WO2022148328A1

WO2022148328A1 - Joint actuator and control method therefor, robot, storage medium and electronic device

Info

Publication number: WO2022148328A1
Application number: PCT/CN2021/144069
Authority: WO
Inventors: 黄晓庆; 张站朝; 罗程
Original assignee: 达闼机器人有限公司
Priority date: 2021-01-11
Filing date: 2021-12-31
Publication date: 2022-07-14
Also published as: CN112809676B; CN112809676A

Abstract

A joint actuator, comprising a controller (101), a sensor (102), a power assembly (103) and a motor driver (201), wherein the controller (101) is used to issue a decision instruction to a central processing unit (501) of a robot according to sensor data detected by the sensor (102), the central processing unit (501) generates first control information according to the decision instruction, and the controller (101) is further used to generate motor control parameters according to the first control information, and output, to the motor driver (201), second control information containing the motor control parameters; and the motor driver (201) is used to acquire the second control information, drive the power assembly (103) according to the motor control parameters in the second control information, and execute a target action. The joint actuator precisely controls a target action executed thereby according to sensor data, improving the accuracy of executing a task by a robot, and improving the success rate of task execution in a complex and variable environment. Further provided are a method for controlling a joint actuator, a robot, a storage medium and an electronic device.

Description

Joint actuator and control method thereof, robot, storage medium and electronic device

cross reference

This application claims the priority of the Chinese patent application filed on January 11, 2021 with the application number 202110032101.7 and the invention titled "Joint actuator and its control method, robot, storage medium and electronic device", all of which The contents are incorporated herein by reference.

technical field

The present disclosure relates to the field of robotics, and in particular, to a joint actuator and a control method thereof, a robot, a storage medium, and an electronic device.

Background technique

With the continuous development and progress of robot technology, people's demand for robots is also increasing, and robots are required to complete more sophisticated and complex target tasks. The joint actuator is one of the important components of the robot, which can be used to receive control information corresponding to the target task, and execute the target action according to the control information to complete the target task. However, in the related art, the joint actuator will be affected by the external environment when performing the target action. Under the complex and changeable external environment, there may be problems that the target action fails to be executed or the target task cannot be achieved after the target action is executed.

SUMMARY OF THE INVENTION

In order to solve the above problems, the present disclosure provides a joint actuator and a control method thereof, a robot, a storage medium and an electronic device.

In a first aspect, the present disclosure provides a joint actuator comprising a controller, a sensor and a power assembly, the controller being connected to the sensor and the power assembly, wherein:

The controller is configured to acquire the sensor data detected by the sensor, and upload the sensor data to the server, so that the server can issue decision-making instructions to the central processor of the robot according to the sensor data, so that all The central processing unit generates first control information according to the decision instruction, where the first control information is used to control the joint actuator to perform a target action;

The controller is further configured to acquire the first control information generated by the central processing unit, and control the operation of the power component according to the first control information to execute the target action.

In a first aspect, the present disclosure provides a joint actuator comprising a controller, a sensor, a power assembly and a motor driver, wherein:

the controller, configured to issue a decision-making instruction to the central processing unit of the robot according to the sensor data detected by the sensor, and the central processing unit generates first control information according to the decision-making instruction;

The controller is further configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver;

The motor driver is configured to acquire the second control information, drive the power component according to the motor control parameters in the second control information, and execute the target action.

Further, the power assembly includes a servo motor, and the motor driver is connected with the servo motor and the controller, wherein:

The motor driver is configured to drive the servo motor to run according to the motor control parameter to execute the target action when the second control information is acquired.

Further, the servo motor adopts amorphous material.

Further, the power assembly further includes a reducer, and the reducer is connected to the servo motor, wherein:

The speed reducer is used to reduce the motor speed of the servo motor to increase the torque.

Further, the joint actuator further includes a PON-CAN bus interface, and the controller further includes a network processor NPU, wherein:

The network processor NPU is configured to upload the sensor data to the server through the PON-CAN bus interface.

Further, the joint actuator also includes a control board, wherein:

The controller, the PON-CAN bus interface and the motor driver are all integrated on the control motherboard.

Further, the sensor data includes one or more of environmental data, position data and actuator power data.

Further, in the case that the sensor data includes the environment data, the sensor includes an environment sensor; or,

Where the sensor data includes the position data, the sensor includes a spatial position sensor and/or a high-precision position sensor; or,

Where the sensor data includes the actuator dynamics data, the sensors include force feedback sensors and/or high precision torque sensors.

In a second aspect, the present disclosure provides a joint actuator, the joint actuator includes a controller, a sensor and a power assembly, the controller is connected to the sensor and the power assembly, wherein:

The controller is configured to acquire sensor data detected by the sensor, and upload the sensor data to a server, and the server sends a decision-making instruction to the central processing unit of the robot according to the sensor data, and the central processing unit The controller generates first control information according to the decision instruction;

Further, the joint actuator further includes a motor driver, the power component includes a servo motor, and the motor driver is connected with the servo motor and the controller, wherein:

the controller, configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver;

Further, the servo motor adopts amorphous material.

Further, the joint actuator also includes a control board, wherein:

In a third aspect, the present disclosure provides a robot comprising a central processing unit, a switching and routing assembly, and one or more joint actuators, the central processing unit communicating with the one through the switching and routing assembly or multiple joint actuators are connected; wherein, the joint actuator is the above-mentioned joint actuator.

Further, the switching and routing component is configured to transmit the first control information generated by the central processing unit to the joint actuator, and the switching and routing component includes a PON-CAN bus.

