Three-axis robot control method and device

Abstract

The invention provides a three-axis robot control method and device, and belongs to the technical field of robot control, and the method comprises the steps: carrying out the recognition of a plurality of first objects based on a target recognition algorithm, and obtaining a target object; controlling the three-axis robot to perform sight tracking on the target object based on the tracking algorithm, wherein the sight tracking is tracking of the target object by a built-in camera of the three-axis robot; and controlling the three-axis robot to perform motion tracking on the target object based on a path planning algorithm, wherein the motion tracking is the tracking of the target object by the movement of the three-axis robot. According to the three-axis robot control method and device, the accuracy and reliability of target tracking can be improved, and then the accuracy and reliability of robot control are improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of robot control technology, and more specifically, to a three-axis robot control method and device. Background Art

[0002] In the field of modern automated control and monitoring, target recognition and tracking technologies are crucial, and three-axis robots are responsible for identifying and tracking target objects in many scenarios, such as automatic recognition three-axis robots that accurately lock onto drone targets, and three-axis robots carried by high-altitude drones that automatically identify and track ground targets.

[0003] Due to the interference of the external environment, the traditional target tracking method has low tracking accuracy and reliability, and thus cannot control the three-axis robot to effectively track the target. Therefore, a stable and reliable three-axis robot control method is urgently needed. Summary of the invention

[0004] The purpose of the present disclosure is to provide a three-axis robot control method and device to improve the accuracy and reliability of target tracking, thereby improving the accuracy and reliability of robot control.

[0005] A first aspect of the embodiments of the present disclosure provides a three-axis robot control method, comprising: Identify the plurality of first objects based on a target recognition algorithm to obtain a target object; Based on the tracking algorithm, the three-axis robot is controlled to track the target object by sight. The sight tracking is the tracking of the target object by the built-in camera of the three-axis robot. Based on the path planning algorithm, the three-axis robot is controlled to track the target object. The motion tracking is the tracking of the target object by the movement of the three-axis robot.

[0006] A second aspect of the embodiments of the present disclosure provides a three-axis robot control device, comprising: A target recognition module, used to identify a plurality of first objects based on a target recognition algorithm to obtain a target object; The sight tracking module is used to control the three-axis robot to track the target object based on the tracking algorithm. The sight tracking is the tracking of the target object by the built-in camera of the three-axis robot; The motion tracking module is used to control the three-axis robot to track the target object based on the path planning algorithm. The motion tracking is the tracking of the target object by the movement of the three-axis robot.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned three-axis robot control method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned three-axis robot control method are implemented.

[0009] The beneficial effects of the three-axis robot control method and device provided by the embodiments of the present disclosure are: The present disclosure can quickly identify the target object from multiple first objects through the target recognition algorithm, and combined with the tracking algorithm, the three-axis robot can track the target object in real time, ensuring that the robot can stably track the target. The present disclosure is based on the path planning algorithm. The three-axis robot can plan the optimal path from the current position to the target object position, ensuring that the robot reaches the tracking position efficiently, improving the accuracy and reliability of target tracking, and thereby improving the accuracy and reliability of robot control. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic flow chart of a three-axis robot control method provided in one embodiment of the present disclosure; Figure 2 A structural block diagram of a three-axis robot control device provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic flow chart of a three-axis robot control method provided in an embodiment of the present disclosure, the method comprising: S101: Identify a plurality of first objects based on a target recognition algorithm to obtain a target object.

[0015] In this embodiment, the target recognition algorithm can be a feature extraction algorithm, such as scale-invariant feature transformation, oriented gradient histogram and other methods, or it can be a trained support vector machine model or neural network model, etc., the purpose of which is to determine the tracked object from multiple objects.

[0016] The first object refers to an object that appears in the effective detection area of ​​the robot, and the target object is a preset object that needs to be tracked. For example, our application scenario is to detect and track drones in the air from the ground. If flocks of birds, airplanes and drones appear in the effective detection area of ​​the robot, then the flocks of birds, airplanes and drones are all first objects. The images collected by the robot can be identified through a trained neural network model to determine the target object, that is, the drone.

