A robot control system and a control method thereof

Abstract

The application relates to the technical field of intelligent manufacturing, and discloses a robot control system and a control method thereof, the robot control system comprising a sensor unit, a control unit, an intelligent control unit and a robot; the control unit is used for being dragged to perform an action; the sensor unit sends parameters of the action of the control unit to the intelligent control unit after obtaining the parameters; the intelligent control unit generates a control program according to the parameters of the action and sends the control program to the robot; and the robot performs the action according to the control program. The hand action is adjusted according to the position and posture provided by the control unit in real time, and the hand is simultaneously moved and twisted, so that the position and the posture are simultaneously adjusted; the operation is simple and intuitive, and does not need to be operated by professional personnel of the robot.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, in particular to a robot control system and a control method thereof. BACKGROUND

[0002] High degree of freedom manipulator robot is a robot with multiple degrees of freedom. For example, 7 degrees of freedom, since the 7 degrees of freedom robot not only meets the requirements of 6 degrees of freedom in space, but also has one more dimension, so he can not only reach any position and any posture in the operating range, even if there are obstacles and other situations in space, the 7 degrees of freedom robot can try to bypass the obstacles to reach the desired position and posture. Therefore, the 7 degrees of freedom robot is called "redundant robot", he is more flexible and can adapt to more complex environment. But accordingly, he is also more difficult to control.

[0003] The current programming process of the robot includes:

[0004] a) Determine all the work points of the robot;

[0005] b) Manually operate the robot to reach each work point in turn and complete the corresponding work. Record each work point to prepare for the next step of programming;

[0006] c) Through programming, let the robot reach each work point in turn and complete the work. If necessary, repeat the program to complete the same work in a loop.

[0007] As can be seen, to realize the programming of the robot, first of all, manual operation is necessary, and the operator must find all the work points manually and operate the tool (suction cup, gripper, torque wrench, etc.) to complete the corresponding work (suction of goods, grabbing parts, tightening screws, etc.) at the work point. But first of all, such operation requires very high professionalism and must be completed after professional training. Secondly, the operator must write a program to complete the automatic control of the robot, which also requires professional knowledge and training, therefore, an untrained person cannot complete the work of robot programming, which greatly limits the application of the robot.

[0008] Although professional robot programmers are familiar with the operation mode of the robot and the knowledge of programming, it is not easy to complete the programming work of the robot. On the one hand, the operation of the existing robot is not easy, and the manual operation work still needs long and hard work. On the other hand, the professional robot programmers are not familiar with the work to be completed. For example, the work of assembling a television set using a robot. The television set assembler is very familiar with the assembly work of the television set, but does not know how to operate the robot and complete the programming work. And the robot programmer does not understand the assembly work of the television set. Therefore, both sides still need to cooperate to complete it. This process is time-consuming and laborious, increases the production cost, and also limits the application of the robot. SUMMARY

[0009] The purpose of the present application is to provide a robot control system and its control method, which uses the action of the control unit to transmit the action parameters to the intelligent control unit to generate the control program to drive the robot action. The whole operation is simple and does not need the participation of professional personnel, greatly reducing the difficulty of using the robot.

[0010] In the first aspect, the present application provides a robot control system, comprising: a sensor unit, a control unit, an intelligent control unit and a robot;

[0011] The control unit is used to be pulled to perform an action;

[0012] The sensor unit is used to obtain the parameters of the action of the control unit and send them to the intelligent control unit;

[0013] The intelligent control unit is used to generate a control program according to the parameters of the action and send it to the robot;

[0014] The robot is used to act according to the control program.

[0015] As a further improvement of the present application, the control unit comprises a plurality of rotation units connected in sequence to form a high-degree-of-freedom control mechanism; at least one sensor unit is provided on each rotation unit.

[0016] As a further improvement of the present application, it further comprises a perception unit, which is arranged in the environment of the robot and is used to obtain the information of the environment and the operated object in the working process of the robot and send it to the intelligent control unit. The perception unit comprises a camera, a temperature sensor, a pressure sensor, a torque sensor, a motion sensor, a laser sensor, a photoelectric sensor and a level sensor.

[0017] In the second aspect, the present application provides a control method of a robot control system, comprising a training mode; the training mode comprises:

[0018] The sensor unit sends the action parameter of the operation unit to the intelligent control unit after obtaining the action parameter of the operation unit.