In a fourth aspect, the present disclosure provides a method for controlling a joint actuator, which is characterized by being applied to a controller for a joint actuator, where the joint actuator includes a controller, a sensor, a power component, and a motor driver, and the method includes :

obtaining sensor data detected by the sensor;

Issue a decision instruction to the central processor of the robot according to the sensor data, and the central processor generates first control information according to the decision instruction;

generating motor control parameters according to the first control information, and outputting second control information including the motor control parameters to the motor driver;

obtaining the second control information;

The power component is driven according to the motor control parameters in the second control information to execute the target action.

Further, the power assembly includes a servo motor, the motor driver is connected with the servo motor and the controller, and the power assembly is controlled to operate according to the second control information to execute the target action include::

Second control information including the motor control parameter is output to the motor driver, and the motor driver drives the servo motor to run according to the motor control parameter to execute the target action.

Further, the joint actuator further includes a PON-CAN bus interface, and the uploading of the sensor data to the server includes:

The sensor data is uploaded to the server through the PON-CAN bus interface.

In a fifth aspect, the present disclosure provides a method for controlling a joint actuator, which is characterized by being applied to a controller for a joint actuator, the joint actuator comprising a controller, a sensor and a power component, the controller and the A sensor is connected to the power assembly; the method includes:

obtaining sensor data detected by the sensor;

uploading the sensor data to a server, and the server issues a decision-making instruction to the central processing unit of the robot according to the sensor data, and the central processing unit generates first control information according to the decision-making instruction;

obtaining the first control information generated by the central processing unit;

The power component is controlled to operate according to the first control information to execute the target action.

Further, the joint actuator further includes a motor driver, the power component includes a servo motor, the motor driver is connected with the servo motor and the controller, and the control of the motor according to the first control information The power component operates to perform the target action including:

generating motor control parameters according to the first control information;

Outputting second control information including the motor control parameters to the motor driver, so that the motor driver drives the servo motor to run according to the motor control parameters to execute the target action.

The sensor data is uploaded to the server through the PON-CAN bus interface.

In a sixth aspect, the present disclosure provides a computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the above method are implemented.

In a seventh aspect, the present disclosure provides an electronic device, characterized in that it includes:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of the above method.

Using the above technical solution, the joint actuator includes a controller, a sensor, a power component and a motor driver, wherein: the controller is configured to issue a decision-making instruction to the central processing unit of the robot according to the sensor data detected by the sensor , the central processing unit generates first control information according to the decision-making instruction; the controller is further configured to generate motor control parameters according to the first control information, and output the motor control parameters to the motor driver. second control information; the motor driver is configured to acquire the second control information, drive the power component according to the motor control parameters in the second control information, and execute the target action. On the other hand, the joint actuator includes a controller, a sensor and a power component. The controller acquires the sensor data detected by the sensor and uploads the sensor data to the server, so that the server can download the data to the central processing unit of the robot according to the sensor data. issue a decision instruction, so that the central processing unit generates first control information according to the decision instruction, and the first control information is used to control the joint actuator to perform the target action; further, the controller can also obtain the above-mentioned central processing unit generated by the and control the operation of the power component according to the first control information to execute the target action. In this way, accurate sensor data can be obtained through the sensors in the joint actuator, and the target action performed by the joint actuator can be precisely controlled according to the sensor data, thereby improving the accuracy of the robot's task execution and enabling the robot to perform tasks in complex and changeable environments. Improve the success rate of task execution.

Other features and advantages of the present disclosure will be described in detail in the detailed description that follows.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and together with the following detailed description, are used to explain the present disclosure, but not to limit the present disclosure. In the attached image:

FIG. 1 is a schematic structural diagram of a joint actuator provided by an embodiment of the present disclosure;

FIG. 2 is a schematic structural diagram of a second joint actuator provided by an embodiment of the present disclosure;

3 is a schematic structural diagram of a third joint actuator provided by an embodiment of the present disclosure;

4 is a schematic structural diagram of a fourth joint actuator provided by an embodiment of the present disclosure;

5 is a schematic structural diagram of a robot provided by an embodiment of the present disclosure;

6 is a flowchart of a method for controlling a joint actuator provided by an embodiment of the present disclosure;

FIG. 7 is a flowchart of another joint actuator control method provided by an embodiment of the present disclosure;

8 is a block diagram of an electronic device provided by an embodiment of the present disclosure;

FIG. 9 is a block diagram of another electronic device provided by an embodiment of the present disclosure.

Detailed ways

The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, but not to limit the present disclosure.

In the following description, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

First, the application scenarios of the present disclosure will be described. The present disclosure can be applied to the field of robotics, especially the field of joint actuators for robots. The joint actuator generally completes the target task by receiving control information corresponding to the target task and executing the target action according to the control information. In the related art, the joint actuator cannot obtain sensor data, and the sensor data can be used to represent the information of the joint actuator itself and the external environment; changes, the joint actuator continues to execute the target action, which may cause the target action to fail or fail to complete the target task. For example, the joint actuator performs the target action of grabbing the target object at position A according to the received control information, and during the grabbing process, the target object moves to position B due to the external force, and continues to follow the original position. If some control information executes the grab action, the grab will fail, and the target action needs to be adjusted according to the B position of the target object after moving.

In order to solve the above problems, the present disclosure provides a joint actuator and a control method thereof, a robot, a storage medium and an electronic device. The joint actuator includes a controller, a sensor and a power component. The controller obtains the sensor data detected by the sensor and uploads the sensor data to the server, so that the server can issue decision instructions to the central processor of the robot according to the sensor data. , so that the central processing unit generates first control information according to the decision instruction, and the first control information is used to control the joint actuator to perform the target action; further, the controller can also obtain the first control information generated by the central processing unit. control information, and control the power component to run according to the first control information to execute the target action. In this way, accurate sensor data can be obtained through the sensors in the joint actuator, and the target action performed by the joint actuator can be precisely controlled according to the sensor data, thereby improving the accuracy of the robot's task execution and enabling the robot to perform tasks in complex and changeable environments. Improve the success rate of task execution.