[0017] S102: Controlling the three-axis robot to track the target object based on the tracking algorithm. The line of sight tracking is the tracking of the target object by a built-in camera of the three-axis robot.

[0018] In this embodiment, the tracking algorithm may be a particle filter algorithm. The three-axis robot has three movable axes that can move and rotate in different directions in space, thereby achieving tasks such as operation and tracking of target objects.

[0019] The target object is the object that needs to be tracked. Line of sight tracking refers to real-time tracking of the target through the rotation of the built-in camera of the three-axis robot to prevent the target from being lost and causing tracking failure. For example, when the target object is detected to appear in the right edge area of ​​the image, the camera is controlled to rotate to the right, and the same applies to other directions. The built-in camera can be a camera device installed inside or on the body of the three-axis robot to capture images or videos of the target object and provide information about the target object to the tracking algorithm.

[0020] S103: Controlling the three-axis robot to track the target object based on the path planning algorithm. The motion tracking is the tracking of the target object by the movement of the three-axis robot.

[0021] In this embodiment, the path planning algorithm can be the Dijkstra algorithm or the A-star algorithm, which calculates an optimal path from the current position of the robot to the position of the target object according to the current position of the robot, the position of the target object, and the distribution of obstacles in the surrounding environment. The control system sends control instructions to each axis of the three-axis robot based on the path planning result, adjusts the movement of the axis, and makes the robot move along the planned path.

[0022] That is, gaze tracking controls the movement of the robot's built-in camera, while motion tracking controls the movement of the robot.

[0023] From the above, it can be concluded that the present disclosure can quickly identify the target object from multiple first objects through the target recognition algorithm, and combined with the tracking algorithm, the three-axis robot can track the target object in real time, ensuring that the robot can stably track the target. The present disclosure is based on the path planning algorithm. The three-axis robot can plan the optimal path from the current position to the target object position, ensuring that the robot reaches the tracking position efficiently, improving the accuracy and reliability of target tracking, and thereby improving the accuracy and reliability of robot control.

[0024] In one embodiment of the present disclosure, the three-axis robot control method further includes: Determine the position error, velocity error and basic motion characteristics of the target object based on radar.

[0025] The tracking algorithm is a particle filter algorithm; Based on the tracking algorithm, the three-axis robot is controlled to track the target object, including: Determine the number of particles based on the underlying motion characteristics; Determine the initial weight of each particle based on the number of particles; Initialize the particle filter algorithm based on the number of particles, the initial weight of each particle, the position error and the velocity error; Determine a motion model based on basic motion features, and determine a predicted state of a target object based on the motion model and the initialized particles; Based on the predicted state, the three-axis robot is controlled to track the target object.

[0026] In this embodiment, the purpose of the radar is to perform preliminary monitoring of the target object first, so that the subsequent particle filter algorithm is more accurate and reliable. The radar can be the radar of the three-axis robot itself, or it can be not set in the three-axis robot, and the detected data is sent to the three-axis robot through relevant equipment.

[0027] Position error refers to the distance between the possible position of the target object and the predicted position, and speed error refers to the difference between the possible speed of the target and the predicted speed. For example, the application scenario is a three-axis robot locking and tracking a drone target. Since drones move fast in the air, have strong maneuverability, and complex state changes, drones can move in a larger airspace. Compared with ground targets, their position error and speed error are larger.

[0028] Basic motion features refer to some basic descriptions of the motion state of the target object, such as whether the target object is moving at a constant speed or at an accelerated speed.

[0029] The position error, speed error and basic motion characteristics of the target object can be determined in advance by preliminarily detecting the speed and speed change rate of the target object through radar. For example, they can be obtained through a preset first mapping table, such as Table 1.

[0030]

[0031] It should be noted that Table 1 is only part of the data in the first mapping table. In addition, there are other value ranges. The position error, speed error, etc. can be limited according to a wider range of speeds or range speed change rates.

[0032] In this embodiment, corresponding conditions may also be preset in advance, for example, in response to the basic moving speed of the target object being greater than the first speed threshold, the first speed error is used as the speed error, and the first position error is used as the position error; In response to the base moving speed of the target object being less than or equal to the first speed threshold, the second speed error is used as the speed error, and the second position error is used as the position error.

