Robot motion control parameter optimization method, system, intelligent terminal and medium

Abstract

The application discloses a robot motion control parameter optimization method and system, an intelligent terminal and a medium. The method comprises the following steps: obtaining a to-be-optimized motion control parameter, performing actual motion control testing according to the to-be-optimized motion control parameter, determining a virtual testing function threshold value based on a target function and a result of the actual motion control testing; performing virtual motion control testing according to the to-be-optimized motion control parameter, iteratively updating the to-be-optimized motion control parameter until a virtual testing function value determined according to a result of the virtual motion control testing and the target function is not greater than the virtual testing function threshold value; performing actual motion control testing according to the to-be-optimized motion control parameter, updating the target function according to a result of the actual motion control testing; returning to the step of performing virtual motion control testing on the robot according to the to-be-optimized motion control parameter until a parameter optimization termination condition is met, and obtaining a target motion control parameter after optimization. In this way, the parameter optimization efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot control, and particularly relates to a robot motion control parameter optimization method and system, an intelligent terminal and a medium. BACKGROUND

[0002] With the progress of science and technology, robots are applied more and more widely. When the robot is controlled, in order to improve the accuracy of motion control, the motion control parameters of the robot need to be optimized.

[0003] In the prior art, a large number of actual motion control tests are usually performed on the robot, and the motion control parameters are optimized according to the results of the actual motion control tests. The problem of the prior art is that the optimization of the motion control parameters only depends on the test results of the actual motion control tests, a large number of actual motion control tests need to be performed, the test workload is large, resource consumption is large, and it is not conducive to improving the parameter optimization efficiency.

[0004] Therefore, the related technology needs to be improved and developed. SUMMARY

[0005] The main purpose of the present application is to provide a robot motion control parameter optimization method and system, an intelligent terminal and a medium, which aims to solve the technical problems in the related art that the optimization of the motion control parameters only depends on the test results of the actual motion control tests, a large number of actual motion control tests need to be performed, the test workload is large, resource consumption is large, and it is not conducive to improving the parameter optimization efficiency.

[0006] In order to achieve the above purpose, the first aspect of the present application provides a robot motion control parameter optimization method, wherein the robot motion control parameter optimization method comprises:

[0007] obtaining a to-be-optimized motion control parameter, performing an actual motion control test on a robot according to the to-be-optimized motion control parameter, and determining a virtual test function threshold value based on a preset target function and a result of the actual motion control test;

[0008] performing at least one virtual motion control test on the robot according to the to-be-optimized motion control parameter, to iteratively update the to-be-optimized motion control parameter, until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold value;

[0009] performing an actual motion control test on the robot according to the to-be-optimized motion control parameter, and updating the target function according to a result of the actual motion control test;

[0010] The step of performing the virtual motion control test on the robot according to the to-be-optimized motion control parameter is executed until a preset parameter optimization termination condition is met, and an optimized target motion control parameter is obtained, wherein the parameter optimization termination condition includes that a number of times of performing the actual motion control test reaches a preset maximum actual test number.

[0011] Optionally, the obtaining the to-be-optimized motion control parameter, performing the actual motion control test on the robot according to the to-be-optimized motion control parameter, and determining the virtual test function threshold based on the preset target function and a result of the actual motion control test include:

[0012] The to-be-optimized motion control parameter is obtained, wherein the to-be-optimized motion control parameter includes at least one of a motor torque, a PID controller gain, and a joint angle.

[0013] The actual motion control test is performed on the robot according to the to-be-optimized motion control parameter.

[0014] The first actual test function value is determined based on the target function and a result of the actual motion control test.

[0015] The function final target threshold is determined according to the first actual test function value, wherein the function final target threshold is less than the first actual test function value.

[0016] The virtual test function threshold is determined according to the first actual test function value and the function final target threshold, wherein the virtual test function threshold is not greater than the first actual test function value and not less than the function final target threshold.

[0017] Optionally, the determining the first actual test function value based on the target function and the result of the actual motion control test includes:

[0018] The actual state parameter of the robot during the actual motion control test is collected.

[0019] The expected state parameter corresponding to the to-be-optimized motion control parameter is obtained.

[0020] The first actual test function value is calculated by the target function according to the actual state parameter and the expected state parameter.

[0021] Optionally, the performing the virtual motion control test on the robot according to the to-be-optimized motion control parameter to iteratively update the to-be-optimized motion control parameter until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold includes:

[0022] obtaining a virtual control parameter generation rule;

[0023] generating a virtual test control parameter according to the virtual control parameter generation rule and the to-be-optimized motion control parameter;

[0024] performing a virtual motion control test according to the virtual test control parameter, and determining a virtual test function value based on the target function and a result of the virtual motion control test;

[0025] updating the to-be-optimized motion control parameter according to the virtual test control parameter, and returning to the step of generating a virtual test control parameter according to the virtual control parameter generation rule and the to-be-optimized motion control parameter until the virtual test function value is not greater than the virtual test function threshold.

[0026] Optionally, the method further comprises:

[0027] when performing each virtual motion control test, if a virtual test function value corresponding to the virtual motion control test is not less than the first actual test function value, updating the virtual control parameter generation rule, generating a new virtual test control parameter according to the updated virtual control parameter generation rule, and re-performing the virtual motion control test based on the new virtual test control parameter until the virtual test function value corresponding to the virtual motion control test is less than the first actual test function value.

[0028] Optionally, the target function comprises a plurality of pre-designed calculation items in weighted summation;

[0029] The pre-designed calculation items comprise a position error item, a velocity error item, an energy consumption item, a state entropy item and a control strategy entropy item;

[0030] The position error item is used to represent a difference between an actual position of the robot and an expected position;

[0031] The velocity error item is used to represent a difference between an actual velocity of the robot and an expected velocity;

[0032] The energy consumption item is used to represent energy consumed by the robot in performing motion;

[0033] The state entropy item is used to represent a degree of disorder of a state of the robot;

[0034] The control strategy entropy item is used to represent a diversity of a control strategy of the robot.

[0035] Optionally, the performing an actual motion control test on the robot according to the to-be-optimized motion control parameter, and updating the target function according to a result of the actual motion control test comprises:

[0036] controlling the robot to return to the initial position;

[0037] performing a real motion control test on the robot according to the to-be-optimized motion control parameter;

[0038] determining a second real test function value based on the target function and a result of the real motion control test;

[0039] if the second real test function value is not greater than the final target threshold of the function, regarding the to-be-optimized motion control parameter as the optimized target motion control parameter, and ending the motion control parameter optimization process;

[0040] if the second real test function value is greater than the final target threshold of the function, updating the weight values corresponding to each pre-designed calculation item in the target function according to the second real test function value.