The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic structural diagram of a joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 1 , the joint actuator may include a controller 101, a sensor 102, and a power assembly 103. The controller 101, the sensor 102, and the power assembly 103 connections, where:

The sensor 102 is used to acquire sensor data of the joint actuator.

The controller 101 is configured to acquire sensor data detected by the sensor 102, and upload the sensor data to the server, so that the server can issue decision-making instructions to the central processing unit of the robot according to the sensor data, so that the central processing The decision instruction generates first control information, where the first control information is used to control the joint actuator to perform the target action.

The controller 101 is further configured to acquire the first control information generated by the central processing unit, and control the operation of the power component according to the first control information, so as to execute the target action.

The controller is further configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver; the motor driver is configured to obtain the second control information The control information drives the power component according to the motor control parameters in the second control information to execute the target action.

The power assembly includes a servo motor, and the motor driver is connected with the servo motor and the controller, wherein: the motor driver is used for obtaining the second control information according to the The motor control parameters drive the servo motor to run and execute the target action.

Among them, the above-mentioned controller can obtain sensor data and upload it to the server through the on-board interface, wherein the on-board interface can include GPIO (General-Purpose Input/Output, general-purpose input and output) port, UART (Universal Asynchronous Receiver/Transmitter) , Universal Asynchronous Receiver Transmitter) interface, I2C (Inter-Integrated Circuit, two-wire serial bus) interface, SPI (SDH Physical Interface, SDH physical interface), SDIO (Secure Digital Input and Output, secure digital input and output card) One or more of interface methods such as interface, USB (Universal Serial Bus, Universal Serial Bus) interface.

The first control information may include first control instructions and/or first control data, and the central controller of the robot may transmit the first control information to the controller of the joint actuator through the exchange and routing components of the robot; or The first control information can be written into a memory, and the first control information can be read from the memory by the controller of the joint actuator.

It should be noted that, the sensor 102 may be one or more. For example, the sensor 102 may include lidar, 3D depth vision camera, RGB (red, green and blue) camera, binocular SLAM (Simultaneous Localization And Mapping) camera, ultrasonic sensor, IMU (Inertial Measurement Unit, One or more of inertial measurement unit), air detection sensor and temperature and humidity sensor. The above-mentioned sensor data may include the shape of the target object measured by lidar, 3D depth vision camera or ultrasonic sensor and the distance (depth) from the target object to the joint actuator; or, may include the air measured by the air detection sensor. Pressure; alternatively, it can include temperature and humidity measured by a temperature and humidity sensor; alternatively, it can include an environmental map obtained through an RGB camera or a binocular SLAM camera. Of course, the sensor data may also include any one or more of the above information.

Optionally, the controller 101 may acquire the sensor raw data detected by the sensor 102, and obtain the sensor data after preprocessing the sensor raw data, wherein the preprocessing may include processing such as denoising, enhancement, and optimization.

The above-mentioned server may be a cloud server, a desktop computer, or other electronic devices having a memory and a processor. The server and the robot applying the joint actuator can be connected through wired network or wireless network. Thereby, the above sensor data is acquired, a decision-making instruction can be generated according to the sensor data, and the decision-making instruction can be issued to the central processing unit of the robot. The decision instruction can represent a new task instruction or an adjustment to the original task instruction.

Using the above joint actuator, the joint actuator includes a controller, a sensor and a power component. The controller obtains the sensor data detected by the sensor and uploads the sensor data to the server, so that the server can report to the robot center according to the sensor data. The processor issues a decision-making instruction, so that the central processing unit generates first control information according to the decision-making instruction, and the first control information is used to control the joint actuator to perform the target action; further, the controller can also obtain the above-mentioned central processing unit. The processor generates the first control information, and controls the power component to operate according to the first control information, so as to execute the target action. In this way, accurate sensor data can be obtained through the sensors in the joint actuator, and the target action performed by the joint actuator can be precisely controlled according to the sensor data, thereby improving the accuracy of the robot's task execution and enabling the robot to perform tasks in complex and changeable environments. Improve the success rate of task execution.

FIG. 2 is a schematic structural diagram of another joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 2 , on the basis of the joint actuator shown in FIG. 1 , the joint actuator may further include a motor driver 201 . The assembly may include a servo motor 202, the motor driver 201 is connected to the servo motor 202 and the controller 101, wherein:

The controller 101 is configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver 201;

The motor driver 201 is configured to drive the servo motor 202 to run according to the motor control parameter under the condition of acquiring the second control information, so as to execute the above-mentioned target action.

The second control information may also include second control instructions and/or second control data. The motor driver may be a motor driver with DSP (Digital Signal Process, digital signal processing) processing capability. When the second control information is obtained, digital signal processing can be performed on the second control information to obtain motor control parameters, and the servo motor 202 is driven to run according to the motor control parameters, and the motor driver drives the servo motor to run. It can include SVPWM (Space Vector Pulse Width Modulation, different switching modes of three-phase inverters) or SPWM (Sinusoidal Pulse Width Modulation, sinusoidal pulse width modulation).

In this way, through the motor driver and the servo motor, under the control of the controller, the target action can be executed according to the first control information.

Further, the above-mentioned servo motor 202 can be made of amorphous material.

