Operation trajectory control method and apparatus, device, and storage medium

Abstract

An operation trajectory control method and apparatus (800), a device (900), and a storage medium, relating to the field of engineering machinery. The method comprises: previewing a target trajectory at a first trajectory point to determine a second trajectory point, wherein the target trajectory is a trajectory planned in advance for a superstructure working device of working machinery; acquiring a plurality of third trajectory points, wherein the plurality of third trajectory points comprises the second trajectory point and at least one trajectory point following the second trajectory point; and inputting the plurality of third trajectory points into a preset computation model to obtain a target control quantity for moving from the first trajectory point to the second trajectory point, wherein the computation model is used for determining a plurality of control quantities respectively corresponding to the plurality of third trajectory points, predicting, on the basis of the plurality of control quantities, a plurality of fourth trajectory points respectively corresponding to the plurality of third trajectory points, constructing an objective function with respect to the plurality of control quantities on the basis of the plurality of third trajectory points and the plurality of fourth trajectory points, and solving the objective function to obtain the target control quantity; and using the target control quantity to control operation of the superstructure working device.

Description

A control method, device and equipment of a running track and a storage medium

[0001] Cross-reference to Related Applications

[0002] This application claims the benefit of Chinese Patent Application No. 202411251048.X, filed September 6, 2024, the contents of which are incorporated by reference herein. TECHNICAL FIELD

[0003] The present application relates to the field of engineering machinery, and in particular to a control method, device, equipment and storage medium of a running track. BACKGROUND

[0004] In working machines such as tower cranes, truck cranes, aerial work platforms, etc., there is often a need for running track control of the working device. For example, in the on-load scene of an unmanned tower crane, it is one of the key technologies to realize automatic hoisting by precisely controlling the running track of the hook of the tower crane through the power system of the tower crane so that the hook reaches the destination position at the correct time. Currently, the track control of the hook generally adopts a Proportion Integral Differential (PID) control method, which is easy to implement in engineering, but since the tower crane working scene has a large hysteresis phenomenon, and the track control belongs to a multiple-input multiple-output system, while the PID control is a linear control technology, it is difficult to apply to the track control system of the tower crane. SUMMARY

[0005] The present application provides a control method, device, equipment and storage medium of a running track, which is used to solve the position deviation and time deviation problems caused by the hysteresis phenomenon in the on-load scene of the working machine.

[0006] To achieve the above object, a first aspect of the present application provides a control method of a running track, comprising: determining a second track point by previewing a target track at a first track point; wherein the target track is a track planned in advance for an upper working device of a working machine, and the first track point and the second track point are two different track points in the target track; obtaining a plurality of third track points in the target track, the plurality of third track points including the second track point and at least one track point after the second track point; inputting the plurality of third track points into a preset calculation model to obtain a target control amount of the upper working device from the first track point to the second track point; wherein the calculation model is used to determine a plurality of control amounts corresponding to the plurality of third track points respectively, predict a plurality of fourth track points corresponding to the plurality of third track points respectively based on the plurality of control amounts, construct a target function about the plurality of control amounts based on the plurality of third track points and the plurality of fourth track points, and obtain the target control amount by solving the target function; and controlling the upper working device to run by using the target control amount.

[0007] A second aspect of the present application provides a control device of a running track, the device being a working machine or being applied to the working machine, the device comprising:

[0008] a processing unit configured to determine a second track point by previewing a target track at a first track point; wherein the target track is a track planned in advance for an upper working device of a working machine, and the first track point and the second track point are two different track points in the target track;

[0009] an obtaining unit configured to obtain a plurality of third track points in the target track, the plurality of third track points including the second track point and at least one track point after the second track point;

[0010] the processing unit is further configured to input the plurality of third track points into a preset calculation model to obtain a target control amount of the upper working device from the first track point to the second track point; wherein the calculation model is used to determine a plurality of control amounts corresponding to the plurality of third track points respectively, predict a plurality of fourth track points corresponding to the plurality of third track points respectively based on the plurality of control amounts, construct a target function about the plurality of control amounts based on the plurality of third track points and the plurality of fourth track points, and obtain the target control amount by solving the target function;

[0011] the processing unit is further configured to control the upper working device to run by using the target control amount.

[0012] A third aspect of the present application provides an electronic device, comprising:

[0013] a memory for storing program instructions;

[0014] a processor for invoking the program instructions stored in the memory to perform the steps included in the method according to any one of the first aspect.

[0015] A fourth aspect of the present application provides a computer readable storage medium storing a computer program, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the method according to any one of the first aspect.

[0016] A fifth aspect of the present application provides a computer program product comprising computer program code which, when executed on a computer, causes the computer to perform the method according to any one of the first aspect.

[0017] The present application selects a tracking trajectory point by pre-lookahead, determines an optimal control amount for reaching the tracking trajectory point by using an iterative optimization calculation model, and controls the upper attachment device such as a hook to move from a current trajectory point to the tracking trajectory point by using the optimal control amount, so as to minimize the position deviation after reaching. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application, and do not limit the present application in any manner.

[0019] FIG. 1 is a structural schematic diagram of a tower crane according to an embodiment;

[0020] FIG. 2 is a flowchart of a control method of a running trajectory according to an embodiment of the present application;

[0021] FIG. 3 is a schematic diagram of a pre-lookahead process according to an embodiment of the present application;

[0022] FIG. 4 is a schematic diagram of an implementation process of a genetic optimization algorithm according to an embodiment of the present application;

[0023] FIG. 5 is a schematic diagram of an architecture of a tower crane system according to an embodiment of the present application;

[0024] FIG. 6 is a schematic diagram of a correction effect according to an embodiment of the present application;

[0025] FIG. 7 is a schematic diagram of an architecture of a trajectory control system according to an embodiment of the present application;

[0026] FIG. 8 is a structural schematic diagram of a control device of a running trajectory according to an embodiment of the present application;

[0027] FIG. 9 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", and the like in the description, claims, and above drawings of the present disclosure are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0030] The scheme of the present application is applied to the upper-attachment working scene of an unmanned working machine, and is used for controlling the running track of the upper-attachment working device of the working machine. Exemplarily, the working machine can be a tower crane, a mobile crane, an aerial working device, a pump truck, an excavator, a fire truck, an arm robot, etc. The mobile crane can be a truck crane, a caterpillar crane, etc. Exemplarily, when the working machine is a tower crane or a mobile crane, the upper-attachment working device of the working machine can be a hook. When the working machine is an excavator, the upper-attachment working device of the working machine can be a bucket. When the working machine is an aerial working machine or a fire truck, the upper-attachment working device of the working machine can be a working bucket. When the working machine is an arm robot, the upper-attachment working device of the working machine can be an actuator at the end of the arm.

