Motion control method and system of trowel robot and trowel robot

Abstract

The embodiments of the present application provide a motion control method, system, and trowel robot for a troweling robot, relating to the field of robot control technology. The motion control method for the troweling robot includes: obtaining dynamic parameter information and motor load rate information of the troweling robot; obtaining environmental information of the location of the troweling robot; inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information; inputting the dynamic parameter information and the ground environmental parameter information into a model prediction controller to obtain inclination adjustment information; and controlling the troweling robot's troweling disc mechanism according to the inclination adjustment information. The motion control method for the troweling robot can achieve the technical effect of improving the accuracy and smoothness of the troweling robot's movement control.

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a motion control method and system for a trowel robot, a trowel robot, an electronic device, and a computer-readable storage medium. Background Art

[0002] The function of a floor trowel robot is to finish the concrete surface after initial setting and before final setting. Robot-troweled concrete surfaces are smoother and flatter than those produced manually, significantly improving the concrete's surface density and wear resistance, and increasing work efficiency by over five times compared to manual work. Floor trowel robots are widely used for slurry mixing, leveling, and finishing concrete surfaces in high-standard factories, warehouses, parking lots, plazas, airports, and frame buildings.

[0003] Currently, commercially available trowel robots are generally classified into two types of semi-automatic devices: handheld and ride-on. Both these robots utilize a propeller-like trowel with rotary power to smooth and finish the surface. As trowel robots work on the ground, the surface environment constantly changes. Their control systems are nonlinear and time-varying, making precise automated control of their position, posture, and speed difficult. They also suffer from poor interference immunity and robustness. Currently, handheld trowel robots rely on a manually operated handle to guide their movement, while ride-on trowel robots rely on a manually operated joystick to guide their movement. Both require manual labor and result in low construction efficiency. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a motion control method, system, trowel robot, electronic device and computer-readable storage medium for a trowel robot, which can achieve the technical effect of improving the accuracy and smoothness of the motion control of the trowel robot.

[0005] In a first aspect, an embodiment of the present application provides a motion control method for a trowel robot, comprising:

[0006] Obtaining dynamic parameter information and motor load rate information of the trowel robot;

[0007] Obtaining environmental information of the location of the trowel robot;

[0008] Inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information;

[0009] Inputting the dynamic parameter information and the ground environment parameter information into a model prediction controller to obtain tilt angle adjustment information;

[0010] The wiping disc mechanism of the trowel robot is controlled according to the inclination adjustment information.

[0011] In the above implementation process, the motion control method of the trowel robot realizes model predictive control through a model predictive controller; the motion control method is based on the model predictive controller of the trowel robot, and takes the body state of the trowel robot (motor load rate information, dynamic parameter information) and ground environment parameter information as feedback input, so as to predict and comprehensively optimize the state and inclination output of the trowel machine, thereby calculating the current optimal inclination adjustment information, so that the trowel robot can achieve precise and smooth motion control in different ground environments; thus, the motion control method of the trowel robot can achieve the technical effect of improving the accuracy and smoothness of the mobile control of the trowel robot.

[0012] Furthermore, the trowel robot includes a positioner, an inertial measurement unit, and a visual sensor, and the step of obtaining the dynamic parameter information and motor load rate information of the trowel robot includes:

[0013] Obtaining motor load rate information of the trowel robot;

[0014] Acquire locator data, inertial measurement unit data, and vision sensor data;

[0015] The locator data, the inertial measurement unit data and the visual sensor data are subjected to sensor fusion to obtain the dynamic parameter information, where the dynamic parameter information includes position information, velocity information, attitude angle information and angular velocity information.

[0016] In the above implementation process, by installing a locator, an inertial measurement unit and a visual sensor on the trowel robot, the position, posture, speed and ground information of the fuselage are perceived, thereby providing a highly robust multi-sensor fusion-motion state perception solution.

[0017] Furthermore, the environmental information includes ground wetness information, and the step of inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information includes:

[0018] Obtaining motor load change rate information according to the motor load rate information;

[0019] The motor load rate information, the motor load change rate information and the ground dryness and wetness information are input into a preset neural network to obtain ground environment parameter information.

[0020] In the above implementation process, the motor load change rate information can be obtained by calculating the motor load rate information; based on the preset neural network, through the collection of a large amount of ground environment annotations (ground wetness information) and motor load rate information, the preset neural network is input for training to obtain the nonlinear relationship between the ground environment friction coefficient and the motor load rate and wetness, and the corresponding ground environment parameter information is obtained to achieve accurate perception of the ground environment friction coefficient.

