A method, device, equipment and medium for anti-sway control of unmanned vehicles

Abstract

This invention provides an anti-sway control method, device, equipment, and medium for an unmanned vehicle. The anti-sway control method includes: acquiring the vehicle's operating parameters in real time, including the rope length between the vehicle and the load; fitting a rope length function based on the rope length; constructing an oscillation period function based on the rope length function; solving the oscillation period function to calculate the load's oscillation period; calculating the vehicle's acceleration / deceleration duration based on the oscillation period; and controlling the vehicle based on the operating parameters and the acceleration / deceleration duration. The anti-sway control method, device, equipment, and medium for an unmanned vehicle provided by this invention can eliminate load swaying.

Description

Technical Field

[0001] This invention relates to the industrial field, and in particular to an anti-sway control method, device, equipment, and medium for unmanned vehicles. Background Technology

[0002] Overhead cranes are key equipment for material handling in warehouses, achieving precise positioning through three-dimensional coordinated movement of the main trolley (horizontal movement), auxiliary trolley (lateral movement), and load lifting. The overhead crane uses flexible steel wire ropes to connect the load, effectively absorbing impact energy during acceleration and braking while transmitting driving force, thus improving stability during transport. This structural feature makes it an important support tool for efficient warehouse operations.

[0003] However, the low damping characteristics of flexible connections cause the load to easily sway during gear changes between the trolley and crane. This uncontrolled swaying not only exacerbates wear on the mechanical structure but also poses a safety hazard, potentially causing the load to collide with surrounding facilities. Traditional methods for eliminating swaying rely on manual, repeated start-stop adjustments to the equipment's motion, which is not only complex but also significantly prolongs the work cycle, hindering the overall operational efficiency of the storage area. Therefore, improvements are needed. Summary of the Invention

[0004] The purpose of this invention is to provide an anti-sway control method, device, equipment and medium for unmanned vehicles, which can eliminate load swaying.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] This invention provides an anti-sway control method for unmanned vehicles, comprising:

[0007] The operating parameters of the vehicle are acquired in real time, including the rope length between the vehicle and the load;

[0008] Based on the rope length of the operating parameters, fit a rope length function;

[0009] Construct the oscillation period function based on the rope length function;

[0010] Solve the oscillation period function to calculate the oscillation period of the load;

[0011] The acceleration and deceleration duration of the vehicle is calculated based on the oscillation period.

[0012] The train operation is controlled based on the operating parameters and the acceleration / deceleration duration.

[0013] In one embodiment of the present invention, the oscillation period function is expressed as: The rope length function is expressed as: ,in, The acceleration representing the change in rope length. Indicates in The initial rope length at that moment, Indicates the number of oscillation periods. Represents gravitational acceleration. Indicates time.

[0014] In one embodiment of the present invention, the step of calculating the acceleration and deceleration duration of the vehicle based on the oscillation period includes:

[0015] Based on a preset oscillation model, the acceleration / deceleration duration is calculated according to the oscillation period; the oscillation model represents the functional relationship between the acceleration / deceleration duration and the oscillation period.

[0016] In one embodiment of the present invention, the step of controlling the vehicle operation based on the operating parameters and the acceleration / deceleration duration includes:

[0017] The target speed of the vehicle is calculated based on the vehicle's acceleration, speed, and acceleration / deceleration duration in the operating parameters.

[0018] The vehicle is controlled based on the target speed and the acceleration / deceleration duration.

[0019] In one embodiment of the present invention, the step of controlling the vehicle movement based on the target speed and the acceleration / deceleration duration includes:

[0020] Calculate the displacement deviation and the corresponding rate of change of deviation based on the running speed, the acceleration, and the acceleration / deceleration duration;

[0021] Based on the displacement deviation and the corresponding rate of change of the deviation, overshoot risk data are calculated using a pre-trained risk assessment model; the risk assessment model is a deep neural network model.

[0022] The vehicle is controlled based on the comparison between the overshoot risk data and the corresponding risk threshold.