It should be noted that compared with traditional motor materials (such as traditional silicon steel), amorphous materials have low loss, excellent magnetic properties, high wear resistance, corrosion resistance, high hardness and toughness, high resistivity and electromechanical coupling properties Therefore, it can effectively reduce the iron loss of the motor and reduce the temperature rise. In addition, under the same excitation magnetic field strength, the magnetic flux density of traditional motor materials decreases rapidly with the change of frequency, while the decrease of amorphous materials is smaller. It can be seen that the use of amorphous materials at higher frequencies has greater advantages. For example, Fe-based amorphous alloys (Fe-based amorphous alloys) are a kind of amorphous materials, and the molecules (or atoms, ions) that make up its substances are not regularly periodic in space, and there are no crystal grains, crystals of crystalline alloys. world exists.

In this way, the above-mentioned servo motor adopts amorphous material, which can effectively reduce losses, improve motor efficiency, light weight and small size, especially high-speed or high-power density motors that work at high frequencies can play a significant advantage.

Optionally, the servo motor 202 may be an AC servo driver with high torque density using amorphous materials, which has the advantages of high torque-to-inertia ratio, no brushes and commutation sparks, etc., which can further improve the performance of the joint actuator.

FIG. 3 is a schematic structural diagram of another joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 3 , on the basis of the joint actuator shown in FIG. 2 , the power assembly may further include a speed reducer 302 . 302 is connected with the servo motor 202, wherein:

The speed reducer 302 is used to reduce the motor speed of the servo motor 202 to increase the torque.

Wherein, the reducer 302 may be a reducer corresponding to the target reduction ratio. For example, the reducer may include an RV reducer, a roller reducer, a pendulum reducer, a planetary reducer, a planetary plus end gear, a lantern gear and One or more of harmonic reducers.

It should be noted that the reducer is a precise power transmission mechanism, which can use the speed converter of the gear to decelerate the number of revolutions of the servo motor to the required number of revolutions, and obtain a larger torque device, thereby reducing the speed of the servo motor. speed of the motor to increase the torque. In this way, the speed reducer makes the servo motor run at a suitable speed, and accurately reduces the speed to the speed required by each part of the robot, which improves the rigidity of the mechanical body and outputs a larger torque.

Further, as shown in FIG. 4 , the power assembly may further include an encoder 402, and the encoder 402 may be an encoder supporting unidirectional high precision, or an encoder supporting bidirectional high precision, and the encoder may be used for Measure the rotation angle and speed of the servo motor, and transmit the rotation angle and speed to the motor driver, so that the motor driver can adjust the motor control parameters according to the rotation angle and speed. The above-mentioned servo motor, high-precision encoder and reducer corresponding to the target reduction ratio are integrated into the joint actuator, as the power component of the joint actuator, for executing more precise target actions.

FIG. 4 is a schematic structural diagram of another joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 4 , the joint actuator further includes a PON-CAN bus interface 401, and the controller may include a network processor NPU, wherein:

The NPU is used for uploading the sensor data to the server through the PON-CAN bus interface.

It should be noted that CAN is the abbreviation of Controller Area Network, and PON (Passive Optical Network: Passive Optical Network) is a pure medium network, which is based on passive optical fiber networking to avoid electromagnetic interference from external equipment. It reduces the failure rate of lines and external equipment, improves system reliability, saves maintenance costs, and can provide very high bandwidth to meet high-speed transmission requirements. Compared with active systems, PON has the advantages of saving optical cable resources, sharing bandwidth resources, saving equipment room investment, high equipment security, fast network construction speed, and low comprehensive network construction cost. The passive technology can be combined with a variety of technologies, including APON (ATM Passive Optical Networks, a passive optical network based on cell transmission protocol), GPON (Gigabit-Capable Passive Optical Networks, passive optical networks with gigabit capabilities) Optical Network) and EPON (Ethernet Passive Optical Network, Ethernet Passive Optical Network), etc.

In this way, through the PON-CAN bus interface and the NPU, a PON-CAN communication bus supporting high frequency and ultra-large bandwidth is realized, thereby enhancing the processing efficiency and action execution efficiency of the joint actuator.

Further, as shown in FIG. 4 , the joint actuator may further include a control board 403 , wherein: the controller, the PON-CAN bus interface and the motor driver are all integrated on the control board.

In this way, through the integration of the control board, the space of the joint actuator is saved, the volume of the joint actuator is reduced, and the integration degree and performance of the joint actuator are improved.

Optionally, as shown in FIG. 4 , the controller may also include a central processing unit (CPU) and an image processing unit (GPU), wherein: the CPU and the GPU are used to perform data operations in parallel according to the first control information to generate motor control parameters. , the processing bit width of the processor includes one or more of 32 bits, 64 bits and 128 bits.

In addition, as shown in FIG. 4 , the joint actuator may further include a memory MEM, and the memory MEM may also be integrated on the control main board 403 . The memory may be a high-speed memory chip, for example, the high-speed memory chip may include Flash (flash memory), SRAM (Static Random-Access Memory, static random access memory), SDRAM (Synchronous Dynamic Random-Access Memory, synchronous dynamic random access memory) One or more of ROM (Read-Only Memory, read-only memory). The memory can be used to store and obtain data that needs to be transmitted to and from the CPU, GPU, NPU, and sensors.

In this way, by integrating the CPU, GPU, NPU, motor driver and high-speed memory chip on the control board of the joint actuator, the volume of the joint actuator can be further reduced, and the integration degree and performance of the joint actuator can be improved.

In other embodiments of the present disclosure, the sensor data detected by the above-mentioned sensor 102 may include one or more of environmental data, position data and actuator dynamic data, wherein the environmental data may be used to characterize the joint actuator. information of the external environment at the location; the position data may include the spatial position information of the joint actuator, or the distance information between the joint actuator and the target object; the actuator power data may include the magnitude and direction of the torque output by the joint actuator , and the force of the joint actuator.

Further, where the sensor data includes environmental data, the sensor may include an environmental sensor; or,

Where the sensor data includes the actuator dynamics data, the sensor includes a force feedback sensor and/or a high precision torque sensor.

