Robot testing system, method and computer readable storage medium

Abstract

The present application discloses a robot testing system, method and computer-readable storage medium. The present application includes a digital twin, a measurement and control entity and a control domain. The digital twin is used to obtain robot characteristics and robot application scenarios. The digital twin is used to establish a robot model and a test environment model based on the robot characteristics and the robot application scenarios; the measurement and control entity is used to obtain the robot model and the test environment model from the digital twin. The measurement and control entity is also used to obtain robot test indicators, and test the operation data of the robot model in the test environment model according to the robot test indicators; the control domain obtains the robot model, the test environment model and the operation data. The present application can establish a simulated robot model to be tested according to the parameters of a real robot, and test the robot model to be tested and the test environment model.

Description

Technical Field

[0001] The present application relates to the field of robot testing technology, and in particular to a robot testing system, method and computer-readable storage medium. Background Art

[0002] With the advancement of technology, robots are being used more and more widely. In the process of robot development and testing, robots need to be tested. However, robots usually include a mechanical system and a control system, and the mechanical system and the control system are relatively independent. Therefore, in the process of testing robots, the data interaction between the mechanical system and the control system is poor during the collaborative testing, and the closed loop of test data cannot be achieved. Summary of the invention

[0003] In view of this, the present application provides a robot testing system, method and computer-readable storage medium, which can establish a simulated robot model to be tested and a test environment model according to the parameters of a real robot and its operating environment, and test the robot model to be tested and the test environment model to obtain the operating data of the robot to be tested, and then judge whether its error value is higher than the preset error index according to the operating data of the robot to be tested; if its error value is higher than the preset error index, the robot model to be tested and the test environment model can be re-debugged and updated according to the error value, and then retested according to the updated model until the error values ​​of all error types are lower than the preset error index. The present application can improve the data interactivity between modules through two-way communication connections among digital twins, measurement and control entities and control domains, has the advantage of high integration, and can realize data closed loop during robot testing.

[0004] The first aspect of the present application provides a robot testing system, which includes: a digital twin, a measurement and control entity and a control domain, wherein the digital twin, the measurement and control entity and the control domain are bidirectionally connected in communication; the digital twin is used to obtain robot characteristics and robot application scenarios, and the digital twin is also used to establish a robot model and a test environment model according to the robot characteristics and the robot application scenarios; the measurement and control entity is used to obtain the robot model and the test environment model from the digital twin, and the measurement and control entity is also used to obtain robot test indicators, and test the operation data of the robot model in the test environment model according to the robot test indicators; the control The control domain is used to obtain the robot test indicators and the operation data, and the control domain is also used to obtain the error value of the robot model operation according to the robot test indicators and the operation data, and to determine whether the error value of the robot model operation is higher than the preset error indicator; if the error value of the robot model operation is higher than the preset error indicator, the control domain is also used to transmit the error value of the robot model operation to the digital twin, and the digital twin is also used to update the test environment model and the robot model according to the error value of the robot model operation; the measurement and control entity is also used to test the operation data of the updated robot model in the updated test environment model according to the robot test indicators.

[0005] In a possible implementation of the present application, the robot testing system further includes a physical entity, which is bidirectionally communicatively connected to the measurement and control entity; the physical entity is used to generate the robot testing indicator and send the robot testing indicator to the measurement and control entity.

[0006] In a possible implementation of the present application, the physical entity is also used to obtain test instructions from the measurement and control entity, run and generate operation data of the physical entity according to the test instructions, and send the operation data of the physical entity to the measurement and control entity; the measurement and control entity is also used to send the operation data of the physical entity to the control domain; the control domain is also used to obtain an error value of the operation of the physical entity based on the operation data of the physical entity and the robot test index, and determine whether the error value of the operation of the physical entity is higher than the preset error index. If the error value of the operation of the physical entity is higher than the preset error index, the error value of the operation of the physical entity is stored in the physical entity.

[0007] In a possible implementation of the present application, the digital twin includes a modeling module and a model management module; the modeling module is used to establish the robot model and the test environment model according to the robot characteristics and the robot application scenarios; the model management module is used to simplify and / or optimize the robot model according to the robot model and the robot test indicators, and send the optimized robot model to the measurement and control entity; the measurement and control entity tests whether the error value of the optimized robot model test operation is higher than the preset error indicator. If the error value of the optimized robot model test operation is higher than the preset error indicator, the control domain is also used to transmit the error value of the optimized robot model operation to the digital twin, and the digital twin is also used to update the test environment model and the robot model according to the error value of the optimized robot model operation.

[0008] In a possible implementation of the present application, the digital twin also includes a simulation module; the simulation module includes a kinematics simulation submodule, a statics simulation submodule, a dynamics simulation submodule and a semi-physical simulation submodule; the kinematics simulation submodule is used to verify the motion function of the optimized robot model; the statics simulation submodule is used to verify the strength and stiffness of the optimized robot model after the kinematics simulation submodule is verified; the dynamics simulation submodule is used to verify the dynamic characteristics of the optimized robot model after the statics simulation submodule is verified; the semi-physical simulation submodule is used to verify the feasibility of the optimized robot model, the test environment model and the physical entity after the dynamics simulation submodule is verified.

[0009] In a possible implementation of the present application, the digital twin also includes a twin co-intelligence module, and a bidirectional communication connection is established between the twin co-intelligence module, the modeling module, the model management module and the simulation module, and the twin co-intelligence module is used to transmit data between the modeling module, the model management module and the simulation module; the model management module is also used to update the optimized robot model and the test environment model according to the verification results; the twin co-intelligence module is used to store the robot model and the test environment model optimized by the model management module.

[0010] In a possible implementation manner of the present application, the control domain includes a decision module, and the decision module is used to generate the robot test index according to the robot characteristics and the robot application scenario.