[0023] In one embodiment of the present invention, the step of calculating the displacement deviation and the corresponding rate of change of deviation based on the running speed, the acceleration, and the acceleration / deceleration duration includes:

[0024] Calculate the target displacement of the vehicle based on the operating speed, the acceleration, and the acceleration / deceleration duration;

[0025] Calculate the displacement deviation between the vehicle's displacement and the corresponding target displacement in the operating parameters;

[0026] Calculate the corresponding rate of change of deviation based on the displacement deviation.

[0027] In one embodiment of the present invention, the step of controlling the vehicle based on the comparison result of the overshoot risk data and the corresponding risk threshold includes:

[0028] Determine the overshoot risk data and its corresponding risk threshold:

[0029] When the overshoot risk data is less than the risk threshold, the vehicle is controlled according to the target speed and the acceleration / deceleration duration;

[0030] Otherwise, based on the acceleration, a feedback value is calculated using a pre-trained dynamic compensation model; the dynamic compensation model is a deep neural network model.

[0031] The target speed is adjusted based on the feedback value;

[0032] The vehicle movement is controlled based on the adjusted target speed and the acceleration / deceleration duration.

[0033] The present invention also discloses an anti-sway control device for an unmanned vehicle, comprising:

[0034] The data acquisition module is used to acquire the operating parameters of the vehicle in real time, including the rope length between the vehicle and the load.

[0035] The function fitting module is used to fit a rope length function based on the rope length of the running parameters;

[0036] The function construction module is used to construct the oscillation period function based on the rope length function;

[0037] The period calculation module is used to solve the oscillation period function and calculate the oscillation period of the load;

[0038] The duration calculation module is used to calculate the acceleration and deceleration duration of the vehicle based on the oscillation period;

[0039] The speed control module is used to control the vehicle's movement based on the operating parameters and the acceleration / deceleration duration.

[0040] The present invention also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the anti-sway control method for the unmanned vehicle.

[0041] The present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the anti-sway control method for the unmanned vehicle.

[0042] As described above, this invention provides an anti-sway control method, device, equipment, and medium for unmanned vehicles. Through intelligent control, it effectively solves the problems of low efficiency and safety hazards caused by load inertial swaying in traditional vehicle operations. By actively suppressing load swaying during the gear shifting phases of the trolley and crane, it ensures that the load quickly returns to zero and comes to a stop when moving at a constant speed, eliminating the impact and wear on the mechanical structure caused by uncontrolled swaying. Furthermore, by replacing the traditional repeated start-stop mode with an adaptive acceleration adjustment strategy, it significantly shortens the operation cycle.

[0043] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of an anti-sway control method for an unmanned vehicle according to an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the swing angle and angular velocity in one embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of an anti-sway control device for an unmanned vehicle according to an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention.

[0049] In the diagram: 100, Data acquisition module; 200, Function fitting module; 300, Function construction module; 400, Period calculation module; 500, Duration calculation module; 600, Speed ​​control module; 10, Electronic equipment; 11, Memory; 12, Processor. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Please see Figure 1This invention discloses an anti-sway control method for unmanned overhead cranes, which can be applied to unmanned overhead crane automated operation systems. When unmanned overhead cranes transport steel coils in a warehouse, the load experiences inertial swaying due to the flexible connection between the load and the crane (such as a steel wire rope) caused by the starting, stopping, acceleration, and deceleration of the trolley / cart. This swaying can lead to inaccurate load positioning, reduced work efficiency, and even collisions. Traditional manual operation relies on repeated starting and stopping to suppress the swaying, which is inefficient and dependent on experience. Automated control can quickly suppress the swaying, improving the work efficiency and control accuracy of the unmanned overhead crane. The anti-sway control method may include: step S10, real-time acquisition of the crane's operating parameters, including the rope length between the crane and the load, the crane's acceleration, the crane's speed, and the crane's displacement.