[0021] Furthermore, the step of inputting the dynamic parameter information and the ground environment parameter information into a model predictive controller to obtain tilt angle adjustment information includes:

[0022] Obtaining dynamic parameter setting data;

[0023] According to the dynamic parameter setting data, the dynamic parameter information, and the ground environment parameter information, the model prediction controller is input to correct and generate a linearized dynamic prediction model;

[0024] generating an objective function of a controller according to the linearized dynamics prediction model;

[0025] The objective function is solved to obtain the tilt adjustment information.

[0026] In the above implementation process, the dynamic parameter setting data, dynamic parameter information, and ground environment parameter information are input into the model prediction controller, wherein the ground environment parameter information is used as a correction parameter to finally generate the objective function of the controller; the objective function is based on the preset dynamic model and ground environment parameter information, with the machine status and output at the current moment and in the future as the optimization core, while taking into account the maximum adjustment amount and response time of the inclination angle of the trowel mechanism, thereby realizing the precise construction and intelligent construction of the trowel robot and improving the operating efficiency of the trowel robot.

[0027] Furthermore, in the step of inputting the dynamic parameter setting data, the dynamic parameter information, and the ground environment parameter information into the model prediction controller to correct and generate a linearized dynamic prediction model, the linearized dynamic prediction model includes a linearized dynamic formula, which is:

[0028]

[0029] Among them, X is the difference matrix between the dynamic parameter setting data and the dynamic parameter information, U is the inclination information of the wiping disc mechanism, A is the first coefficient matrix, B is the second coefficient matrix, and the first coefficient matrix and the second coefficient matrix are determined by the mechanical structure of the trowel robot and the ground environment parameter information.

[0030] Furthermore, in the step of generating an objective function of the controller according to the linearized dynamic prediction model, the objective function is:

[0031]

[0032] in, is a one-dimensional matrix composed of the output changes of the trowel robot from the current moment to the future control domain moment, H is the third coefficient matrix, and p is the fourth coefficient matrix.

[0033] Furthermore, the step of controlling the wiping disc mechanism of the trowel robot according to the inclination adjustment information includes:

[0034] Obtaining current position parameter information of the trowel robot;

[0035] The wiping disc mechanism of the trowel robot is controlled according to the current position parameter information and the inclination adjustment information.

[0036] In a second aspect, an embodiment of the present application provides a motion control system for a trowel robot, comprising:

[0037] A first acquisition module is used to obtain dynamic parameter information and motor load rate information of the trowel robot;

[0038] A second acquisition module is used to obtain environmental information of the location of the trowel robot;

[0039] A ground environment parameter module, configured to input the motor load rate information and the environment information into a preset neural network to obtain ground environment parameter information;

[0040] A tilt adjustment information module, configured to input the dynamic parameter information and the ground environment parameter information into a model prediction controller to obtain tilt adjustment information;

[0041] A control module is used to control the wiping disc mechanism of the trowel robot according to the inclination adjustment information.

[0042] Furthermore, the trowel robot includes a locator, an inertial measurement unit, and a visual sensor, and the first acquisition module includes:

[0043] A first acquiring unit is used to acquire motor load rate information of the trowel robot;

[0044] a second acquisition unit, configured to acquire locator data, inertial measurement unit data, and visual sensor data;

[0045] A fusion unit is used to perform sensor fusion on the locator data, the inertial measurement unit data and the visual sensor data to obtain the dynamic parameter information, where the dynamic parameter information includes position information, velocity information, attitude angle information and angular velocity information.

[0046] Furthermore, the environmental information includes ground wetness information, and the ground environmental parameter module includes:

[0047] a motor load change rate unit, configured to obtain motor load change rate information according to the motor load rate information;

[0048] The ground environment parameter unit is used to input the motor load rate information, the motor load change rate information and the ground dryness and wetness information into a preset neural network to obtain ground environment parameter information.

[0049] Furthermore, the tilt adjustment information module includes:

[0050] A setting data acquisition unit, used for acquiring dynamic parameter setting data;

[0051] A linearized dynamics unit, configured to input the dynamics parameter setting data, the dynamics parameter information, and the ground environment parameter information into a model prediction controller, and to correct and generate a linearized dynamics prediction model;

[0052] An objective function unit, configured to generate an objective function of a controller according to the linearized dynamics prediction model;

[0053] The tilt angle adjustment information unit is used to solve the objective function and obtain the tilt angle adjustment information.