[0031] For the convenience of description, the working machine is taken as a tower crane and the upper-attachment working device is taken as a hook for example in the following description.

[0032] A tower crane, also known as tower machine, tower crane, etc., is mainly used for vertical and horizontal transportation of materials in building construction and installation of building construction, and mainly consists of three parts of metal structure, working mechanism and electrical system. Among them, the metal structure includes multiple structures such as tower body, movable arm, base, attachment rod, trolley, etc., the working mechanism mainly includes lifting, amplitude changing, rotating, and some tower cranes can also include a walking part, and the electrical system includes motor, frequency converter, controller, power distribution frame, connection line and lighting device, etc. As an example, refer to FIG. 1, a structural schematic diagram of a tower crane provided by an embodiment of the present application. The hoisting process of the tower crane mainly relies on the lifting, rotating and amplitude changing of the hook, and the electrical system determines the frequency that the controller needs to output at each trajectory point in the trajectory according to the pre-planned trajectory of the hook, so that the hook can accurately reach the next trajectory point from the current trajectory point within the set time.

[0033] Among them, trajectory planning refers to planning the path between the starting point and the ending point of the hook in the hoisting operation scene as a series of trajectory points, and the time length between any two trajectory points is fixed. The process of trajectory planning needs to reasonably plan the distance between each two trajectory points according to the speed and acceleration of the hook movement of the tower crane. For example, in the case of slow speed of the hook at the starting stage, the distance between two trajectory points needs to be set small under the condition of fixed time length; in the case of fast speed of the hook at the middle stage, the distance between two trajectory points needs to be set large under the condition of fixed time length. The output frequency of the controller of the tower crane needs to make the hook move from the current trajectory point to the next trajectory point within the fixed time length. However, the tower crane has a large hysteresis phenomenon, such as communication delay, delay caused by mechanical structure (such as gap between gears in the rotating mechanism, causing delay in the rotating process of the gears), delay in motor starting, etc. The hysteresis phenomenon of the tower crane will cause that when the hook is controlled to move at the calculated output frequency at the current trajectory point, it cannot reach the next trajectory point within the set time.

[0034] To solve the above hysteresis phenomenon, the related art proposes a variety of trajectory automatic control schemes such as PID control, feedforward-feedback control, intelligent control and model predictive control. Among them, PID control is a commonly used linear control technology, easy to implement in engineering, but its regulation lags behind the disturbance and regulation hysteresis, causing the control output value to be unstable, and it is difficult to apply to the control system of the tower crane which is nonlinear, large inertia and large hysteresis. In feedforward-feedback control, feedforward control is to use input directly to output, which responds quickly, but is easy to cause overcompensation and undercompensation. The stability of the combination control scheme of feedforward and feedback is poor. Intelligent control schemes include neural network control, fuzzy control and deep learning-based control. Intelligent control has good robustness and self-adaptive ability, but it needs a lot of professional experience and a lot of data support, and the preparation time for training is long, and there is a lack of rigorous stability proof, which may exist uncertainty in the actual control process. Model predictive control is widely used in handling nonlinear systems and multi-input multi-output systems with constraints, which predicts the future dynamic behavior by using the established model, and then solves the optimal control and implements it according to the constraint conditions and performance indicators. Each step of the rolling updates the real-time information to correct the prediction of the future dynamic behavior. Most of the current researches use Lagrange equation to model the dynamics of the tower crane, and determine the output frequency based on the model prediction. However, the process of constructing the model is very complex, so the real-time performance of the application is poor.

[0035] Therefore, the present application proposes a motion trajectory control scheme. To solve the hysteresis phenomenon, the present application proposes to select a tracking trajectory point by preview, determine the optimal control amount for reaching the tracking trajectory point using an iterative optimization calculation model, and use the optimal control amount to control the hook to move from the current trajectory point to the tracking trajectory point, so as to minimize the position deviation after reaching.

[0036] The scheme of the present application will be described in detail below. Exemplarily, referring to FIG. 2, a flowchart of a motion trajectory control method provided by an embodiment of the present application is shown. Optionally, the method flow shown in FIG. 2 is applied to a tower crane, and can be executed by any controller in the tower crane. The present application does not limit the execution subject of the method flow shown in FIG. 2. The method flow shown in FIG. 2 specifically includes:

[0037] 201, determining a second trajectory point by previewing a target trajectory at a first trajectory point.

[0038] The target trajectory is a trajectory planned in advance for the hook of the tower crane, and the target trajectory includes a plurality of trajectory points, and any two adjacent trajectory points are separated by a fixed time length. Alternatively, it can also be referred to as a fixed period between any two trajectory points, that is, the trajectory control is periodically performed, and the trajectory control is performed once every time a trajectory point is reached, so that the hook can reach the next trajectory point at the time of the next trajectory point.

[0039] Optionally, when the preview is performed, the preview time is first determined, and then the second time is obtained by delaying the preview time at the first time corresponding to the first trajectory point, and the trajectory point corresponding to the second time is the second trajectory point obtained by the preview. As an example, refer to FIG. 3, which is a schematic diagram of a preview process provided by an embodiment of the present application.

[0040] As shown in FIG. 3, the first time corresponding to the first trajectory point is set as the k time, and under normal circumstances (as shown in the first time axis in FIG. 3), the hook can reach the trajectory point at the (k+n) time after the set control amount is applied at the k time, and the reference trajectory is k-(k+n). Wherein, n is the fixed time length between any two trajectory points introduced in the above embodiment. However, due to the existence of hysteresis and the influence of external factors, the preview time m is used for preview, and as shown in the second time axis in FIG. 3, the hook can reach the trajectory point at the (k+m+n) time after the set control amount is applied at the (k+m) time. The reference trajectory is (k+m)-(k+m+n). Further, the reference trajectory is updated, as shown in the third time axis in FIG. 3, and the updated reference trajectory is m-(m+n).

