Robot data acquisition method and system, storage medium, equipment and program product

Abstract

The embodiment of the invention provides a robot data collection method and system, a storage medium, equipment and a program product. The robot data collection method comprises the steps that a data collection management source of a robot is determined; the data acquisition management source comprises one or more of a cloud data acquisition management source and a human-computer interface data acquisition management source; and providing the robot data of the robot to the data acquisition management source through a data acquisition interface corresponding to the data acquisition management source. According to the invention, unified management of robot data acquisition can be realized, multiple data acquisition management sources such as a cloud end and a human-computer interface are supported, and a good software generalization ability is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of robotics technology, and in particular to a robot data acquisition method and system, storage medium, device, and program product. Background Art

[0002] The rapid development of artificial intelligence and robotics has led to a surge in demand for robotic data acquisition. For example, in order to leverage robotic data, it is necessary to collect multimodal motion data while the robot performs a fixed task. This data can include, for example, the motion trajectory of the gripper or dexterous hand, changes in joint angles, and the posture of the end effector.

[0003] At present, there are many types of robots, and the interface standards of robots developed by different robot manufacturers are not unified, which makes it difficult to achieve unified management of robot data collection.

[0004] Based on this, embodiments of the present application provide a robot data collection method and system, storage medium, device and program product to improve related technologies. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a robot data acquisition method and system, storage medium, equipment and program product, which can realize unified management of robot data acquisition, support multiple data acquisition management sources such as cloud and human-computer interface, and have good software generalization capabilities.

[0006] The purpose of the embodiments of the present application is achieved by using the following technical solutions:

[0007] In the first aspect, an embodiment of the present application provides a robot data collection method, which includes: determining the data collection management source of the robot; the data collection management source includes one or more cloud-based data collection management sources and human-machine interface data collection management sources; and providing the robot data of the robot to the data collection management source through the corresponding data collection interface of the data collection management source.

[0008] In some embodiments, the cloud-based data acquisition management source includes a cloud-based data acquisition management platform; or, the human-machine interface data acquisition management source includes a human-machine interface data acquisition management application.

[0009] In some embodiments, the data acquisition management source is determined based on the data acquisition management source information of the robot; the data acquisition management source information includes one or more of cloud data acquisition management source information and human-machine interface data acquisition management source information; the process of obtaining the data acquisition management source information includes: when the robot is started, reading the data acquisition management source information of the robot.

[0010] In some embodiments, the data acquisition interface corresponding to the data acquisition management source is determined based on the data acquisition management source and a first interface adaptation file, and the first interface adaptation file uses JSON format to store the data acquisition management source and its corresponding data acquisition interface.

[0011] In some embodiments, the robot data acquisition process includes: receiving input and output data of the input and output devices of the robot; performing one or more of data storage, data uploading, data verification and fault monitoring on the input and output data to obtain the robot data.

[0012] In some embodiments, the input and output devices are determined based on the input and output device information of the robot; and the process of obtaining the input and output device information includes: reading the input and output device information of the robot when the robot is started.

[0013] In some embodiments, the input and output data are received via a device interface corresponding to the input and output device.

[0014] In some embodiments, the device interface corresponding to the input / output device is determined based on the input / output device and a second interface adaptation file, and the second interface adaptation file stores the input / output device and its corresponding device interface in JSON format.

[0015] In some embodiments, the process of acquiring the input and output data includes: driving the input and output device through a driver management module corresponding to the input and output device to obtain the input and output data.

[0016] In some embodiments, the method further includes: enabling a driver management module corresponding to the input / output device.

[0017] In some embodiments, the drive management module corresponding to the input and output device is determined according to the device configuration information of the robot; the process of obtaining the device configuration information includes: reading the device configuration information of the robot when the robot is started.

[0018] In some embodiments, the input / output data is provided by an input / output data provider, and the input / output data provider is used to obtain the input / output data from the input / output device.

[0019] In some embodiments, the input and output data include one or more of the robot's image data, force feedback data, joint variable data, end effector posture data, sensor drive data, motor control data, peripheral drive data, and controller management data.

[0020] In the second aspect, an embodiment of the present application provides a robot data acquisition system, which includes: a process management module for determining the data acquisition management source of the robot; the data acquisition management source includes one or more cloud-based data acquisition management sources and human-machine interface data acquisition management sources; a data acquisition management interaction layer for providing the robot data of the robot to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source.

[0021] In some embodiments, the system also includes: a data acquisition task management layer, which is used to receive input and output data of the input and output devices of the robot; perform one or more of data storage, data upload, data verification and fault monitoring on the input and output data to obtain the robot data and provide it to the data acquisition management interaction layer.

[0022] In some embodiments, the system further includes: an input / output device interaction layer, configured to receive the input / output data through corresponding device interfaces of the input / output devices, and to provide the input / output data to the data acquisition task management layer.

[0023] In some embodiments, the system further includes: an input / output device driver layer, configured to drive the input / output device through a driver management module corresponding to the input / output device, so as to obtain the input / output data and provide the data to the input / output device interaction layer.

[0024] In some embodiments, the process management module is used to enable a corresponding driver management module of the input and output device.

[0025] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the robot data collection method described in any one of the first aspects is implemented.

[0026] In a fourth aspect, an embodiment of the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the robot data collection method described in any one of the first aspects is implemented.

[0027] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the robot data collection method described in any one of the first aspects.