[0041] The second aspect of the present application provides a robot motion control parameter optimization system, wherein the robot motion control parameter optimization system comprises:

[0042] a first real test module, configured to obtain a to-be-optimized motion control parameter, perform a real motion control test on a robot according to the to-be-optimized motion control parameter, and determine a virtual test function threshold based on a preset target function and a result of the real motion control test;

[0043] a virtual test module, configured to perform at least one virtual motion control test on the robot according to the to-be-optimized motion control parameter, and iteratively update the to-be-optimized motion control parameter until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold;

[0044] a second real test module, configured to perform a real motion control test on the robot according to the to-be-optimized motion control parameter, and update the target function according to a result of the real motion control test;

[0045] an iteration control module, configured to return to perform the at least one virtual motion control test on the robot according to the to-be-optimized motion control parameter until a preset parameter optimization termination condition is met, and obtain an optimized target motion control parameter, wherein the parameter optimization termination condition comprises that a number of times of performing the real motion control test reaches a preset maximum number of real tests.

[0046] The third aspect of the present application provides an intelligent terminal, the intelligent terminal comprising a memory, a processor, and a robot motion control parameter optimization program stored in the memory and executable on the processor, the robot motion control parameter optimization program implementing the steps of any one of the robot motion control parameter optimization methods when executed by the processor.

[0047] The fourth aspect of the present application provides a computer-readable storage medium, the computer-readable storage medium storing a robot motion control parameter optimization program, the robot motion control parameter optimization program implementing the steps of any one of the robot motion control parameter optimization methods when executed by a processor.

[0048] As can be seen, in the present application, the motion control parameters to be optimized are obtained, a virtual motion control test is performed on the robot according to the motion control parameters to be optimized, a virtual test function threshold is determined based on a preset target function and a result of the actual motion control test; at least one virtual motion control test is performed on the robot according to the motion control parameters to be optimized, and the motion control parameters to be optimized are iteratively updated until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold; an actual motion control test is performed on the robot according to the motion control parameters to be optimized, and the target function is updated according to a result of the actual motion control test; the step of performing at least one virtual motion control test on the robot according to the motion control parameters to be optimized is returned to be executed until a preset parameter optimization termination condition is met, and the optimized target motion control parameters are obtained, wherein the parameter optimization termination condition comprises that a number of times of performing the actual motion control test reaches a preset maximum actual test number.

[0049] Compared with the prior art, in the scheme corresponding to the robot motion control parameter optimization method provided by the present application, when the parameter optimization is performed, not only the actual motion control test is relied on, but also the virtual motion control test and the actual motion control test are combined to perform the parameter optimization. In this way, the virtual motion control test is introduced to optimize the motion control parameters to be optimized, which can reduce the dependence on the actual motion control test, thereby facilitating to reduce the test workload, reduce resource consumption, and improve the parameter optimization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 is a flowchart of a robot motion control parameter optimization method provided by an embodiment of the present application;

[0052] Figure 2 is a specific flowchart of a robot motion control parameter optimization method provided by an embodiment of the present application;

[0053] Figure 3 is a component module diagram of a robot motion control parameter optimization system provided by an embodiment of the present application;

[0054] Figure 4 is an internal structure principle block diagram of an intelligent terminal provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] In the following description, for the purposes of explanation and not limitation, specific details are set forth, such as particular sequences of steps, techniques, etc., in order to provide a thorough understanding of the embodiments of the application. However, it will be apparent to those skilled in the art that the application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, and circuits are omitted so as not to obscure the description of the application with unnecessary detail.

[0056] It should be understood that the term “comprises / comprising” when used in this specification and the appended claims, specifies the presence of stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0057] It should also be understood that the terms used in the specification and the appended claims are intended to describe particular embodiments and do not intend to limit the present application. As used in the specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0058] It should be further understood that the term “and / or” used in the specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations thereof, and includes these combinations.

[0059] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when," or "upon," or "in response to a determination," or "in response to a classification" depending on the context. Similarly, the phrase "if determined" or "if classified [a described condition or event]" can be interpreted as meaning "upon determining," or "in response to determining," or "upon classifying," or "in response to classifying [a described condition or event]" depending on the context.

[0060] The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort fall within the protection scope of the present application.

[0061] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, but the present application can also be implemented in other manners different from those described herein, and a person of ordinary skill in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0062] At present, the application of robots is more and more extensive, and the motion control of robots is also more and more concerned. When controlling the robot, in order to improve the accuracy of motion control, the motion control parameters of the robot need to be optimized. In the field of robot motion control testing, especially for the optimization of motion control strategy of humanoid robots, at present, it mainly depends on a large number of actual motion tests.

[0063] In one application scenario, a parameter optimization method includes the following steps: presetting control parameters: according to experience or preliminary design, setting initial motion control parameters for a humanoid robot, such as motor torque, joint angle, etc. Actual motion test: controlling the robot to perform actual motion according to the preset parameters, recording various parameters in the motion process through sensors, such as position, speed, acceleration, energy consumption, etc. Data analysis and adjustment: analyzing the test data, evaluating the motion performance of the robot, and adjusting the control parameters according to the evaluation results. Repeat the test: repeat the above steps, gradually optimize the control parameters through multiple actual motion tests, to achieve better control effect.

[0064] The above method has the disadvantages of large test workload, low test efficiency, large resource consumption, slow optimization speed, etc. Specifically, the above method relies on a large number of actual motion control tests, so the test workload is large. Each test requires the robot to perform actual motion, and the test period is long. Moreover, the test results are affected by environmental factors and equipment, and the stability and repeatability of the test results are poor. When performing actual motion tests, a large amount of space is occupied, a large amount of energy is consumed, and the test cost is increased. At the same time, because the robot needs to perform actual motion for each test, the motion control strategy optimization speed is slow, that is, it is not conducive to improving the parameter optimization efficiency.