[0054] Furthermore, the control module includes:

[0055] A current position parameter unit, used to obtain current position parameter information of the trowel robot;

[0056] A control unit is used to control the wiping disc mechanism of the trowel robot according to the current position parameter information and the inclination adjustment information.

[0057] In a third aspect, an embodiment of the present application provides a trowel robot, wherein the movement of the trowel robot executes the motion control method of the trowel robot described in any one of the first aspects.

[0058] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.

[0059] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the first aspects.

[0060] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0061] Other features and advantages disclosed in the present application will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present application.

[0062] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 A schematic flow chart of a motion control method for a trowel robot provided in an embodiment of the present application;

[0065] Figure 2 A schematic flow chart of another motion control method for a trowel robot provided in an embodiment of the present application;

[0066] Figure 3 A schematic diagram of the structure of a trowel robot provided in an embodiment of the present application;

[0067] Figure 4 A schematic structural diagram of the trowel robot provided in an embodiment of the present application from another perspective;

[0068] Figure 5 A structural block diagram of the motion control system of the trowel robot provided in an embodiment of the present application;

[0069] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0070] Icons: 101-locator; 102-first wiper mechanism; 103-second wiper mechanism; 104-wiper tilt control mechanism; 105-visual sensor; 106-wiper tilt axis; 107-tilt axis adjustment motor; 110-first acquisition module; 120-second acquisition module; 200-ground environment parameter module; 300-tilt adjustment information module; 400-control module; 510-processor; 520-communication interface; 530-memory; 540-communication bus. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0072] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0073] The embodiments of the present application provide a motion control method, system, electronic device and computer-readable storage medium for a trowel robot, which can be applied to the trowel operation process of the trowel robot; the motion control method of the trowel robot realizes model predictive control through a model predictive controller; the motion control method is based on the model predictive controller of the trowel robot, and uses the body state of the trowel robot (motor load rate information, dynamic parameter information) and ground environment parameter information as feedback input, so as to predict and comprehensively optimize the state and inclination output of the trowel machine, thereby calculating the current optimal inclination adjustment information, so that the trowel robot can realize precise and smooth motion control in different ground environments; thus, the motion control method of the trowel robot can achieve the technical effect of improving the accuracy and smoothness of the movement control of the trowel robot.

[0074] See Figure 1 , Figure 1 The following is a flow chart of a motion control method for a trowel robot provided in an embodiment of the present application. The motion control method for a trowel robot includes the following steps:

[0075] S110: Acquire dynamic parameter information and motor load rate information of the trowel robot.

[0076] S120: Obtaining environmental information of the location of the trowel robot;

[0077] For example, the motor load rate information, i.e., the motor load rate of the main shaft of the troweling robot, can reflect the ground friction to a certain extent; the environmental information includes the ground wetness information, which can be obtained by a visual sensor installed on the troweling robot.

[0078] Exemplarily, the dynamic parameter information includes information such as the position, posture, speed, and angular velocity of the trowel robot.

[0079] S200: Inputting motor load rate information and environmental information into a preset neural network to obtain ground environmental parameter information.

[0080] Exemplarily, the ground environment parameter information includes the ground environment friction coefficient; by inputting the motor load rate information and the ground wetness information into the preset neural network, a large amount of data training of the preset neural network is achieved, and the ground environment friction coefficient is accurately estimated based on the current motor load (motor load rate information) and wetness (ground wetness information), and the estimated information is provided to the model prediction controller to realize the correction of the dynamic model.

[0081] Exemplarily, the contents of the model predictive controller include inputting dynamic parameters and ground information, as well as obtaining and correcting the dynamic model, and then solving the tilt adjustment information according to the objective function under the preset control domain and control domain, that is, the embodiment of the present application uses a model predictive controller to solve the optimal tilt angle.

[0082] S300: Inputting dynamic parameter information and ground environment parameter information into a model prediction controller to obtain tilt angle adjustment information.

[0083] S400: Controlling the wiping disc mechanism of the trowel robot according to the inclination adjustment information.

