Unmanned forklift intelligent control method and system

Abstract

The invention discloses an intelligent control method and system for an unmanned forklift, and relates to the technical field of unmanned forklift control, and the method comprises the steps: constructing a sensing layer through the deployment of a multi-dimensional sensor, and obtaining the data of the unmanned forklift; correcting the position by using a preset position optimization algorithm according to the data to generate accurate positioning information; establishing a dynamic model according to the data, defining an optimization problem according to accurate positioning information in combination with the dynamic model and a path planning result, solving an optimal control sequence by using a nonlinear optimization algorithm, extracting control input at the current moment, applying the control input to a driving and steering system, and performing intelligent control. High-precision positioning is realized by adopting a preset position optimization algorithm, the adaptability to environment change and sensor noise is enhanced, efficient path planning and tracking control are carried out based on accurate positioning information and a dynamic model, and it is ensured that the unmanned forklift can realize accurate navigation in a dynamic and complex storage environment. And the efficiency and reliability of logistics operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned forklift control, and in particular to an unmanned forklift intelligent control method and system. Background Art

[0002] With the rapid development of the modern logistics industry, the application of automated equipment in warehousing and transportation is becoming more and more widespread. As an important part of automated logistics equipment, the research and application of intelligent control technology for unmanned forklifts has become the key to improving logistics efficiency and reducing labor costs. However, the existing unmanned forklift control methods still face many challenges in terms of precise positioning, path planning and dynamic control.

[0003] In the existing technology, in order to improve the positioning accuracy and control stability of unmanned forklifts, researchers have introduced multi-sensor data fusion technology, which uses data from multiple sensors to build a unified environmental model and accurate positioning information. However, in the process of multi-sensor data fusion, how to effectively integrate the data characteristics of different sensors and deal with the heterogeneity and noise interference between data are still technical problems that need to be solved urgently.

[0004] In addition, the existing unmanned forklift control algorithms mostly use linear control methods, which are difficult to deal with the nonlinear dynamic characteristics and complex constraints in practical applications. How to combine high-precision multi-sensor positioning information with complex nonlinear dynamic models to design efficient optimization algorithms still needs further research. Summary of the invention

[0005] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide an unmanned forklift intelligent control method and system to solve the above-mentioned technical problems.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent control method for an unmanned forklift, comprising:

[0007] By deploying multi-dimensional sensors to build a perception layer, the status data, location data and static environment feature location data of the unmanned forklift can be obtained;

[0008] According to the position data of the unmanned forklift and the position data of the static environment characteristics, the position data of the unmanned forklift is corrected by using a preset position optimization algorithm to generate accurate positioning information;

[0009] A dynamic model of the unmanned forklift is established according to the state data of the unmanned forklift, an optimization problem is defined according to the precise positioning information, in combination with the dynamic model and the path planning result, and an optimal control sequence is solved using a nonlinear optimization algorithm;

[0010] The control input at the current moment is extracted according to the optimal control sequence and applied to the driving and steering systems of the unmanned forklift for intelligent control.

[0011] The present invention is further configured such that the multi-dimensional sensor includes a laser radar, a camera, an ultrasonic sensor, an inertial measurement unit and an ultra-wideband positioning base station, and the status data includes linear velocity, driving torque, friction torque, angular velocity and steering angle.

[0012] The present invention is further configured to correct the position data of the unmanned forklift using a preset position optimization algorithm, including:

[0013] Starting from the initial moment, the position data of the unmanned forklift in the time series is obtained according to the time step t (x 1 (t),x 2 (t)) and static environment feature position data (l 1 (t),l 2 (t)), calculate the measured distance s(t) between the unmanned forklift and the static environment feature;

[0014] According to the location data of the unmanned forklift (x 1 (t),x 2 (t)), static environment feature location data (l 1 (t),l 2 (t)) and the measured distance s(t) to calculate the geometric deviation metric at time step t;

[0015] According to the calculation of the dynamic residual enhancement of time step t at time step t, the dynamic residual enhancement of all time steps is accumulated and summed to obtain the total cost function;

[0016] By minimizing the total cost function, we can solve (x 1 (t),x 2 (t)) to obtain precise positioning information.

[0017] The present invention is further configured such that the calculation logic of the geometric deviation metric at time step t is: D(t)=((x 1 (t)-l 1 (t)) 2 +(x 2 (t)-l 2 (t)) 2 ) α -(s(t)) 2α , where D(t) is the geometric deviation measure at time step t, and α is the polynomial transformation order that controls the geometric difference;

[0018] The calculation logic of dynamic residual enhancement at time step t is: R(t) = (D(t)) 2exp(δ·sin(β·s(t))), where R(t) is the dynamic residual enhancement at time step t, δ is the frequency parameter of the modulating sine function, and β is the scale parameter of the control exponential factor;

[0019] The calculation logic of the total cost function is: Among them, C is the total cost function and M is the number of time steps.

[0020] The present invention is further configured to solve (x 1 (t),x 2 (t)) to obtain precise positioning information, including:

[0021] Calculate the minimum total cost function C for the position variable x 1 (t) and x 2 The partial derivative of (t) and

[0022] Set initial estimates of location variables and And the number of iteration steps k = 0;

[0023] At each iteration k, the geometric deviation measure D is calculated (k) (t), dynamic residual enhancement R (k) (t) and partial derivatives and

[0024] According to the partial derivative and Update the position variable, Among them, η is the learning rate parameter, which is used to control the update step size;

[0025] Calculate the cost function value of the current iteration step, Determine whether the convergence condition is met|C (k+1) -C (k) |<∈, where ∈ is the preset convergence threshold;

[0026] When the change in the cost function between two consecutive iterations is less than the preset threshold ∈, the iteration process is terminated and the precise positioning information is output.