[0011] In a possible implementation of the present application, the control domain also includes a co-intelligence twin, and a bidirectional communication connection is established between the co-intelligence twin, the physical entity and the digital twin, and the co-intelligence twin is used to transmit data between the physical entity and the digital twin; the control domain also includes a human-computer interface and application software, and a bidirectional communication connection is established between the decision module, the co-intelligence twin, the human-computer interface and the application software, and the application software is used to provide a software architecture, software protocol and communication protocol for interaction between the decision module and the co-intelligence twin; the human-computer interface is used to realize data interaction between the decision module and the co-intelligence twin.

[0012] The second aspect of the present application provides a robot testing method, which is applied to the robot testing system as described in the first aspect, including: obtaining robot characteristics and robot application scenarios; establishing a robot model and a test environment model based on the robot characteristics and the robot application scenarios; obtaining robot testing indicators; testing the operation data of the robot model in the test environment model based on the robot testing indicators; obtaining an error value of the robot model operation based on the robot testing indicators and the operation data, and determining whether the error value of the robot model operation is higher than a preset error indicator; if the error value of the robot model operation is higher than the preset error indicator, updating the test environment model and the robot model based on the error value of the robot model operation; and testing the operation data of the updated robot model in the updated test environment model based on the robot testing indicators.

[0013] A second aspect of the present application provides a computer-readable storage medium, wherein the computer storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the robot testing method as described in the second aspect.

[0014] The robot testing system, method and computer-readable storage medium provided in the present application establish a simulated robot model to be tested and a test environment model through the parameters of a real robot and its operating environment, and test the robot model to be tested and the test environment model to obtain the operating data of the robot to be tested, and then judge whether its error value is higher than the preset error index according to the operating data of the robot to be tested; if its error value is higher than the preset error index, the robot model to be tested and the test environment model can be re-debugged and updated according to the error value, and then retested according to the updated model until the error values ​​of all error types are lower than the preset error index. The present application can improve the data interactivity between modules through two-way communication connections among digital twins, measurement and control entities and control domains, has the advantage of high integration, and can realize data closed loop during robot testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the hardware structure of a multi-legged robot provided in one embodiment of the present application.

[0016] Figure 2 It is a schematic diagram of the hardware structure of a multi-legged robot provided in another embodiment of the present application.

[0017] Figure 3 It is a module schematic diagram of a robot testing system provided in one embodiment of the present application.

[0018] Figure 4 It is a module schematic diagram of a robot testing system provided in another embodiment of the present application.

[0019] Figure 5 It is a flowchart of a robot testing method provided in one embodiment of the present application.

[0020] Main component symbols

[0021] Multi-legged robot 100

[0022] Mechanical Unit 101

[0023] Driver board 1011

[0024] Motor 1012

[0025] Mechanical Structure 1013

[0026] Body 1014

[0027] Legs 1015

[0028] Foot 1016

[0029] Head structure 1017

[0030] Tail structure 1018

[0031] Carrying structure 1019

[0032] Saddle structure 1020

[0033] Camera structure 1021

[0034] Communication unit 102

[0035] Sensor unit 103

[0036] Interface unit 104

[0037] Storage unit 105

[0038] Display unit 106

[0039] Display panel 1061

[0040] Input unit 107

[0041] Touch Panel 1071

[0042] Other input devices 1072

[0043] Touch detection device 1073

[0044] Touch Controller 1074

[0045] Control module 110

[0046] Power 111

[0047] Robotic testing system 200; 200a

[0048] Digital Twin 210

[0049] Simulation Module 211

[0050] Kinematics simulation submodule 2111

[0051] Statics simulation submodule 2112

[0052] Dynamics simulation submodule 2113

[0053] Semi-physical simulation submodule 2114

[0054] Modeling Module 212

[0055] Model Management Module 213

[0056] Twin Co-Intelligence Module 214

[0057] Twin Interface 2141

[0058] Twin Modeling 2142

[0059] Twin Optimization 2143

[0060] Twin Management 2144

[0061] Measurement and Control Entity 220

[0062] Control Domain 230

[0063] Decision Module 231

[0064] Shared intelligence twin 232

[0065] Human-Machine Interface 233

[0066] Application Software 234

[0067] Physical Entity 240 DETAILED DESCRIPTION

[0068] It should be noted that in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0069] It should also be noted that the method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchangeable with each other, and some of the steps can also be deleted.

[0070] With the advancement of technology, robots need to be tested during the process of robot development and testing. However, robots usually include a mechanical system and a control system, and the mechanical system and the control system are relatively independent. Therefore, during the testing of the robot, the data interaction between the mechanical system and the control system is poor during the collaborative testing, and the closed loop of the test data cannot be achieved.

[0071] Therefore, the embodiments of the present application provide a robot testing system, method and storage medium, which can establish a simulated robot model to be tested and a test environment model according to the parameters of a real robot and its operating environment, and test the robot model to be tested and the test environment model to obtain the operating data of the robot to be tested, and then judge whether its error value is higher than the preset error index according to the operating data of the robot to be tested. If its error value is higher than the preset error index, the robot model to be tested and the test environment model can be re-debugged and updated according to the error value, and then retested according to the updated model until the error values ​​of all error types are lower than the preset error index, so that a data closed loop can be achieved.

[0072] See also Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of a multi-legged robot 100 according to one embodiment of the present application. Figure 1In the illustrated embodiment, the multi-legged robot 100 includes a mechanical unit 101, a communication unit 102, a sensor unit 103, an interface unit 104, a storage unit 105, a display unit 106, an input unit 107, a control module 110, and a power supply 111. The various components of the multi-legged robot 100 can be connected in any manner, including wired or wireless connections. Those skilled in the art will appreciate that Figure 1 The specific structure of the multi-legged robot 100 shown in the figure does not constitute a limitation of the multi-legged robot 100. The multi-legged robot 100 may include more or fewer components than shown in the figure. Some components are not essential components of the multi-legged robot 100 and can be omitted or combined as needed without changing the essence of the invention.