[0084] For example, a model predictive controller, based on dynamic modeling and assisted by a neural network, can determine changes in the ground environment (friction coefficient), predict the state and output of the trowel robot over a period of time, and establish a comprehensive target optimization function. Thus, the inclination adjustment information becomes the optimal control variable, and the inclination axis of the trowel mechanism is adjusted accordingly, allowing the trowel robot to maintain the desired dynamic parameters. When subjected to external interference, the trowel robot can also quickly regain stability. This method differs from traditional methods in that it not only considers the robot's current state but also predicts its future state and uses it as an optimization metric. This method has good foresight and achieves a high degree of intelligence.

[0085] In some embodiments, the motion control method is based on the model predictive controller of the trowel robot, and takes the body state of the trowel robot (motor load rate information, dynamic parameter information) and ground environment parameter information as feedback input, so as to predict and comprehensively optimize the state and inclination output of the trowel machine, thereby calculating the current optimal inclination adjustment information, so that the trowel robot can achieve precise and smooth motion control in different ground environments; thus, the motion control method of the trowel robot can achieve the technical effect of improving the accuracy and smoothness of the trowel robot's mobile control, improving the robot's operating efficiency, and reducing the robot's construction failure rate.

[0086] See Figure 2 , Figure 2 A flowchart of another motion control method for a trowel robot provided in an embodiment of the present application.

[0087] Exemplarily, the trowel robot includes a positioner, an inertial measurement unit, and a visual sensor. S110: the step of obtaining dynamic parameter information and motor load rate information of the trowel robot includes:

[0088] S111: Obtaining the motor load rate information of the trowel robot;

[0089] S112: Acquire locator data, inertial measurement unit data, and visual sensor data;

[0090] S113: Perform sensor fusion on the locator data, the inertial measurement unit data, and the visual sensor data to obtain dynamic parameter information, which includes position information, velocity information, attitude angle information, and angular velocity information.

[0091] For example, by installing a locator, an inertial measurement unit (IMU), and a visual sensor on the trowel robot, the robot can sense its position, attitude, velocity, and ground information, thereby providing a highly robust multi-sensor fusion motion state perception solution. Alternatively, the locator can be a Global Navigation Satellite System (GNSS) locator, a base station navigation locator, or other similar locator. The specific positioning method of the locator is not limited here.

[0092] For example, obtaining information about a trowel robot's current motion state is fundamental to its motion control. GNSS, IMU, and vision sensors can sense the robot's position, attitude, velocity, angular velocity, and other information. These sensors complement each other's strengths and weaknesses, and their combined information provides the trowel robot with centimeter-level accuracy. Construction sites often face the absence of GPS signals, but the fusion of IMUs and vision sensors can still achieve high-precision positioning. Furthermore, vision sensors can identify obstacles and the ground environment.

[0093] Exemplarily, the environmental information includes ground wetness information. S200: Inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information includes:

[0094] S210: Obtaining motor load change rate information according to the motor load rate information;

[0095] S220: Inputting the motor load rate information, the motor load change rate information and the ground wetness information into a preset neural network to obtain ground environment parameter information.

[0096] For example, the motor load change rate information can be obtained by calculating the motor load rate information; based on the preset neural network, through the collection of a large amount of ground environment annotations (ground wetness information) and motor load rate information, the preset neural network is input for training to obtain the nonlinear relationship between the ground environment friction coefficient and the motor load rate and wetness, and the corresponding ground environment parameter information is obtained to achieve accurate perception of the ground environment friction coefficient.

[0097] In some implementation scenarios, the frictional forces on the trowel blades of trowel robots can be affected by factors such as wetness and the type of material used. This can significantly impact the robot's motion control. Visual sensors can determine the wetness of the floor, while the load factor of the trowel's spindle motor can, to a certain extent, reflect the friction. A neural network, trained on extensive data, accurately estimates the friction coefficient of the floor environment based on the current motor load and wetness. This information is then fed into a model predictive controller to refine the pre-set dynamics model.

[0098] Exemplarily, S300: inputting dynamic parameter information and ground environment parameter information into a model predictive controller to obtain tilt angle adjustment information includes:

[0099] S310: Acquiring dynamic parameter setting data;

[0100] S320: Correcting and generating a linearized dynamic prediction model based on the dynamic parameter setting data, dynamic parameter information, and ground environment parameter information input into the model prediction controller;

[0101] S330: Generate an objective function of the controller according to the linearized dynamic prediction model;

[0102] S340: Solve the objective function to obtain tilt adjustment information.