[0065] To solve at least one of the above technical problems, in the scheme provided by the present application, the motion control parameters to be optimized are obtained, one actual motion control test is performed on the robot according to the motion control parameters to be optimized, and a virtual test function threshold is determined based on a preset target function and the results of the actual motion control test. At least one virtual motion control test is performed on the robot according to the motion control parameters to be optimized, and the motion control parameters to be optimized are iteratively updated until the virtual test function value determined according to the results of the virtual motion control test and the target function is not greater than the virtual test function threshold. One actual motion control test is performed on the robot according to the motion control parameters to be optimized, and the target function is updated according to the results of the actual motion control test. The step of performing at least one virtual motion control test on the robot according to the motion control parameters to be optimized is returned to be executed until a preset parameter optimization termination condition is met, and the target motion control parameters optimized are obtained, wherein the parameter optimization termination condition includes that the number of times of performing actual motion control tests reaches a preset maximum actual test number.

[0066] Compared with the prior art, in the scheme corresponding to the robot motion control parameter optimization method provided by the present application, when performing parameter optimization, not only actual motion control tests are relied on, but also virtual motion control tests and actual motion control tests are combined to perform parameter optimization. In this way, the introduction of virtual motion control tests to optimize the motion control parameters to be optimized can reduce the dependence on actual motion control tests, thereby facilitating the reduction of test workload, the reduction of resource consumption, and the improvement of parameter optimization efficiency.

[0067] As shown in Figure 1 The present application provides a robot motion control parameter optimization method, which specifically includes the following steps:

[0068] In step S100, the motion control parameters to be optimized are obtained, one actual motion control test is performed on the robot according to the motion control parameters to be optimized, and a virtual test function threshold is determined based on a preset target function and the results of the actual motion control test.

[0069] wherein the to-be-optimized motion control parameter is a motion control parameter that needs to be optimized, in an application scenario, a preset initial motion control parameter is acquired or an initial motion control parameter is input by a user, and the initial motion control parameter is taken as the to-be-optimized motion control parameter.

[0070] In the embodiments of the present application, the motion control parameter is a parameter used for controlling the robot to move. It should be noted that the embodiments of the present application take the motion control of a humanoid robot as an example for specific description, but this is not a specific limitation.

[0071] In the embodiments of the present application, the initial actual test of the robot and the acquisition of the control parameter are performed first. Specifically, the humanoid robot starts from an initial state, moves according to a preset initial motion control parameter (such as motor torque, joint angle, etc.), and is recorded as the first test (for example, the humanoid robot is commanded to move from position a to position b, or the key center of gravity of the leg of the humanoid robot is commanded to move from position c to position d). During the movement, the position, speed, acceleration, energy consumption and other key parameters of the robot are recorded by sensors and other devices.

[0072] Specifically, the to-be-optimized motion control parameter is acquired, one actual motion control test of the robot is performed according to the to-be-optimized motion control parameter, a virtual test function threshold is determined based on a preset target function and a result of the actual motion control test, and the method comprises the following steps.

[0073] The to-be-optimized motion control parameter is acquired, wherein the to-be-optimized motion control parameter comprises at least one of a motor torque, a PID controller gain and a joint angle;

[0074] One actual motion control test of the robot is performed according to the to-be-optimized motion control parameter;

[0075] A first actual test function value is determined based on the target function and the result of the actual motion control test;

[0076] A function final target threshold is determined according to the first actual test function value, wherein the function final target threshold is less than the first actual test function value;

[0077] A virtual test function threshold is determined according to the first actual test function value and the function final target threshold, wherein the virtual test function threshold is not greater than the first actual test function value and not less than the function final target threshold.

[0078] It should be noted that in the embodiments of the present application, the motion control parameters to be optimized are represented and processed in a sequence manner. The above-mentioned objective function is a function pre-constructed for evaluating the control level (for example, control accuracy, robot state after control) of the motion control parameters to be optimized. The specific form of the above-mentioned objective function can be set and adjusted according to actual needs, or the required objective function can be constructed in real time according to actual motion control parameters to be optimized, which is not limited here.

[0079] In the embodiments of the present application, the above-mentioned objective function includes a plurality of pre-designed calculation items in weighted summation;

[0080] The above-mentioned pre-designed calculation items include a position error item, a speed error item, an energy consumption item, a state entropy item and a control strategy entropy item;

[0081] The above-mentioned position error item is used to represent the difference between the actual position of the robot and the expected position;

[0082] The above-mentioned speed error item is used to represent the difference between the actual speed of the robot and the expected speed;

[0083] The above-mentioned energy consumption item is used to represent the energy consumed by the robot in performing motion;

[0084] The above-mentioned state entropy item is used to represent the degree of confusion of the state of the robot;

[0085] The above-mentioned control strategy entropy item is used to represent the diversity of the control strategy of the robot.

[0086] In one application scenario, the objective function is constructed according to the actually tested parameters, and the above-mentioned objective function is shown in the following formula (1):

[0087]

[0088] And Wherein, J represents the function value calculated based on the objective function. u represents the control parameter sequence, for example, it can be the motion control parameter to be optimized, and specifically it can include the control parameter sequence of motor torque, PID controller gain, joint angle, etc. T represents the total time step of the test, and t represents the tth time step.

[0089] The weight coefficient of the position error, the initial value of which is pre-set, can be set and adjusted according to actual needs, and its value depends on the importance of the position error to the control target, and has a minimum limit, and the minimum limit can be set and adjusted according to actual needs. The position error corresponding to the tth time step.

[0090] The weight coefficient representing the speed error has a corresponding initial value preset, which can be set and adjusted according to actual needs, and the value depends on the importance of the speed error to the control target, and has a minimum limit, and the minimum limit can be set and adjusted according to actual needs. The speed error corresponding to the tth time step is used to emphasize the motion smoothness.

[0091] w c The weight coefficient representing the energy consumption has a corresponding initial value preset, which can be set and adjusted according to actual needs, and the value depends on the importance of the energy consumption to the control target, and has a minimum limit, and the minimum limit can be set and adjusted according to actual needs.c t The energy consumption corresponding to the tth time step.

[0092] The weight coefficient representing the state entropy has a corresponding initial value preset, which can be set and adjusted according to actual needs, and the value depends on the importance of the state entropy to the control target, and has a minimum limit, and the minimum limit can be set and adjusted according to actual needs. The state entropy corresponding to the tth time step is used to reflect the chaos degree of the robot state.

[0093] The weight coefficient representing the control strategy entropy has a corresponding initial value preset, which can be set and adjusted according to actual needs, and the value depends on the importance of the control strategy entropy to the control target, and has a minimum limit, and the minimum limit can be set and adjusted according to actual needs. The control strategy entropy corresponding to the tth time step is used to reflect the diversity or uncertainty of the control strategy.