[0041] 202, obtain a plurality of third trajectory points in the target trajectory.

[0042] The plurality of third trajectory points include the second trajectory point and at least one trajectory point after the second trajectory point in the target trajectory

[0043] 203, input the plurality of third trajectory points into a preset calculation model to obtain a target control amount of the hook from the first trajectory point to the second trajectory point.

[0044] The calculation model is used to determine a plurality of control amounts corresponding to the plurality of third trajectory points, and predict a plurality of fourth trajectory points corresponding to the plurality of third trajectory points based on the plurality of control amounts. The control amount is used to control the movement of the hook, and different control amounts control different accelerations of the hook. When predicting the fourth trajectory point, the acceleration of the hook can be determined according to the control amount of the third trajectory point, and the position that the hook can reach, that is, the fourth trajectory point, can be calculated according to the acceleration.

[0045] Further, the computing model is also used to construct a target function of the plurality of control quantities based on the plurality of third trajectory points and a plurality of fourth trajectory points. Exemplarily, the fourth trajectory points are predicted trajectory points, which have a position deviation from the third trajectory points in the actual target trajectory, and the target function is constructed based on the position deviation between the third trajectory points and the fourth trajectory points, that is, based on the deviation between the predicted positions and the pre-planned positions. After the target function is constructed, the target function is iteratively optimized and solved to obtain the target control quantity.

[0046] It should be noted that the specific implementation of the control quantity corresponding to different working machines is different, and the embodiments of the present application are introduced taking the tower crane as an example. In the tower crane scenario, the control quantity is the power output by the motor of the tower crane, and different power outputs (that is, different control quantities) of the motor can control the hook to move at different accelerations. If the working machine is a mobile crane, for example, the working machine is a truck crane, and the truck crane is controlled through a hydraulic system, then the control quantity can be the opening of the hydraulic valve, and different openings of the hydraulic valve can control the hook to move at different accelerations. Subsequently, the tower crane is still taken as an example for introduction. In the tower crane scenario, the control quantity includes the slewing control quantity, the luffing control quantity, and the hoisting control quantity.

[0047] 204, control the hook to run by using the target control quantity.

[0048] Exemplarily, according to the introduction in step 201, it can be known that the trajectory control is periodically performed, and the control period is a fixed time length between any two trajectory points, so when the target control quantity is used to control the hook to run, the hook can be controlled to run for a fixed time length. After the running is completed, the next trajectory control is started.

[0049] Based on the above scheme, in order to solve the hysteresis phenomenon existing in the tower crane system, the present application proposes that first, the tracked trajectory points are estimated forward for a period of time through pre-estimation to determine a plurality of trajectory points obtained after pre-estimation. Further, a plurality of predicted trajectory points corresponding to the plurality of trajectory points are predicted according to the control quantities of the plurality of trajectory points, a target function is constructed based on the position deviation between the predicted trajectory points and the trajectory points in the actual target trajectory, the target function is iteratively optimized and solved to obtain the target control quantity for controlling the hook to run. On the one hand, since the target control quantity is solved based on the position deviation, the position deviation after the hook runs is minimized. On the other hand, compared with the traditional scheme of constructing a prediction model, the scheme of the present application for constructing a target function based on the position deviation and solving the target function has lower complexity and is easy to implement.

[0050] Before solving the target control quantity of the hook operation, the trajectory needs to be pre-sighted first. During the execution of the pre-sighting process, the pre-sighting time is a key parameter affecting the trajectory tracking. If the pre-sighting time is too long, the distance between the second trajectory point obtained after pre-sighting and the current first trajectory point will be too large, so that the control quantity is large, and the tracked trajectory point will be ahead; on the contrary, if the pre-sighting time is too short, the control quantity will be small, so that the trajectory point cannot be accurately reached. Based on this, the genetic optimization algorithm can be used to determine the appropriate pre-sighting time based on the current first trajectory point.

[0051] The genetic optimization algorithm is a self-adaptive global optimization probability search algorithm. The basic idea of the genetic algorithm can be expressed by borrowing the terminology of biological genetics: the genetic optimization algorithm starts from a population representing the possible potential solution set of the problem, which is composed of a certain number of individuals coded by genes. Each individual is actually a chromosome with characteristics. Chromosomes, as the main carrier of genetic material, are a collection of multiple genes, and their internal performance (i.e., genotype) is a certain combination of genes, which determines the external performance (i.e., traits) of the individual. Therefore, the mapping from phenotype to genotype, i.e., the encoding work, needs to be implemented at the beginning. After the initial population is generated, the principle of "survival of the fittest" is followed to produce better and better individuals through generations. In each generation, individuals are selected according to their fitness in the problem domain, and genetic operators are used for combination and mutation to produce a population representing a new solution set. This process will cause the population to evolve like natural evolution, with the offspring population more adapted to the environment than the previous generation. The optimal individual in the final population can be decoded as an approximate optimal solution to the problem. As an example, the implementation process of the genetic optimization algorithm can be seen in FIG. 4. The implementation process of the genetic optimization algorithm will be introduced below in conjunction with FIG. 4:

[0052] Step one: initialization. Set the evolution parameters and randomly generate the initial population.

[0053] Step two: calculate the fitness value of each individual in the initial population. Different fitness functions are used for different problems, and the corresponding fitness function can be set according to the specific problem scenario. Each individual is input into the fitness function to obtain the corresponding fitness value.

[0054] Step three: judge whether the optimization criterion is met. If it is met, the evolution is ended and the approximate optimal solution is output; if it is not met, the evolution is continued.

[0055] Step four: selection. The selection algorithm can be pre-set to select good individuals from the current population to make them as parents to reproduce the next generation.

[0056] Step five: crossover. The crossover operator is applied to the parent population. Crossover is the most important genetic operation in genetic optimization algorithm. Through crossover operation, new individuals can be obtained, which combine the characteristics of their parent individuals.