For example, as shown in FIG. 4 , the above-mentioned sensor 102 may include one or more of an environmental sensor, a spatial position sensor, a force feedback sensor, a high-precision torque sensor and a high-precision position sensor. in:

Environmental sensors, which can include air temperature and humidity sensors, evaporation sensors, rain sensors, light sensors, wind speed and direction sensors, cameras, etc., can accurately measure the environmental information where the joint actuators are located.

The spatial position sensor can be used to measure the three-dimensional spatial position of the target object under three-dimensional coordinates.

The force feedback sensor can be used to measure the force of the joint actuator.

High-precision torque sensor can be used to measure the magnitude and direction of torque output by joint actuators.

A high-precision position sensor that can be used to measure the position of a target object and convert it into a usable output signal. The position sensor is a contact type or a proximity type, wherein the contact type position sensor detects the contact position of the joint actuator itself and the target object by contacting and squeezing with the target object; while the proximity type position sensor can be used without direct contact with the object. Detect the relative position of the joint actuator itself and the target object.

In this way, through the above one or more sensors, multi-dimensional sensor data can be realized, and the sensor data can be uploaded to the server to form a multi-dimensional control self-feedback system, which improves the accuracy and success of the joint actuator in executing the target action. Rate.

Optionally, the manner in which the above-mentioned server generates the decision instruction according to the sensor data may include any one of the following two manners:

Manner 1: An initial task instruction may be generated according to the above sensor data, and the initial task instruction may be used as a decision instruction.

In this mode, the joint actuator is currently in an idle state, that is, no target action is performed. At this time, if the server receives the target task input by the user, it can generate an initial task instruction according to the above sensor data and the target task, and send the initial task instruction as a decision instruction to the central processing unit of the robot. For example, the server receives the target task input by the user as "pick up a glass of water", and the sensor data contains the information of the paper cup and the water dispenser, as well as the distance information between the water dispenser and the joint actuator, then the sensor data and the target task can be generated based on the sensor data and the target task. The initial task instruction of "use a paper cup to pick up a glass of water from the water dispenser", and use the initial task instruction as a decision-making instruction.

In addition, if the server does not receive the target task input by the user, it can also automatically generate the target task according to the sensor data and the preset task rules, and generate an initial task instruction according to the sensor data and the target task, and use the initial task instruction as the decision instruction. For example, taking the sensor data as environmental data and the sensor as an environmental sensor as an example, the environmental sensor may be a camera, and the environmental data may include a real-time environmental image within a specified environmental range captured by the camera. Perform image recognition processing to determine that there is waste on the ground within the specified environmental range, and the preset task rules include "the task of cleaning the ground needs to be started when there is waste on the ground", the server will be based on the sensor data and The task rule can automatically generate the target task of "cleaning the ground", and further generate an initial task instruction according to the sensor data and the target task. The initial task instruction may include moving to the location of the waste and recycling the waste to a designated location. .

In a second manner, a new task instruction may be generated after adjusting the current task instruction according to the above sensor data, and the new task instruction may be used as the decision instruction.

In this mode, the joint actuator is currently in a working state, that is, the target action corresponding to the current task instruction is being executed. At this time, the server can determine whether the current task instruction needs to be adjusted according to the sensor data; if it is determined that the current task instruction needs to be adjusted according to the sensor data, a new task instruction can be generated according to the sensor data as the decision instruction; If the instruction and the sensor data determine that the original task instruction does not need to be adjusted, the decision instruction may not be generated, or the generated decision instruction is to continue executing the original task instruction.

The above-mentioned method of determining whether the current task instruction needs to be adjusted according to the sensor data may include: if the sensor data related to the target object in the current task instruction has changed, it is determined that the current task instruction needs to be adjusted; If the sensor data related to the target object has not changed, it is determined that the current task instruction does not need to be adjusted. For example, the current task command is to grab the target object at position A, and the target object in the sensor data has moved from position A to position B, or a new obstacle appears between the joint actuator and the position A where the target object is located. , in this way, it can be determined that the current task command needs to be adjusted, and a new task command can be generated according to the sensor data as the decision command; on the contrary, if the position of the target object in the sensor data remains unchanged, and the joint actuator and the target object If the environment on the path has not changed, it can be determined that the current task instruction does not need to be adjusted, the decision instruction may not be generated, or the generated decision instruction is to continue to execute the original task instruction, and the joint executor continues to execute the original target action.

It should be noted that, the specific manner in which the above server generates the decision instruction according to the sensor data may also refer to the implementation manner in the related art, which is not limited in the present disclosure.

In this way, by adjusting the execution of the target action through the sensor data, it is possible to ensure the smooth completion of the target action.

In addition, the joint actuator in the present disclosure may be an SCA (Smart Compliant Actuator, smart flexible actuator), and the smart flexible actuator can combine the above-mentioned controllers, sensors, motor drivers, servo motors, reducers, encoders and other cores The components are highly integrated, forming a highly integrated intelligent and flexible joint actuator, which is one-tenth the volume of the traditional servo system under the same performance; the above-mentioned servo motor can use amorphous materials to support high-frequency operation; the above-mentioned controller By acquiring the sensor data detected by the sensor, and uploading the sensor data to the server through the high-speed and stable PON-CAN bus, the server can issue decision-making instructions to the central processing unit of the robot according to the sensor data, so that the central processing unit can make the decision based on the sensor data. The decision-making instruction generates first control information, and the first control information is used to control the joint actuator to perform the target action; the controller may also obtain the first control information, and control the CPU-based computing process or the CPU-based calculation process according to the first control information. The GPU calculates in parallel, outputs the second control information to the motor driver, and drives the servo motor to run through the motor driver to execute the target action, thereby forming a control self-feedback system.