[0073] Combine the following Figure 1 The various components of the multi-legged robot 100 are introduced in detail:

[0074] The mechanical unit 101 is the hardware of the multi-legged robot 100. Figure 1 As shown, the mechanical unit 101 may include a driving plate 1011, a motor 1012, and a mechanical structure 1013. Figure 2 As shown, the mechanical structure 1013 may include a body 1014, an extendable leg 1015, and a foot 1016. In other embodiments, the mechanical structure 1013 may also include an extendable mechanical arm (not shown), a rotatable head structure 1017, a swingable tail structure 1018, a load-bearing structure 1019, a saddle structure 1020, a camera structure 1021, etc. It should be noted that each component module of the mechanical unit 101 may be one or more, and may be set according to specific circumstances. For example, there may be four legs 1015, and each leg 1015 may be configured with three motors 1012, and the corresponding motors 1012 are 12.

[0075] The communication unit 102 can be used to receive and send signals, and can also communicate with the network and other devices. For example, after receiving the instruction information sent by the remote control or other multi-legged robot 100 to move in a specific direction at a specific speed according to a specific gait, it is transmitted to the control module 110 for processing. The communication unit 102 includes a WiFi module, a 4G module, a 5G module, a Bluetooth module, an infrared module, etc.

[0076] The sensing unit 103 is used to obtain information data about the environment around the multi-legged robot 100 and to monitor parameter data of each component inside the multi-legged robot 100, and send it to the control module 110. The sensing unit 103 includes a variety of sensors, such as sensors for obtaining information about the surrounding environment: laser radar (for long-range object detection, distance determination and / or speed value determination), millimeter wave radar (for short-range object detection, distance determination and / or speed value determination), camera, infrared camera, global navigation satellite system (GNSS, Global Navigation Satellite System), etc. For example, sensors for monitoring each component inside the multi-legged robot 100: inertial measurement unit (IMU, Inertial Measurement Unit) (for measuring the value of velocity value, acceleration value and angular velocity value), plantar sensor (for monitoring the position of the plantar force point, plantar posture, ground contact force size and direction), temperature sensor (for detecting component temperature). As for other sensors such as load sensors, touch sensors, motor angle sensors, torque sensors, etc. that can also be configured for the multi-legged robot 100, they will not be repeated here.

[0077] The interface unit 104 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more components within the multi-legged robot 100, or may be used to output (e.g., data information, power, etc.) to an external device. The interface unit 104 may include a power port, a data port (such as a USB port), a memory card port, a port for connecting a device having an identification module, an audio input / output (I / O) port, a video I / O port, etc.

[0078] The storage unit 105 is used to store software programs and various data. The storage unit 105 may mainly include a program storage area and a data storage area, wherein the program storage area may store operating system programs, motion control programs, application programs (such as text editors), etc.; the data storage area may store data generated by the multi-legged robot 100 during use (such as various sensor data obtained by the sensor unit 103, log file data), etc. In addition, the storage unit 105 may include a high-speed random access memory, and may also include a non-volatile memory, such as a disk storage, a flash memory, or other volatile solid-state memory.

[0079] The display unit 106 is used to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0080] The input unit 107 can be used to receive input digital or character information. Specifically, the input unit 107 may include a touch panel 1071 and other input devices 1072. The touch panel 1071, also known as a touch screen, can collect the user's touch operation (such as the user's operation on the touch panel 1071 or near the touch panel 1071 using the palm, finger or suitable accessory), and drive the corresponding connection device according to a pre-set program. The touch panel 1071 may include two parts: a touch detection device 1073 and a touch controller 1074. Among them, the touch detection device 1073 detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller 1074; the touch controller 1074 receives the touch information from the touch detection device 1073, converts it into contact coordinates, and then sends it to the control module 110, and can receive and execute commands sent by the control module 110. In addition to the touch panel 1071, the input unit 107 may also include other input devices 1072. Specifically, other input devices 1072 may include but are not limited to one or more of a remote control operating handle, etc., which are not specifically limited here.

[0081] Furthermore, the touch panel 1071 may cover the display panel 1061. When the touch panel 1071 detects a touch operation on or near it, it transmits the information to the control module 110 to determine the type of the touch event. Then, the control module 110 provides corresponding visual output on the display panel 1061 according to the type of the touch event. Figure 1 In the embodiment, the touch panel 1071 and the display panel 1061 are used as two independent components to respectively realize the input and output functions. However, in some embodiments, the touch panel 1071 and the display panel 1061 can be integrated to realize the input and output functions, which is not limited here.

[0082] The control module 110 is the control center of the multi-legged robot 100. It uses various interfaces and lines to connect the various components of the entire multi-legged robot 100, and controls the multi-legged robot 100 as a whole by running or executing software programs stored in the storage unit 105 and calling data stored in the storage unit 105.

[0083] The power supply 111 is used to supply power to each component. The power supply 111 may include a battery and a power control board. The power control board is used to control functions such as battery charging, discharging, and power consumption management. Figure 1 In the illustrated embodiment, the power supply 111 is electrically connected to the control module 110. In other embodiments, the power supply 111 may also be electrically connected to the sensor unit 103 (such as a camera, a radar, a speaker, etc.) and the motor 1012. It should be noted that each component may be connected to a different power supply 111 or powered by the same power supply 111.

[0084] On the basis of the above embodiments, in some embodiments, a terminal device can be used to communicate with the multi-legged robot 100. When the terminal device communicates with the multi-legged robot 100, the terminal device can send instruction information to the multi-legged robot 100, and the multi-legged robot 100 can receive the instruction information through the communication unit 102, and when the instruction information is received, the instruction information can be transmitted to the control module 110, so that the control module 110 can process the received instruction information.

[0085] Terminal devices include but are not limited to: mobile phones with image capture capabilities, tablet computers, servers, personal computers, wearable smart devices, and other electrical devices.