[0057] Step six: mutation. The mutation operator is applied to the current population. First, a random individual is selected from the population. Then, the data values of the selected individual are randomly changed with a certain probability to obtain a new individual.

[0058] After selection, crossover and mutation operations, a new population is obtained. Return to step two until the approximate optimal solution is output.

[0059] In one possible implementation, when determining the preview time using the genetic optimization algorithm, a fitness function can be first set. For example, the position deviation between the current first trajectory point and the trajectory point after the first trajectory point in the target trajectory can be used as the fitness function. Further, a primary population is generated according to a preset boundary value. Each individual in the primary population is an initially set preview time. Further, the trajectory point corresponding to each individual is determined. For example, when determining the trajectory point corresponding to each individual, the preview time of each individual can be divided by the fixed time interval between any two trajectory points to determine the future trajectory point corresponding to each individual.

[0060] Further, the fitness value of the trajectory point corresponding to each individual can be determined based on the position deviation between the trajectory point corresponding to each individual and the first trajectory point. The individual with a fitness value less than a set threshold is selected as a parent individual, and the individual not less than the set threshold is eliminated. Further, the crossover operator and the mutation operator in the genetic optimization algorithm are used to perform genetic operations on the parent individuals to generate a new population. Based on the new population, the step of calculating the fitness value is returned to be executed until the number of genetic operations reaches a number threshold, and the preview time corresponding to the optimal individual with the smallest fitness value is output.

[0061] After determining the preview time, the second trajectory point corresponding to the preview time can be determined, and further, a plurality of third trajectory points can be obtained. The plurality of third trajectory points include the second trajectory point and at least one trajectory point after the second trajectory point in the target trajectory. Further, the plurality of third trajectory points are input into the calculation model to determine the target control amount.

[0062] For example, in the process of determining the target control amount, the calculation model first determines the fourth trajectory point corresponding to each of the plurality of third trajectory points according to the control amount of the plurality of third trajectory points. For example, the calculation model can predict the position that can be reached by controlling the operation of the hook according to the control amount of the third trajectory point, and the predicted position is the fourth trajectory point.

[0063] In some embodiments, when determining the fourth trajectory point corresponding to the third trajectory point, a plurality of fitting functions previously constructed for different hook loads and different control quantity ranges can be obtained, wherein each fitting function is used to represent the mapping relationship between the control quantity and the hook acceleration. For example, in the scenario of a tower crane, the hook of the tower crane moves under the control of the motor of the tower crane, and different output powers of the motor can control the hook to move at different accelerations. The output power of the motor is determined based on the output frequency of the controller of the tower crane, and the output frequency of the controller has a fixed mapping relationship with the output power of the motor. Therefore, it can be considered that different output frequencies of the controller can control the hook to move at different accelerations.

[0064] Based on this, the fitting function between the control quantity and the hook acceleration constructed in the scenario of a tower crane can be represented as a fitting function between the output frequency of the controller and the acceleration of the hook, that is, a fitting function between the output frequency and the acceleration of the hook is constructed in different hook loads and different output frequency ranges. When selecting the fitting function, the corresponding target fitting function can be selected from the fitting functions previously constructed based on the current load of the hook and the output frequency range to which the first output frequency belongs. The first output frequency is the output frequency corresponding to the third trajectory point (that is, the control quantity of the third trajectory point in the foregoing).

[0065] Further, the first output frequency is input into the target fitting function to obtain a target acceleration corresponding to the first output frequency, and the fourth trajectory point is determined based on the target acceleration. For example, according to the description in the above embodiments, it can be known that the plurality of third trajectory points and the plurality of fourth trajectory points are in one-to-one correspondence, and when each fourth trajectory point in the plurality of fourth trajectory points is determined, the output frequency of the third trajectory point corresponding to each fourth trajectory point is determined. The determination process of the fourth trajectory point A is described below as an example:

[0066] The target acceleration corresponding to the output frequency of the third trajectory point A is determined based on the fitting function previously constructed. The third trajectory point A is the third trajectory point corresponding to the fourth trajectory point A in the plurality of third trajectory points.

[0067] Further, the fourth trajectory point A is calculated according to the fourth trajectory point B, the fixed time interval between any two adjacent trajectory points in the target trajectory, the target acceleration, and the current speed of the hook. For example, fourth trajectory point B + fixed time interval * speed + 1 / 2 * target acceleration 2 * fixed time interval = fourth trajectory point A. The fourth trajectory point B is the previous fourth trajectory point of the fourth trajectory point A, and the previous fourth trajectory point of the first fourth trajectory point in the plurality of fourth trajectory points is the first trajectory point.

[0068] Below, the process of constructing a fitting function between the output frequency of the controller and the acceleration of the hook is introduced. In the traditional scheme, the process of establishing a dynamic model is complex, and because the parameters of the frequency converter, the parameters of the motor, the friction of the trolley and other system parameters cannot be accurately measured, the modeling process is difficult to implement. Based on this, the application proposes to construct a fitting function based on historical data to reduce complexity. The application proposes to ignore the friction and air resistance when constructing the fitting function, ignore the influence of the tower crane tilting, pitching and deformation, ignore the coupling relationship between the tower crane rotation, amplitude and lifting, regard the load, hook and trolley as a point, regard the tower crane arm as a non-deformable rigid body, and ignore the elastic deformation of the steel wire rope. The process of constructing the fitting function can refer to the following steps one-four:

[0069] Step one: obtain a plurality of data groups of historical records under different hook loads.

[0070] Each data group includes an acceleration and an output frequency. By way of example, the hook load can be divided into three cases of light load, medium load and heavy load, and each case is analyzed and processed respectively.

[0071] Step two: cluster the data groups, and segment the data based on the slope of the data group distribution trajectory and the order of the polynomial function.

[0072] By way of example, after obtaining the data, the data group can be characterized as a discrete distributed point in a coordinate system with acceleration as the longitudinal coordinate and output frequency as the transverse coordinate. Further, the discrete points are clustered, and the application does not limit the clustering algorithm, such as mean shift clustering algorithm, K-Means clustering algorithm, density-based clustering algorithm with noise (Density-Based Spatial Clustering of Applications with Noise, DBSCAN), expectation-maximization (Expectation-Maximization, EM) clustering algorithm, and agglomerative hierarchical clustering algorithm.