[0103] Exemplarily, the controller is the motion control mechanism of the trowel robot; the dynamic parameter setting data is the set expected data, such as the expected position, expected speed, expected attitude angle, etc. of the trowel robot; the dynamic parameter setting data, dynamic parameter information, and ground environment parameter information are input into the model prediction controller, where the ground environment parameter information is used as a correction parameter to finally generate the objective function of the controller; the objective function is based on the preset dynamic model and ground environment parameter information, with the machine state and output at the current moment and a period of time in the future as the core of optimization, while taking into account the maximum adjustment amount and response time of the inclination angle of the trowel mechanism, thereby realizing the precise construction and intelligent construction of the trowel robot and improving the operating efficiency of the trowel robot.

[0104] Exemplarily, in the step of correcting and generating a linearized dynamic prediction model based on the dynamic parameter setting data, dynamic parameter information, and ground environment parameter information input into the model prediction controller, the linearized dynamic prediction model includes a linearized dynamic formula, which is:

[0105]

[0106] Among them, X is the difference matrix between the dynamic parameter setting data and the dynamic parameter information, U is the inclination information of the wiping disc mechanism, A is the first coefficient matrix, and B is the second coefficient matrix. The first coefficient matrix and the second coefficient matrix are determined by the mechanical structure of the trowel robot and the ground environment parameter information.

[0107] For example, in the step of generating the objective function of the controller according to the linearized dynamic prediction model, the objective function is:

[0108]

[0109] in, It is a one-dimensional matrix composed of the output changes of the wiping robot from the current moment to the future control domain moment, H is the third coefficient matrix, and p is the fourth coefficient matrix.

[0110] Exemplarily, the third coefficient matrix and the fourth coefficient matrix are related parameters determined by the predicted state quantity, the predicted output quantity, the control domain, the prediction domain, and the control coefficient weight.

[0111] Exemplarily, S400: the step of controlling the wiping disc mechanism of the trowel robot according to the tilt adjustment information includes:

[0112] S410: Obtaining current position parameter information of the trowel robot;

[0113] S420: Controlling the wiping disc mechanism of the trowel robot according to the current position parameter information and the tilt angle adjustment information.

[0114] Exemplarily, the trowel robot may be adjusted to a desired state (ie, a target state) by combining the current position parameter information and the tilt adjustment information.

[0115] See Figure 3 and Figure 4 , Figure 3 This is a schematic diagram of the structure of the trowel robot provided in an embodiment of the present application. Figure 4 This is a structural schematic diagram of the trowel robot provided in an embodiment of the present application from another perspective; the trowel robot includes a robot body, a positioner 101, a first trowel mechanism 102, a second trowel mechanism 103, a trowel inclination control mechanism 104, a visual sensor 105, a trowel inclination axis 106, and an inclination axis adjustment motor 107.

[0116] For example, the purpose of the motion control method of the trowel robot provided in the embodiment of the present application is to provide a motion control method of the trowel robot based on model predictive control, which solves the problem that the current trowel robot relies on manual assisted traction and cannot perform autonomous and precise moving operations.

[0117] For example, a highly robust multi-sensor fusion solution is provided to enable a trowel robot to perceive its motion state and the ground environment. The trowel robot is equipped with a positioner 101, an IMU, and a visual sensor 105 (binocular camera). These three sensors can sense the robot's position, attitude, velocity, angular velocity, and other information. The positioner 101 can achieve long-term positioning, but its data update frequency is low, which poses a risk of signal loss. The IMU has a high data update frequency, resulting in high accuracy in short periods of time. Over long periods of time, GPS can calibrate the IMU's errors to ensure accuracy. Over short periods of time, the IMU can provide higher-frequency positioning data, reducing the risk of signal loss from the positioner 101. The data frequency and positioning accuracy of the visual sensor 105 depend on the quality of the sensor and the corresponding visual algorithm. Its inclusion improves the robustness of the entire positioning system. Even in the event of complete signal loss from the positioner 101, the dual fusion of the IMU and visual sensor 105 can still ensure a certain level of accuracy. Furthermore, the visual sensor 105 can determine obstacles around the robot and assess the wetness of the ground environment based on captured images. The three sensors complement each other's strengths and weaknesses, and the information fusion of the three can provide the smoothing robot with centimeter-level accurate status information.