[0086] The instruction information can be determined according to preset conditions. For example, as described above, the multi-legged robot 100 includes a sensing unit 103. The sensing unit 103 can generate instruction information according to the current environment in which the multi-legged robot 100 is located. The control module 110 determines whether the current speed value of the multi-legged robot 100 meets the corresponding preset conditions based on the instruction information. If satisfied, the current speed value and the current gait of the multi-legged robot 100 will be maintained. If not satisfied, the target speed value and the corresponding target gait will be determined according to the corresponding preset conditions, so that the multi-legged robot 100 can be controlled to move with the target speed value and the corresponding target gait.

[0087] The sensing unit 103 may also include an environmental sensor, which may include a temperature sensor, an air pressure sensor, a visual sensor, and a sound sensor. The instruction information may include temperature information, air pressure information, image information, and sound information. The communication method between the environmental sensor and the control module 110 may be wired communication or wireless communication. The wireless communication method includes, but is not limited to: wireless network, mobile communication network (3G, 4G, 5G, etc.), Bluetooth, and infrared.

[0088] Figure 3 FIG. 2 is a schematic diagram of a module of a robot testing system 200 according to an embodiment of the present application. Figure 3 As shown, the robot testing system 200 includes at least the following modules: a digital twin 210, a measurement and control entity 220, and a control domain 230. The digital twin 210, the measurement and control entity 220, and the control domain 230 are bidirectionally connected in communication.

[0089] It is understood that the digital twin 210 can be a simulation model established in a computer program. The simulation model is completely consistent with the operating performance of the real robot, and the simulation model can achieve real-time simulation of the real robot. For example, the digital twin 210 can be used to establish a model of a multi-legged robot. It is understood that the multi-legged robot model established by the digital twin 210 can simulate in real time such as Figure 1 or Figure 2 The multi-legged robot 100 is shown.

[0090] In this embodiment, the digital twin 210 is used to obtain the characteristics of the robot to be tested and the application scenario of the robot to be tested. It can be understood that the characteristics of the robot to be tested include the mechanism, parts, three-dimensional parameters and parameters such as the motion trajectory of the robot to be tested. The application scenario of the robot to be tested includes the scene in which the robot to be tested works. For example, when the robot to be tested is an industrial robot, the application scenario of the robot to be tested can be set to a factory environment to simulate the working environment of the robot to be tested.

[0091] In this embodiment, the digital twin 210 is also used to establish a robot model and a test environment model according to the characteristics of the robot to be tested and the application scenario of the robot to be tested. Specifically, the digital twin 210 can establish a robot model to be tested and a test environment model in a computer program according to the mechanism, parts, three-dimensional parameters and motion trajectory of the robot to be tested.

[0092] In this embodiment, the measurement and control entity 220 is used to obtain the test index of the robot to be tested and the robot model and the test environment model from the digital twin 210. It can be understood that the test index of the robot to be tested can be the test task and parameter when testing the robot, for example, the test index can be moving a certain distance, adjusting to a specified posture, maintaining a certain speed, etc. It can be understood that different sensors can be included in the test environment model. The measurement and control entity 220 can apply the sensor data in the test environment simulated by the digital twin 210 and the test index of the robot to be tested to test the running data of the robot model to be tested in the test environment model. It can be understood that the running data of the robot model in the test environment model is the actual running parameters when the robot model performs the corresponding operation according to the test index. It can be understood that after the measurement and control entity 220 obtains the running data of the robot model to be tested in the test environment model, the running data of the robot model to be tested in the test environment model is sent to the control domain 230.

[0093] In this embodiment, the control domain 230 is the highest decision-making layer and the highest data processing center in the architecture of the robot testing system 200 . The control domain 230 is used to handle data interaction and data processing between various modules and sub-modules in the robot testing system 200 .

[0094] It can be understood that the control domain 230 is used to obtain robot test indicators and operating data from the measurement and control entity 220, and obtain the error value of the robot model operation based on the test indicators and operating data of the robot to be tested and determine whether the error value is higher than the preset error indicator.

[0095] It can be understood that the error types of the robot model operation include position error, posture error, motion time error, speed error, acceleration error, sensor error, etc. It can be understood that different error type data can have different preset error indicators, and the operator can adjust the preset error indicator according to the error type.

[0096] The control domain 230 can obtain the error value and the true value of the operation of the robot model to be tested according to the operation data of the robot model to be tested in the test environment model, and judge whether the error value is lower than the preset error index according to the error value and the true value. For example, the control domain 230 can judge whether the error value is lower than the preset error index according to the ratio or difference between the error value and the true value. It can be understood that the error value is the error value of the robot model to be tested from the standard, and the true value is the actual value of the operation of the robot model to be tested. Taking the test index as the specified robot model to be tested to move to the specified position (such as specifying the robot to move to 8cm) as an example, when the preset position error index of the robot model is 10%, the control domain 230 detects that the position of the robot to be tested is 2cm away from the specified position, and the actual position of the robot to be tested is 10cm, the error index is 20%, and the obtained error index is compared with the preset error index, 20%>10%, that is, the actual error value is higher than the preset error index, therefore, the robot model to be tested needs to be re-debugged.

[0097] In this embodiment, when the error value is higher than the preset error index, the control domain 230 is also used to transmit the error value to the digital twin 210. The digital twin 210 is also used to re-debug and update the robot model to be tested and the test environment model according to the error value, and transmit the updated robot model to be tested and the test environment model to the measurement and control entity 220, so that the measurement and control entity 220 can retest the updated robot model to be tested and the test environment model. Specifically, the measurement and control entity 220 is also used to test the running data of the updated robot model in the updated test environment model according to the robot test index. The control domain 230 obtains the error value and error index of the updated robot model operation, and determines whether the new error index is higher than the preset error index. If it is still higher than the preset error index, the above test and update steps are repeated. If it is lower than the preset error index, the error of the test index of the next robot to be tested is tested until the error index of all error types is lower than the preset error index.

[0098] It can be understood that the robot testing system 200 provided in the embodiment of the present application can establish a simulated robot model to be tested and a test environment model according to the parameters of the real robot and its operating environment, and test the robot model to be tested and the test environment model to obtain the operating data of the robot to be tested, and then judge whether its error value is higher than the preset error index according to the operating data of the robot to be tested. If its error index is higher than the preset error index, the robot model to be tested and the test environment model can be re-debugged and updated according to the error value, and then retested according to the updated model until the error values ​​of all error types are lower than the preset error index, so that a data closed loop can be achieved.