[0028] The embodiment of the present application provides a robot data acquisition method and system, storage medium, device and program product. The method determines the robot's data acquisition management source; the data acquisition management source includes one or more of a cloud data acquisition management source and a human-machine interface data acquisition management source; and the robot data of the robot is provided to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source. By determining the robot's data acquisition management source, the robot data of the robot is provided to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source. In this way, through a unified data acquisition specification, the data acquisition requirements of different data acquisition management sources for the same type of robot can be met, and the data acquisition management sources of different types of robots can also be adapted in the interactive layer interface, thereby achieving unified management of robot data acquisition, and reducing the software development cost required to adapt to different data acquisition management sources, and having good software generalization capabilities. In addition, by supporting multiple data acquisition management sources such as the cloud and the human-machine interface, it can meet the robot data acquisition requirements in different scenarios and reduce the management cost of robot data acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The embodiments of the present application are further described below with reference to the accompanying drawings and specific implementation methods.

[0030] Figure 1 It is a flow chart of a robot data collection method provided in an embodiment of the present application.

[0031] Figure 2 It is a structural diagram of a robot data acquisition system provided in an embodiment of the present application.

[0032] Figure 3 It is a structural diagram of another robot data acquisition system provided in an embodiment of the present application.

[0033] Figure 4 This is a schematic diagram of the platform software architecture of a robot data acquisition system provided in an embodiment of the present application.

[0034] Figure 5 This is a structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of the embodiments of the present application.

[0036] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0037] The rapid development of artificial intelligence and robotics has generated a significant demand for robotic data acquisition. However, robot designs, such as those of humanoid robots, vary significantly across different manufacturers, not only in hardware structure (e.g., wheeled versus bipedal, number of fisheye cameras, etc.), but also in software implementation. Consequently, unified interface standards have yet to be established among manufacturers, making them extremely difficult to achieve in the short term.

[0038] See also Figure 1 , Figure 1 This is a schematic diagram of a robot data collection process provided in an embodiment of the present application.

[0039] In order to solve the problem that it is difficult to achieve unified management of data collection of different types of robots due to the lack of unified interface standards of different types of robots, the embodiment of the present application proposes a robot data collection method, such as Figure 1 As shown, the method includes steps S101 to S102.

[0040] Step S101: Determine the data acquisition and management source of the robot; the data acquisition and management source includes one or more of a cloud data acquisition and management source and a human-machine interface data acquisition and management source.

[0041] Step S102: providing the robot data of the robot to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source.

[0042] In some embodiments, the robot data collection method can be executed on a robot data collection system. For example, the robot data collection system can include: a process management module, a data acquisition management interaction layer, a data acquisition task management layer, an input / output device interaction layer, and an input / output device driver layer; the process management module interacts with the data acquisition management interaction layer, the data acquisition task management layer, the input / output device interaction layer, and the input / output device driver layer, respectively.

[0043] In some embodiments, the robot data acquisition system can be deployed on the robot device side, for example, it can be deployed on the robot body. For example, the robot data acquisition system can be mounted on the data acquisition control module of the domain controller of the robot body, or the robot data acquisition system can also be deployed on a local device that is directly connected to the robot body (for example, through a physical interface or a local area network) and can complete real-time interaction.

[0044] In some embodiments, the robot may be, for example, a bipedal robot (also known as a humanoid robot, a humanoid robot), a quadrupedal robot, a wheeled robot, or other bionic robots, or the robot may also be an industrial robot, which is not limited in the above embodiments.

[0045] In some embodiments, the robot's data acquisition management source is used to manage the collected robot data. The robot data may include multimodal motion data when the robot performs a fixed task. For example, it may include one or more of the following: the motion trajectory of the gripper or dexterous hand, joint angle changes, end effector posture and other data.

[0046] In some embodiments, the cloud-based data acquisition management source includes a cloud-based data acquisition management platform; or, the human-machine interface data acquisition management source includes a human-machine interface data acquisition management application.

[0047] A cloud-based data acquisition and management platform refers to a data acquisition and management platform based on cloud computing, which is responsible for collecting data from various devices (for example, different types of robots) and processing, storing and analyzing data. Robot data can be stored in a cloud database by the cloud-based data acquisition and management platform.

[0048] A human-machine interface data acquisition and management application is a data acquisition and management application integrated with the human-machine interface (HMI) and can be deployed on the device side of a robot. For example, this application can be deployed on an HMI device integrated into the robot or on an external HMI device.

[0049] In some embodiments, the data acquisition and management source specified by the robot manufacturer can be determined as the data acquisition and management source of the robot. For example, a robot manufacturer specifies a cloud-based data acquisition and management platform as the data acquisition and management source for the robots it produces.

[0050] In other embodiments, the data acquisition and management source of the robot can be determined based on the robot's configuration file. The robot's configuration file can include the robot's device model, device configuration, and data acquisition and management source information.

[0051] Exemplarily, the device configuration of the robot may include the input and output device configuration of the robot to indicate the existing hardware devices of the robot, which may include one or more of sensors (such as cameras, microphones, lidars, etc.), motors, controllers, speakers and expression displays.

[0052] Exemplarily, the cloud data acquisition management source information includes the cloud data acquisition management source model, such as the cloud data acquisition management platform model, and the human-machine interface data acquisition management source information includes the HMI data acquisition management platform model.

[0053] Specifically, the robot's configuration file can be a file that is pre-configured with the robot's data acquisition management source based on the application requirements of the robot purchaser. For example, some purchasers may need to use a cloud-based data acquisition management source to manage the robot data of a certain type of robot (for example, the robot model is model a). In this case, the data acquisition management source of this type of robot can be pre-configured as a cloud-based data acquisition management source in the robot's configuration file; while other purchasers may need to use a human-machine interface data acquisition management source to manage the robot data of this type of robot. In this case, the data acquisition management source of this type of robot can be pre-configured as a human-machine interface data acquisition management source in the robot's configuration file. It is understandable that both the cloud-based data acquisition management source and the human-machine interface data acquisition management source can be configured as the data acquisition management source of the same type of robot.

[0054] For example, for the robot of manufacturer B, the cloud data acquisition management source can be configured as the data acquisition management source of the robot of manufacturer B according to the application requirements of purchaser A, or the human-machine interface data acquisition management source can be configured as the data acquisition management source of the robot of manufacturer B according to the application requirements of purchaser C.