[0033] The basic moving speed is the moving speed of the target object obtained by detecting the target object through the radar. The position error and speed error can be determined based on this. The first speed threshold can be preset based on experience. The first speed error is greater than the second speed error, and the first position error is greater than the second position error. The first speed error, the first position error, the second speed error, and the second position error can all be determined based on actual conditions.

[0034] In this embodiment, the number of particles is determined based on the basic motion characteristics, including: in response to the basic motion characteristic being uniform motion, the number of particles is determined as the first number of particles; in response to the basic motion characteristic being non-uniform motion, the number of particles is determined as the second number of particles, and the first number of particles is less than the second number of particles. This is because if the motion of the target object is more complex and the uncertainty is large, in order to more accurately cover the possible state space of the target, more particles are required; conversely, if the motion of the target object is relatively simple and stable, the number of particles can be appropriately reduced. Therefore, when the basic motion characteristic is uniform motion, a smaller number can be set, and when the basic motion characteristic is not uniform motion, a larger number can be set. The first number of particles and the second number of particles are preset values, which can be determined by the number of particles used to solve similar problems in the art or set based on experience.

[0035] When the particle filter algorithm is initialized, an initial weight is assigned to each particle. The initial weight of each particle is equal, because the target object has not been tracked at this time. When there is no other known information, the weight of each particle should be the same, that is, the initial weight = 1 / the number of particles. For example, if the number of particles is 500, the initial weight of each particle is 1 / 500.

[0036] The initial state of the particle filter algorithm is set by comprehensively utilizing the previously determined number of particles, the initial weight of each particle, and the position error and velocity error obtained by the radar, in preparation for the subsequent use of the algorithm for target state estimation and tracking.

[0037] Determining a motion model based on basic motion features means selecting or constructing a suitable motion model based on the basic motion features of the target object previously determined by the radar. For example, in response to the basic motion feature being uniform motion, a uniform linear motion model is determined as the motion model; in response to the basic motion feature being non-uniform motion, a uniform acceleration motion model is determined as the motion model.

[0038] By using the determined motion model and the initialized particles, the state of the target object at the current moment or in the future, such as position and speed (i.e. predicted state), is predicted through calculation and reasoning of the particle filter algorithm. Based on the predicted state of the target object obtained by the particle filter algorithm, control instructions are sent to the three-axis robot so that the robot's built-in camera can always aim at the target object, realize the line of sight tracking of the target object, and prevent tracking failure.

[0039] In this embodiment, the present disclosure introduces radar to determine the position error, velocity error and basic motion characteristics of the target object, providing more accurate and comprehensive initial information for the subsequent particle filter algorithm, improving the convergence speed and tracking accuracy of the tracking algorithm, especially when the motion state of the target object is complex and changeable. The application of the particle filter algorithm, combined with the information provided by the radar, enables the three-axis robot to effectively deal with the uncertainty of the target object in a dynamic environment, enhancing the robustness of the present disclosure. This embodiment dynamically adjusts the number of particles according to the basic motion characteristics, ensures the accuracy of tracking, reduces the computational complexity, improves the accuracy and reliability of target tracking, and thus improves the accuracy and reliability of robot control.

[0040] In one embodiment of the present disclosure, the three-axis robot control method further includes: In response to controlling the three-axis robot to track the target object based on the predicted state for a time period exceeding a first time period; Determine observation noise based on noise characteristics, and determine an observation model based on the observation noise; Update the initial weight of each particle based on the observation model to obtain the first weight of each particle; In response to the first weight satisfying the resampling condition, resampling each particle to obtain a second number of particles, and determining a second predicted state of the target object based on the second number of particles and the motion model; Based on the second predicted state, the three-axis robot is controlled to track the target object.

[0041] In this embodiment, the prediction step is based on the state of the previous moment and the motion model to infer the state of the current moment. However, the motion model itself is an approximation of the actual motion, which has certain inaccuracies, and these errors will continue to accumulate over time. Relying only on the predicted state, the error may become larger and larger, causing the tracking of the target to gradually deviate from the true trajectory.