[0019] The intelligent control unit generates a control program according to the action parameter and sends it to the robot.

[0020] The robot completes a control process according to the control program.

[0021] As a further improvement of the present application, an application mode is further included, which comprises:

[0022] The intelligent control unit adopts a machine learning algorithm to train and learn a robot control program generation module according to the action parameter, and automatically generates a control program to control the movement of the robot.

[0023] As a further improvement of the present application, the intelligent control unit sorts and combines different operation processes to generate a control program.

[0024] As a further improvement of the present application, the intelligent control unit simultaneously receives operation information of multiple operation units and information of multiple sensor units.

[0025] The control program of the corresponding robot is generated according to the operation information of the multiple operation units and the information of the multiple sensor units.

[0026] As a further improvement of the present application, the sensing unit collects environmental and operated object parameters and sends them to the intelligent control unit, and the intelligent control unit optimizes the generation of the control program according to the environmental and operated object parameters.

[0027] As a further improvement of the present application, when the robot completes different control tasks, it includes:

[0028] When the operated object is the same and the position and attitude of the operated object are kept the same, the robot is operated by the operation unit to complete a control process on the operated object; the intelligent control unit converts the control process into a control program and directly sends it to the robot, so that the robot repeats the control process.

[0029] When the operated object is the same and the position and attitude of the operated object are kept the same, the robot is operated by the operation unit to complete a control process on the operated object; the intelligent control unit converts the control process into a control program and directly sends it to the robot, so that the robot repeats the control process.

[0030] When the operated objects are the same, but the positions and postures of the operated objects are different, the robot is operated by the operation unit to complete several similar operation processes; the intelligent control unit learns from the several similar operation processes and the positions and postures of the corresponding operated objects to automatically generate a robot control program and directly send the robot control program to the robot, so that the robot completes the operation process.

[0031] When the operated objects are different and the positions and postures of the operated objects are also different, the robot is operated by the operation unit to complete an operation process with common points; the intelligent control unit learns from the several operation processes and the positions and postures of the corresponding operated objects perceived by the perception unit and stores the learning results; when a specific operation is needed for an operated object that has been perceived or has not been perceived, the intelligent control unit automatically generates a robot control program and directly sends the robot control program to the robot, so that the robot completes the operation process.

[0032] As a further improvement of the present application, the action parameters include a time-rotation angle sequence of each rotation unit during the dragging or pulling of the operation unit.

[0033] Compared with the prior art, the present application has the following beneficial effects:

[0034] The present application measures the rotation angle of the operation unit in real time and accurately by the built-in sensor unit, and then feeds back to the intelligent control unit in real time, so that the intelligent control unit generates a control program according to the rotation angle; real-time control and accurate control are realized. The operator adjusts the hand movement according to the position and posture provided by the operation unit in real time, and simultaneously moves and twists the hand, so as to simultaneously adjust the position and posture. Such operation is simple and intuitive, and does not need professional personnel to operate the robot. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 is a schematic diagram of a robot control system provided by an embodiment of the present application;

[0036] Figure 2 is a schematic diagram of communication between the operation unit and the robot provided by an embodiment of the present application;

[0037] Figure 3 is a schematic diagram of dragging (or pulling) of the operation unit provided by an embodiment of the present application;

[0038] Figure 4 is a schematic diagram of the operation unit provided by an embodiment of the present application. DETAILED DESCRIPTION

[0039] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort should belong to the protective scope of the present application.

[0040] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0041] In order to more clearly illustrate the embodiments of the present application or the prior technical solutions, the drawings required in the embodiments or the prior technical description will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by a person of ordinary skill in the art without creative effort under the premise of not paying creative effort.

[0042] Term explanation:

[0043] Degrees of freedom: In general, the degrees of freedom are the same as the "number of independent rotation axes" of the robot, that is, a robot with 7 degrees of freedom must have 7 independent rotation axes.

[0044] Working point: The working point generally refers to the spatial position of the robot when operating the operated object, and in general, the working point is at the most front end of the robot.

[0045] When the robot works, the position and posture of the operated object must be known, and the working point of the robot must be moved to the corresponding position and posture for operation. To describe the position and posture in space, a coordinate system must be established. There are generally two coordinate systems that can be described: a global coordinate system and an axis coordinate system.