[0099] It can be understood that the robot testing system 200 provided in the embodiment of the present application can improve the data interactivity between the modules through the two-way communication connection between the digital twin 210, the measurement and control entity 220 and the control domain 230, and can realize data fusion and interaction between the digital domain and the physical domain, thereby improving the data interactivity between the robot's mechanical system (physical domain) and the control system (digital domain) when testing the robot, and has the advantage of high integration.

[0100] The robot test system 200 proposed in the present application, the digital twin 210, the measurement and control entity 220 and the control domain 230 are directly connected in bidirectional communication, and the data interactivity between the modules in the robot test system 200 is strong. The robot test system 200 can update the robot model according to the test results of the robot model, and test the updated robot, and realize the closed loop of data after completing a specific number of times or a certain error is lower than a preset value.

[0101] Please also read Figure 4 , Figure 4 FIG. 2 is a schematic diagram of a module of a robot testing system 200a according to another embodiment of the present invention. Figure 4 As shown, the robot testing system 200a also includes the following modules: a digital twin 210, a measurement and control entity 220, and a control domain 230. Figure 3 The robot testing system 200 shown in the figure is different in that the robot testing system 200a also includes a physical entity 240, the digital twin 210 includes a simulation module 211, a modeling module 212, a model management module 213 and a twin co-intelligence module 214, the simulation module 211 includes a kinematics simulation submodule 2111, a statics simulation submodule 2112, a dynamics simulation submodule 2113 and a semi-physical simulation submodule 2114, the twin co-intelligence module 214 includes a twin interface 2141, twin modeling 2142, twin optimization 1243 and twin management 2144, and the control domain 230 also includes a decision module 231, a co-intelligence twin 232, a human-machine interface 233 and application software 234.

[0102] In this embodiment, the physical entity 240 may be a physical robot or a physical sensor. The physical entity 240 is connected to the measurement and control entity 220 in a two-way communication manner. The physical entity 240 is used to obtain a test instruction from the measurement and control entity 220, and to run and generate operation data of the physical entity 240 according to the test instruction of the measurement and control entity 220, and to send the operation data of the physical entity 240 to the measurement and control entity 220.

[0103] It is understood that the physical entity 240 also includes a cross-domain functional entity, which can realize information interaction, data storage and security functions. It is understood that the cross-domain connection entity can realize data interaction between the physical domain (physical entity 240) and the digital domain (digital twin 210, measurement and control entity 220 and control domain 230), and store the data generated during the interaction. The physical entity 240 is connected to the control domain 230 and the control digital twin 210 through the cross-domain connection entity, and the acquired parameters of the physical robot or the parameters of the physical sensor are transmitted to the control domain 230 and the control digital twin 210.

[0104] It can be understood that when the physical entity 240 is a physical robot, the measurement and control entity 220 can test the physical entity 240 through the test instruction to obtain the operation data of the physical entity 240. It can be understood that the control domain 230 is also used to obtain the error value of the operation of the physical entity 240 according to the operation data of the physical entity 240 and the robot test index, and to determine whether the error value of the operation of the physical entity 240 is higher than the preset error index. If the error value of the operation of the physical entity 240 is higher than the preset error index, the control domain 230 stores the error value of the operation of the physical entity 240 in the cross-domain functional entity in the physical entity. It can be understood that when the physical entity 240 is a physical robot, the digital twin 210 cannot immediately correct its physical structure according to the error value of the operation of the physical entity 240. Therefore, the error value of the operation of the physical entity 240 can be stored in the cross-domain functional entity in the physical entity for subsequent adjustment of the model or mold of the physical robot.

[0105] It can be understood that the physical entity 240 can also be a partial component or part of the physical robot, and the measurement and control entity 220 can test the operating parameters of the partial component or part of the physical robot.

[0106] It is understood that when the physical entity 240 is a partial mechanism or part of a physical robot, the digital twin 210 is also used to generate a partial robot model. It is understood that the partial robot model generated by the digital twin 210 can be combined with some components or parts of the physical robot to form a complete robot model, robot mechanism or robot part. The measurement and control entity 220 can also test the operating parameters of the partial mechanism or part of the physical robot and the partial robot model generated by the digital twin 210. When the physical entity 240 is a partial mechanism or part of the physical robot, the control domain 230 can test the error index of the partial robot model, send the corresponding index to the digital twin 210, so that the digital twin can update the partial robot model, and store the error index of the partial mechanism or part of the physical robot in the cross-domain functional entity within the physical entity, so as to adjust the partial mechanism or part of the physical robot later.

[0107] It is understood that the physical entity 240 is also used to generate test indicators for the robot to be tested, and send the test indicators for the robot to be tested to the measurement and control entity 220. It is understood that the measurement and control entity 220 is also used to test the operation data of the robot model in the test environment model according to the test indicators for the robot to be tested.

[0108] In this embodiment, the robot test system 200a can analyze and verify the motion function of the robot model to be tested through the kinematics simulation submodule 2111. Specifically, the motion function of the robot model to be tested includes the interference of different mechanisms in the robot model to be tested, the motion trajectory of different parts, that is, the motion range and motion state of different mechanisms or parts, and the speed, acceleration and displacement of the movement of parts in different mechanisms. It can be understood that since the robot test system 200 and the robot test system 200a need to test the kinematic performance of the robot model to be tested in three-dimensional space, and the three-dimensional space has six degrees of freedom, namely three degrees of freedom of movement and three degrees of freedom of rotation, when the kinematics simulation submodule 2111 is used to analyze and verify the motion function of the robot model to be tested, the parameters of the six degrees of freedom of the robot model to be tested can be analyzed, and then the motion function of the robot model to be tested under different degrees of freedom can be obtained.