FIG. 5 is a schematic structural diagram of a robot provided by an embodiment of the present disclosure. As shown in FIG. 5 , the robot includes a central processing unit 501, a switching and routing component 502, and one or more joint actuators 503 (as shown in the figure). joint actuator 5031, joint actuator 5032, ..., joint actuator 503n), the central processing unit is connected with the one or more joint actuators through the switching and routing component; wherein:

The central processing unit 501 is configured to generate first control information according to the received decision-making instruction; wherein, the first control information is used to control the joint actuator to perform the target action, and the decision-making instruction is to send the server to the robot center according to the sensor data. The instruction issued by the processor, the sensor data is the sensor data obtained by the joint actuator through the sensor.

The switching and routing component 502 is configured to transmit the first control information generated by the central processing unit to the joint actuator.

The joint actuator 503 may be the joint actuator in any of the above embodiments of the present disclosure.

Wherein, the first control information may include first control instructions and first control data. The switching and routing component may include one or more interfaces among CANOpen, EtherCAT, and CAN2.0, so as to realize the connection and data transmission between the central processing unit and the joint actuator.

In this way, through this solution, a very powerful distributed computing robot body can be constructed. Through the cooperation of the central processing unit and one or more joint actuators, the sensors of the joint actuators can obtain accurate sensor data, and accurately control according to the sensor data. The target action performed by the joint actuator improves the accuracy of the robot's task execution, and can improve the success rate of task execution in a complex and changeable environment.

Optionally, the switching and routing components described above may include a PON-CAN bus.

Wherein, the central processing unit is connected to one or more joint actuators via the PON-CAN bus, and the first control information generated by the central processing unit can directly enter the CPU or GPU through the network processor NPU through the PON-CAN bus interface.

In addition, the above switching and routing components can support data Layer 2 network switching and Layer 3 network routing between the central controller and one or more joint actuators, and all network connections can support IPv4 or IPv6 network protocols. Such a robot composed of multiple joints will form a distributed network, and each joint is a network computing node.

In this way, through the above-mentioned PON-CAN bus, compared with the traditional robot bus technology, it has high-frequency, stable and ultra-large bandwidth communication capabilities; it supports IPv4/IPv6 network protocols, so that a distributed network is formed between multiple joints of the robot body. Each joint actuator is a network node, thereby enhancing the processing efficiency and action execution efficiency of the joint actuator. At the same time, in the case of multi-robot collaboration, the PON-CAN summary can be used as an independent IP subnet interconnection between the robot and the cloud server, which can realize multi-robot cooperation to complete more complex tasks.

FIG. 6 is a flowchart of a method for controlling a joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 6 , the execution body of the method may be a controller of a joint actuator, and the joint actuator includes a controller, a sensor and a a power assembly, the controller is connected with the sensor and the power assembly; the method includes:

S601. Acquire sensor data detected by a sensor.

Wherein, the sensor data may include one or more of environmental data, position data and actuator power data, wherein the environmental data may be used to characterize the information of the external environment where the joint actuator is located; the position data may include the joint The spatial position information of the actuator, or the distance information between the joint actuator and the target object; the actuator power data may include the magnitude and direction of the torque output by the joint actuator, and the force of the joint actuator. The controller can acquire sensor data detected by the sensor through an on-board interface, where the on-board interface can include one or more of a GPIO port, a UART interface, an I2C interface, an SPI, an SDIO interface, and a USB interface.

Optionally, in this step, the acquired sensor raw data can be used as sensor data; the sensor raw data obtained by the sensor detection can also be obtained, and the above sensor data can be obtained after preprocessing the sensor raw data, wherein, Preprocessing can include denoising, enhancement, and optimization.

S602. Issue a decision-making instruction to the central processing unit of the robot according to the sensor data, and the central processing unit generates first control information according to the decision-making instruction.

Wherein, the first control information is used to control the joint actuator to perform the target action, and the first control information may include first control instructions and/or first control data, and the central controller of the robot may exchange and The routing component transmits the first control information to the controller of the joint actuator; the first control information may also be written into a memory, and the controller of the joint actuator reads the first control information from the memory.

The server may be a cloud server, a desktop computer, or other electronic devices including a memory and a processor. The sensor data can be uploaded to the server through the above-mentioned on-board interface, or the sensor data can be uploaded to the server through the robot's bus interface.

Similarly, the manner in which the above server generates a decision instruction according to the sensor data may include any one of the following two manners:

S603. Generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver.

Using the above method, the sensor data detected by the sensor is acquired, and the sensor data is uploaded to the server, so that the server can issue a decision-making instruction to the central processing unit of the robot according to the sensor data, so that the central processing unit generates a decision-making instruction according to the first control information; then obtain the first control information generated by the central processing unit, generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver.

S604. Acquire the second control information.

S605. Drive the power component according to the motor control parameters in the second control information to execute the target action.

In this embodiment of the present disclosure, the joint actuator further includes a motor driver, the power component includes a servo motor, the motor driver is connected with the servo motor and the controller, and executing the target action may include the following steps:

First, generating motor control parameters according to the first control information;

Then, the second control information including the motor control parameter is output to the motor driver, so that the motor driver drives the servo motor to run according to the motor control parameter to execute the target action.

In addition, the joint actuator may also include a PON-CAN bus interface, and the above step S602 uploading the sensor data to the server may include:

The sensor data is uploaded to the server through the PON-CAN bus interface.

In this way, since the PON-CAN bus avoids the influence of electromagnetic interference and provides an ultra-large bandwidth, the processing efficiency and action execution efficiency of the joint actuator are enhanced.