[0055] In some embodiments, the process management module can be used to read the robot's configuration file when the robot starts up to determine the robot's data acquisition management source.

[0056] In some embodiments, the data acquisition and management interaction layer can be used to provide the robot data of the robot to the data acquisition and management source via the corresponding data acquisition interface of the data acquisition and management source. For example, the data acquisition and management interaction layer can determine the corresponding data acquisition interface of the data acquisition and management source based on a predefined first interface adaptation file and the data acquisition and management source information broadcast by the process management module. The first interface adaptation file can store the adaptation relationship between the data acquisition and management source and its corresponding data acquisition interface.

[0057] In the above embodiment, by determining the robot's data acquisition management source, the robot's robot data is provided to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source. In this way, through a unified data acquisition specification, the data acquisition needs of different data acquisition management sources for the same type of robot can be met. It is also possible to adapt the data acquisition management sources of different types of robots in the interactive layer interface, thereby achieving unified management of robot data acquisition and reducing the software development costs required to adapt to different data acquisition management sources, and having good software generalization capabilities. In addition, by supporting multiple data acquisition management sources such as cloud and human-machine interface, it can meet the robot data acquisition needs in different scenarios and reduce the management costs of robot data acquisition.

[0058] In order to determine the data acquisition management source of the robot, in some embodiments, the data acquisition management source is determined based on the data acquisition management source information of the robot, and the data acquisition management source information may include one or more of cloud data acquisition management source information and human-machine interface data acquisition management source information.

[0059] As an example, the cloud-based data acquisition management source information may include the data acquisition interface information corresponding to the cloud-based data acquisition management source, and the human-machine interface data acquisition management source information may include the data acquisition interface information corresponding to the human-machine interface data acquisition management source. The data acquisition interface is used to transmit the robot's robot data to the corresponding data acquisition management source.

[0060] As an example, the data acquisition management source information may be pre-written into a configuration file on the robot device side, and the data acquisition management source information of the robot may be read from the configuration file on the robot device side to determine the data acquisition management source of the robot.

[0061] In some embodiments, the robot's data acquisition and management source information may include cloud-based data acquisition and management source information and a human-machine interface data acquisition and management source. If the robot's current network environment is abnormal (for example, the network is unstable or disconnected), the human-machine interface data acquisition and management source is determined as the robot's data acquisition and management source; if the robot's current network environment is normal, the cloud-based data acquisition and management source is determined as the robot's data acquisition and management source. In this way, when the network is unstable and the robot data cannot be provided to the cloud-based data acquisition and management platform, the robot can be switched to the local human-machine interface data acquisition and management source in a timely manner, thereby ensuring that the robot data is not lost. This allows for unified management of data acquisition for different robots while being able to adapt to different network environments, thereby improving the reliability of robot data acquisition.

[0062] In some embodiments, the process of obtaining the data acquisition management source information may include: reading the data acquisition management source information of the robot when the robot is started. For example, when the robot is started, the data acquisition management source information of the robot may be read from the robot's configuration file by the process management module to determine the robot's data acquisition management source.

[0063] In some embodiments, the cloud data acquisition management source can be a cloud data acquisition management platform built by the robot purchaser, or it can be a cloud data acquisition management platform provided by the robot manufacturer, or it can be a cloud data acquisition management platform provided by a third party (for example, a cloud service provider).

[0064] In the above embodiment, by reading the robot's data acquisition management source information when the robot is started, it can automatically adapt to different data acquisition environments without manual configuration. While achieving unified management of data acquisition from different robots, it further improves the software generalization capability.

[0065] In some embodiments, the robot is a first robot, and the robot data provided to the data acquisition management source of the first robot may include: first robot data obtained based on the first robot's own input and output data, and / or second robot data obtained based on the second robot's input and output data; wherein the first robot and the second robot are of different types, or the first robot and the second robot belong to different robot manufacturers. For example, for a robot from manufacturer B (which can serve as the first robot) and a robot from manufacturer C (which can serve as the second robot) purchased by customer A, the robot data of the robot from manufacturer B and the robot data of the robot from manufacturer C can be uniformly connected to the data acquisition management platform provided by manufacturer B (e.g., a cloud-based data acquisition management platform).

[0066] In order to determine the data acquisition interface corresponding to the data acquisition management source, in some embodiments, the data acquisition interface corresponding to the data acquisition management source can be determined based on the data acquisition management source and the first interface adaptation file, and the first interface adaptation file can use JSON format to store the data acquisition management source and its corresponding data acquisition interface.

[0067] Exemplarily, by reading the first interface adaptation file when the robot is started and configuring the data acquisition interface for the robot's data acquisition management source in the first interface adaptation file in JSON (JavaScript Object Notation, a lightweight data exchange format), the robot's robot data is provided to the corresponding data acquisition management source. For example, the image data captured by the robot is uploaded to the cloud data acquisition management source through the data acquisition interface corresponding to the cloud data acquisition management source. For example, the posture data of the robot is provided to the human-machine interface data acquisition management source through the data acquisition interface corresponding to the human-machine interface data acquisition management source.

[0068] In the above embodiment, the first interface adaptation file uses JSON to store the data acquisition management source and its corresponding data acquisition interface, thereby realizing the binding of the data acquisition management source and the data acquisition interface. In this way, in the process of realizing unified management of data acquisition of various types of robots, automatic adaptation of the interface can be achieved, further improving the generalization capability of the software.

[0069] In some embodiments, the robot data may include one or more of the following: input and output data of the input and output devices of the robot, and data obtained by processing the input and output data of the input and output devices of the robot.