[0109] In this embodiment, after the kinematics simulation submodule 2111 analyzes and verifies the motion function of the robot model to be tested, the robot testing system 200a can verify the strength and stiffness of the robot model to be tested through the statics simulation submodule 2112. It can be understood that the statics analysis can be used to test the static balance and moment balance of the robot model to be tested to obtain the strength and stiffness of the robot model to be tested.

[0110] In this embodiment, the robot testing system 200a can verify the dynamic characteristics of the robot model to be tested through the dynamic simulation submodule 2113 after analyzing and verifying the strength and stiffness of the robot model to be tested in the static simulation submodule 2112. It can be understood that the parameters such as the mass and moment of inertia of each mechanism and part of the robot model to be tested are analyzed and optimized so that the robot model to be tested meets the dynamic response requirements under the premise of meeting the strength requirements.

[0111] In this embodiment, after the dynamics simulation submodule 2113 verifies the dynamic characteristics of the robot model to be tested, the robot testing system 200a can verify the physical feasibility of the robot model to be tested, the test environment model and the physical entity 240 through the semi-physical simulation submodule 2114.

[0112] It can be understood that the robot test system 200a first applies the kinematic simulation submodule 2111 to perform kinematic simulation, which can verify the motion function, so that the function can be quickly verified and fast iteration can be achieved. Then, statics simulation is performed by the statics simulation submodule 2112 to analyze whether the stiffness and strength of the model meet the requirements. Subsequently, dynamics simulation is performed again by the dynamics simulation submodule 2113, and dynamics simulation is to verify whether the dynamic characteristics of the model meet the force requirements during the motion process. When the stiffness, strength and mechanical properties all meet the requirements, semi-physical simulation analysis can be performed by the semi-physical simulation submodule 2114. The robot test system 200a can make the simulation result more accurate by setting the above-mentioned simulation sequence, and the efficiency of simulation is higher, and the time of the robot test system 200a when simulating the robot model can be reduced.

[0113] In this embodiment, the decision module 231 is used to obtain the characteristics of the robot to be tested and the application scenario of the robot to be tested, and generate the robot test index according to the characteristics of the robot to be tested and the application scenario of the robot to be tested. Specifically, the decision module 231 can be manually input with the robot test index, or the robot test index can be generated by the artificial intelligence model according to the characteristics of the robot to be tested and the application scenario of the robot to be tested.

[0114] In this embodiment, the modeling module 212 is used to establish the robot model to be tested and the test environment model according to the mechanism, parts, three-dimensional parameters and motion trajectory of the robot to be tested. Specifically, the modeling module 212 establishes the robot model to be tested and the test environment model, and the model management module 213 is used to optimize the robot model to be tested to improve the test efficiency.

[0115] It is understood that the model management module 213 can simplify, optimize and store the robot model to be tested and the test environment model, and the simplification method includes but is not limited to dimensionality reduction, clustering, parameter change, linear modeling and nonlinear modeling. It is understood that when the robot model to be tested is relatively complex, the appearance of some parts of the robot to be tested can be adjusted to a cylinder or a sphere, and the joints of the robot to be tested can be simplified, which can simplify the amount of data required for calculation and improve the test efficiency when testing the robot model to be tested. It is understood that when the robot to be tested has more driving joints, when verifying its movement ability, the degrees of freedom of irrelevant joints can be reduced, for example, three degrees of freedom are adjusted to one, so as to reduce the amount of data to be processed and improve the calculation efficiency. It is understood that when a large number of irregular models are included in the robot model to be tested, its model can be optimized by linear modeling and nonlinear modeling.

[0116] In this embodiment, the twin co-intelligence module 214 is used to store the robot model and the test environment model optimized by the model management module 213. The twin co-intelligence module 214 can realize data sharing and communication sharing among the digital twin 210, the measurement and control entity 220, the control domain 230 and the physical entity 240, and the twin co-intelligence module 214 can also realize function sharing with the co-intelligence twin 232 in the control domain 230.

[0117] In this embodiment, the twin interface 2141 is used to process the information transmission between the modeling module 212 and the model management module 213, that is, the twin interface 2141 as the information interface in the twin co-intelligence module 213 can realize the information exchange and data integration in the twin co-intelligence module 214. Twin modeling 2142 is used to generate a new model with a higher degree of integration from the data of the modeling module 212 and the model management module 213. It can be understood that the twin modeling 2142 improves the real-time operation of the robot test system 200a by generating a new model, while improving the quality of the model and the interactivity between models. Twin optimization 1243 is used to optimize the twin modeling 2142 by combining the data of the external and internal modules. Twin management 2144 is used to realize the update, maintenance and change of the twin interface 2141, twin modeling 2142 and twin optimization 1243. Twin management 2144 is also used to record and manage the database of digital twins, and record information such as the version number of the twin.

[0118] In this embodiment, the co-intelligent twin 232 bidirectionally communicates with the physical entity 240, the measurement and control entity 220, and the digital twin 210, and the co-intelligent twin 232 is used to transmit data between the physical entity 240 and the digital twin 210 to realize the interaction between the control domain 230 and external data. It can be understood that the co-intelligent twin 232 is also the control center in the control domain 230. For example, the co-intelligent twin 232 can control the digital twin 210 to establish the robot model to be tested and the test environment model; the co-intelligent twin 232 can also control the measurement and control entity 220 to test the operation data of the robot model to be tested in the test environment model.

[0119] In this embodiment, the application software 234 is used to provide the necessary software architecture, software protocol, communication protocol and other operating environments for the information and data interaction between the decision module 231 and the co-intelligence twin 232.

[0120] In this embodiment, the human-machine interface 233 is used to realize data interaction between the decision module 231 and the co-intelligent twin 232. It can be understood that when the decision module 231 can be manually input with robot test indicators, the operator can operate the application software 234 through the human-machine interface 233 to realize the information entry of the robot test indicators.