[0052] In some embodiments, the operating parameters of the trolley are a set of dynamic data used to describe the working status of the trolley system in real time. The operating parameters may include the real-time positions of the trolley, carriage, and load; the operating speeds of the trolley, carriage, and load; the accelerations of the trolley and carriage; the swing angle of the load; the angular velocity of the load's swing; and the length of the suspension rope between the carriage and the load. Specifically, the trolley can move horizontally along the track, the carriage can move laterally along the trolley, the swing angle of the load refers to the deflection angle of the suspension rope relative to the vertical direction, and the angular velocity of the swing refers to the rate of change of the swing angle.

[0053] In some embodiments, the absolute or relative positions of the trolley and the load on the track can be detected by positioning devices (such as Gray busbars, encoders, laser rangefinders, etc.) to obtain the real-time positions of the trolley, the load, and the load. The length of the suspension rope between the trolley and the load can be measured by an encoder or laser rangefinder of the hoisting mechanism. The swing angle of the load can be measured by a camera and a light source (reflector).

[0054] In some embodiments, the anti-sway control method may further include: step S20, fitting a rope length function based on the rope length of the operating parameters.

[0055] In some embodiments, the accelerations of the large and small vehicles can be constant or vary with time; no restriction is imposed here. Once the length of the suspension rope is obtained, it can be fitted. Assuming the suspension rope contracts with uniform acceleration, or the rope length is adjusted, a rope length function can be obtained, expressed as: ,in, The acceleration representing the change in rope length. Indicates in The initial rope length at that moment.

[0056] In some embodiments, the anti-sway control method may further include: step S30, constructing an oscillation period function based on the rope length function.

[0057] In some embodiments, the operation of the trolley is divided into the movement of a main trolley and a secondary trolley. The main trolley moves along the ground track (the direction of movement of the main trolley can be defined as the X-axis), and the secondary trolley moves along the direction of the main trolley track (the direction of movement of the secondary trolley can be defined as the Y-axis). The lifting direction of the load can be defined as the Z-axis. The movements of the main trolley (X-axis) and the load (Z-axis) are linked, mainly affected by the physical relationship between centripetal force and tangential velocity. The movements of the secondary trolley (Y-axis) and the load (Z-axis) have a combined effect, jointly influencing the trajectory of the suspended load. When the secondary trolley moves at a constant speed and the rope length changes, the change in rope length will cause the trajectory of the suspended load to change in a spiral pattern. When the angular velocity of the load is 0, the system reaches a state of equilibrium. During operation, the graphical method cannot be directly applied to solve the actual control process. Therefore, a numerical solution method is used to calculate the system stability point during the operation of the unmanned trolley automatic operation system.

[0058] In some embodiments, the vehicle operation state model can be used to describe the dynamic characteristics of the vehicle-load system, and the vehicle operation state model can be a high-order nonlinear differential equation. Due to the nonlinearity of the unmanned vehicle automatic operation system (such as centripetal force and rope length changes in circular motion) and the limitations of graphical methods, numerical methods (such as the Runge-Kutta method) are required to solve for the stable point. The vehicle operation state model can characterize the functional relationship between swing angle, angular velocity, rope length, and displacement.

[0059] In some embodiments, since the anti-sway control of the X and Z axes (trolley and load) and the anti-sway control of the Y and Z axes (trolley and load) are relatively independent, they can be analyzed separately. During the analysis, to simplify the system analysis, the following assumptions are made: the suspension rope is rigid (no extension), air resistance and wind force are ignored, suspension rope damping is not considered, the load is abstracted as a point mass (ignoring shape and mass distribution), and the motions of the trolley and the load are independent of each other.

[0060] In some embodiments, the vehicle operation state model can be represented as: ;in, It is expressed as the swing angle (including the swing angle of the load relative to the trolley and the swing angle of the load relative to the trolley). Represented as The first derivative, i.e., angular velocity (including the angular velocity of the load relative to the large vehicle and the angular velocity of the load relative to the small vehicle). This is expressed as the length of the suspension rope; Represented as The first derivative of the rope length is the rate of change of the rope length. Represented as The second derivative; It is expressed as the displacement of the vehicle (including the displacement of the main vehicle and the trolley), which can be calculated from the real-time position of the main vehicle and the trolley. Represented as The second derivative of the acceleration of the large vehicle and the acceleration of the small vehicle; It is expressed as gravitational acceleration.