[0042] Therefore, when the time for the three-axis robot to track the target object based on the predicted state exceeds the first time length, the weight of each particle should be updated and the position should be re-predicted to better track the target object. The first time length can be determined according to the actual situation during the experiment. For example, if it is found that the target cannot be effectively tracked after 10 seconds, the first time length can be set to 10 seconds.

[0043] The noise feature refers to whether there is noise caused by the target object being blocked or direct ambient light during the tracking process.

[0044] Determining observation noise based on the noise feature, and determining an observation model based on the observation noise, including, in response to the target object being blocked and / or the ambient light being directly illuminated, determining the observation noise based on a first observation noise covariance matrix; In response to the target object being not blocked and the ambient light being not direct, the observation noise is determined based on a second observation noise covariance matrix.

[0045] The first observation noise covariance matrix can be , the second observation noise covariance matrix can be , the 50 in the observation noise covariance matrix means the noise variance for the position observation, which is set to 50 square meters in the x, y, and z directions. The purpose is to prevent tracking failure and reduce errors.

[0046] The observation model can be ,in, It is at the moment The observed value of is the observation matrix, Representative moments The state vector of the target object, is the observation noise vector, and or , Indicates time.

[0047] It is obtained through the motion model of the above part. For example, the above motion model is uniform acceleration motion, and its motion model is ,in Representative moments The state vector of the target object, Representative moments The state vector of the target object, It's time The velocity vector, is the acceleration vector, is the time interval. The above motion model calculates its The state at the moment can include the position and speed information of the target object, which can be expressed as , that is, the position coordinates and speed information in three directions.

[0048] The element values ​​of the observation matrix depend on the specific observation method and physical model. In this application, it can be , can also be set based on experience and reference matrices when solving similar problems.

[0049] Then the observed values ​​can be Calculate the importance weight of each particle. The weight is calculated based on the likelihood of the observation value in the state of the particle, that is, update the initial weight of each particle based on the observation model to obtain the first weight of each particle, including: Determine the observation likelihood of each particle based on the observation model; The time decay factor is introduced into the weight update formula to obtain the first weight update formula; The initial weight of each particle is updated based on the observation likelihood of each particle and the first weight update formula to obtain the first weight of each particle.

[0050] Specifically, the weight is calculated based on the likelihood probability of the observation value in the particle state, that is, ,in , Indicates Particles at time The state vector of the target object, It is Particles at time The velocity vector, It is Particles at time The acceleration vector, It is at the moment Observed value of .

[0051] The weight update formula can be ,in, is the observation dimension, which is 2 in this application.

[0052] in, , represents transpose, the denominator is a normalization constant used to ensure that the integral of the probability density function over the entire observation space is equal to 1. The exponential part in the numerator Reflects the observed value Based on the particle prediction state The degree of difference between is the residual vector between the observed and predicted observations, The residuals are weighted, and the inverse of the covariance matrix makes the residuals have a relatively small impact in the direction with more noise, and a relatively large impact in the direction with less noise. In general, the larger the value of this exponential term, the closer the observed value is to the predicted state of the particle, and the higher the particle weight. Through this calculation method, the particle filter algorithm can update the particle weights according to the observed data, and then filter out particles that are more in line with the actual state of the target.

[0053] In this embodiment, the time decay factor is also taken into account. The state of the target object changes over time. For example, when tracking a moving target object, its motion mode, speed, direction, etc. may change. The ability of observation data and particle weights at earlier times to describe the target state at the current moment will gradually weaken. The introduction of the time decay factor can allow the algorithm to pay more attention to recent observations and state information, so that the weight update can better adapt to the dynamic changes of the target state and improve the tracking accuracy and adaptability of the target. For example, if the target object originally moves in a uniform straight line and suddenly starts to turn, the time decay factor can allow the algorithm to adjust the particle weights more quickly according to the new observations without relying too much on the weight information during the previous uniform motion.