[0094] The above objective function is used to evaluate the performance of the motion control strategy (i.e. motion control parameters), and the objective function includes multiple calculation items, including position error item, speed error item, energy consumption item, state entropy item and control strategy entropy item, and other calculation items can be set according to actual needs, which are not limited here. Each index in each calculation item corresponds to a corresponding weight coefficient. The position error, speed error, energy consumption, state entropy and control strategy entropy at this time can be calculated according to the measured control input parameter sequence, and then the objective function value is obtained. Specifically, according to the results of the first actual motion control test, the corresponding objective function value is calculated based on the above objective function, which is used as the first actual test function value k1.

[0095] Further, the first actual test function value k1 is used to set the function final target threshold k last , and the function final target threshold k lastThe specific setting mode can be set and adjusted according to actual needs, and generally has 0 < k last <k1.

[0096] In the embodiments of the present application, the meanings and calculation methods of each calculation term of the above-mentioned objective function are also specifically described. Specifically, represents a term in the objective function composed of a position error term and its weight coefficient, and is used to represent the weighted absolute value sum of the position error at time point t. It measures the difference between the actual position of the robot (or the center of gravity position of a part of the robot, such as the center of gravity position of the leg of the robot) and the expected position.

[0097] represents a term in the objective function composed of a velocity error term and its weight coefficient, and is used to represent the weighted absolute value sum of the velocity error at time point t. It measures the difference between the actual velocity of the robot (or the center of gravity velocity of a part of the robot, such as the center of gravity velocity of the leg of the robot) and the expected velocity.

[0098] w c c t represents a term in the objective function composed of an energy consumption term and its weight coefficient, and is used to represent the energy consumed by the robot in executing motion at time point t. The specific calculation formula depends on the energy consumption model and the kinematics model of the robot, and one calculation method of the above-mentioned energy consumption term is shown in the following formula (2):

[0099]

[0100] wherein c t represents the energy consumption of the robot or a part of the robot from the initial position to time point t, and n represents the total number of motors corresponding to the robot or the part of the robot. i (t) represents the power of the i th motor at time point t, which is generally calculated by the motor torque and angular velocity formula, for example, P = τω for a DC motor, wherein τ represents the torque and ω represents the angular velocity of the motor. Δt represents the time interval from the initial position of the robot or a part of the robot to time point t.

[0101] represents a term in the objective function composed of a state entropy term and its weight coefficient, and is used to represent the uncertainty or degree of confusion of the state of the robot at time point t, which is usually calculated using the entropy formula of the probability distribution, as shown in the following formula (3):

[0102]

[0103] wherein, The state entropy of the robot at time point t, in the motion control of humanoid robots, the state of the robot is defined as a series of variables related to the motion of the robot. These variables can include robot joint angles, joint speeds, joint or limb positions and poses, external forces or torques acting on the robot, etc.; the state space of the robot can be generally defined as a series of discrete combinations of joint angles, joint speeds, positions and poses. And through the sensor data or kinematics model to estimate the probability of the robot in each time point in these states, according to the probability distribution using the entropy calculation formula to calculate the state entropy, the higher the state entropy, means that the motion state of the robot is unstable or there is a greater uncertainty.

[0104] B i (t) represents the probability of the robot being in the i-th state at time point t, which is generally estimated by using Bayesian network or Markov chain Monte Carlo method (MCMC), and m represents the number of possible states of the robot.

[0105] represents an item in the objective function composed of the control strategy entropy term and its weight coefficient, used to represent the uncertainty or diversity of the control strategy. Probabilistic control strategy can use similar entropy formula of probability distribution to calculate, as shown in the following formula (4):

[0106]

[0107] Wherein, The control strategy entropy of the robot at time point t, in the motion control of embodied intelligent humanoid robots, the control strategy entropy includes but is not limited to robot joint angles and speeds, ground conditions, obstacle positions, lighting conditions, robots need to complete walking, running, jumping, grasping objects, etc. Task, the battery capacity, temperature, motor state of the robot, etc. Internal parameters that may affect the performance and stability of the robot; the control strategy entropy measures the uncertainty of the robot when facing multiple possible control strategies at time t. For example, when facing an obstacle, the embodied intelligent robot can choose to bypass, jump or stop; the higher the control strategy entropy, the more complex the decision the robot faces in the current state, which means that the embodied intelligent robot needs to adjust the strategy more flexibly to cope with uncertainty, so it is necessary to minimize the control strategy entropy to promote the robot to select a more certain and efficient control strategy in the motion control test.

[0108] To calculate the control strategy entropy, first of all, it is necessary to clarify all the control strategies or actions that the robot can take. These strategies or actions constitute the control strategy space of the robot, for each possible control strategy or action, the probability of its occurrence in the current state needs to be calculated, and the formula of entropy is used for calculation.

[0109] q j (t) The probability of the robot selecting the jth control action at time point t can be estimated using a Bayesian network or a Markov chain Monte Carlo method. h represents the number of possible control actions of the robot.

[0110] In an application scenario, the determination of the first actual test function value based on the target function and the result of the actual motion control test includes:

[0111] Collecting actual state parameters of the robot during the actual motion control test;

[0112] Obtaining expected state parameters corresponding to the motion control parameters to be optimized;

[0113] According to the actual state parameters and the expected state parameters, the first actual test function value is calculated by the target function.

[0114] In this way, the actual state parameters of the robot during the actual motion control are collected, and the first actual test function value is calculated according to the target function. The specific actual state parameters to be collected are determined according to the specific form of the target function, which is not limited here.

[0115] Step S200: performing at least one virtual motion control test on the robot according to the motion control parameters to be optimized, to iteratively update the motion control parameters to be optimized, until a virtual test function value determined according to the result of the virtual motion control test and the target function is not greater than a virtual test function threshold value.

[0116] It should be noted that in the embodiments of the present application, parameter optimization is performed in combination with virtual motion control test. Before iteration of the virtual test, a stage threshold value of the last actual test target function value is determined according to a preset rule, and is taken as the virtual test function threshold value k 1(1) , and k last ≤k 1(1) ≤k1. The generation method of the virtual test function threshold value k 1(1) can be set and adjusted according to actual needs, for example, it can be set as k 1(1) =αk1, 0<α<1, and k last ≤k 1(1) .