[0061] In some embodiments, in the vehicle operation state model , For unknown quantities, , , As parameters, the vehicle operation state model can be viewed as a second-order differential equation with varying parameters. Assuming , , , Plot the numerical solution graph of the second-order differential equation as follows: Figure 2 As shown, Figure 2 The x-axis represents angular velocity, and the y-axis represents the swing angle. From Figure 2 As can be seen from the graph, as the rope length changes, the trajectory of the trolley and the carriage changes in a spiral pattern during uniform motion. The graph shows that the angular velocity at the intersection of the graph and the Y-axis is 0, at which point the system reaches equilibrium. Since the graphical method cannot be directly applied to solving the actual control process, numerical methods can be used to find the stable point.

[0062] In some embodiments, when the rope length remains unchanged, the vehicle operation state model can be solved to calculate the swing angle and angular velocity change functions, expressed as: , ;in, Indicates the swing angle. Indicates angular velocity. Indicates the acceleration of the vehicle. Represents gravitational acceleration. Represents the function of rope length. This represents time. The swing angle and angular velocity can be periodic functions. In this case, the swing period function can be constructed based on the rope length function, expressed as: .

[0063] In some embodiments, the anti-sway control method may further include: step S40, solving the oscillation period function to calculate the oscillation period of the load.

[0064] In some embodiments, in a preset state, i.e. , , It can solve the model of the train's operating state. Due to the swing angle and angular velocity They're all about time. The function, and the swing angle and angular velocity Since they are all periodic functions, the oscillation periodic function can be approximated as follows: ,in, This indicates the number of oscillation periods. When the rope length remains constant, take... , ,at this time Since the rope length remains constant, the oscillation period function can be simplified to: The oscillation period function matches the oscillation period of the swing angle, which verifies the correctness of the oscillation period function. Specifically, when n=1, the oscillation period of the load can be calculated.

[0065] In some embodiments, the anti-sway control method may further include: step S50, calculating the acceleration and deceleration duration of the vehicle based on the oscillation period. Step S50 may include the following steps: calculating the acceleration and deceleration duration based on a preset oscillation model and the oscillation period; the oscillation model represents the functional relationship between the acceleration / deceleration duration and the oscillation period.

[0066] In some embodiments, taking the variable-speed operation of the trolley as an example, the trolley undergoes uniform acceleration with a constant acceleration, causing the load to oscillate. The oscillation process of the load can be divided into an initial stage, an acceleration stage, a deceleration stage, and a return stage. In the initial stage, the load moves from its initial position (swing angle)... angular velocity The pendulum begins to swing towards the equilibrium angle; during the acceleration phase, the swing angle and angular velocity gradually increase until the equilibrium angle is reached, at which point the angular velocity reaches its maximum value, but the swing angle does not reach its maximum value; during the deceleration phase, due to the angular velocity... The swing angle continues to increase, but due to the influence of the system's net force (such as gravity and centripetal force), the angular velocity gradually decreases until the angular velocity... At this time, the swing angle The load reaches its maximum value; during the retracement phase, the load swings back to its initial position, a process symmetrical to the acceleration phase, until the swing angle and angular velocity return to zero.

[0067] In some embodiments, the oscillation period T is determined by system characteristics (such as rope length). Gravitational acceleration The formula is determined by... When the shift time t matches T, the oscillation energy is completely absorbed, and the load returns to a steady state. That is, when the acceleration or deceleration duration t of the trolley is an integer multiple of the oscillation period T (i.e., t = nT, where n is a positive integer), the oscillation angle... and angular velocity It can return to zero. When the swing angle... and angular velocity When the load returns to zero, if the trolley moves at a constant speed, the load is no longer disturbed by acceleration, and the swaying is effectively suppressed. By controlling the acceleration and deceleration time t of the trolley to be an integer multiple of the sway period T, sway-free switching can be achieved, improving the efficiency and safety of train operation.

[0068] In some embodiments, the anti-sway control method may further include: step S60, controlling the vehicle according to operating parameters and acceleration / deceleration duration. Step S60 may include the following steps: step S61, calculating the target speed of the vehicle based on the vehicle's acceleration, operating speed, and acceleration / deceleration duration in the operating parameters.