[0073] After clustering, the data groups are segmented according to the slope of the curve obtained by the combination of points in the coordinate system and the order of the curve fitting function. The curve slopes and function orders of different segments of the data groups are different.

[0074] Step three: function fitting for different segmented data groups to determine the fitting function of each segment.

[0075] Optionally, the fitting function can be a high-order polynomial fitting function. The function fitting method is not limited to: least squares method, Fourier series fitting, sine function fitting, etc. As an example, the expression between the acceleration and the output frequency after function fitting can be seen in the following formula (1):

[0076] where k is an arbitrary time in the trajectory control process, a k+1 is the acceleration at time k+1, u k is the output frequency at time k. f1, f2, f n are the fitting functions of different segments respectively, the number of segments of rotation, amplitude and lifting can be different. F 1min , F 1max , F 2min , F 2max , F nmin , F nmax are the critical values of the output frequency of each segment respectively.

[0077] Step four: smooth the boundaries of each segment.

[0078] Based on the above scheme, since the function fitting of the whole will cause the function expression to be complex, the local details will be ignored. Therefore, the application proposes to fit the data after segmentation, which can reduce the function order and improve the calculation rate, while paying attention to the local details to improve the accuracy of the function, and filtering out the outlier data in the data clustering process to reduce the influence of disturbance error.

[0079] After determining the plurality of fourth trajectory points based on the pre-constructed fitting function and the control quantity of the plurality of third trajectory points, a target function about the plurality of control quantities can be further constructed according to the position deviation between the plurality of third trajectory points and the plurality of fourth trajectory points, and the target control quantity is obtained by solving the target function. As an example, the target function can refer to the following formula (2):

[0080] where J(k) is the target function value at time k, x ref (k+i) is the trajectory point in the target trajectory at time (k+i), x pre (k+i) is the predicted trajectory point at time (k+i), P is the prediction time domain, q i is the preset weighting coefficient of the state quantity.

[0081] In some embodiments, the target function can also be constructed based on the variation of the plurality of control quantities corresponding to the plurality of third trajectory points respectively. For example, the target function is constructed based on the variation between the control quantity corresponding to the third trajectory point A and the control quantity corresponding to the third trajectory point B. Wherein, the third trajectory point A and the third trajectory point B are two trajectory points in the plurality of third trajectory points, and the third trajectory point B is the previous third trajectory point of the third trajectory point A. As an example, the target function with the control quantity variation can refer to the following formula (3):

[0082] wherein J(k) is a target function value at time k, x ref (k+i) is a trajectory point in the target trajectory at time (k+i), x pre (k+i) is a predicted trajectory point at time (k+i), Au(k+j) is a change in the control amount between time (k+j) and time (k+j-1), P is a prediction time domain, q i is a preset weighting coefficient of the state quantity, M is a control time domain, r j is a preset weighting coefficient of the control amount. Exemplarily, the weighting coefficient of the control amount and the weighting coefficient of the state quantity can be obtained by bisection. Wherein the control time domain M is less than the prediction time domain P. If the prediction time domain P is too small, the tower crane system cannot respond to sudden changes in the trajectory; on the contrary, if the prediction time domain P is too large, the system will respond too slowly to disturbances. Therefore, the application proposes that the value of the prediction time domain P needs to be greater than the adjustment time of the system response, and the value of the control time domain M can be 10%-20% of P.

[0083] In one possible implementation, constraints can also be added in the process of solving the target function. For example, state constraints, control amount constraints, speed constraints, acceleration constraints, and initial position constraints can be added to accurately determine the target control amount.

[0084] In some embodiments, after determining the target control amount, the hook can be controlled to move from the first trajectory point to the second trajectory point according to the target control amount, and the length of time for the movement is a fixed length of time between any two adjacent trajectory points, that is, the period of trajectory control. Exemplarily, after controlling the hook to run, the actual trajectory point reached after running can be recorded, and based on the deviation between the actual trajectory point reached and the second trajectory point, the predicted trajectory point is corrected in the next control period to realize the rolling optimization of the predicted trajectory point.

[0085] For example, the actual trajectory point reached after each controlled hook movement can be obtained through the tower crane's sensors. As an example, see Figure 5, a schematic diagram of the architecture of a tower crane system provided in this application embodiment, specifically including: a controller, a frequency converter, a motor, an actuator, and sensors. The controller is used to perform operations such as trajectory planning and trajectory control. Although not shown in Figure 5, the controller may include the tower crane's industrial computer, a programmable logic controller (PLC) at the base of the tower, and a PLC controller on the tower. Sensors are used to collect the actual operating status of the hook and report it to the controller, so that the controller can correct the current trajectory control based on the real-time operating status collected by the sensors. The following describes the correction of the predicted trajectory point obtained by predicting time k from time k+1 using the predicted trajectory point obtained by predicting time k from time k-1 and the actual trajectory point reached at time k:

[0086] For example, the predicted trajectory point at time k-1, the actual trajectory point reached at time k, and the target control quantity required to reach the trajectory point at time k+1 can be obtained. The obtained parameters are input into a pre-trained deep learning model, which outputs a correction value to correct the predicted trajectory point at time k+1 obtained from the prediction at time k. When performing trajectory control at time k, the correction value can be used to compensate for the predicted trajectory point at time k+1 after the predicted trajectory point at time k+1 is obtained, and then trajectory control is performed based on the corrected predicted trajectory point at time k+1. For example, the corrected predicted trajectory point at time k+1 can be determined using the following formula (4): x pre (k+1)=x k+1 +f(x pre (k), x fb Formula (4) (k), u(k))

[0087] Where, x pre (k+1) represents the corrected predicted trajectory point at time k+1, x k+1 Let x be the predicted trajectory point at time k+1. pre (k) represents the predicted trajectory point at time k, x fb u(k) is the actual trajectory point reached at time k, u(k) is the target control variable at time k, and f is the pre-trained deep learning model.