[0070] In order to obtain the robot data of the robot, in some embodiments, the process of obtaining the robot data may include: receiving input and output data of the input and output devices of the robot; performing one or more processing of data storage, data uploading, data verification and fault monitoring on the input and output data to obtain the robot data.

[0071] In some embodiments, the input / output devices are configured to perform at least one data processing operation related to data input and data output. Exemplarily, the input / output devices may include one or more of the following: the robot's sensors (e.g., cameras, microphones, lidars, etc.), motors, controllers, speakers, and expression displays. For example, if the input / output devices are configured to perform data processing operations related to data input, the input / output devices may include sensors; sensors may include, for example, one or more of the following: cameras, microphones, lidars, touch sensors, temperature sensors, humidity sensors, and inertial measurement units (IMUs). If the input / output devices are configured to perform data processing operations related to data output, the input / output devices may include one or more of the following: motors, controllers, speakers, and expression displays. Motors may include, for example, one or more of the following: dexterous hand motors, robotic arm motors, bipedal motors, head motors, waist motors, and other motors. Controllers may include, for example, one or more of the following: power boards, microcontroller units (MCUs), and other controllers. In addition, the input and output devices may also include peripheral devices, which include one or more of the following: robot handles, virtual reality (VR) devices, motion capture devices and other peripheral devices.

[0072] In some embodiments, the input and output data may include one or more of the following: the robot's image data, force feedback data, visual data, auditory data, tactile data, olfactory data, taste data, joint variable data, end-effector pose data, sensor drive data, motor control data, peripheral drive data, and controller management data. This allows for the collection of multimodal data, including the robot's body data and environmental data.

[0073] In the above embodiment, the data acquisition task management layer can be used to receive the input and output data of the input and output devices of the robot, and perform one or more of the following processes: data storage, data uploading, data verification and fault monitoring on the input and output data to obtain the robot data. In this way, by processing the input and output data in different ways, the needs of different robot data acquisition tasks can be met, and the software generalization capability is further improved.

[0074] Exemplarily, the data acquisition task management layer may include at least one of the following: a data acquisition task management module, a data storage module, a data upload module, a data verification module, and a fault monitoring module.

[0075] In some embodiments, the data acquisition management interaction layer can determine a processing method for input and output data by reading the robot device configuration information broadcast by the process management module, and then process the input and output data accordingly based on the determined processing method. The robot device configuration information broadcast by the process management module can be read from the robot's configuration file by the process management module when the robot is started.

[0076] The storage processing of the input and output data may include: sending an instruction to the data storage module via the data acquisition task management module to instruct the storage module to start, stop, or interrupt the data storage operation. In addition, the data acquisition task management module may receive feedback from the data storage module to indicate whether the storage operation of the input and output data was successful.

[0077] The process of uploading input and output data may include: receiving, via a data upload module, an upload request for input and output data from a data acquisition task management module, and executing a data upload operation corresponding to the upload request. Furthermore, the data upload module may return feedback information corresponding to the upload request to the data acquisition task management module, indicating whether the upload operation for the input and output data was successful.

[0078] The verification process for input and output data may include: verifying the input and output data through a data verification module, obtaining a verification result, and feeding the verification result back to the fault monitoring module. The verification process may include, for example, at least one of the following: range checking (e.g., whether the data is within a reasonable range), timestamp continuity (e.g., whether the data is generated at a consistent time), and correlation verification (e.g., whether the data from multiple sensors is logically consistent).

[0079] The process of fault monitoring for input and output data may include: generating fault information based on the verification results of the input and output data by the fault monitoring module, for use in task management arbitration. The fault information may include, for example, the time of occurrence of the fault and the type of device error.

[0080] In order to determine the input and output devices of the robot, in some embodiments, the input and output devices can be determined based on the input and output device information of the robot; the process of obtaining the input and output device information can include: reading the input and output device information of the robot when the robot is started.

[0081] In some embodiments, the input / output device information may be identification information of the input / output device. The identification information of the input / output device may be, for example, the device name or device model of the input / output device. The device model of the input / output device may include, for example, information such as the manufacturer name, device type, and performance parameters.

[0082] In the above embodiment, when the robot starts up, the process management module can read the robot's input and output device information from the robot's configuration file and broadcast it. The input and output device information is used to determine the robot's input and output devices. For example, if the input and output device information includes the device model of a temperature sensor, it can be determined that the input and output device includes a temperature sensor. For another example, if the input and output device information includes the device signal of a flexible hand motor, it can be determined that the input and output device includes a flexible hand motor.

[0083] In some embodiments, the input and output data may be received via a device interface corresponding to the input and output device. For example, the input and output device information of the robot and the corresponding device interface information may be configured in a configuration file of the robot.

[0084] In some embodiments, the device interface corresponding to the input / output device can be determined based on the input / output device and a second interface adaptation file. The second interface adaptation file can store the input / output device and its corresponding device interface in JSON format. For example, the second interface adaptation file may store the device interface corresponding to the camera as " / dev / video0"; for example, the second interface adaptation file may store the device interface corresponding to the dexterous hand motor as " / dev / motor0".

[0085] In some embodiments, the input / output device interaction layer may be used to determine the device interface corresponding to the input / output device based on the second interface adaptation file and the input / output device information broadcast by the process management module.

[0086] In the above embodiment, by abstracting the interfaces of the robot's input and output devices, an interface adaptation file for adapting to different input and output devices is defined in JSON format on the robot device side. This allows automatic device interface adaptation by reading this interface adaptation file and combining it with the robot's existing input and output devices. This allows a robot equipped with different input and output devices to be delivered to a purchaser for data collection. The robot only needs to use the defined input and output devices and their corresponding device interfaces in the second interface adaptation file to search for the corresponding device interface. This allows the robot to receive input and output data from the device interface through the device interface, further enhancing the software's generalization capabilities.