[0046] Global coordinate system: It refers to the spatial x-y-z spatial coordinate system, which can represent the position and posture of the working point by (x, y, z, a, b, g) 6-dimensional coordinates.

[0047] Axis coordinate system: When the rotation angles of each axis are fixed, the position and posture of the working point are uniquely determined, so (j1, j2, j3, j4, j5, j6, j7) 7 angle coordinates can be used to represent the position and posture of the working point (j1 represents the rotation angle of the first axis, and so on).

[0048] Description of the working point: Global coordinate system can be used, or the rotation axis coordinate system can be used, and conversion between the two is necessary.

[0049] As shown in Figure 1 The first object of the present application is to provide a robot control system, comprising a sensor unit, a manipulation unit, an intelligent control unit and a robot.

[0050] The manipulation unit is used to be pulled to perform actions; the sensor unit acquires parameters of the actions of the manipulation unit and sends them to the intelligent control unit; the intelligent control unit generates a control program according to the parameters of the actions and sends it to the robot; and the robot performs actions according to the control program.

[0051] The present application will be described in detail below in combination with specific embodiments:

[0052] As shown in Figure 2 The present application uses a high-degree-of-freedom manipulation unit 100 to manipulate a robot 200, so that ordinary operators can manipulate the robot 200. The degree of freedom of the manipulation unit 100 is generally high, for example, it can be 6 or 7 degrees of freedom of control.

[0053] In use, the operator drags (or pulls) and rotates the manipulation point A to manipulate. The manipulation point is located at the front end of the manipulation unit, as shown below Figure 3 When A is dragged and rotated, each rotation axis will rotate to meet the requirement of dragging.

[0054] As a specific scheme, while operating, the manipulation unit synchronously transmits the rotation angle of each rotation axis to the intelligent control unit through wired or wireless means, and finally sends it to the robot control system. The robot control system controls each rotation axis of the robot to rotate to the corresponding rotation angle according to the received rotation angle, so as to achieve the purpose of controlling the robot; and complete the whole process of robot operation.

[0055] The control process is as follows: the intelligent control unit inputs the received angle information sequence during the operation into an algorithm module, learns the angle information sequence of the whole operation process through the algorithm module, and through one or more such learning processes, the algorithm module can automatically generate a robot control program. Sending the control program to the robot can obtain the required motion trajectory and operation of the robot, thereby completing the automatic writing of the control program.

[0056] The application uses a high degree of freedom control unit to control the robot, instead of the existing and conventional control method, uses the control unit to control the robot, obtains the desired motion trajectory and operation of the robot, and uses the angle information transmitted by the control unit as the original information of automatic programming; uses an algorithm to train and learn the angle information transmitted by the control unit, and finally automatically generates a robot motion control program.

[0057] As shown in Figure 4 For example, the control unit 100 can include a plurality of rotation units 10 connected in sequence, and at least one sensor unit is arranged on each rotation unit. The rotation units 10 are connected through a connecting piece 20. The sensor unit can be an angle sensor.

[0058] As an example, for example, the rotation unit includes a first shell, a second shell, a torsion device, a bearing, an angle sensor, a communication control module and the like in the first shell, the bearing is installed on a bearing seat, the first shell is connected with the bearing seat, a rotating head can be rotatably arranged in the bearing, and the rotating head is connected with the output end of the torsion device to transmit the torsion force. The angle sensor and the communication control module are both installed in a sensor sleeve, the sensor sleeve is connected with the second shell, and an internal connection end of the second shell penetrates through the sensor sleeve and is connected with the rotating head. In work, the first shell is connected with the bearing seat, the second shell is connected with the sensor sleeve, and the first shell and the second shell rotate relative to each other.

[0059] The angle sensor inside the rotation unit can measure the relative rotation angle of the first shell and the second shell in real time.

[0060] As a further improvement, the rotation unit has a torsion device, when there is no external force to twist the rotation device, the torsion device is in an initial state and does not generate a torsion force. When there is an external force to twist the rotation unit, the torsion device also generates a torsion force to resist the external applied torsion force. When the external applied torsion force disappears, the torsion device makes the rotation unit return to the initial position.