[0088] It should be noted that this application does not limit the model for the output correction value. It can be a deep learning model, a convolutional neural network model, or a stacked autoencoder network model, etc. For ease of description, a deep learning model will still be used as an example.

[0089] As an example, referring to FIG. 6, a correction effect diagram provided by the embodiment of the present application is shown. As shown in FIG. 6, curve 1 is the trajectory after control at time (k-1), and in the case of no correction, the hook will run according to the trajectory shown by curve 1. Point A is the trajectory point actually reached at time k, and point B is the predicted trajectory point obtained by predicting the trajectory point at time k at time (k-1), and the distance between point A and point B is the prediction error at time (k-1). The point A, point B and the target control amount determined at time (k-1) are input into the deep learning model to obtain a correction value at time k. Further, at time k, the predicted trajectory point at time (k+1) is compensated and corrected by using the correction value, and then control is performed. As shown in FIG. 6, curve 2 is the trajectory before correction at time k, and point C is the predicted trajectory point at time (k+1) predicted before correction. Curve 3 is the trajectory after correction at time k, and point D is the predicted trajectory point at time (k+1) after correction. The distance between point C and point D is the correction value output by the deep learning model.

[0090] Optionally, the deep learning model can be trained by using the actual position and the predicted position at each time in the history and the target control amount at each time as the model input, and using the position deviation at each time as the model output. Next, the training process of the deep learning model is specifically introduced:

[0091] Step one: offline data collection.

[0092] Specifically, the trajectory point actually reached at each time in the past and the predicted trajectory point are collected.

[0093] Step two: model training.

[0094] Exemplarily, the training sample can be created first: the predicted trajectory point at time k predicted at time (k-1), the trajectory point actually reached at time k and the target control amount at time (k-1) are taken as the model input sample in the training sample, and the deviation between the predicted trajectory point at time (k+1) predicted at time k and the actual trajectory point at time (k+1) is taken as the model output sample in the training sample. Further, the model input sample is input into the model, the loss function value of the model is calculated according to the difference between the output result and the model output sample, the parameters of the model are optimized based on the loss function value, and the trained model is obtained.

[0095] Step three: offline verification.

[0096] Exemplarily, after obtaining the model, the model can also be verified and evaluated by using the verification sample set to determine whether the model can be put into use.

[0097] Optionally, the method described in the above embodiments can be executed by a controller of the tower crane, or by a specific processing module in the controller. For example, referring to FIG. 7, an architecture diagram of a trajectory control system provided in the embodiments of the present application is shown, which includes a trajectory processing module, a model prediction module, an execution module, and a predicted position correction module. The model prediction module includes a prediction unit and a function solving unit.

[0098] In FIG. 7, the trajectory processing module is configured to obtain each trajectory point included in the real-time planned target trajectory. Further, the trajectory planning module is configured to obtain a plurality of third trajectory points by pre-aiming the target trajectory based on the current first trajectory point. The process of determining the pre-aiming time and the process of pre-aiming can be found in the above embodiments, and will not be described herein. Further, the trajectory planning module outputs the determined plurality of third trajectory points to the model prediction module.

[0099] The model prediction module receives the plurality of third trajectory points and determines a plurality of control amounts corresponding to the plurality of third trajectory points, respectively. The prediction unit in the model prediction module is configured to predict a plurality of fourth trajectory points corresponding to the plurality of third trajectory points based on the plurality of control amounts. The prediction is achieved by using a pre-constructed fitting function, and the specific prediction process can be found in the above embodiments, and will not be described herein. For example, after predicting the plurality of fourth trajectory points, the prediction unit can transmit the plurality of fourth trajectory points to the predicted position correction module.

[0100] The function solving unit in the model prediction module is configured to construct a target function based on the position deviation between the plurality of third trajectory points and the plurality of fourth trajectory points, and the variation between adjacent control amounts in the plurality of control amounts, and to solve the target function to obtain a target control amount. For example, after obtaining the target control amount, the prediction unit in the model prediction module can store the target control amount for subsequent optimization of the pre-constructed fitting function.

[0101] After obtaining the target control amount, the model prediction module transmits the target control amount to the execution module and the predicted position correction module.

[0102] The execution module can include the motor described in the above embodiments, which is configured to control the hook to operate using the received target control amount. The operating time is a fixed time interval between any two trajectory points, i.e., a fixed period of trajectory control. The execution module also includes the sensor described in the above embodiments, which is configured to transmit the actual trajectory point reached by the hook after the fixed time interval to the predicted position correction module.

[0103] The predicted position correction module receives the target control quantity and the predicted fourth trajectory points from the model prediction module, and receives the actually arrived trajectory points from the execution module, obtains a correction value based on the received parameters and the pre-trained deep learning model, and transmits the correction value to the model prediction module, so that the model prediction module corrects the predicted trajectory point at the next moment based on the correction value.

[0104] Based on the same concept as the above method, referring to FIG. 8, a control device 800 for operating a trajectory is provided in an embodiment of the present application. The device 800 is used to implement each step in the above method embodiment, and will not be described here again to avoid repetition. The device 800 includes an acquisition unit 801 and a processing unit 802.

[0105] The processing unit 802 is configured to determine a second trajectory point by pre-aiming at a target trajectory at a first trajectory point; wherein the target trajectory is a trajectory pre-planned for an upper working device of the working machine, and the first trajectory point and the second trajectory point are two different trajectory points in the target trajectory.

[0106] The acquisition unit 801 is configured to acquire a plurality of third trajectory points in the target trajectory, the plurality of third trajectory points including the second trajectory point and at least one trajectory point after the second trajectory point.

[0107] The processing unit 802 is further configured to input the plurality of third trajectory points into a preset calculation model to obtain a target control quantity of the upper working device from the first trajectory point to the second trajectory point; wherein the calculation model is configured to determine a plurality of control quantities corresponding to the plurality of third trajectory points respectively, predict a plurality of fourth trajectory points corresponding to the plurality of third trajectory points respectively based on the plurality of control quantities, construct a target function about the plurality of control quantities based on the plurality of third trajectory points and the plurality of fourth trajectory points, and obtain the target control quantity by solving the target function.

[0108] The processing unit 802 is further configured to control the upper working device to run by using the target control quantity.