[0117] Specifically, the at least one virtual motion control test on the robot according to the motion control parameters to be optimized, to iteratively update the motion control parameters to be optimized, until the virtual test function value determined according to the result of the virtual motion control test and the target function is not greater than the virtual test function threshold value, includes:

[0118] obtaining a virtual control parameter generation rule;

[0119] generating a virtual test control parameter according to the virtual control parameter generation rule and the to-be-optimized motion control parameter;

[0120] performing a virtual motion control test according to the virtual test control parameter, and determining a virtual test function value based on the target function and a result of the virtual motion control test;

[0121] updating the to-be-optimized motion control parameter according to the virtual test control parameter, and returning to perform the step of generating a virtual test control parameter according to the virtual control parameter generation rule and the to-be-optimized motion control parameter until the virtual test function value is not greater than the virtual test function threshold.

[0122] Further, the method further comprises:

[0123] when performing each virtual motion control test, if a virtual test function value corresponding to the virtual motion control test is not less than the first actual test function value, updating the virtual control parameter generation rule, generating a new virtual test control parameter according to the updated virtual control parameter generation rule, and re-performing the virtual motion control test based on the new virtual test control parameter until the virtual test function value corresponding to the virtual motion control test is less than the first actual test function value.

[0124] The virtual control parameter generation rule is used to adjust the to-be-optimized motion control parameter to generate a virtual test control parameter required when performing a virtual motion control test. The virtual control parameter generation rule can be pre-set, selected from a pre-set virtual control parameter generation rule library, or input or adjusted in real time by a user, and is not specifically limited herein.

[0125] In the embodiments of the application, the previous actual test parameter (i.e. the to-be-optimized motion control parameter such as motor torque, controller PID gain, joint angle, etc.) is generated into a virtual test control parameter within the allowed range of each parameter setting (for example, the allowed setting range of motor torque of the current posture of the robot leg, or the allowed value range of the controller PID gain, or the allowed angle setting range of the joint).

[0126] In an application scenario, the virtual control parameter generation rule includes: in each virtual motion control test iteration, the virtual test control parameter value is calculated through the rule. For example, the parameter to be optimized corresponding to a certain robot is θ. On the premise that θ1 satisfies the value range corresponding to this parameter, let θ1 = βθ, where 0 < β < 1. Here, θ1 is the virtual test control parameter generated based on the parameter to be optimized θ, and the value of β can be determined according to the actual rule.

[0127] It should be noted that in the first virtual motion control test, the value of the parameter to be optimized for motion control can be adjusted to obtain the virtual test control parameter, or the parameter to be optimized for motion control can be directly used as the virtual test control parameter for the current iteration, and no specific limitation is made here.

[0128] Calculate the virtual test function value k of the first iteration using the generated virtual test control parameter 1(v1) , that is, using the virtual generated control parameter sequence (virtual test control parameter sequence), through models such as the robot dynamics model, calculate the corresponding position error, speed error, energy consumption, state entropy, and control strategy entropy, so as to determine the corresponding virtual test function value k 1(v1) . There should be k 1(v1) < k1, where k1 is the objective function value calculated and determined according to the previous actual motion control test, that is, the first actual test function value k1.

[0129] If k 1(v1) ≥ k1 at this time, replace the corresponding virtual control parameter generation rule until k 1(v1) < k1. For example, the original virtual control parameter generation rule θ1 = βθ can be updated to θ1 = (1 + β)θ, where 0 < β < 1.

[0130] If the virtual test function value k 1(v1) is greater than the virtual test function threshold k determined based on the previous actual motion control test 1(1) , that is, k 1(v1) > k 1(1) , perform the second virtual iteration and ensure that the virtual test function value k of the first virtual iteration 1(v1) is greater than the virtual test function value k of the second iteration 1(v2) , that is, k 1(v2) < k 1(v1) .

[0131] And so on, the virtual parameter iteration based on the virtual motion control test will continue until the virtual test function value k of the nth virtual iteration obtained by calculation 1(vn) is not greater than the above virtual test function threshold k 1(1) , that is, k 1(vn) ≤ k 1(1)The virtual test iteration is terminated, and the parameter sequence at the completion of the virtual iteration (i.e., the updated motion control parameters to be optimized based on the virtual motion control test) is obtained as the control parameter sequence for the next actual test.

[0132] In step S300, an actual motion control test is performed on the robot according to the motion control parameters to be optimized, and the objective function is updated according to the result of the actual motion control test.

[0133] Specifically, the actual motion control test performed on the robot according to the motion control parameters to be optimized and the updating of the objective function according to the result of the actual motion control test include:

[0134] The robot is controlled to return to the initial position.

[0135] An actual motion control test is performed on the robot according to the motion control parameters to be optimized.

[0136] A second actual test function value is determined based on the objective function and the result of the actual motion control test.

[0137] If the second actual test function value is not greater than the final objective threshold of the function, the motion control parameters to be optimized are taken as the optimized target motion control parameters, and the motion control parameter optimization process is ended.

[0138] If the second actual test function value is greater than the final objective threshold of the function, the weight values corresponding to each pre-designed calculation item in the objective function are updated according to the second actual test function value.

[0139] Specifically, the robot is returned to the initial position, the next actual motion control test is performed according to the motion control parameters to be optimized obtained after the completion of the virtual test, and the position, speed, acceleration, energy consumption, and other key data of the robot during the test are recorded by sensors and other devices. The objective function value of the actual motion control test, i.e., the second actual test function value k2, is calculated according to the actually measured data.

[0140] If k2≤k last , the actual test iteration is ended, and the motion control parameters to be optimized at this time are taken as the final optimized target motion control parameters.

[0141] Otherwise, if k2>k last , the weight coefficient values corresponding to the position error, speed error, energy consumption, state entropy, and control strategy entropy in the next virtual test are reset by comparing the actual objective function values of the previous and current actual tests.

[0142] According to the target function after updating the weight coefficient value, the actual test target function value obtained by recalculation is k 2,chg , and the final target threshold of the function is reset to k last,chg . It should be noted that k 2,chg is obtained based on the updated target function using the same data as when calculating k2 last,chg is obtained based on the updated target function using the same data as when calculating k last .

[0143] If k 2,chg ≤ k last,chg , that is, the target function value after resetting the weight of the target function is not greater than the final target threshold of the function, indicating that the target function weight resetting fails, at this time, the weight before resetting the target function and the final target threshold of the function are restored, and the next virtual motion control test is returned to perform virtual test iteration.