[0121] It can be understood that the robot testing system 200a provided in the embodiment of the present application, in addition to the same beneficial effects as the robot testing system 200, can also test a physical robot or a combination of a physical robot and a robot model in the digital domain, and obtain the actual operating data of the robot, and then determine whether its error value is higher than a preset error index based on the actual operating data of the robot. If its error value is higher than the preset error index, the error index of the physical robot can be stored for subsequent improvement of the physical robot, until the error indicators of all error types are measured and obtained. This allows the physical robot to be tested in combination with a digital twin model, and the error indicators of the physical robot can be saved for subsequent improvement of the physical robot.

[0122] It can be understood that the robot test system 200a provided in the embodiment of the present application can establish a robot model, test the robot model, and correct the robot model according to the test results to achieve a data closed loop. It can be understood that each cycle can be regarded as a data closed loop. It can be understood that the number of data closed loops can be set manually, and the more the number of data closed loops, the closer the effect of the digital twin is to the real physical scene. In some embodiments, the robot test system 200a can set the number of data closed loops according to the error index or relative error rate of the simulation environment and the real environment. For example, the robot test system 200a can set a fixed number of data closed loops, and after the number of data closed loops reaches the number of closed loops, the test of the robot model is terminated to complete the data closed loop. For another example, the robot test system 200a can also determine the number of data closed loops according to the error index. For example, taking the error index as the robot model to be tested moving to a specified position as an example, when the real position of the robot model and the specified position are lower than the error index (such as 1cm), the test of the robot model is terminated to complete the data closed loop.

[0123] The robot test system 200a provided in the embodiment of the present application can realize the integration of the robot test system 200a through the two-way communication connection between the digital twin 210, the measurement and control entity 220, the control domain 230 and the physical entity 240. At the same time, data interaction and fusion can also be realized between the various modules and sub-modules inside the robot test system 200a, thereby improving the degree of integration of the robot test system 200a. For example, a two-way communication connection can also be realized between the simulation module 211, the modeling module 212, the model management module 213 and the twin co-intelligence module 214 inside the digital twin 210, and the data between each module can be interacted, which can improve the degree of integration of the digital twin 210.

[0124] Figure 5 is a flowchart of a robot testing method according to an embodiment of the present application. The robot testing method is applied to Figure 3 The robot testing system 200 shown or Figure 4 The robot testing system 200a shown in FIG. Figure 5 As shown, the robot testing method includes at least the following steps.

[0125] S100: Acquire robot features and robot application scenarios.

[0126] In this embodiment, the robot features and robot application scenarios can be obtained through the digital twin 210. It can be understood that the robot features to be tested include the mechanism, parts, three-dimensional parameters and parameters such as the motion trajectory of the robot to be tested. The robot application scenario to be tested includes the scene in which the robot to be tested works. For example, when the robot to be tested is an industrial robot, the robot application scenario to be tested can be set to a factory environment to simulate the working environment of the robot to be tested.

[0127] S200: Establish a robot model and a test environment model according to robot characteristics and robot application scenarios.

[0128] In this embodiment, the robot model and the test environment model can be established according to the robot characteristics and the robot application scenario through the digital twin 210. Specifically, the digital twin 210 can establish the robot model to be tested and the test environment model in the computer program according to the parameters such as the mechanism, parts, three-dimensional parameters and motion trajectory of the robot to be tested.

[0129] S300: Obtain robot test indicators.

[0130] In this embodiment, the robot test index can be obtained through the measurement and control entity 220. It can be understood that the test index of the robot to be tested can be the test task and parameters when testing the robot. For example, the test index can be moving a certain distance, adjusting to a specified posture, maintaining a certain speed, etc. It can be understood that different sensors can be included in the test environment model.

[0131] S400: Testing the operation data of the robot model in the test environment model according to the robot test index.

[0132] In this embodiment, the operation data of the robot model in the test environment model can be tested according to the robot test index by the measurement and control entity 220. Specifically, the measurement and control entity 220 can apply the sensor data in the test environment simulated by the digital twin 210 and the test index of the robot to be tested to test the operation data of the robot model to be tested in the test environment model. It can be understood that the operation data of the robot model in the test environment model is the actual operation parameters when the robot model performs the corresponding operation according to the test index. It can be understood that after the measurement and control entity 220 obtains the operation data of the robot model to be tested in the test environment model, the operation data of the robot model to be tested in the test environment model is sent to the control domain 230.

[0133] S500: Obtaining an error value of the robot model operation according to the robot test index and operation data.

[0134] In this embodiment, the operation data from the measurement and control entity 220 can be obtained through the control domain 230, and the error value of the robot model operation can be obtained according to the test index and operation data of the robot to be tested.

[0135] S600: Determine whether the error value of the robot model operation is higher than a preset error index.

[0136] In this embodiment, the control domain 230 can be used to determine whether the error value of the robot model operation is higher than the preset error index. The control domain 230 can obtain the error value and the true value of the robot model operation to be tested according to the operation data of the robot model to be tested in the test environment model, and determine whether the error value is lower than the preset error index according to the ratio between the error value and the true value. It can be understood that the error value is the error value of the robot model to be tested from the standard, and the true value is the actual value of the robot model to be tested.

[0137] S700: Update the test environment model and the robot model according to the error value of the robot model operation.

[0138] In this embodiment, if the error value is higher than the preset error index, the error value can be transmitted to the digital twin 210 through the control domain 230. The digital twin 210 is also used to re-debug and update the robot model to be tested and the test environment model according to the error value, and transmit the updated robot model to be tested and the test environment model to the measurement and control entity 220, so that the measurement and control entity 220 can retest the updated robot model to be tested and the test environment model.

[0139] S800: Testing the running data of the updated robot model in the updated test environment model according to the robot test index.

[0140] In this embodiment, the operation data of the robot model in the test environment model can be tested by the measurement and control entity 220 and transmitted to the control domain 230. The control domain 230 obtains the error value and error index of the updated robot model operation, and determines whether the new error index is higher than the preset error index. If it is still higher than the preset error index, the above test and update steps are repeated. If it is lower than the preset error index, the error of the test index of the next robot to be tested is tested until the error indicators of all error types are lower than the preset error indicators.