[0087] In order to obtain input and output data from the input and output devices of the robot, in some embodiments, the process of obtaining the input and output data includes: driving the input and output devices via a driver management module corresponding to the input and output devices to obtain the input and output data. The driver management module can be, for example, a software component that controls the input and output devices, such as a standard driver or a third-party driver.

[0088] In the above embodiment, the input / output device driver layer can be used to drive the input / output device through the corresponding driver management module to obtain the input / output data, for example, the camera of the robot can be driven to obtain image data through the camera driver module.

[0089] Exemplarily, the input and output devices include sensors, and the sensor drive management module can be used to drive one or more of the following sensors of the robot: lidar, fisheye camera, depth camera, angle sensor, displacement sensor, torque sensor, inertial measurement unit (IMU) and other sensors, etc., to collect one or more of the robot's embodied data and sensor drive data. Embodied data may, for example, include one or more of the robot's image data, joint variable data and end effector posture data for sensing the environment and its own state. Sensor drive data may, for example, include control instructions for the drive management module to drive the sensor action to ensure the normal operation of the sensor.

[0090] Illustratively, the input and output devices include motors. The motor drive management module can be used to drive one or more of the following motors of the robot: dexterous hand motors, robotic arm motors, bipedal motors, head motors, waist motors, and other motors, so that the motors generate motor control data. The motor control data includes, for example, control instructions and / or control parameters for driving the motors, such as motor speed, angle, and / or direction.

[0091] Exemplarily, the input and output devices include peripheral devices, and the driver management module of the peripheral devices can be used to drive one or more of the following peripheral devices of the robot: a robot handle, a VR device, a motion capture device, and other peripheral devices, so that the peripheral devices generate peripheral driver data. The peripheral driver data can, for example, include communication data for interaction between the robot and the outside world, and the communication data can include one or more of the following: communication protocol data, device connection status, and user input commands (e.g., touch commands, key input, voice commands), etc.

[0092] Exemplarily, the input / output device includes a controller. The controller's drive management module can be used to drive one or more of the following controllers of the robot: a power board, an MCU, or other controllers, so that the controller generates controller management data. Controller management data may include, for example, current, voltage, motion control parameters, and / or robot operating status monitoring data.

[0093] In some embodiments, the method may further include: activating a driver management module corresponding to the input / output device. For example, based on the model of the input / output device for which input / output data is to be generated, a driver management module corresponding to the model of the input / output device may be determined, and the corresponding driver management module may be loaded and activated from the device driver layer. In the above embodiment, when the robot is started, the driver management module corresponding to the robot's input / output device may be activated via the process management module, enabling the driver management module to drive the input / output device to generate the corresponding input / output data, thereby obtaining robot data.

[0094] In order to determine the corresponding drive management module of the input and output device, in some embodiments, the corresponding drive management module of the input and output device is determined based on the device configuration information of the robot; the process of obtaining the device configuration information includes: reading the device configuration information of the robot when the robot is started.

[0095] In some embodiments, when the robot is started, the device configuration information of the robot can be read by the process management module, and the corresponding drive management module of the input and output devices of the robot can be determined according to the device configuration information.

[0096] For example, the device configuration of robots from the same manufacturer may vary depending on the application scenario requirements. For example, a home service robot from manufacturer B requires panoramic monitoring, and its input and output devices typically include a fisheye camera. In this case, the device configuration information for the home service robot will configure the driver management module corresponding to the fisheye camera as the fisheye camera driver management module. When collecting robot data from the home service robot, the fisheye camera driver management module will be enabled to drive the fisheye camera for data collection. For another example, a factory-based fixed robot does not require panoramic monitoring, and its input and output devices do not include a fisheye camera. In this case, the device configuration information for the factory-based fixed robot will not configure the driver management module corresponding to the fisheye camera. As a result, the fisheye camera driver management module will not be enabled when collecting robot data from the home service robot.

[0097] In some embodiments, the robot's device configuration information can include the name or path of the driver management module corresponding to the robot's input and output devices. For example, when the robot is started, the name or path of the driver management module corresponding to the robot's input and output devices can be determined based on the device configuration information in the robot's configuration file. The driver management module corresponding to the robot's input and output devices can be enabled through the process management module, so that the driver management module corresponding to each input and output device drives each input and output device to generate corresponding input and output data. In the above embodiment, by reading the robot's device configuration information, the driver management module corresponding to the robot's input and output devices can be enabled based on the robot's device configuration information, achieving automatic adaptation between the input and output devices and the driver management module to drive the input and output devices to generate input and output data. If a new input and output device is added to the robot or the configuration is changed, there is no need to modify the code, only to update the configuration file. For example, when a new type of camera is added, it is only necessary to specify the driver management module corresponding to the newly added camera in the device configuration information. The newly added camera can then be driven by enabling the driver management module to achieve image data acquisition without the need for special adjustments, which has good software generalization, versatility, and extensibility.

[0098] In some embodiments, the input / output data may be provided by an input / output data provider, which may be used to obtain the input / output data from the input / output device. Exemplarily, the input / output data provider may be deployed on the same robot as the robot data acquisition system (e.g., a domain controller of the same robot). For example, the input / output data provider may be a robot software component or robot hardware device provided by a second robot manufacturer that can serve as an external data input source in the robot data acquisition system provided by a first robot manufacturer.

[0099] For example, for robots from Manufacturer B and Manufacturer C purchased from the same buyer, the robot data must be uniformly connected to the data acquisition management platform of Manufacturer B. Then, the input and output data of the robot from Manufacturer C can be transmitted by the input and output data provider of the robot from Manufacturer C to the data acquisition task management layer of the robot from Manufacturer B to obtain the robot data that needs to be uploaded to the data acquisition management platform of Manufacturer B.