[0069] In some embodiments, after calculating the acceleration and deceleration durations, the target speed of the vehicle can be calculated using the obtained operating speed and acceleration / deceleration durations. Target speed It can be represented as: , This can be expressed as running speed. This can be expressed as the acceleration of a vehicle. It can be expressed as the duration of acceleration and deceleration.

[0070] In some embodiments, step S60 may further include the following step: step S62, controlling the vehicle movement based on the target speed and acceleration / deceleration duration.

[0071] In some embodiments, once the target speed is calculated, open-loop control can be performed on the vehicle based on the target speed and the acceleration / deceleration duration. Open-loop control refers to pre-setting control variables (acceleration / deceleration duration, preset target speed curve) without relying on real-time feedback. To improve control performance, feedback control can be introduced on top of the open-loop control, collecting the vehicle's displacement in real time and dynamically adjusting the control variables.

[0072] In some embodiments, step S62 may include the following step: calculating the displacement deviation and the corresponding rate of change of deviation based on the running speed, acceleration, and acceleration / deceleration duration. Specifically, the above step may include:

[0073] Calculate the target displacement of the vehicle based on its operating speed, acceleration, and acceleration / deceleration duration;

[0074] Calculate the displacement deviation between the vehicle's displacement and the corresponding target displacement in the operating parameters;

[0075] Calculate the corresponding rate of change of deviation based on the displacement deviation.

[0076] In some embodiments, after controlling the vehicle, the target displacement of the vehicle can be calculated based on its initial position, operating speed, acceleration, and acceleration / deceleration duration. For example, the acceleration / deceleration duration can be 20 seconds, and a time node can be set at 1-second intervals. For instance, the first time node could be 1 second after the vehicle accelerates / decelerates, and the second time node could be 2 seconds after the vehicle accelerates / decelerates. Of course, the specific time interval is not limited. The target displacement of the vehicle relative to its initial position can be calculated at each preset time node.

[0077] In some embodiments, after controlling the vehicle's movement, the displacement of the vehicle relative to its initial position can be calculated using the vehicle's real-time position and its initial position. Subsequently, the displacement deviation between the displacement and the corresponding target displacement can be calculated at the same time point.

[0078] In some embodiments, after calculating the displacement deviation, the displacement deviation can be fitted with time to obtain the corresponding fitting function. Subsequently, the first derivative of the displacement deviation can be solved to calculate the corresponding rate of change of deviation.

[0079] In some embodiments, step S62 may further include the following step: calculating overshoot risk data using a pre-trained risk assessment model based on the displacement deviation and the corresponding rate of change of deviation. The risk assessment model may be a DNN deep neural network model. Overshoot risk data The calculation formula can be expressed as: , , ;in, It can be expressed as displacement. This can be expressed as displacement deviation. This can be expressed as the rate of change of deviation. It can be represented as a time-series vector. This can be represented as the weight values ​​of the j-th output layer. It can be represented as the j-th Gaussian activation function of the hidden layer. It can be represented as the weight center of the j-th Gaussian activation function. It can be represented as the base width, and m can be represented as the number of output layer weights.

[0080] In some embodiments, step S62 may further include the following step: controlling the vehicle's operation based on a comparison between the overshoot risk data and the corresponding risk threshold. Specifically, the above steps may include:

[0081] Determine the overshoot risk data and the corresponding risk threshold:

[0082] When the overshoot risk data is less than the risk threshold, the driving is controlled according to the target speed and acceleration / deceleration duration;

[0083] Otherwise, the feedback value is calculated based on the acceleration using a pre-trained dynamic compensation model;

[0084] Adjust the target speed based on the feedback value;

[0085] The vehicle is controlled based on the adjusted target speed and acceleration / deceleration duration.

[0086] In some embodiments, the specific size of the risk threshold is not limited, for example, it can be 0.4 / 0.5 / 0.6, etc.