[0054] The weight update formula after the introduction of the time decay factor is the first weight update formula, which can be , Indicates Particles at time The weight value after the introduction of the time decay factor is also the first weight. represents the time decay factor, which can be determined based on experience or experimental process data. The initial weight of each particle can be updated according to the first weight update formula and the observation likelihood of each particle to obtain the first weight of each particle.

[0055] It should be noted that the first weight should be normalized to prevent the sum of the first weights from being different from 1. After the above description, the first weight of each particle can be obtained. When the first weight meets the resampling condition, resampling is performed. Whether the resampling condition is met can be judged by the following method: The effective number of particles is determined based on the first weight of each particle.

[0056] In response to the effective particle number being less than the effective value, the first weight satisfies the resampling condition.

[0057] In response to the effective particle number being greater than or equal to the effective value, the first weight does not satisfy the resampling condition.

[0058] The effective number of particles can be determined according to the effective particle number calculation formula. For example, the effective particle number calculation formula is: , the effective value can be determined according to the actual scenario.

[0059] It can be concluded from the above that the present disclosure can more accurately describe the observation process of the target object and reduce the tracking deviation caused by observation error by introducing an observation model and dynamically determining the observation noise according to the noise characteristics. This embodiment considers the time decay factor in the weight update mechanism, so that the present disclosure can pay more attention to recent observation data, improve the adaptability to the dynamic changes of the target object state, thereby improving the tracking accuracy and stability, and further improving the accuracy and reliability of robot control. This embodiment sets a threshold for the number of effective particles, and triggers resampling only when the weight distribution is extremely uneven, thereby avoiding unnecessary computational overhead and improving the efficiency of the present disclosure.

[0060] In one embodiment of the present disclosure, the three-axis robot control method further includes: In response to a rate of change of a first number of consecutive second predicted states being less than a first rate of change, increasing a time decay factor based on a first time step; In response to the rate of change of the second predicted states for the consecutive first number being greater than the second rate of change, the time decay factor is decreased based on the second time step.

[0061] In this embodiment, when the change rate of the second predicted state of the first number of consecutive times is less than the first change rate, it indicates that the state of the target object changes slowly and stably. At this time, the time decay factor is increased based on the first time step. Increasing the time decay factor will increase the proportion of historical weights in the current weight calculation, because the current target state is relatively stable and historical information has a high reference value, which allows the algorithm to track the target state more smoothly and reduce the sharp fluctuations in weights caused by single observation errors.

[0062] If the change rate of the second predicted state of the first number of consecutive times is greater than the second change rate, it indicates that the state of the target object changes rapidly. At this time, the time decay factor is reduced based on the second time step. Reducing the time decay factor will attenuate the influence of the historical weight, pay more attention to the current observation data, track the sudden change of the target state more quickly, and adjust the estimation of the state of the target object in time. The first change rate and the second change rate are empirical preset values.

[0063] The change rate of the second predicted state can be determined by the similarity of the second predicted state in two consecutive frames, for example, it can be calculated by cosine similarity, etc. The higher the similarity, the lower the change rate. The first time step and the second time step can be determined based on the difference in the change rate, for example, the first time step , the second time step ,in, are the initial values ​​of the first time step and the second time step, are the linear coefficients used to adjust the first time step and the second time step, respectively, which can be determined according to experiments. is the actual rate of change, is the first rate of change, is the second rate of change.

[0064] From the above, it can be concluded that the present invention dynamically adjusts the time attenuation factor so that the present invention can adjust the degree of dependence on historical information and current observation data according to the speed of change of the state of the target object, thereby enabling the three-axis robot to maintain stable tracking performance when facing target objects with different dynamic characteristics, thereby improving the adaptability and robustness of tracking.

[0065] In one embodiment of the present disclosure, determining a predicted state of a target object based on a motion model and initialized particles includes: Determine a noise-free predicted state of a target object based on a motion model; In response to the environmental characteristic satisfying the first environmental condition, taking the noise-free prediction state as the prediction state; In response to the environmental feature not satisfying a first environmental condition, Gaussian noise is determined based on the environmental feature, and a predicted state is determined based on the Gaussian noise and a noise-free predicted state; the first environmental condition includes an environmental wind speed being less than a first wind speed.