[0061] The embodiment of the application can also increase a sensing unit. The sensing unit can be a camera, a temperature sensor, a pressure sensor, a torque sensor, a motion sensor, a laser sensor, a photoelectric sensor, a level sensor and the like. The sensing unit is used to obtain the position and attitude information of the operated object and the environmental information of the robot control site, and is sent to the intelligent control unit. This is optional, and some learning processes do not require a sensing unit.

[0062] The operation unit sends the movement information of each rotating shaft to the intelligent control unit during being dragged or pulled. The intelligent control unit can receive the movement information of each rotating shaft output by the operation unit, and forward the movement information to the robot to control the movement of the robot. Meanwhile, the intelligent control unit can also receive the information of the sensing unit, and train the robot control program generation module according to the movement information (or / and) the sensing information by using a machine learning algorithm. The robot control program generation module can generate a robot control program, and send the robot control program to the robot, so as to control the movement of the robot. Then, the robot moves according to the movement information sent by the intelligent control unit or the robot control program.

[0063] A second object of the present application is to provide a control method of a robot control system, comprising the following steps:

[0064] The sensor unit sends the action parameters of the operation unit to the intelligent control unit.

[0065] The intelligent control unit generates a control program according to the action parameters, and sends the control program to the robot.

[0066] The robot completes an operation process according to the control program.

[0067] During the operation, the operation unit synchronously transmits the rotation angle of each rotating shaft to the mechanical arm of the robot through a wired or wireless manner, and performs real-time control. The robot control system controls each rotating shaft of the robot to rotate to the corresponding rotation angle according to the received rotation angle, so as to achieve the purpose of controlling the robot.

[0068] Further, the robot also transmits corresponding information to the system through the sensing unit (for example, stress, temperature, posture, video, etc.), so as to provide more information for the operator to operate.

[0069] The specific control method comprises the following two stages:

[0070] Training stage:

[0071] The operator drags or pulls the operation unit to control the position and posture of the operation unit in real time, and sends the movement information of each rotating shaft of the operation unit to the intelligent control unit.

[0072] The sensing unit sends the obtained information to the intelligent control unit.

[0073] The intelligent control unit receives the movement information of each rotating shaft sent by the operation unit, and sends the movement information of the rotating shaft to the robot. Meanwhile, the intelligent control unit receives the information of the sensing unit.

[0074] The robot completes the operation movement according to the received movement information.

[0075] Meanwhile, the intelligent control unit adopts machine learning algorithm, uses the perception information and the motion information sent by the operation unit to train the internal robot control program generation module.

[0076] Application stage:

[0077] The robot control program generated by the robot control program generation module in the intelligent control unit is sent to the robot to control the motion of the robot. In this process, the operator and the operation unit will no longer be needed.

[0078] There can be multiple robot control program generation modules in the intelligent control unit. The multiple generated robot control program generation modules can be sorted and combined to generate new and more complex robot control programs. The intelligent control unit simultaneously processes the operation information of multiple operation units and the information of multiple perception units; generates control program generation modules for multiple robots according to the operation information of multiple operation units and the information of multiple perception units, and controls the cooperative motion of multiple robots.

[0079] The intelligent control unit can record part or all of the operation process of the operation unit in real time, and can record the information perceived by the perception unit. The recording function of the intelligent control unit is used for the subsequent training and learning, and automatic programming preparation.

[0080] When facing different control tasks:

[0081] a) When the operated objects are the same, and the positions and postures of the operated objects are kept unchanged, the operation unit can be used to operate the robot to complete a control process on the operated object (for example, picking up the operated object from point A, keeping the posture unchanged, moving and finally placing it at point B). The intelligent control unit can record this operation process, and can convert this operation process into a control program, and directly send it to the robot, so that the robot repeats the just operation process without the intervention of the operation unit. In this process, the perception unit can not be needed.

[0082] This operation can avoid manual programming, and does not need professional programmers, but only needs skilled workers on the production line. The user of the robot usually does not have professional robot programmers, but has a large number of skilled workers. This can reduce the programming and use cost of the robot.

[0083] b) When the same object is operated, the position and posture of the operated object are kept the same, the robot can be operated by the control unit to repeat the operation process several times. The intelligent control unit can learn from the several operation processes, and finally convert the several operation processes into a control program, which is directly sent to the robot, so that the robot can complete an operation process without the intervention of the control unit. This operation process is different from any previous operation process, but is an optimization of the previous operation process. In this process, the perception unit can not be needed.