[0100] In the above embodiments, for scenarios where the interaction layer is difficult to adapt due to special software or non-disclosure of competitor information, the corresponding software layer (for example, the data acquisition task management layer of the robot of manufacturer B) can be flexibly called on demand for the robot (for example, the robot of manufacturer B), and at the same time, some software layers of other robots (for example, the input and output device interaction layer of the robot of manufacturer C) can be connected to achieve the connection between the corresponding software layers of different types of robots, meet the data collection requirements of different types of robots connecting to the same data acquisition management source, reduce the software development cost required for unified management of data collection of different types of robots, and further improve the generalization of the software.

[0101] Reference Figure 2 and Figure 3 As shown, Figure 2 This is a schematic diagram of the structure of a robot data acquisition system provided in an embodiment of the present application. Figure 3 It is a structural diagram of another robot data acquisition system provided in an embodiment of the present application.

[0102] The present application embodiment provides a robot data collection system, which can be used to implement the robot data collection method provided in the above embodiment. Figure 2 As shown, the system includes: a process management module and a data acquisition management interaction layer; the process management module is used to determine the data acquisition management source of the robot; the data acquisition management source includes one or more cloud-based data acquisition management sources and human-machine interface data acquisition management sources; the data acquisition management interaction layer is used to provide the robot data of the robot to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source.

[0103] In some embodiments, the robot data acquisition system can be deployed on the robot device side, for example, it can be deployed on the robot body. For example, the robot data acquisition system can be mounted on the data acquisition control module of the domain controller of the robot body, or the robot data acquisition system can also be deployed on a local device that is directly connected to the robot body (for example, through a physical interface or a local area network) and can complete real-time interaction.

[0104] In some embodiments, as Figure 3 As shown, the system may further include a data acquisition task management layer; the data acquisition task management layer is used to receive input and output data of the input and output devices of the robot, and perform one or more of data storage, data upload, data verification and fault monitoring on the input and output data to obtain the robot data and provide it to the data acquisition management interaction layer.

[0105] In some embodiments, as Figure 3 As shown, the system may further include an input / output device interaction layer: the input / output device interaction layer is configured to receive the input / output data through the corresponding device interfaces of the input / output devices, and provide the input / output data to the data acquisition task management layer.

[0106] In some embodiments, as Figure 3 As shown, the system may further include an input / output device driver layer: the input / output device driver layer is used to drive the input / output device through the corresponding driver management module of the input / output device to obtain the input / output data and provide it to the input / output device interaction layer.

[0107] In some embodiments, the process management module may be used to enable a corresponding driver management module of the input / output device.

[0108] Next, we take humanoid robot data collection as an example and combine it with Figure 4 , further illustrating the technical solutions provided in the embodiments of this application.

[0109] like Figure 4 As shown, Figure 4 This is a schematic diagram of the platform software architecture of a robot data acquisition system provided in an embodiment of the present application.

[0110] The robot data acquisition system can be deployed on the robot device side, for example, it can be deployed on the humanoid robot body. For example, the robot data acquisition system can be mounted on the data acquisition control module of the domain controller of the robot body, or the robot data acquisition system can also be deployed on a device that is directly connected to the humanoid robot body (for example, through a physical interface or local area network) and can complete real-time interaction.

[0111] See also Figure 4 The robot data acquisition system can include: a process management module, a data acquisition management interaction layer, a data acquisition task management layer, an input / output device interaction layer, and an input / output device driver layer. The process management module interacts with the data acquisition management interaction layer, the data acquisition task management layer, the input / output device interaction layer, and the input / output device driver layer respectively.

[0112] For different application scenarios, some layers of software can be developed and tested as needed, and then integrated, thereby reducing the difficulty of humanoid robot data acquisition management and improving software development efficiency.

[0113] The process management module can be used to determine the data acquisition and management source of the humanoid robot. Specifically, the process management module's functions may include: automatically starting up after the humanoid robot device is powered on, reading and broadcasting the humanoid robot's device model, device configuration, and the model of the data acquisition and management source adapted for the humanoid robot (for example, the model of the cloud-based data acquisition and management platform, or the management platform model of the HMI data acquisition and management application), and interacting with the corresponding interaction layer or driver layer in the robot's data acquisition system as needed based on this information.

[0114] It should be noted that during the production process of humanoid robots, depending on the customer needs, the device model, device configuration and data acquisition management source model of the humanoid robot body can be written into the local humanoid robot through a configuration file, and support can be read by the process management software module at startup.

[0115] The data acquisition management interaction layer can be used to receive robot data provided by the data acquisition task management layer, and provide the robot data to the data acquisition management source of the humanoid robot through the corresponding data acquisition interface of the data acquisition management source of the humanoid robot.

[0116] The data acquisition management interaction layer may include at least one of the following: a cloud interface management software module and an HMI interface management software module, which perform interface abstraction for the cloud data acquisition management platform and the HMI data acquisition management application respectively, and implement interface adaptation through a configuration file in JSON format (i.e., corresponding to the first interface adaptation file in the aforementioned embodiment).

[0117] It should be noted that during the production process of the robot, the device model of the robot body, the data acquisition management source model and the interface mapping relationship of each model can be stored in the local machine through a JSON file. In this way, when the same model of robot is produced and delivered to different customers to use different data acquisition management sources for data collection, there is no need to make a lot of software changes and tests. The process management module only needs to broadcast each model after the robot is started, and the data acquisition management interaction layer will perform interface adaptation according to the pre-defined JSON file and the models broadcast by the process management module, so as to realize automatic adaptation of the data acquisition interface.

[0118] The data acquisition task management layer can be used to receive input and output data provided by the input and output device interaction layer, and perform one or more of the following processes on the input and output data: data storage, data upload, data verification, and fault monitoring, so as to obtain robot data and provide it to the data acquisition management interaction layer.