FIG. 7 is a flowchart of another method for controlling a joint actuator provided by an embodiment of the present disclosure. As shown in FIG. 7 , the execution body of the method may be a controller of a joint actuator, and the joint actuator includes a controller and a sensor. and a power assembly, the controller is connected with the sensor and the power assembly; the method includes:

S701. Acquire sensor data detected by a sensor.

Wherein, the sensor data may include one or more of environmental data, position data and actuator power data, wherein the environmental data may be used to characterize the information of the external environment where the joint actuator is located; the position data may include the joint The spatial position information of the actuator, or the distance information between the joint actuator and the target object; the actuator power data may include the magnitude and direction of the torque output by the joint actuator, and the force of the joint actuator. The controller can acquire sensor data detected by the sensor through an onboard interface, where the onboard interface can include one or more of a GPIO port, a UART interface, an I2C interface, an SPI, an SDIO interface, and a USB interface.

S702. Upload the sensor data to a server, so that the server issues a decision instruction to the central processor of the robot according to the sensor data, so that the central processor generates first control information according to the decision instruction.

S703: Acquire the first control information generated by the central processing unit.

S704. Control the power component to run according to the first control information to execute the target action.

Using the above method, the sensor data detected by the sensor is acquired, and the sensor data is uploaded to the server, so that the server can issue a decision-making instruction to the central processing unit of the robot according to the sensor data, so that the central processing unit generates a decision-making instruction according to the first control information; then obtain the first control information generated by the central processing unit, and control the power assembly to run according to the first control information to execute the target action, so as to obtain accurate sensor data through the sensor, and execute the The target action corresponding to the sensor data improves the accuracy of the robot's task execution, and can improve the success rate of task execution in a complex and changeable environment.

Further, in some other embodiments of the present disclosure, the joint actuator further includes a motor driver, the power component includes a servo motor, and the motor driver is connected with the servo motor and the controller, and the above step S704 is based on the first step. The control information to control the operation of the power component to perform the target action may include the following steps:

The sensor data is uploaded to the server through the PON-CAN bus interface.

FIG. 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. As shown in FIG. 8 , the electronic device 800 may include: a processor 801 and a memory 802 . The electronic device 800 may also include one or more of a multimedia component 803 , an input/output (I/O) interface 804 , and a communication component 805 .

Wherein, the processor 801 is used to control the overall operation of the electronic device 800 to complete all or part of the steps in the above-mentioned multi-robot control method. The memory 802 is used to store various types of data to support operations on the electronic device 800, such data may include, for example, instructions for any application or method operating on the electronic device 800, and application-related data, Such as contact data, messages sent and received, pictures, audio, video, and so on. The memory 802 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable programmable read-only memory ( Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (Read-Only Memory, ROM for short), magnetic memory, flash memory, magnetic disk or optical disk. Multimedia components 803 may include screen and audio components. Wherein the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in memory 802 or transmitted through communication component 805 . The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, a button, and the like. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them The combination is not limited here. Therefore, the corresponding communication component 805 may include: Wi-Fi module, Bluetooth module, NFC module and so on.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processor (Digital Signal Processor, DSP for short), digital signal processing equipment (Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components Implementation is used to execute the above-mentioned multi-robot control method.

In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned multi-robot control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the electronic device 800 to implement the above-mentioned multi-robot control method.

FIG. 9 is a block diagram of an electronic device 900 according to an exemplary embodiment. For example, the electronic device 900 may be provided as a server. 9 , an electronic device 900 includes a processor 922 , which may be one or more in number, and a memory 932 for storing a computer program executable by the processor 922 . The computer program stored in memory 932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 922 may be configured to execute the computer program to perform the above-described multi-robot control method.

In addition, the electronic device 900 may also include a power supply assembly 926, which may be configured to perform power management of the electronic device 900, and a communication component 950, which may be configured to enable communication of the electronic device 900, eg, wired or wireless communication. Additionally, the electronic device 900 may also include an input/output (I/O) interface 958 . Electronic device 900 may operate based on an operating system stored in memory 932, such as Windows Server, Mac OS, Unix, Linux, and the like.

In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned multi-robot control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 932 including program instructions, and the above-mentioned program instructions can be executed by the processor 922 of the electronic device 900 to implement the above-mentioned multi-robot control method.

In another exemplary embodiment, there is also provided a computer program product comprising a computer program executable by a programmable apparatus, the computer program having, when executed by the programmable apparatus, for performing the above The code part of the multi-robot control method.

The preferred embodiments of the present disclosure have been described above in detail with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above-mentioned embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure. These simple modifications all fall within the protection scope of the present disclosure.

In addition, it should be noted that each specific technical feature described in the above-mentioned specific implementation manner may be combined in any suitable manner under the circumstance that there is no contradiction. In order to avoid unnecessary repetition, various possible combinations are not described in the present disclosure.

In addition, the various embodiments of the present disclosure can also be arbitrarily combined, as long as they do not violate the spirit of the present disclosure, they should also be regarded as the contents disclosed in the present disclosure.