[0084] This operation mainly avoids defects in one operation process. Through multiple operations, the intelligent control unit can abstract better position, posture, speed, etc., and form a more optimal operation process. In this process, the intelligent control unit already has a preliminary abstraction function.

[0085] c) When the same object is operated, the position and posture of the operated object are kept the same, the robot can be operated by the control unit to repeat the operation process several times. The intelligent control unit can learn from the several operation processes, and finally convert the several operation processes into a control program, which is directly sent to the robot, so that the robot can complete an operation process without the intervention of the control unit. This operation process is different from any previous operation process, but is an optimization of the previous operation process. In this process, the perception unit can not be needed.

[0086] For example, in existing automated production, the supply material needs to be placed neatly and fixed in position, which requires high automation, is more complex, is not easy to change, and has higher cost. The above control process does not require too many requirements for the placement of raw materials, and does not require manual robot programming.

[0087] d) When the operated objects are different, and the positions and postures of the operated objects are also different, the control unit can be used to operate the robot to complete the control process with common points (for example, all are turned upside down by 180 degrees), and the intelligent control unit can be trained according to the control process and the positions and postures of the operated objects sensed by the sensing unit. Through learning of the control process, the ability of automatic programming is obtained for the control with common points. When the operated object that has been sensed or has not been sensed needs to be operated, the intelligent control unit can automatically generate a program and directly send the program to the robot, so that the robot can realize the whole process of the control. The intelligent control unit is not to copy or call the previous control program, but to generate a new program for the operated object that has not been seen through learning. The process needs the participation of the sensing unit. The learning process of the intelligent control unit can be performed once, multiple times or continuously.

[0088] The learning ability of the intelligent control unit of the application is not only for a specific operated object or a specific control common point. The intelligent control unit can learn multiple different operated objects and multiple different operations through learning, and finally has the ability of automatic programming.

[0089] Further, the intelligent control unit can sort and combine different operation processes to generate a larger control program, and realize combination of the operation processes.

[0090] In the application, the control program of the robot is generated according to the control information of the control units and the information of the sensing units. For example, the intelligent control unit can receive the control information of two control units and the information of multiple sensing units at the same time. For example, double-hand operation can be realized, and more sensor information can be recorded.

[0091] The main advantages of the application are:

[0092] 1) Since the control unit is operated by manual dragging (or pulling), compared with the traditional operation mode of clicking button, setting parameter and rotating wheel, the operation is more intuitive. When the operator wants the robot to move to a point in space, the operator only needs to drag the control unit to the corresponding position with hand, and stops the dragging action when the robot reaches the desired position. When the operator wants the robot to adjust the posture, the operator only needs to rotate the hand to adjust the posture of the control unit, and stops the hand action when the desired posture is reached. In fact, the operator completely adjusts the hand action according to the position and posture of the control unit provided in real time, and simultaneously moves and twists the hand to adjust the position and posture. Such operation is simple and intuitive, and does not need professional personnel to operate the robot.

[0093] For example, the action of the operation unit can be copied to the robot by the intelligent control unit in the form of a "copy" action. The sensor unit plays a role in collecting action parameters. Each degree of freedom of the operation unit can correspond to each degree of freedom of the robot, one degree of freedom corresponds to one sensor, and the collection-processing-execution is realized in a one-to-one correspondence.

[0094] If the situation is more complex, the degrees of freedom of the operation unit and the robot are not consistent, the learning algorithm of the intelligent control unit can also be used to obtain the matching control operation.

[0095] 2) The operator completes the work (such as assembling a television) by operating the robot. This process can be performed only once or several times. The algorithm module processes the angle information returned by the operation unit to obtain the action required by the robot to complete the work. This process is completely automatic and does not require the intervention of the operator. When this process is completed, the control program is automatically generated without the intervention of a professional programmer.

[0096] 3) In traditional robot applications, when the production line or the product needs to be changed (for example, when the model of the television changes), all the robots on the production line need to be reprogrammed. This process must be completed by the robot professional and the production line technician. The whole process not only takes time and effort, but also increases the cost of the manufacturer. This is a great obstacle for manufacturers to use robots. Using the method of the present application, the operator only needs to be familiar with the use of the operation unit, and then operates the robot to complete the production process one or more times to automatically generate the control program without the intervention of a dedicated robot programmer. The operation unit is simple and intuitive to use, and is much simpler than traditional robot operation and programming. This greatly reduces the difficulty of using robots and promotes the popularization and application of robots.