[0087] In some embodiments, when the overshoot risk data is less than the risk threshold, it can be assumed that the vehicle is accelerating or decelerating according to the target speed and acceleration / deceleration duration. In this case, there is no need to adjust the target speed, and the vehicle can continue to be controlled according to the target speed and acceleration / deceleration duration.

[0088] In some embodiments, when the overshoot risk data is greater than or equal to the risk threshold, it can be considered that the vehicle is not accelerating or decelerating according to the target speed and acceleration / deceleration duration. In this case, the target speed needs to be adjusted. A feedback value can be calculated using a pre-trained dynamic compensation model. The dynamic compensation model can be a DNN deep neural network model. Feedback value The calculation formula can be expressed as: ;in, This can be represented as the weight matrix of the hidden layer of a DNN neural network. Let be the weight matrix of the output layer of the DNN neural network. This can be represented as the activation function of a DNN neural network. It can be represented as a time-series vector. Where u can be represented as the acceleration of the vehicle, t can be represented as the acceleration / deceleration duration, and kz can be represented as the corresponding time node.

[0089] In some embodiments, after the feedback value is calculated, the feedback value can be added to the acceleration to obtain the adjusted acceleration. Subsequently, the target velocity can be readjusted according to the adjusted acceleration to obtain the adjusted target velocity.

[0090] In some embodiments, when controlling the vehicle, the frequency converter in the motor drive system of the main vehicle or the trolley can be sent according to the adjusted target speed and acceleration / deceleration duration. The frequency converter outputs current and voltage to the motor system, and the motor system generates driving torque to drive the main vehicle or the trolley to run, so that the load can run quickly and stably to the predetermined position.

[0091] Please see Figure 3The present invention also discloses an anti-sway control device for an unmanned vehicle, and the above-mentioned anti-sway control method can be applied to the anti-sway control device. The anti-sway control device may include: a data acquisition module 100, a function fitting module 200, a function construction module 300, a period calculation module 400, a duration calculation module 500, and a speed control module 600.

[0092] In some embodiments, the data acquisition module 100 can be used to acquire the operating parameters of the vehicle in real time, including the rope length between the vehicle and the load.

[0093] In some embodiments, the function fitting module 200 can be used to fit a rope length function based on the rope length of the running parameters.

[0094] In some embodiments, the function construction module 300 can be used to construct an oscillation period function based on a rope length function.

[0095] In some embodiments, the period calculation module 400 can be used to solve the oscillation period function and calculate the oscillation period of the load.

[0096] In some embodiments, the duration calculation module 500 can be used to calculate the acceleration and deceleration duration of the vehicle based on the oscillation period.

[0097] In some embodiments, the speed control module 600 can be used to control the vehicle's movement based on operating parameters and acceleration / deceleration duration.

[0098] Specific limitations regarding the anti-shake control device can be found in the limitations of the anti-shake control method above, and will not be repeated here. Each module in the aforementioned anti-shake control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the memory in the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the memory can call and execute the corresponding operations of each module.

[0099] Please see Figure 4 In one embodiment, the electronic device 10 may include a memory 11, a processor 12 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 12, such as a program for anti-shake control of an unmanned vehicle.

[0100] In one embodiment, the memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 10, such as the portable hard drive of the electronic device 10. In other embodiments, the memory 11 can also be an external storage device of the electronic device 10, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 10. Furthermore, the memory 11 can include both internal storage units and external storage devices of the electronic device 10. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 10, such as anti-shake control code for autonomous vehicles, but also to temporarily store data that has been output or will be output.

[0101] In one embodiment, the processor 12 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 12 is the control unit of the electronic device 10, connecting various components of the electronic device 10 via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., anti-shake control programs for unmanned vehicles) and calls data stored in the memory 11 to perform various functions and process data of the electronic device 10.

[0102] In one embodiment, the processor 12 executes the operating system of the electronic device 10 and various installed applications. The processor 12 executes the applications to implement the steps in the above-described anti-sway control method for the unmanned vehicle.