[0119] The data acquisition task management layer may include at least one of the following: a data acquisition task management module, a data storage module, a data upload module, and a data verification and fault monitoring module (corresponding to the data verification module and fault monitoring module in the aforementioned embodiment).

[0120] The data acquisition task management module can be used for at least one of the following: requesting the data storage module to start, end or interrupt data storage, and receive feedback information; requesting the data upload module to perform corresponding data upload operations and receive feedback information.

[0121] The data storage module can be used to receive requests from the data acquisition task management module, perform corresponding data storage operations, and provide feedback information to the data acquisition task management module.

[0122] The data upload module can be used to receive requests from the data acquisition task management module, perform corresponding data upload operations, and provide feedback information to the data acquisition task management module.

[0123] The data verification module can be used to read data for verification and feed the results back to the fault monitoring module.

[0124] The fault monitoring module can be used to summarize fault information based on the data verification results of the data verification module, and feed back the fault information summary results to the data acquisition task management module for arbitration of task management by the data acquisition task management module.

[0125] It should be noted that during the robot's production process, the robot's device configuration can be stored locally. This allows the data acquisition task management layer to read the robot device configuration broadcast by the process management module after the robot starts, and perform data storage, data upload, data verification, and / or fault monitoring based on the configuration. This allows the functions of the various modules in the data acquisition task management layer to be reused without requiring special adjustments. This means that the modules in the data acquisition task management layer are highly versatile, further enhancing the software's generalization capabilities.

[0126] The I / O device interaction layer can include an I / O device interface management module, which abstracts interfaces for I / O devices and automatically adapts device interfaces through JSON files. The I / O device interface management module is strongly associated with the I / O devices. When I / O devices switch, the I / O device interface management module must synchronously adapt the corresponding device interface.

[0127] It should be noted that the robot's existing input and output devices can be written locally in JSON format into an interface adaptation file (i.e., corresponding to the second interface adaptation file in the aforementioned embodiment) for adapting to different input and output devices. Thus, after the humanoid robot is started, automatic interface adaptation can be achieved by reading the interface adaptation file and combining it with the robot device configuration broadcast by the process management module. This method can reduce the workload of software development and testing when humanoid robots with different device configurations are produced and delivered to the purchaser for data collection. By simply writing the appropriate input and output device configuration, the pre-defined interface adaptation JSON file can be used to search for and obtain the adaptation interface, further enhancing the software's generalization capabilities.

[0128] The input / output device driver layer may include at least one of the following: a motor control management module, an external device driver module, and other controller management modules. The input / output device driver layer reads the robot device configuration broadcast by the process management module after the humanoid robot starts up, confirms the humanoid robot's existing hardware configuration range, and then drives the corresponding input / output devices through the corresponding driver management modules to obtain input / output data and provide it to the input / output device interaction layer.

[0129] The sensor driver module, for example, may include one or more of the following: lidar driver, fisheye camera driver, and depth camera driver, etc., which can be used to drive and adapt different sensors installed on the robot to ensure the output of the sensor.

[0130] The motor control management module may include, for example, one or more of the following: a dexterous hand motor management module, a robotic arm motor management module, a bipedal motor management module, a head motor management module, and a waist motor management module, etc., and may be used to drive and adapt the different motors installed on the humanoid robot to ensure the input and output of the motors;

[0131] External device driver modules, for example, may include one or more of the following: a handle driver module, a VR driver module, and a motion capture device driver module, etc., which can be used to drive and adapt different external devices installed on the robot to ensure the input and output of the peripheral devices;

[0132] Other controller management modules, for example, may include one or more of the following: a power board management module and an MCU management module, etc., which can be used to adapt the interfaces of other controllers of the robot to ensure the input and output of other controllers.

[0133] It's understandable that the modules described above within the input and output device driver layer are strongly tied to the robot's device configuration. By reading the robot device configuration broadcast by the process management module and confirming the humanoid robot's existing hardware configuration range, the corresponding driver management module can be called based on that range, enabling device driver and adaptation without requiring special adjustments, further enhancing the software's generalizability.

[0134] In addition, for half-stack software delivery scenarios, where the interaction layer is difficult to adapt due to special software or lack of open competitor information, the process management module can be used to call the corresponding software layer in the robot data acquisition system on demand based on the robot device model, while also docking some of the software in the original robot data acquisition system to achieve adaptation. For example, if the robots of Manufacturer B and Manufacturer C purchased by Purchaser A need to be uniformly docked to Manufacturer B's data acquisition management platform, then based on the input and output device interaction layer and input and output device driver layer software provided by Manufacturer C, Manufacturer B only needs to call the data acquisition management interaction layer and data acquisition management interaction layer based on the robot device model through the process management module after the robot is started, without calling the device interaction layer and input and output device driver layer to achieve adaptation. In this scenario, Manufacturer B still does not need to modify or test the software of the original robot data acquisition system, thus further improving the software generalization capability.

[0135] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the robot data collection methods in the above embodiments is implemented.

[0136] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements any one of the robot data collection methods in the above embodiments.

[0137] The computer program product may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the computer program product of the embodiments of the present application is not limited thereto, and the computer program product may be any combination of one or more computer-readable media.

[0138] See also Figure 5 , Figure 5 This is a structural block diagram of a computer device provided in an embodiment of the present application.

[0139] An embodiment of the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above-mentioned robot data collection methods when executing the computer program.

[0140] The embodiments of the present application do not limit the computer device, which may be, for example, a local computer device, a cloud computer device, a distributed computer device, etc.

[0141] The computer device may include: a memory 110, a processor 120, and a communication interface 130. The memory 110, the processor 120, and the communication interface 130 are connected via an internal connection path.

[0142] The memory 110 is used to store computer programs. In some implementations, the computer programs may include codes for implementing the methods of the embodiments of the present application.