[0097] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0098] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it, although the above embodiments of the present application have been described in detail, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application. Any modification or equivalent replacement, which should be covered within the protection scope of the claims of the present application.

Claims

1. A robot control system, characterized in that, The application relates to a control system for a robot, which comprises a sensor unit, a control unit, an intelligent control unit and a robot. The control unit is used for performing actions in traction. The control unit synchronously transmits the rotation angle of each rotation shaft to the intelligent control unit through wired or wireless transmission, and finally sends the rotation angle to a robot control system, which controls the rotation of each rotation shaft of the robot to the corresponding rotation angle according to the received rotation angle. The sensor unit is used for acquiring parameters of the actions of the control unit and sending the parameters to the intelligent control unit. The intelligent control unit is used for generating a control program according to the parameters of the actions and sending the control program to the robot. The intelligent control unit inputs the received angle information sequence during the operation process into an algorithm module, learns the angle information sequence of the whole operation process through the algorithm module, and automatically generates a robot control program through one or more learning processes. The robot is used for performing actions according to the control program. The intelligent control unit records part or all of the operation process of the control unit and the information perceived by the sensor unit in real time. When facing different control tasks: When the operated objects are the same and the positions and postures of the operated objects are kept unchanged, the robot is operated by the control unit to complete a control process, the intelligent control unit converts the control process into a control program and directly sends the control program to the robot, so that the robot repeats the control process. When the operated objects are the same and the positions and postures of the operated objects are kept unchanged, the robot is operated by the control unit to complete a control process, the intelligent control unit converts the control process into a control program and directly sends the control program to the robot, so that the robot repeats the control process. When the operated objects are the same but the positions and postures of the operated objects are different, the robot is operated by the control unit to complete several similar control processes, the intelligent control unit learns the similar control processes and the positions and postures of the corresponding operated objects, automatically generates a robot control program and directly sends the robot control program to the robot, so that the robot completes the control process. When the operated objects are different and the positions and postures of the operated objects are different, the robot is operated by the control unit to complete a control process with common points, the intelligent control unit learns the control processes and the positions and postures of the corresponding operated objects perceived by the sensor unit, automatically generates a robot control program and directly sends the robot control program to the robot, so that the robot completes the control process. The control unit comprises a plurality of rotation units which are sequentially connected to form a high-degree-of-freedom control mechanism, and each rotation unit is provided with at least one sensor unit. ​ The robot control system further comprises a perception unit arranged in a robot environment, configured to acquire environment and operated object information during a robot working process and send the information to the intelligent control unit, the perception unit comprising a camera, a temperature sensor, a pressure sensor, a torque sensor, a motion sensor, a laser sensor, and a level sensor; The algorithm module can process the angle information returned by the control unit to obtain the action required by the robot to complete the work and automatically generate a control program.

2. A control method of a robot control system characterized by, The robot control system of claim 1 comprises a training mode, wherein the training mode comprises: The sensor unit sends the action parameters of the control unit to the intelligent control unit; The intelligent control unit generates a control program according to the action parameters and sends the control program to the robot; The robot completes a control process according to the control program.

3. The control method of the robot control system according to claim 2, characterized by, The application mode comprises: The intelligent control unit adopts a machine learning algorithm to train and learn a robot control program generation module according to the action parameters and automatically generate a control program to control the movement of the robot.

4. The control method of the robot control system according to claim 2 or 3, characterized by, The intelligent control unit sorts and combines different operation processes to generate a control program.

5. The control method of the robot control system according to claim 2 or 3, characterized by, The intelligent control unit simultaneously receives control information of multiple control units and information of multiple sensor units; The control program of the corresponding robot is generated according to the control information of the multiple control units and the information of the multiple sensor units.

6. The control method of the robot control system according to claim 2 or 3, characterized by, The perception unit collects environment and operated object parameters and sends the parameters to the intelligent control unit, and the intelligent control unit optimizes and generates a control program according to the environment and operated object parameters.

7. The control method of the robot control system according to claim 2, wherein The action parameters comprise time-rotation angle sequences of each rotation unit during the dragging or pulling process of the control unit.

Images