[0144] If k 2,chg > k last,chg , indicating that the target function weight resetting succeeds, at this time, the weight after resetting the target function and the final target threshold of the function are used, that is, the updated weight coefficient is retained, and k last = k last,chg , and the next virtual motion control test is returned to perform virtual test iteration.

[0145] Step S400, return to execute the above-mentioned step of performing at least one virtual motion control test on the robot according to the above-mentioned motion control parameter to be optimized, until the preset parameter optimization termination condition is met, and the optimized target motion control parameter is obtained, wherein the parameter optimization termination condition includes that the number of times of performing actual motion control test reaches the preset maximum actual test number.

[0146] The parameter optimization termination condition can be set and adjusted according to actual needs, and the preset maximum actual test number can also be set and adjusted according to actual needs, which is not limited here. In the embodiment of the application, the parameter optimization termination condition also includes that the second actual test function value is not greater than the final target threshold of the function.

[0147] It should be noted that when updating the weight coefficients in the target function, the update can be performed according to a pre-set update rule, and the corresponding update rule can be set and adjusted according to actual needs, which is not limited here.

[0148] The embodiment of the application also provides a specific method for updating the weight values of each item in the target function. Specifically, the evaluation of the two tests is w c c t , The contribution of each change value to the change of the objective function value, and the adjustment of each weight coefficient value according to the respective contribution size, a reset scheme is as follows.

[0149] Suppose the actual test before and after And The percentage of each change value in the change value (Δk=k1-k2) of the objective function value of the actual test before and after is δ1, δ2, δ3, δ4 and δ5 respectively. Then set the adjusted weights as follows:

[0150] After normalization, the new weight coefficient values are shown in the following formulas (5) to (9):

[0151]

[0152] At this time, the updated objective function is shown in the following formula (10):

[0153]

[0154] Wherein, there are That is, the sum of the weight coefficients is 1.

[0155] According to the objective function after updating the weight coefficient value, the actual test objective function value recalculated is k 2,chg , and the final target threshold of the function is reset to k last,chg . Because the weights of the objective function change, the final target threshold of the reset function

[0156] If k 2,chg ≤ k last,chg , the weights and the final target threshold of the function before the reset of the objective function are restored, and the next virtual motion control test is returned to perform virtual test iteration.

[0157] If k 2,chg > k last,chg , the weights and the final target threshold of the function after the reset of the objective function are used, that is, the updated weight coefficients are retained, and k last = k last,chg , the next virtual motion control test is returned to perform virtual test iteration.

[0158] From the above, the robot motion control parameter optimization method provided in the embodiments of the present application, the motion control parameters to be optimized are obtained, the robot is tested for actual motion control once according to the motion control parameters to be optimized, and a virtual test function threshold is determined based on a preset target function and a result of the actual motion control test; the robot is tested for virtual motion control at least once according to the motion control parameters to be optimized, so as to iteratively update the motion control parameters to be optimized, until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold; the robot is tested for actual motion control once according to the motion control parameters to be optimized, and the target function is updated according to a result of the actual motion control test; the step of testing the robot for virtual motion control at least once according to the motion control parameters to be optimized is returned to be executed until a preset parameter optimization termination condition is met, and the target motion control parameters optimized are obtained, wherein the parameter optimization termination condition includes that a number of times of actual motion control test reaches a preset maximum actual test number.

[0159] Compared with the prior art, in the scheme corresponding to the robot motion control parameter optimization method provided in the embodiments of the present application, when the parameter optimization is performed, not only the actual motion control test is relied on, but also the virtual motion control test and the actual motion control test are combined to perform the parameter optimization. In this way, the virtual motion control test is introduced to optimize the motion control parameters to be optimized, which can reduce the dependence on the actual motion control test, thereby being beneficial to reduce the test workload, reduce resource consumption, and be beneficial to improve the parameter optimization efficiency.

[0160] In the embodiments of the present application, the robot motion control parameter optimization method is also described in detail based on a specific application scenario. Figure 2 is a specific flowchart of a robot motion control parameter optimization method provided in the embodiments of the present application. As shown in Figure 2 In the embodiments of the present application, step S1 is first executed, that is, an initial actual test is performed. Step S1 includes sub-step S11, specifically, the first actual test is performed using a preset control parameter sequence (that is, the initial motion control parameters to be optimized), and robot motion related data is collected.

[0161] Further, step S2 is executed, that is, the target function is constructed. Specifically, it includes: sub-step S21, defining an input parameter sequence, a time step and each weight coefficient; sub-step S22, calculating a position error, a speed error, an energy consumption, a state entropy and a control strategy entropy; sub-step S23, setting a target function threshold k last(i.e. function final target threshold), and calculate the target function value k1 (i.e. first actual test function value) at this time according to the measured data. It should be noted that the above target function can be constructed in real time, or can be constructed in advance, which is not specifically limited here.

[0162] Further, step S3 is executed, i.e. virtual test iteration is performed. Specifically, it includes: sub-step S31, generating virtual test parameters (i.e. virtual test control parameters), and defining a virtual test phase threshold k 1(1) (i.e. virtual test function threshold); sub-step S32, calculating the virtual target function value (i.e. virtual test function value at virtual test time) k 1(v1) , k 1(v2) , … k 1(vn) , and ensuring that it decreases with iteration; sub-step S33, repeating the virtual iteration test until k 1(vn) ≤ k 1(1) .

[0163] Further, step S4 is executed, i.e. actual test iteration is performed. Specifically, it includes: sub-step S41, controlling the robot to perform actual movement according to the parameters determined by the virtual iteration test iteration; sub-step S42, recording key data and calculating the target function value k2 (i.e. second actual test function value) at this time; sub-step S43, if k2≤ k last , the actual test iteration is ended, and the motion control parameters to be optimized at this time are taken as the final optimized target motion control parameters; sub-step S44, if k2> k last , reset the weight coefficients in the target function, and according to the updated weight coefficient value after the target function, the actual test target function value obtained by re-calculation is k 2,chg , and the following determination is made: S441, if k 2,chg ≤ k last , the target function weight resetting fails, the weights of each item of the target function before resetting are restored, and step S5 is executed; S442, if k 2,chg > k last , it indicates that the target function weight resetting is successful, and step S5 is executed. It should be noted that the above determination process can also compare k 2,chg with the updated target threshold k last,chg determined based on the reset target function, which is not specifically limited here.