[0118] For example, to enable a trowel robot to more accurately perceive the ground environment, thereby correcting the ground friction information in the dynamic model and helping the controller adapt to ground changes, a method for online prediction of ground environment parameter information based on a preset neural network is provided. The visual sensor 105 can determine the wetness of the ground environment, while the load on the trowel robot's spindle motor can reflect the magnitude of the ground friction. A neural network trained with a large amount of ground wetness and motor load data can describe this nonlinear relationship, allowing the trained neural network to perceive ground environment changes in real time.

[0119] For example, in order to enable the trowel robot to intelligently adjust the trowel disc to control itself to the desired state, a trowel robot motion control method based on model predictive control is provided. This method is based on model predictive controller information, with the machine state and output at the current moment and in the future as the core of optimization. At the same time, it can also take into account the maximum adjustment amount of the trowel disc inclination and the response time. Unlike traditional methods, this method has a certain degree of predictability and continuously performs rolling optimization and feedback correction. It can obtain the optimal output amount of the trowel disc inclination from the current moment to a period of time in the future. The controller selects the output amount at the current moment as the current inclination adjustment amount.

[0120] Combine Figures 1 to 4 The specific application process of the motion control method of the trowel robot provided in the embodiment of the present application is as follows:

[0121] Step 1: The visual sensor 105 obtains the ground wetness coefficient (ground wetness information) based on the ground image. The motor driver can read the motor load of the trowel robot (motor load rate information). The trowel robot is placed on a friction test platform (a custom-designed platform with a fixed base, the same concrete material used at the construction site laid on the bottom layer. The robot is moved at different speeds and angular velocities under different wetness conditions. The friction force acting on the robot body is deduced using tension sensors, torque sensors, and its own motion data). The friction reaction force acting on the trowel robot under different wetness conditions and loads is obtained. After a large amount of data is collected and labeled, the neural network is trained (a fully connected neural network is selected, and the number of layers and neurons in each layer is determined by the data volume and computing power).

[0122] Step 2: Obtain dynamic parameter setting data, including the desired position x d and y d , travel speed V d , and the desired attitude angle φ d ;

[0123] Step 3: Data from the positioner 101, IMU, and vision sensor 105 are fused (based on an extended Kalman filter) to obtain information such as the actual position [x, y], velocity v, attitude angle φ, and angular velocity ω of the trowel sensor. The first and second trowel mechanisms 102, 103 are controlled by the trowel robot's spindle motors, maintaining synchronization. Their interaction with the ground surface affects the spindle motor load. The trowel mechanism's speed can be set via the remote control or the robot's app.

[0124] Step 4: Read the motor load rate information L from the spindle motor driver and calculate the motor load change rate information The ground wetness information λ is obtained from the visual sensor.

[0125] Step 5: Input the preset neural network to obtain the friction correction coefficient γ.

[0126] Step 6: The ground environment change information is passed to the dynamic equation f(x, u) to modify it. At the same time, the dynamic equation takes local linearization measures, and finally obtains its linearized dynamic equation in the form of

[0127] in, And U=[θ L ,θ R ] Tare the inclination angles of the first wiping mechanism 102 and the second wiping mechanism 103 respectively. The first coefficient matrix and the second coefficient matrix are determined by the specific mechanical structure of the trowel robot and the ground information;

[0128] Step 7: The dynamic equation obtained in step 6 is used as the prediction model. The specific form of the controller's objective function is: The matrices H and p are determined by the predicted state quantity and predicted output quantity, control domain, prediction domain and control coefficient weight, etc. The model predictive controller will solve the objective function by quadratic programming under specified constraints (such as the maximum tilt angle adjustment value, adjustment response speed, etc.) to find the optimal tilt angle value θ that the current wiper (first wiper mechanism 102, second wiper mechanism 103) needs to achieve. L and θ R ;

[0129] Step 8: The trowel robot is equipped with a trowel tilt axis adjustment motor. The tilt axis adjustment motor 107 adjusts the position of the trowel tilt axis 106. Make the wiper disc tilt angle control mechanism 104 (the mechanism is fixedly connected to the tilt shaft and the tilt angle is equal) reach a given tilt angle θ L and θ R .

[0130] in, and θ L and θ R There are quantitatively precise mathematical relationships, such as Figure 4 As shown, according to the mathematical relationship, we can get θ L and θ R Then we can reversely infer The motor position mode can be used to quickly adjust the inclination axis motor to Position, without other adjustment algorithms. This can quickly and quantitatively adjust the inclination angle and improve response. Its mathematical relationship is as follows:

[0131]

[0132] Among them, the specific expressions of W, a and b are related to the design dimensions of the fuselage structure.