[0109] In one or more possible embodiments, the calculation model is further configured to construct the target function based on a change amount of adjacent control quantities in the plurality of control quantities.

[0110] In one or more possible embodiments, the acquisition unit 801 is further configured to acquire a plurality of fitting functions pre-constructed for different upper working device loads and different control quantity ranges; wherein any one fitting function is used to represent a mapping relationship between a control quantity and an acceleration of the upper working device.

[0111] The processing unit 802 is further configured to select a target fitting function from the plurality of fitting functions based on a current loading operation device load of the loading operation device and a control quantity range to which a first control quantity belongs, wherein the first control quantity is a control quantity corresponding to the third trajectory point.

[0112] The processing unit 802 is further configured to determine a target acceleration corresponding to the first control quantity by using the target fitting function.

[0113] The processing unit 802 is further configured to determine the fourth trajectory point based on the target acceleration.

[0114] In one or more possible embodiments, the acquisition unit 801 is further configured to acquire a plurality of data groups recorded in history under the first loading operation device load; each data group includes an acceleration and a control quantity.

[0115] The processing unit 802 is further configured to segment the plurality of data groups to obtain a plurality of segments according to a distribution of the plurality of data groups in a coordinate system with an acceleration as a longitudinal coordinate and a control quantity as a transverse coordinate, wherein the distribution is used to represent a slope of a curve obtained by combining points corresponding to the plurality of data groups in the coordinate system and is used to represent an order of a function fitted by the curve; different segments include data groups with different slopes and orders.

[0116] The processing unit 802 is further configured to determine a fitting function corresponding to the first loading operation device load and a first control quantity range by performing function fitting on data of a first segment, wherein the first segment is any one of the plurality of segments, and the first control quantity range is determined according to control quantities in the data groups included in the first segment.

[0117] In one or more possible embodiments, the processing unit 802 is specifically configured to:

[0118] Determine a preview time based on a position deviation between the first trajectory point and a trajectory point located after the first trajectory point in the target trajectory by using a genetic optimization algorithm as a fitness function;

[0119] Determine the second trajectory point at a second time according to the first time corresponding to the first trajectory point and the preview time.

[0120] In one or more possible embodiments, the processing unit 802 is specifically configured to:

[0121] Generate a primary population based on a preset boundary value; each individual in the primary population is an initially set preview time;

[0122] The fitness value is calculated according to the distance between the trajectory point corresponding to each individual and the first trajectory point, and individuals in the initial population with a fitness value less than a set threshold are taken as parent individuals;

[0123] The parent individuals are subjected to genetic operations by using a crossover operator and a mutation operator in a genetic optimization algorithm to generate a new population, and the step of calculating the fitness value is returned to be executed based on the new population until the number of genetic operations reaches a number threshold, and the preview time corresponding to an optimal individual is output; the optimal individual is an individual with the minimum fitness value.

[0124] In one or more possible embodiments, the acquisition unit 801 is further configured to acquire a predicted trajectory point obtained when the first trajectory point is predicted at a fifth trajectory point; the fifth trajectory point is a previous trajectory point of the first trajectory point.

[0125] The processing unit 802 is further configured to correct the fourth trajectory point based on the predicted trajectory point and the first trajectory point.

[0126] In one or more possible embodiments, the processing unit 802 is specifically configured to:

[0127] The acquisition unit 801 acquires a second control amount determined at the fifth trajectory point; the second control amount is a control amount for controlling the upper attachment working device to reach the predicted trajectory point from the fifth trajectory point;

[0128] The second control amount, the predicted trajectory point, and the first trajectory point are input into a pre-trained deep learning model to output a correction value for correcting the fourth trajectory point; the deep learning model is trained by using historical data of operation of the upper attachment working device;

[0129] The correction value is compensated into the fourth trajectory point to obtain a corrected fourth trajectory point.

[0130] FIG. 9 shows a structural schematic diagram of an electronic device 900 provided in an embodiment of the present application. The electronic device 900 in the embodiment of the present application can further include a communication interface 903, for example, a network interface, and the electronic device can transmit data through the communication interface 903.

[0131] In the embodiment of the present application, the memory 902 stores instructions executable by the at least one controller 901, and the at least one controller 901 can be configured to execute each step in the above method by executing the instructions stored in the memory 902, for example, the controller 901 can realize the functions of each unit in FIG. 8.

[0132] The controller 901 is a control center of the electronic device, and can connect each part of the electronic device through various interfaces and lines, and execute instructions stored in the memory 902 and call data stored in the memory 902. Optionally, the controller 901 can include one or more processing units, and the controller 901 can integrate an application controller and a modem controller, wherein the application controller mainly processes operating systems and applications, and the modem controller mainly processes wireless communication. It can be understood that the above-mentioned modem controller can also not be integrated into the controller 901. In some embodiments, the controller 901 and the memory 902 can be implemented on the same chip, and in some embodiments, they can also be implemented on separate chips respectively.

[0133] The controller 901 can be a general controller, such as a central controller (CPU), a digital signal controller, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general controller can be a microcontroller or any conventional controller. The steps disclosed in combination with the embodiments of the present application can be directly executed by the hardware controller or executed by a combination of hardware and software modules in the controller.

[0134] The memory 902 is a non-volatile computer readable storage medium, and can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 902 can include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card type memory, random access memory (RAM), static random access memory (SRAM), programmable read only memory (PROM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. The memory 902 is any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited to this. The memory 902 in the embodiments of the present application can also be a circuit or any other device capable of realizing a storage function, used for storing program instructions and / or data.

[0135] The controller 901 is programmed by, for example, embedding the codes corresponding to the methods described in the foregoing embodiments into the chip, so that the chip can execute the steps of the foregoing methods at runtime. How to program the controller 901 is a technology known to those skilled in the art, and will not be described here.

[0136] Those skilled in the art will appreciate that embodiments of the application can be supplied as a method, a system, or a computer program product. Therefore, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code.

[0137] The application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems), and computer program products according to this application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the computer or other programmable data processing apparatus produce the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0138] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in the flowchart one or more flows and / or block diagram one or more blocks.

[0140] Although the preferred embodiments of the application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to include the preferred embodiments and all changes and modifications falling within the scope of the application.