[0164] Specifically, step S5 is to continue iteration, i.e. return to perform steps S3-S4 again until the maximum actual test iteration number is reached.

[0165] Therefore, the method provided by the embodiment of the application can be applied to the field of robot motion control testing, and the motion control parameters or strategies of a robot (especially a humanoid robot) are optimized through virtual and real testing data combination to achieve better control effect. Specifically, the robot motion control testing is performed by using the virtual and real combination testing method, the control strategy / parameters are iteratively optimized by using the virtual motion control testing method between every two actual motion control tests of the robot, and the weights of the errors of the robot reaching the target pose, the errors of the robot reaching the target speed, the energy consumption of reaching the target pose, the state entropy of reaching the target pose and the control strategy entropy of reaching the target pose in the virtual motion control strategy objective function can be dynamically adjusted according to the evaluation of the previous motion control test, so as to adjust the control strategy / parameters of each robot motion control, thereby realizing the iterative optimization of the actual motion control test of the robot, and enabling the robot to finally achieve better motion control effect. The method can reduce the workload of the actual motion control test of the robot, improve the testing efficiency, and further improve the parameter optimization efficiency.

[0166] Specifically, the virtual and real combination testing method is provided in the embodiment of the application, the actual motion test and the virtual motion test of the robot are combined, the iterative optimization is performed through the virtual test, the dependence on the actual motion test is reduced, and thus the testing workload is reduced and the testing efficiency is improved. Specifically, the virtual motion test iteration is inserted between the actual motion tests to reduce the dependence on the actual motion test.

[0167] In the embodiment of the application, the weights of the objective function are also dynamically adjusted, the weight coefficients of the position error, the speed error, the energy consumption, the state entropy and the control strategy entropy in the objective function are dynamically adjusted according to the evaluation result of the previous motion control test, the objective function is more in line with the current control target, and thus the iterative optimization process of the virtual test and the actual test is more effectively guided.

[0168] Further, the virtual test control parameter generation manner is also provided in the embodiment of the application, a method for generating virtual test control parameters based on rules is proposed, the virtual test control parameters are ensured to be within a reasonable range and gradually approach the optimal control parameters.

[0169] Meanwhile, in the embodiment of the application, the objective function is constructed by comprehensively considering the position error, the speed error, the energy consumption, the state entropy and the control strategy entropy and the like, and the performance of the motion control strategy can be more comprehensively evaluated. In addition, a scheme for resetting the weights of the objective function based on the analysis of the change of the actual objective function value of the previous and current actual tests is proposed, the objective function is more in line with the current control target, and thus the optimization efficiency is improved.

[0170] For example, the virtual test control parameter generation manner is based on the rule that the virtual test control parameter is generated by using the previous motion control test result and the current motion control test result. Figure 3Corresponding to the robot motion control parameter optimization method described above, the embodiment of the application further provides a robot motion control parameter optimization system, the robot motion control parameter optimization system comprises:

[0171] The first actual test module 310 is configured to obtain the to-be-optimized motion control parameter, perform an actual motion control test on the robot according to the to-be-optimized motion control parameter, and determine a virtual test function threshold based on a preset target function and a result of the actual motion control test;

[0172] The virtual test module 320 is configured to perform at least one virtual motion control test on the robot according to the to-be-optimized motion control parameter, to iteratively update the to-be-optimized motion control parameter, until a virtual test function value determined according to a result of the virtual motion control test and the target function is not greater than the virtual test function threshold;

[0173] The second actual test module 330 is configured to perform an actual motion control test on the robot according to the to-be-optimized motion control parameter, and update the target function according to a result of the actual motion control test;

[0174] The iteration control module 340 is configured to return to perform the at least one virtual motion control test on the robot according to the to-be-optimized motion control parameter until a preset parameter optimization termination condition is met, to obtain an optimized target motion control parameter, wherein the parameter optimization termination condition comprises that a number of times of performing the actual motion control test reaches a preset maximum actual test number.

[0175] In this way, the scheme corresponding to the robot motion control parameter optimization method provided by the embodiment of the application does not only rely on the actual motion control test when performing parameter optimization, but combines the virtual motion control test and the actual motion control test to perform parameter optimization. In this way, the introduction of the virtual motion control test to optimize the to-be-optimized motion control parameter can reduce the dependence on the actual motion control test, thereby being beneficial to reducing the test workload, reducing resource consumption, and being beneficial to improving the parameter optimization efficiency.

[0176] It should be noted that the specific structure and implementation manner of the robot motion control parameter optimization system and each module or unit thereof can refer to the corresponding description in the above method embodiment, which will not be described here again.

[0177] It should be noted that the division manner of each module of the robot motion control parameter optimization system is not unique, and is not specifically limited here.

[0178] Based on the above embodiment, the application further provides an intelligent terminal, and a principle block diagram thereof can be as shown in Figure 4The intelligent terminal shown in the figure includes a processor, a memory, a network interface and a display screen connected through a system bus. The processor of the intelligent terminal is configured to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a robot motion control parameter optimization program. The internal memory provides an environment for the operating system and the robot motion control parameter optimization program in the non-volatile storage medium. The network interface of the intelligent terminal is configured to communicate with an external terminal through a network connection. The robot motion control parameter optimization program, when executed by the processor, implements the steps of any one of the robot motion control parameter optimization methods described above. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen.

[0179] Those skilled in the art can understand that, Figure 4 The block diagram shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the intelligent terminal to which the scheme of the present application is applied. The specific intelligent terminal can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0180] In one embodiment, an intelligent terminal is provided, which includes a memory, a processor and a robot motion control parameter optimization program stored in the memory and executable on the processor. The robot motion control parameter optimization program, when executed by the processor, implements the steps of any one of the robot motion control parameter optimization methods provided by the embodiments of the present application.

[0181] The embodiments of the present application also provide a computer readable storage medium, which stores a robot motion control parameter optimization program. The robot motion control parameter optimization program, when executed by a processor, implements the steps of any one of the robot motion control parameter optimization methods provided by the embodiments of the present application.