Claims

A joint actuator, characterized in that the joint actuator includes a controller, a sensor, a power component and a motor driver, wherein:

the controller, configured to issue a decision-making instruction to the central processing unit of the robot according to the sensor data detected by the sensor, and the central processing unit generates first control information according to the decision-making instruction;

The controller is further configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver;

The motor driver is configured to acquire the second control information, drive the power component according to the motor control parameters in the second control information, and execute the target action.
The joint actuator according to claim 1, wherein the power component comprises a servo motor, and the motor driver is connected with the servo motor and the controller, wherein:

The motor driver is configured to drive the servo motor to run according to the motor control parameter to execute the target action when the second control information is acquired.
The joint actuator according to claim 2, wherein the servo motor adopts amorphous material.
The joint actuator according to claim 2, wherein the power assembly further comprises a reducer, and the reducer is connected with the servo motor, wherein:

The speed reducer is used to reduce the motor speed of the servo motor to increase the torque.
The joint actuator according to any one of claims 1 to 4, wherein the joint actuator further comprises a PON-CAN bus interface, and the controller further comprises a network processor NPU, wherein:

The network processor NPU is configured to upload the sensor data to the server through the PON-CAN bus interface.
The joint actuator according to claim 5, wherein the joint actuator further comprises a control board, wherein:

The controller, the PON-CAN bus interface and the motor driver are all integrated on the control motherboard.
The joint actuator according to any one of claims 1 to 4, wherein the sensor data includes one or more of environmental data, position data and actuator dynamic data.
The joint actuator of claim 7, wherein:

where the sensor data includes the environment data, the sensor includes an environment sensor; or,

Where the sensor data includes the position data, the sensor includes a spatial position sensor and/or a high-precision position sensor; or,

Where the sensor data includes the actuator dynamics data, the sensors include force feedback sensors and/or high precision torque sensors.
A joint actuator, characterized in that the joint actuator comprises a controller, a sensor and a power assembly, the controller is connected with the sensor and the power assembly, wherein:

The controller is configured to acquire the sensor data detected by the sensor, and upload the sensor data to a server, and the server sends a decision-making instruction to the central processing unit of the robot according to the sensor data, and the central processing unit The controller generates first control information according to the decision instruction;

The controller is further configured to acquire the first control information generated by the central processing unit, and control the operation of the power component according to the first control information to execute the target action.
The joint actuator according to claim 1, wherein the joint actuator further comprises a motor driver, the power component comprises a servo motor, and the motor driver is connected with the servo motor and the controller, in:

the controller, configured to generate motor control parameters according to the first control information, and output second control information including the motor control parameters to the motor driver;

The motor driver is configured to drive the servo motor to run according to the motor control parameter to execute the target action when the second control information is acquired.
The joint actuator according to claim 10, wherein the servo motor adopts amorphous material.
The joint actuator according to claim 10, wherein the power assembly further comprises a reducer, the reducer is connected with the servo motor, wherein:

The speed reducer is used to reduce the motor speed of the servo motor to increase the torque.
The joint actuator according to any one of claims 9 to 12, wherein the joint actuator further comprises a PON-CAN bus interface, and the controller further comprises a network processor NPU, wherein:

The network processor NPU is configured to upload the sensor data to the server through the PON-CAN bus interface.
The joint actuator according to claim 9, wherein the joint actuator further comprises a control board, wherein:

The controller, the PON-CAN bus interface and the motor driver are all integrated on the control motherboard.
The joint actuator according to any one of claims 9 to 12, wherein the sensor data includes one or more of environmental data, position data and actuator dynamic data.
The joint actuator of claim 15, wherein:

where the sensor data includes the environment data, the sensor includes an environment sensor; or,

Where the sensor data includes the position data, the sensor includes a spatial position sensor and/or a high-precision position sensor; or,

Where the sensor data includes the actuator dynamics data, the sensors include force feedback sensors and/or high precision torque sensors.
A robot, characterized in that the robot includes a central processing unit, a switching and routing component, and one or more joint actuators, and the central processing unit is connected to the one or more joints through the switching and routing component The actuators are connected; wherein, the joint actuator is the joint actuator described in any one of the above claims 1 to 16 .
The robot of claim 17, wherein the switching and routing component is configured to transmit the first control information generated by the central processing unit to the joint actuator, the switching and routing component Including PON-CAN bus.
A joint actuator control method, characterized in that it is applied to a controller of a joint actuator, wherein the joint actuator includes a controller, a sensor, a power component and a motor driver, and the method includes:

acquiring sensor data detected by the sensor;

Issue a decision instruction to the central processor of the robot according to the sensor data, and the central processor generates first control information according to the decision instruction;

generating motor control parameters according to the first control information, and outputting second control information including the motor control parameters to the motor driver;

obtaining the second control information;

The power component is driven according to the motor control parameters in the second control information to execute the target action.
The joint actuator according to claim 19, wherein the power component comprises a servo motor, the motor driver is connected with the servo motor and the controller, and the control according to the second control information The power assembly operates to perform the target action comprising:

Second control information including the motor control parameters is output to the motor driver, and the motor driver drives the servo motor to run according to the motor control parameters to execute the target action.
The method according to claim 19, wherein the joint actuator further comprises a PON-CAN bus interface, and the uploading the sensor data to the server comprises:

The sensor data is uploaded to the server through the PON-CAN bus interface.
A joint actuator control method, characterized in that it is applied to a controller of a joint actuator, the joint actuator includes a controller, a sensor and a power assembly, and the controller is connected with the sensor and the power assembly ; the method includes:

acquiring sensor data detected by the sensor;

uploading the sensor data to a server, and the server issues a decision-making instruction to the central processing unit of the robot according to the sensor data, and the central processing unit generates first control information according to the decision-making instruction;

obtaining the first control information generated by the central processing unit;

The power components are controlled to operate according to the first control information to execute the target action.
The method according to claim 22, wherein the joint actuator further comprises a motor driver, the power component comprises a servo motor, the motor driver is connected with the servo motor and the controller, the Controlling the operation of the power component according to the first control information to perform the target action includes:

generating motor control parameters according to the first control information;

Outputting second control information including the motor control parameters to the motor driver, so that the motor driver drives the servo motor to run according to the motor control parameters to execute the target action.
The method according to claim 22, wherein the joint actuator further comprises a PON-CAN bus interface, and the uploading the sensor data to the server comprises:

The sensor data is uploaded to the server through the PON-CAN bus interface.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 19 to 24 are implemented.
An electronic device, comprising:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of the method of any one of claims 19 to 24.