[0066] In this embodiment, the uncertainty of the object's motion is considered during the prediction process, such as the influence of factors such as wind direction and airflow on the target's motion. This uncertainty can be simulated by adding random noise to the particles, such as adding Gaussian noise to the velocity component. When the wind speed is less than the first wind speed, it is considered that the impact on the target object is small, and the addition of noise is not considered at this time. When the wind speed is greater than or equal to the first wind speed, it is considered that the impact on the target object is large, and Gaussian noise should be added at this time.

[0067] Specifically, Gaussian noise can be added to the velocity component ,Right now ,in , is the covariance matrix of the process noise.

[0068] Environmental characteristics include wind speed. The greater the wind speed, the larger the range of the corresponding Gaussian noise, that is, the covariance matrix of the process noise The larger the value in , a mapping table can be pre-set to determine the value in the covariance matrix of the process noise according to the wind speed. For example, the covariance matrix of the process noise corresponding to the wind speed of 5 meters per second is:

[0069] In the matrix, “100” represents the noise variance of the position component, and “50” represents the noise variance of the velocity component in the x, y, and z directions.

[0070] From the above, it can be concluded that the present invention can more accurately predict the future state of the target object by considering the impact of ambient wind speed on the movement of the target object and dynamically adjusting the prediction model according to the wind speed (whether to add Gaussian noise and its size), thereby improving the accuracy and reliability of target tracking, and thus improving the accuracy and reliability of robot control.

[0071] Corresponding to the three-axis robot control method of the above embodiment, Figure 2 This is a structural block diagram of a three-axis robot control device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 , the three-axis robot control device 20 includes: a target recognition module 21, a sight tracking module 22 and a motion tracking module 23; The target recognition module 21 is used to recognize a plurality of first objects based on a target recognition algorithm to obtain a target object; The sight tracking module 22 is used to control the three-axis robot to track the target object based on the tracking algorithm. The sight tracking is the tracking of the target object by the built-in camera of the three-axis robot; The motion tracking module 23 is used to control the three-axis robot to perform motion tracking on the target object based on the path planning algorithm. The motion tracking is the tracking of the target object by the movement of the three-axis robot.

[0072] In one embodiment of the present disclosure, the three-axis robot control device 20 further includes: a radar processing module, which is used to determine the position error, speed error and basic motion characteristics of the target object based on radar.

[0073] In one embodiment of the present disclosure, the tracking algorithm is a particle filter algorithm; The sight tracking module 22 is specifically used to determine the number of particles based on the basic motion characteristics; Determine the initial weight of each particle based on the number of particles; Initialize the particle filter algorithm based on the number of particles, the initial weight of each particle, the position error and the velocity error; Determine a motion model based on basic motion features, and determine a predicted state of a target object based on the motion model and the initialized particles; Based on the predicted state, the three-axis robot is controlled to track the target object.

[0074] In one embodiment of the present disclosure, the three-axis robot control device 20 further includes: a weight updating module for controlling the three-axis robot to track the target object based on the predicted state for a time period exceeding a first duration; Determine observation noise based on noise characteristics, and determine an observation model based on the observation noise; Update the initial weight of each particle based on the observation model to obtain the first weight of each particle; In response to the first weight satisfying the resampling condition, resampling each particle to obtain a second number of particles, and determining a second predicted state of the target object based on the second number of particles and the motion model; Based on the second predicted state, the three-axis robot is controlled to track the target object.

[0075] In one embodiment of the present disclosure, the weight updating module is specifically used to determine the observation likelihood of each particle based on the observation model; The time decay factor is introduced into the weight update formula to obtain the first weight update formula; The initial weight of each particle is updated based on the observation likelihood of each particle and the first weight update formula to obtain the first weight of each particle.

[0076] In one embodiment of the present disclosure, the three-axis robot control device 20 further includes: a time decay adjustment module for increasing a time decay factor based on a first time step in response to a change rate of a first number of consecutive second predicted states being less than a first change rate; In response to the rate of change of the second predicted states for the consecutive first number being greater than the second rate of change, the time decay factor is decreased based on the second time step.