[0182] It should be understood that the sequence of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0183] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example for description, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for convenient distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the apparatus can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0184] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0185] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or in combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different ways to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0186] In the embodiments provided in the present application, it should be understood that the disclosed system / terminal device and method can be implemented in other ways. For example, the above-described system / terminal device embodiments are only schematic, for example, the division of the above modules or units is only a logical function division, and actual implementation can be in another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0187] The above integrated modules / units, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above embodiment methods can also be completed by a computer program instructing related hardware, and the above computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the above computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, electrical signal, and software distribution medium, etc. It should be noted that the content contained in the above computer readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0188] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for optimizing robot motion control parameters, characterized in that, The method includes: Obtain motion control parameters to be optimized, perform an actual motion control test on the robot based on the motion control parameters to be optimized, and determine the threshold of the virtual test function based on the preset objective function and the result of the actual motion control test. The robot is subjected to at least one virtual motion control test based on the motion control parameters to be optimized, so as to iteratively update the motion control parameters to be optimized until the virtual test function value determined based on the results of the virtual motion control test and the objective function is not greater than the virtual test function threshold. The robot is subjected to an actual motion control test based on the motion control parameters to be optimized, and the objective function is updated based on the results of the actual motion control test. Return to the step of performing at least one virtual motion control test on the robot based on the motion control parameters to be optimized, until the preset parameter optimization termination condition is met, and obtain the optimized target motion control parameters. The parameter optimization termination condition includes the number of actual motion control tests performed reaching the preset maximum number of actual tests.

2. The method for optimizing robot motion control parameters according to claim 1, characterized in that, The process of acquiring motion control parameters to be optimized, performing an actual motion control test on the robot based on the motion control parameters to be optimized, and determining a virtual test function threshold based on a preset objective function and the results of the actual motion control test includes: Obtain the motion control parameters to be optimized, wherein the motion control parameters to be optimized include at least one of motor torque, PID controller gain and joint angle; A practical motion control test is conducted on the robot based on the motion control parameters to be optimized. The value of the first actual test function is determined based on the objective function and the results of the actual motion control test. The final target threshold of the function is determined based on the first actual test function value, wherein the final target threshold of the function is less than the first actual test function value; A virtual test function threshold is determined based on the first actual test function value and the final target threshold of the function, wherein the virtual test function threshold is not greater than the first actual test function value and not less than the final target threshold of the function.

3. The method for optimizing robot motion control parameters according to claim 2, characterized in that, Determining the first actual test function value based on the objective function and the results of the actual motion control test includes: Collect the actual state parameters of the robot during actual motion control testing; Obtain the desired state parameters corresponding to the motion control parameters to be optimized; The first actual test function value is obtained by calculating the objective function based on the actual state parameters and the expected state parameters.

4. The method for optimizing robot motion control parameters according to claim 2, characterized in that, The step of performing at least one virtual motion control test on the robot based on the motion control parameters to be optimized, to iteratively update the motion control parameters to be optimized, until the virtual test function value determined based on the results of the virtual motion control test and the objective function is not greater than the virtual test function threshold, includes: Obtain the rules for generating virtual control parameters; Virtual test control parameters are generated based on the virtual control parameter generation rules and the motion control parameters to be optimized. A virtual motion control test is performed based on the virtual test control parameters, and the value of the virtual test function is determined based on the objective function and the results of the virtual motion control test. Update the motion control parameters to be optimized according to the virtual test control parameters, and return to the step of generating virtual test control parameters according to the virtual control parameter generation rules and the motion control parameters to be optimized, until the virtual test function value is not greater than the virtual test function threshold.

5. The method for optimizing robot motion control parameters according to claim 4, characterized in that, The method further includes: When performing each virtual motion control test, if the virtual test function value corresponding to the virtual motion control test is not less than the first actual test function value, the virtual control parameter generation rule is updated, a new virtual test control parameter is generated according to the updated virtual control parameter generation rule, and the virtual motion control test is re-executed based on the new virtual test control parameter until the virtual test function value corresponding to the virtual motion control test is less than the first actual test function value.

6. The method for optimizing robot motion control parameters according to claim 2, characterized in that, The objective function includes multiple pre-defined computational terms that are weighted and summed. The preset calculation items include position error item, velocity error item, energy consumption item, state entropy item, and control strategy entropy item; The position error term is used to characterize the difference between the robot's actual position and its desired position; The speed error term is used to characterize the difference between the robot's actual speed and its expected speed; The energy consumption term is used to characterize the energy consumed by the robot in performing the motion; The state entropy term is used to characterize the degree of state disorder of the robot; The control strategy entropy term is used to characterize the diversity of the robot's control strategies.

7. The method for optimizing robot motion control parameters according to claim 6, characterized in that, The step of performing an actual motion control test on the robot based on the motion control parameters to be optimized, and updating the objective function based on the results of the actual motion control test, includes: Control the robot to return to its initial position; A practical motion control test is performed on the robot based on the motion control parameters to be optimized. The value of the second actual test function is determined based on the objective function and the results of the actual motion control test. If the second actual test function value is not greater than the final target threshold of the function, then the motion control parameter to be optimized is taken as the target motion control parameter after optimization, and the motion control parameter optimization process ends. If the second actual test function value is greater than the final target threshold of the function, then the weight values ​​corresponding to each preset calculation item in the target function are updated according to the second actual test function value.

8. A robot motion control parameter optimization system, characterized in that, The system includes: The first actual test module is used to acquire motion control parameters to be optimized, perform an actual motion control test on the robot based on the motion control parameters to be optimized, and determine the virtual test function threshold based on the preset objective function and the result of the actual motion control test. The virtual testing module is used to perform at least one virtual motion control test on the robot based on the motion control parameters to be optimized, so as to iteratively update the motion control parameters to be optimized until the virtual test function value determined based on the results of the virtual motion control test and the objective function is not greater than the virtual test function threshold. The second actual test module is used to perform an actual motion control test on the robot based on the motion control parameters to be optimized, and to update the objective function based on the result of the actual motion control test. The iterative control module is used to return to the step of performing at least one virtual motion control test on the robot based on the motion control parameters to be optimized, until a preset parameter optimization termination condition is met, and the optimized target motion control parameters are obtained. The parameter optimization termination condition includes the number of actual motion control tests performed reaching a preset maximum number of actual tests.

9. A smart terminal, characterized in that, The intelligent terminal includes a memory, a processor, and a robot motion control parameter optimization program stored in the memory and executable on the processor. When the robot motion control parameter optimization program is executed by the processor, it implements the steps of the robot motion control parameter optimization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a robot motion control parameter optimization program, which, when executed by a processor, implements the steps of the robot motion control parameter optimization method as described in any one of claims 1 to 7.

Images