[0103] In one embodiment, a computer program may be divided into one or more modules, one or more of which are stored in memory 11 and executed by processor 12 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in electronic device 10. For example, the computer program may be divided into a data acquisition module 100, a function fitting module 200, a function construction module 300, a period calculation module 400, a duration calculation module 500, a speed control module 600, etc.

[0104] The embodiments of the present invention disclosed above are merely illustrative of the invention. The embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for anti-roll control of an unmanned vehicle, characterized by, The method comprises the following steps: obtaining the running parameters of the hoist in real time, wherein the running parameters comprise the rope length between the hoist and the load; fitting a rope length function according to the rope length of the running parameters; constructing a swing period function according to the rope length function; solving the swing period function to calculate the swing period of the load; calculating the acceleration / deceleration time of the hoist according to the swing period; calculating the target speed of the hoist according to the acceleration of the hoist, the running speed of the hoist, and the acceleration / deceleration time; calculating the displacement deviation and the corresponding deviation change rate according to the running speed, the acceleration, and the acceleration / deceleration time; According to the displacement deviation and the corresponding deviation change rate, an overshoot risk data is calculated through a pre-trained risk assessment model; the risk assessment model is a deep neural network model; the calculation formula of the overshoot risk data is expressed as: , , , is expressed as displacement, is expressed as displacement deviation, is expressed as deviation change rate, is expressed as a time sequence vector, is expressed as a weight value of the jth output layer, is expressed as the jth Gaussian activation function of the hidden layer, is expressed as the weight center of the jth Gaussian activation function, is expressed as the base width, and m is expressed as the number of output layer weight values. judging the overshoot risk data and the corresponding risk threshold value: controlling the hoist according to the target speed and the acceleration / deceleration time when the overshoot risk data is less than the risk threshold value; Otherwise, according to the acceleration, a feedback value is calculated by a pre-trained dynamic compensation model; the dynamic compensation model is a deep neural network model; the feedback value The calculation formula is expressed as: , wherein, is a weight matrix of a hidden layer of a DNN neural network, is a weight matrix of an output layer of the DNN neural network, is an activation function of the DNN neural network, u represents the acceleration of the vehicle, t represents the acceleration / deceleration time length, and k-z represents the corresponding time node. adjusting the target speed according to the feedback value; controlling the hoist according to the adjusted target speed and the acceleration / deceleration time.

2. The sway control method of an unmanned vehicle according to claim 1, wherein The oscillation period function is expressed as: The rope length function is expressed as: ,in, The acceleration representing the change in rope length. Indicates in The initial rope length at time [time] Indicates the number of oscillation periods. Represents gravitational acceleration. Indicates time.

3. The sway control method of an unmanned vehicle according to claim 1, wherein The step of calculating the acceleration / deceleration time of the hoist according to the swing period comprises the following steps: calculating the acceleration / deceleration time according to the swing period based on a preset swing model; the swing model represents the functional relationship between the acceleration / deceleration time and the swing period.

4. The sway control method of an unmanned vehicle according to claim 1, wherein The step of calculating the displacement deviation and the corresponding deviation change rate according to the running speed, the acceleration, and the acceleration / deceleration time comprises the following steps: calculating the target displacement of the hoist corresponding to the running speed, the acceleration, and the acceleration / deceleration time; calculating the displacement deviation between the displacement of the hoist in the running parameters and the corresponding target displacement; calculating the corresponding deviation change rate according to the displacement deviation.

5. An anti-roll control device for an unmanned vehicle, characterized by comprising: The anti-swing control device of the unmanned hoist comprises: a data acquisition module for obtaining the running parameters of the hoist in real time, wherein the running parameters comprise the rope length between the hoist and the load; a function fitting module for fitting a rope length function according to the rope length of the running parameters; a function construction module for constructing a swing period function according to the rope length function; a period calculation module for solving the swing period function to calculate the swing period of the load; a time calculation module for calculating the acceleration / deceleration time of the hoist according to the swing period; a speed control module for controlling the hoist according to the running parameters and the acceleration / deceleration time.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the anti-swing control method of the unmanned hoist.

7. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 6. The computer program is executed by the processor to realize the steps of the anti-swing control method of the unmanned hoist.

Images