[0077] In one embodiment of the present disclosure, the gaze tracking module 22 is further configured to determine a noise-free predicted state of the target object based on the motion model; In response to the environmental characteristic satisfying the first environmental condition, taking the noise-free prediction state as the prediction state; In response to the environmental feature not satisfying a first environmental condition, Gaussian noise is determined based on the environmental feature, and a predicted state is determined based on the Gaussian noise and a noise-free predicted state; the first environmental condition includes an environmental wind speed being less than a first wind speed.

[0078] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2The functions of modules 21 to 23 are shown.

[0079] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0080] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0081] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0082] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the three-axis robot control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0083] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0084] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0089] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0090] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A three-axis robot control method, characterized in that: include: Identify the plurality of first objects based on a target recognition algorithm to obtain a target object; Controlling the three-axis robot to track the target object based on a tracking algorithm, wherein the line of sight tracking is tracking the target object by a built-in camera of the three-axis robot; The three-axis robot is controlled based on a path planning algorithm to perform motion tracking on the target object, and the motion tracking is the tracking of the target object by the movement of the three-axis robot.

2. The three-axis robot control method according to claim 1, characterized in that: Also includes: The position error, velocity error and basic motion characteristics of the target object are determined based on radar.

3. The three-axis robot control method according to claim 2, characterized in that: The tracking algorithm is a particle filter algorithm; The controlling the three-axis robot to track the target object based on the tracking algorithm includes: determining the number of particles based on the basic motion characteristics; Determine the initial weight of each particle based on the number of particles; Initializing the particle filter algorithm based on the number of particles, the initial weight of each particle, the position error and the velocity error; Determining a motion model based on the basic motion features, and determining a predicted state of the target object based on the motion model and the initialized particles; Based on the predicted state, a three-axis robot is controlled to track the target object.

4. The three-axis robot control method according to claim 3, characterized in that: Also includes: In response to controlling the three-axis robot to perform line of sight tracking on the target object for a time period exceeding a first duration based on the predicted state; Determine observation noise based on the noise characteristics, and determine an observation model based on the observation noise; Updating the initial weight of each particle based on the observation model to obtain a first weight of each particle; In response to the first weight satisfying a resampling condition, resampling each particle to obtain a second number of particles, and determining a second predicted state of the target object based on the second number of particles and the motion model; Based on the second predicted state, the three-axis robot is controlled to track the target object.

5. The three-axis robot control method according to claim 4, characterized in that: The updating of the initial weight of each particle based on the observation model to obtain a first weight of each particle includes: determining an observation likelihood for each particle based on the observation model; The time decay factor is introduced into the weight update formula to obtain the first weight update formula; The initial weight of each particle is updated based on the observation likelihood of each particle and a first weight update formula to obtain a first weight of each particle.

6. The three-axis robot control method according to claim 5, characterized in that: Also includes: In response to a rate of change of a first number of consecutive second predicted states being less than a first rate of change, increasing the time decay factor based on a first time step; In response to a rate of change of a first number of consecutive second predicted states being greater than a second rate of change, the time decay factor is decreased based on a second time step.

7. The three-axis robot control method according to claim 3, characterized in that: The step of determining the predicted state of the target object based on the motion model and the initialized particles includes: Determining a noise-free predicted state of the target object based on the motion model; In response to the environmental characteristic satisfying a first environmental condition, taking the noise-free predicted state as the predicted state; In response to the environmental characteristics not satisfying a first environmental condition, Gaussian noise is determined based on the environmental characteristics, and the predicted state is determined based on the Gaussian noise and the noise-free predicted state; the first environmental condition includes that the environmental wind speed is less than a first wind speed.

8. A three-axis robot control device, characterized in that: include: A target recognition module, used to identify a plurality of first objects based on a target recognition algorithm to obtain a target object; A sight tracking module, used for controlling the three-axis robot to track the target object based on a tracking algorithm, wherein the sight tracking is the tracking of the target object by a built-in camera of the three-axis robot; The motion tracking module is used to control the three-axis robot to perform motion tracking on the target object based on a path planning algorithm, wherein the motion tracking is the tracking of the target object by the movement of the three-axis robot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images