[0141] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the robot testing method as described above.

[0142] The robot testing system 200, robot testing system 200a, robot testing method and computer-readable storage medium provided in the embodiments of the present application can establish a simulated robot model to be tested and a test environment model according to the parameters of a real robot and its operating environment, and test the robot model to be tested and the test environment model, or test the physical robot or the combination of the physical robot and the robot model in the digital domain to obtain the operating data of the robot to be tested, and then determine whether its error value is higher than a preset error index based on the operating data of the robot to be tested. If its error value is higher than the preset error index, the robot model to be tested and the test environment model can be re-debugged and updated according to the error value, and then re-tested according to the updated model until the error values ​​of all error types are lower than the preset error index, thereby achieving a data closed loop.

[0143] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A robot testing system, characterized in that: The robot testing system comprises: a digital twin, a measurement and control entity and a control domain, wherein the digital twin, the measurement and control entity and the control domain are bidirectionally communicated with each other; The digital twin is used to obtain robot characteristics and robot application scenarios. The digital twin is also used to establish a robot model and a test environment model according to the robot characteristics and the robot application scenarios; The measurement and control entity is used to obtain the robot model and the test environment model from the digital twin, and the measurement and control entity is also used to obtain robot test indicators, and test the operation data of the robot model in the test environment model according to the robot test indicators; The control domain is used to obtain the robot test index and the operation data. The control domain is also used to obtain the error value of the robot model operation according to the robot test index and the operation data, and to determine whether the error value of the robot model operation is higher than a preset error index; If the error value of the robot model operation is higher than the preset error index, the control domain is further used to transmit the error value of the robot model operation to the digital twin, and the digital twin is further used to update the test environment model and the robot model according to the error value of the robot model operation; The measurement and control entity is further used to test the operating data of the updated robot model in the updated test environment model according to the robot test index.

2. The robot testing system according to claim 1, characterized in that: The robot testing system further comprises a physical entity, the physical entity being in bidirectional communication connection with the measurement and control entity; The physical entity is used to generate the robot test index and send the robot test index to the measurement and control entity.

3. The robot testing system according to claim 2, characterized in that: The physical entity is further used to obtain a test instruction from the measurement and control entity, run and generate operation data of the physical entity according to the test instruction, and send the operation data of the physical entity to the measurement and control entity; The measurement and control entity is further used to send the operation data of the physical entity to the control domain; The control domain is also used to obtain an error value of the operation of the physical entity based on the operation data of the physical entity and the robot test index, and to determine whether the error value of the operation of the physical entity is higher than the preset error index; if the error value of the operation of the physical entity is higher than the preset error index, the error value of the operation of the physical entity is stored in the physical entity.

4. The robot testing system according to claim 2, characterized in that: The digital twin includes a modeling module and a model management module; The modeling module is used to establish the robot model and the test environment model according to the robot characteristics and the robot application scenario; The model management module is used to simplify and / or optimize the robot model according to the robot model and the robot test index, and send the optimized robot model to the measurement and control entity; the measurement and control entity tests whether the error value of the optimized robot model test operation is higher than the preset error index. If the error value of the optimized robot model test operation is higher than the preset error index, the control domain is also used to transmit the error value of the optimized robot model operation to the digital twin, and the digital twin is also used to update the test environment model and the robot model according to the error value of the optimized robot model operation.

5. The robot testing system according to claim 4, characterized in that: The digital twin also includes a simulation module; The simulation module includes a kinematics simulation submodule, a statics simulation submodule, a dynamics simulation submodule and a semi-physical simulation submodule; The kinematics simulation submodule is used to verify the motion function of the optimized robot model; The statics simulation submodule is used to verify the strength and stiffness of the optimized robot model after the kinematics simulation submodule is verified; The dynamics simulation submodule is used to verify the dynamic characteristics of the optimized robot model after the verification of the statics simulation submodule is completed; The semi-physical simulation submodule is used to verify the feasibility of the optimized robot model, the test environment model and the physical entity after the verification of the dynamics simulation submodule is completed.

6. The robot testing system according to claim 5, characterized in that: The digital twin also includes a twin co-intelligence module, and the twin co-intelligence module, the modeling module, the model management module and the simulation module are bidirectionally connected to each other, and the twin co-intelligence module is used to transmit data between the modeling module, the model management module and the simulation module; The model management module is also used to update the optimized robot model and the test environment model according to the verification result; The twin co-intelligence module is used to store the robot model and the test environment model optimized by the model management module.

7. The robot testing system according to claim 2, characterized in that: The control domain includes a decision module, and the decision module is used to generate the robot test index according to the robot characteristics and the robot application scenario.

8. The robot testing system according to claim 7, characterized in that: The control domain further includes a co-intelligent twin, wherein the co-intelligent twin, the physical entity and the digital twin are bidirectionally connected to each other, and the co-intelligent twin is used to transmit data between the physical entity and the digital twin; The control domain also includes a human-machine interface and application software. The decision module, the co-intelligent twin, the human-machine interface and the application software are bidirectionally connected to each other. The application software is used to provide a software framework, software protocol and communication protocol for interaction between the decision module and the co-intelligent twin. The human-computer interface is used to realize data interaction between the decision-making module and the co-intelligence twin.

9. A robot testing method, applied to the robot testing system according to any one of claims 1 to 8, characterized in that: The robot testing method comprises: Obtain robot features and robot application scenarios; Establishing a robot model and a test environment model according to the robot characteristics and the robot application scenario; Get robot test indicators; Testing the operation data of the robot model in the test environment model according to the robot test index; Acquire an error value of the robot model operation according to the robot test index and the operation data, and determine whether the error value of the robot model operation is higher than a preset error index; If the error value of the robot model operation is higher than the preset error index, updating the test environment model and the robot model according to the error value of the robot model operation; The operating data of the updated robot model in the updated test environment model is tested according to the robot test index.

10. A computer-readable storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the robot testing method according to claim 9.

Images