[0143] The processor 120 is configured to execute the computer program stored in the memory 110 to control the communication interface 130 to receive input data and information and output data such as operation results. In some implementations, when the solutions of the embodiments of the present application are implemented through software or firmware, the computer program for implementing the solutions of the embodiments of the present application may be stored in the processor 120 and executed by the processor 120.

[0144] The memory 110 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (Programmable ROM, PROM), an erasable programmable read-only memory (Erasable PROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory 110 described herein is intended to include, but is not limited to, any memory of these and other suitable types. As an example, the memory 110 includes a random access memory (RAM), a cache memory and a read-only memory (ROM). Among them, the memory 110 stores a computer program, and the computer program can be executed by the processor 120 so that the processor 120 implements the steps of any of the above methods.

[0145] The processor 120 may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor, or the processor 120 may be any conventional processor.

[0146] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 120 or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor 120. The software module can be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 110, and the processor 120 reads the information in the memory 110 and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0147] In some implementations, in addition to the hardware units described above, the computer device may also include software modules, where the software modules may be, for example, an operating system, a basic input and output system (BIOS), application software, etc.

[0148] An operating system manages the hardware and / or software resources of a computer device and is the core and cornerstone of the computer. It handles basic tasks such as managing and allocating memory, prioritizing the supply and demand of system resources, controlling input and output devices, operating the network, and managing the file system. To facilitate user operation, most operating systems provide an interface for users to interact with the system.

[0149] The BIOS is used to run hardware initialization during the power-on boot phase and provide runtime services for the operating system and applications. In some implementations, the BIOS can also monitor and display the processor temperature and execute functions such as adjusting temperature protection strategies.

[0150] Application software, also known as an application program, is software written for a specific user purpose. It is a major category of computer software. For example, application software might be a program used for power control, temperature management, and other purposes.

[0151] It should be understood that the specific examples in this application are only intended to help those skilled in the art better understand the implementation methods of this application, rather than to limit the scope of protection of this application.

[0152] It can be understood that in various implementations of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the present application.

[0153] It can be understood that the various embodiments described in this application can be implemented individually or in combination, and this application is not limited to this.

[0154] Unless otherwise indicated, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art in the art of this application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application. The singular forms "a," "above," and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0155] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0156] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described embodiments may refer to the corresponding processes in other embodiments and will not be repeated here.

[0157] In the embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the technical solutions of this application.

[0159] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0160] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A robot data collection method, characterized in that: The method comprises: Determine the data acquisition and management source of the robot; the data acquisition and management source includes one or more of a cloud data acquisition and management source and a human-machine interface data acquisition and management source; The robot data of the robot is provided to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source.

2. The robot data collection method according to claim 1, characterized in that: The data acquisition management source is determined according to the data acquisition management source information of the robot; the data acquisition management source information includes one or more of cloud data acquisition management source information and human-machine interface data acquisition management source information; The process of acquiring the data acquisition management source information includes: reading the data acquisition management source information of the robot when the robot is started.

3. The robot data collection method according to claim 1, characterized in that: The data acquisition interface corresponding to the data acquisition management source is determined based on the data acquisition management source and a first interface adaptation file, and the first interface adaptation file uses JSON format to store the data acquisition management source and its corresponding data acquisition interface.

4. The robot data collection method according to claim 1, characterized in that: The process of obtaining the robot data includes: receiving input and output data of an input and output device of the robot; One or more of data storage, data uploading, data verification, and fault monitoring are performed on the input and output data to obtain the robot data.

5. The robot data collection method according to claim 4, characterized in that: The input and output data are received via the corresponding device interface of the input and output device; The device interface corresponding to the input / output device is determined based on the input / output device and a second interface adaptation file, and the second interface adaptation file stores the input / output device and its corresponding device interface in JSON format.

6. The robot data collection method according to claim 4, characterized in that: The process of obtaining the input and output data includes: Activate the drive management module corresponding to the input and output device; the drive management module corresponding to the input and output device is determined according to the device configuration information of the robot; driving the input / output device through a corresponding driver management module of the input / output device to obtain the input / output data; The process of acquiring the device configuration information includes: reading the device configuration information of the robot when the robot is started.

7. The robot data collection method according to claim 4, characterized in that: The input and output data are provided by an input and output data provider, and the input and output data provider is used to obtain the input and output data from the input and output device.

8. The robot data collection method according to any one of claims 4 to 7, characterized in that: The input and output data include one or more of the robot's image data, force feedback data, joint variable data, end effector posture data, sensor drive data, motor control data, peripheral drive data and controller management data.

9. A robot data acquisition system, characterized in that: The system comprises: A process management module is used to determine the data acquisition management source of the robot; the data acquisition management source includes one or more of a cloud data acquisition management source and a human-machine interface data acquisition management source; The data acquisition management interaction layer is used to provide the robot data of the robot to the data acquisition management source through the corresponding data acquisition interface of the data acquisition management source.

10. The robot data acquisition system according to claim 9, characterized in that: The system further comprises: The data acquisition task management layer is used to receive input and output data from the input and output devices of the robot; perform one or more of data storage, data upload, data verification and fault monitoring on the input and output data to obtain the robot data and provide it to the data acquisition management interaction layer.

11. The robot data acquisition system according to claim 10, characterized in that: The system further comprises: The input / output device interaction layer is configured to receive the input / output data through the corresponding device interfaces of the input / output devices, and to provide the input / output data to the data acquisition task management layer.

12. The robot data acquisition system according to claim 11, characterized in that: The system further comprises: The input / output device driver layer is used to drive the input / output device through the driver management module corresponding to the input / output device to obtain the input / output data and provide it to the input / output device interaction layer.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the robot data collection method according to any one of claims 1 to 8 is implemented.

14. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the robot data collection method according to any one of claims 1 to 8 when executing the computer program.

15. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the robot data collection method according to any one of claims 1 to 8 is implemented.

Images