[0133] Step 9: After the inclination angle of the wiper is adjusted, return to step 2 for the next cycle (a single cycle of the controller takes 10ms) until the construction operation target is completed.

[0134] See Figure 5 , Figure 5 This is a structural block diagram of the motion control system of the trowel robot provided in an embodiment of the present application. The motion control system of the trowel robot includes:

[0135] A first acquisition module 110 is used to acquire dynamic parameter information and motor load rate information of the trowel robot;

[0136] The second acquisition module 120 is used to obtain environmental information of the location of the trowel robot;

[0137] The ground environment parameter module 200 is used to input the motor load rate information and the environment information into a preset neural network to obtain the ground environment parameter information;

[0138] The tilt adjustment information module 300 inputs the motor load rate information and the environmental information into the model predictive controller to obtain the tilt adjustment information;

[0139] The control module 400 is used to control the wiping disc mechanism of the trowel robot according to the inclination adjustment information.

[0140] Exemplarily, the trowel robot includes a positioner, an inertial measurement unit, and a visual sensor, and the first acquisition module 110 includes:

[0141] A first acquiring unit is used to acquire motor load rate information of the trowel robot;

[0142] a second acquisition unit, configured to acquire locator data, inertial measurement unit data, and visual sensor data;

[0143] The fusion unit is used to perform sensor fusion on the locator data, the inertial measurement unit data and the visual sensor data to obtain dynamic parameter information, which includes position information, velocity information, attitude angle information and angular velocity information.

[0144] Exemplarily, the environmental information includes ground wetness information, and the ground environmental parameter module 200 includes:

[0145] A motor load change rate unit, configured to obtain motor load change rate information according to the motor load rate information;

[0146] The ground environment parameter unit is used to input the motor load rate information, the motor load change rate information and the ground dryness and wetness information into a preset neural network to obtain the ground environment parameter information.

[0147] Exemplarily, the tilt adjustment information module 300 includes:

[0148] A setting data acquisition unit, used for acquiring dynamic parameter setting data;

[0149] The linearized dynamics unit is used to input the dynamics parameter setting data, dynamics parameter information, and ground environment parameter information into the model prediction controller to correct and generate a linearized dynamics prediction model;

[0150] An objective function unit is used to generate an objective function of the controller according to a linearized dynamic prediction model;

[0151] The tilt adjustment information unit is used to obtain tilt adjustment information according to the objective function.

[0152] Furthermore, the control module includes:

[0153] A current position parameter unit, used to obtain current position parameter information of the trowel robot;

[0154] A control unit is used to control the wiping disc mechanism of the trowel robot according to the current position parameter information and the inclination adjustment information.

[0155] It should be understood that Figure 5 The motion control system of the trowel robot shown is similar to Figures 1 to 4 The method embodiments shown correspond to the above and will not be described again here to avoid repetition.

[0156] This application also provides an electronic device, see Figure 6 , Figure 6 This is a block diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 510, a communication interface 520, a memory 530, and at least one communication bus 540. The communication bus 540 is used to enable direct communication between these components. The communication interface 520 of the electronic device in this embodiment of the present application is used to communicate signaling or data with other node devices. The processor 510 may be an integrated circuit chip with signal processing capabilities.

[0157] The processor 510 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or the processor 510 can also be any conventional processor.

[0158] The memory 530 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory 530 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 510, the electronic device can perform the above-mentioned operations. Figures 1 to 4 The various steps involved in the method embodiment.

[0159] Optionally, the electronic device may further include a storage controller and an input / output unit.

[0160] The memory 530, storage controller, processor 510, peripheral interface, and input / output units are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 540. The processor 510 is used to execute executable modules stored in the memory 530, such as software function modules or computer programs included in the electronic device.

[0161] The input and output unit is used to provide users with the ability to create tasks and to create optional time periods or preset execution times for the tasks to enable interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0162] I understand. Figure 6 The structure shown is only for illustration, and the electronic device may also include Figure 6 More or fewer components than shown, or with Figure 6 Different configurations shown. Figure 6 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0163] An embodiment of the present application further provides a storage medium having instructions stored thereon. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, details are not given here.

[0164] The present application also provides a computer program product, which, when running on a computer, enables the computer to execute the method described in the method embodiment.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0166] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0167] If the functions are implemented in the form of software function modules and sold or used as independent products, they 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 prior art 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 several instructions for enabling a computer device (which can be a personal computer, a server, or a 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.

