on the working status and cargo status information; The robot control instructions are encrypted and sent to the collaborative robot, which decrypts and executes the corresponding robot control instructions.

2. The collaborative robot control method based on the Industrial Internet according to claim 1 is characterized in that: The step of capturing images of the goods, identifying the model and posture of the goods based on the image capture results, and obtaining the goods status information specifically includes: Capturing images of the cargo from at least two angles using an image acquisition device to obtain image acquisition results, wherein the image acquisition results include multiple sets of cargo images; Build a binocular image group based on the cargo and generate a cargo space model through binocular image recognition; The size information of the cargo is extracted according to the cargo space model, and the preset cargo database is queried according to the size information of the cargo to determine the model of the cargo and generate cargo status information.

3. The collaborative robot control method based on the Industrial Internet according to claim 1 is characterized in that: The step of obtaining the working status of the collaborative robot and generating the robot control instructions based on the working status and cargo status information specifically includes: Obtain the working status of the collaborative robot and extract the posture parameters of the collaborative robot when the existing instructions are completed; Identify cargo status information and determine the cargo handling area based on the preset cargo database; The robot control instructions are generated based on the posture parameters of the collaborative robot and the operation surface of the goods. The robot control instructions include a time sequence and an action sequence.

4. The collaborative robot control method based on the Industrial Internet according to claim 1 is characterized in that: The steps of encrypting the robot control instructions, sending them to the collaborative robot, and having the collaborative robot decrypt and execute the corresponding robot control instructions specifically include: Randomly generate two sets of encryption functions and send them to the collaborative robot to obtain robot control instructions; Generate two sets of mapping strings based on the two sets of encryption functions, and generate a data mapping relationship table based on the mapping strings; The robot control instructions are converted into data, the converted data is encrypted through a data mapping table, and the encrypted robot control instructions are sent to the corresponding collaborative robot.

5. The method for controlling a collaborative robot based on the Industrial Internet according to claim 4, wherein: After receiving the encrypted robot control instructions, the collaborative robot decrypts them based on the encryption function and performs a validity check on the decrypted robot control instructions. If the check fails, the instruction is judged to be abnormal and an alarm is issued.

6. A collaborative robot control system based on the Industrial Internet, characterized in that: The system comprises: A local area network construction module is used to construct a control local area network, which consists of a control center and multiple collaborative robots. The control center is equipped with an image acquisition device; The cargo information acquisition module is used to capture images of the cargo, identify the model and posture of the cargo based on the image acquisition results, and obtain cargo status information; The instruction generation module is used to obtain the working status of the collaborative robot and generate robot control instructions based on the working status and cargo status information; The data encryption module is used to encrypt the robot control instructions and send them to the collaborative robot, which decrypts and executes the corresponding robot control instructions.

7. The collaborative robot control system based on the Industrial Internet according to claim 6 is characterized in that: The cargo information acquisition module includes: An image acquisition unit, configured to acquire images of the cargo from at least two angles using an image acquisition device to obtain image acquisition results, wherein the image acquisition results include multiple sets of cargo images; A model building unit, configured to build a binocular image group based on the cargo and generate a cargo space model through binocular image recognition; The cargo identification unit is used to extract the size information of the cargo according to the cargo space model, query the preset cargo database according to the size information of the cargo, determine the model of the cargo, and generate cargo status information.

8. The collaborative robot control system based on the Industrial Internet according to claim 6, characterized in that: The instruction generation module includes: A parameter extraction unit is used to obtain the working status of the collaborative robot and extract the posture parameters of the collaborative robot when the existing instructions are completed; An operating surface identification unit is used to identify cargo status information and determine the cargo operating surface based on a preset cargo database; The equipment control unit is used to generate robot control instructions based on the posture parameters of the collaborative robot and the operating surface of the goods. The robot control instructions include time sequences and action sequences.

9. The collaborative robot control system based on the Industrial Internet according to claim 6, characterized in that: The data encryption module includes: A function generation unit is used to randomly generate two sets of encryption functions and send the encryption functions to the collaborative robot to obtain robot control instructions; A mapping table generating unit, configured to generate two sets of mapping strings based on the two sets of encryption functions, and generate a data mapping relationship table based on the mapping strings; The data conversion unit is used to convert the robot control instructions, encrypt the converted data through the data mapping relationship table, and send the encrypted robot control instructions to the corresponding collaborative robot.

10. The collaborative robot control system based on the Industrial Internet according to claim 9, characterized in that: After receiving the encrypted robot control instructions, the collaborative robot decrypts them based on the encryption function and performs a validity check on the decrypted robot control instructions. If the check fails, the instruction is judged to be abnormal and an alarm is issued.

Images