[0141] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A control method of a running track, the method being applied to a working machine, comprising: determining a second track point by previewing a target track at a first track point; wherein the target track is a track planned in advance for an upper working device of the working machine, the first track point and the second track point are two different track points in the target track; obtaining a plurality of third track points in the target track, the plurality of third track points including the second track point and at least one track point after the second track point; inputting the plurality of third track points into a preset calculation model to obtain a target control amount of the upper working device from the first track point to the second track point; wherein the calculation model is used to determine a plurality of control amounts corresponding to the plurality of third track points respectively, predict a plurality of fourth track points corresponding to the plurality of third track points respectively based on the plurality of control amounts, construct a target function about the plurality of control amounts based on the plurality of third track points and the plurality of fourth track points, and obtain the target control amount by solving the target function; controlling the upper working device to run by using the target control amount.

2. The method of claim 1, wherein, The calculation model is further used to construct the target function based on a variation of adjacent control amounts in the plurality of control amounts. 3.The method of claim 1 or 2, wherein the fourth track point corresponding to the third track point is determined in the following manner: Obtaining multiple fitting functions constructed in advance for different upper attachment work device loadings and different control amount ranges; wherein, any fitting function is used to represent a mapping relationship between a control amount and an acceleration of the upper working device; a target fitting function is selected from the plurality of fitting functions based on a current upper working device load of the upper working device and a control amount range to which a first control amount belongs; wherein the first control amount is the control amount corresponding to the third track point; a target acceleration corresponding to the first control amount is determined by using the target fitting function; the fourth track point is determined based on the target acceleration. 4.The method of claim 3, wherein the plurality of fitting functions between the acceleration of the upper working device and the control amount under a first upper working device load are constructed in the following manner: a plurality of data groups recorded in history under the first upper working device load are obtained; each data group includes an acceleration and a control amount; According to the distribution of the plurality of data groups in a coordinate system with acceleration as the longitudinal coordinate and control amount as the transverse coordinate, the plurality of data groups are segmented to obtain a plurality of segments; wherein the distribution is used to represent a slope of a curve obtained by combining points corresponding to the plurality of data groups in the coordinate system, and is used to represent an order of a function fitted to the curve; different segments include data groups corresponding to different slopes and orders; a function is fitted to data of a first segment to determine a fitting function corresponding to the first upper working device load and a first control amount range; the first segment is any one of the plurality of segments, and the first control amount range is determined according to the control amounts in the data groups included in the first segment.

5. The method of claim 1 or 2, wherein, The determining of the second track point by previewing the target track at the first track point specifically comprises: determining a preview time by using a position deviation between the first track point and a track point after the first track point in the target track as a fitness function based on a genetic optimization algorithm. According to the first time corresponding to the first trajectory point and the preview time, the second trajectory point at the second time is determined.

6. The method of claim 5, wherein, The genetic optimization algorithm is used to determine the preview time by taking the deviation between the actual position and the planned position of the trajectory point after the first trajectory point in the target trajectory as the fitness function, and specifically includes: A preliminary population is generated based on a preset boundary value; each individual in the preliminary population is an initially set preview time; The fitness value is calculated according to the distance between the trajectory point corresponding to each individual and the first trajectory point, and the individual with a fitness value less than a set threshold in the preliminary population is taken as a parent individual; The genetic operation is performed on the parent individual by using the crossover operator and the mutation operator in the genetic optimization algorithm to generate a new population, and the step of calculating the fitness value is executed based on the new population until the number of genetic operations reaches a number threshold, and the preview time corresponding to the optimal individual is output; the optimal individual is the individual with the smallest fitness value.

7. The method of claim 3, after determining the fourth trajectory point, the method further comprises: obtaining a predicted trajectory point obtained when a fifth trajectory point predicts the first trajectory point; The fifth trajectory point is the previous trajectory point of the first trajectory point; Based on the predicted trajectory point and the first trajectory point, the fourth trajectory point is corrected.

8. The method of claim 7, wherein, The fourth trajectory point is corrected based on the predicted trajectory point and the first trajectory point, specifically including: obtaining a second control amount determined at the fifth trajectory point; the second control amount is a control amount for controlling the upper attachment working device to reach the predicted trajectory point from the fifth trajectory point; inputting the second control amount, the predicted trajectory point and the first trajectory point into a pre-trained deep learning model to output a correction value for correcting the fourth trajectory point; wherein the deep learning model is trained using historical data of the operation of the upper attachment working device; The correction value is compensated into the fourth trajectory point to obtain the corrected fourth trajectory point.

9. A control device for running a trajectory, the device being a working machine, or the device being applied to the working machine, the device comprising: a processing unit configured to determine a second trajectory point at a first trajectory point of a target trajectory; wherein the target trajectory is a trajectory planned in advance for an upper attachment working device of the working machine, and the first trajectory point and the second trajectory point are two different trajectory points in the target trajectory; an acquisition unit configured to acquire a plurality of third trajectory points in the target trajectory, the plurality of third trajectory points including the second trajectory point and at least one trajectory point after the second trajectory point; The processing unit is further configured to input the plurality of third trajectory points into a preset calculation model to obtain a target control amount of the upper attachment working device from the first trajectory point to the second trajectory point; the calculation model is configured to determine a plurality of control amounts corresponding to the plurality of third trajectory points respectively, predict a plurality of fourth trajectory points corresponding to the plurality of third trajectory points respectively based on the plurality of control amounts, construct a target function about the plurality of control amounts based on the plurality of third trajectory points and the plurality of fourth trajectory points, and obtain the target control amount by solving the target function; The processing unit is further configured to control the upper attachment working device to operate by using the target control amount. 10.An electronic device, comprising a controller and a memory, The memory is configured to store computer programs or instructions. The controller is configured to execute the computer programs or instructions in the memory, so that the method in any one of claims 1-8 is executed. 11.A computer readable storage medium, storing computer executable instructions, which, when invoked by a computer, cause the computer to execute the method in any one of claims 1-8.

12. A computer program product, the computer program product comprising: Computer program code, when running on a computer, causes the computer to execute the method in any one of the above claims 1-8.

Images