[0168] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures.

[0169] The above description is merely a specific embodiment of the present application, but the scope of protection of the present 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 the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0170] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

Claims

1. A motion control method for a trowel robot, characterized in that: include: Obtaining dynamic parameter information and motor load rate information of the trowel robot; Obtaining environmental information of the location of the trowel robot; Inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information; Inputting the dynamic parameter information and the ground environment parameter information into a model prediction controller to obtain tilt angle adjustment information; controlling a wiping disc mechanism of the trowel robot according to the inclination adjustment information; The step of inputting the dynamic parameter information and the ground environment parameter information into a model predictive controller to obtain tilt angle adjustment information includes: Obtaining dynamic parameter setting data; Input the dynamic parameter setting data, the dynamic parameter information, and the ground environment parameter information into a model prediction controller; Generate linearized kinetic prediction models; generating an objective function of a controller according to the linearized dynamics prediction model; The objective function is solved to obtain the tilt adjustment information.

2. The motion control method of the trowel robot according to claim 1, characterized in that: The trowel robot includes a positioner, an inertial measurement unit, and a visual sensor. The step of obtaining dynamic parameter information and motor load rate information of the trowel robot includes: Obtaining motor load rate information of the trowel robot; Acquire locator data, inertial measurement unit data, and vision sensor data; The locator data, the inertial measurement unit data and the visual sensor data are subjected to sensor fusion to obtain the dynamic parameter information, where the dynamic parameter information includes position information, velocity information, attitude angle information and angular velocity information.

3. The motion control method of the trowel robot according to claim 2, characterized in that: The environmental information includes ground wetness information. The step of inputting the motor load rate information and the environmental information into a preset neural network to obtain ground environmental parameter information includes: Obtaining motor load change rate information according to the motor load rate information; The motor load rate information, the motor load change rate information and the ground dryness and wetness information are input into a preset neural network to obtain ground environment parameter information.

4. The motion control method of the trowel robot according to claim 1, characterized in that: In the step of inputting the dynamic parameter setting data, the dynamic parameter information, and the ground environment parameter information into the model prediction controller to generate a linearized dynamic prediction model, the linearized dynamic prediction model includes a linearized dynamic formula, which is: Among them, X is the difference matrix between the dynamic parameter setting data and the dynamic parameter information, U is the inclination information of the wiping disc mechanism, A is the first coefficient matrix, B is the second coefficient matrix, and the first coefficient matrix and the second coefficient matrix are determined by the mechanical structure of the trowel robot and the ground environment parameter information.

5. The motion control method of the trowel robot according to claim 3, characterized in that: In the step of generating the objective function of the controller according to the linearized dynamics prediction model, the objective function is: in, is a one-dimensional matrix composed of the output changes of the trowel robot from the current moment to the future control domain moment, H is the third coefficient matrix, and p is the fourth coefficient matrix.

6. The motion control method of the trowel robot according to claim 1, characterized in that: The step of controlling the wiping disc mechanism of the trowel robot according to the inclination adjustment information includes: Obtaining current position parameter information of the trowel robot; The wiping disc mechanism of the trowel robot is controlled according to the current position parameter information and the inclination adjustment information.

7. A motion control system for a trowel robot, characterized in that: include: A first acquisition module is used to obtain dynamic parameter information and motor load rate information of the trowel robot; A second acquisition module is used to obtain environmental information of the location of the trowel robot; A ground environment parameter module, configured to input the motor load rate information and the environment information into a preset neural network to obtain ground environment parameter information; A tilt adjustment information module, configured to input the dynamic parameter information and the ground environment parameter information into a model prediction controller to obtain tilt adjustment information; A control module, configured to control a wiping disc mechanism of the trowel robot according to the tilt adjustment information; The tilt adjustment information module includes: A setting data acquisition unit, used for acquiring dynamic parameter setting data; A linearized dynamics unit, configured to input the dynamics parameter setting data, the dynamics parameter information, and the ground environment parameter information into a model prediction controller, and to correct and generate a linearized dynamics prediction model; An objective function unit, configured to generate an objective function of a controller according to the linearized dynamics prediction model; The tilt angle adjustment information unit is used to solve the objective function and obtain the tilt angle adjustment information.

8. A trowel robot, characterized in that: The movement of the trowel robot executes the motion control method of the trowel robot according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the motion control method for a trowel robot according to any one of claims 1 to 6 are implemented.

Images