[0027] The present invention is further configured to establish a dynamic model of the unmanned forklift according to the state data of the unmanned forklift, define an optimization problem according to the precise positioning information, combined with the dynamic model and the path planning result, and solve the optimal control sequence using a nonlinear optimization algorithm, including:

[0028] Establish the linear and angular motion equations of the unmanned forklift;

[0029] Discretize the continuous time module to obtain discretized linear motion equations and angular motion equations;

[0030] Represent the dynamic model in matrix form and construct the state update equation;

[0031] At each control moment, an optimization problem with a finite time step length N is defined, and the optimal control sequence is obtained by minimizing the cost function within the next N steps using a nonlinear optimization algorithm.

[0032] The present invention is further configured such that the linear motion equation of the unmanned forklift is: Where m is the total mass of the unmanned forklift, v(t) is the linear velocity of the unmanned forklift at time t, and F d (t) is the driving torque acting on the unmanned forklift at time t, F f (t) is the friction torque acting on the forklift at time t;

[0033] The angular motion equation of the unmanned forklift is: Where I is the moment of inertia of the unmanned forklift about the center of mass, ω(t) is the angular velocity of the unmanned forklift at time t, L is the wheelbase of the unmanned forklift, θ(t) is the steering angle at time t, and C f is the friction coefficient between the tire and the ground;

[0034] The discretized linear equation of motion is: After rearrangement we get: Δt is the discretized time step;

[0035] The discretized angular motion equation is: After rearrangement we get:

[0036] The matrix form of the kinetic model is expressed as: Where X(t) is the state vector at time t, and u(t) is the control input vector at time t;

[0037] The state update equation is: X(t+1)=A·X(t)+B·u(t)+N(X(t),u(t)), where A is the state transfer matrix, B is the control input matrix, N(X(t),u(t)) is a nonlinear interference term,

[0038] The present invention is further configured to define an optimization problem with a finite time step length N at each control moment, and to obtain an optimal control sequence by minimizing the cost function within the next N steps and using a nonlinear optimization algorithm, including:

[0039] Define the objective function and constraints, and set the initial control sequence U 0 (t);

[0040] At the current state point, the nonlinear dynamic model is Taylor expanded, the first-order terms are retained, and the linearized model is obtained;

[0041] Based on the linearized model, the quadratic approximation objective function and constraints are constructed. The sequential quadratic programming algorithm is used to iteratively solve the quadratic approximation problem and update the control increment until the objective function converges. The control input at the current moment is extracted from the optimal control sequence and applied to the dynamic model. The state of the forklift is updated according to the dynamic model and the control input.

[0042] The present invention is further configured such that the objective function is: Among them, J(U(t)) is the objective function of the control sequence U(t), x ref (t+k) is the reference state vector, is the path planning result, Q is the state error weight matrix, and R is the control input weight matrix;

[0043] The constraints are: x(t+k+1)=A·x(t+k)+B·u(t+k)+N(x(t+k),u(t+k)), k=0,1,…,N-1, and the physical constraints of the control input: u min ≤u(t+k)≤u max ,k=0,1,…,N-1,where u min and u max are the minimum and maximum vectors of the control input respectively;

[0044] The nonlinear dynamic model is Taylor expanded, and the first-order terms are retained to obtain the linearized model: x(t+k+1)≈A·x(t+k)+B·u(t+k)+J(t+k)·Δx(t+k), where J is the Jacobian matrix, which represents the partial derivative of the nonlinear term with respect to the state;

[0045] Based on the linearized model, construct the objective function and constraints of quadratic approximation: Among them, J approx (ΔU(t)) is the objective function of quadratic approximation, ΔU(t) is the control input increment vector, H is the Hessian matrix, H = R + B T QB; g is the gradient vector, g = B T Q(x(t+k)-x ref (t+k)).

[0046] The present invention also provides an unmanned forklift intelligent control system, the system comprising:

[0047] Perception module: Build a perception layer by deploying multi-dimensional sensors to obtain the status data, location data, and static environment feature location data of the unmanned forklift;

[0048] Positioning module: Based on the position data of the unmanned forklift and the static environment feature position data, the preset position optimization algorithm is used to correct the position data of the unmanned forklift to generate accurate positioning information;

[0049] Solution module: establish a dynamic model of the unmanned forklift according to the state data of the unmanned forklift, define an optimization problem according to the precise positioning information, combined with the dynamic model and the path planning result, and solve the optimal control sequence using a nonlinear optimization algorithm;

[0050] Control module: extracts the control input at the current moment according to the optimal control sequence, and applies it to the driving and steering systems of the unmanned forklift for intelligent control.

[0051] The present invention provides an intelligent control method and system for an unmanned forklift. The method constructs a perception layer by deploying multi-dimensional sensors to obtain state data, position data and static environment characteristic position data of the unmanned forklift; according to the position data of the unmanned forklift and the static environment characteristic position data, a preset position optimization algorithm is used to correct the position data of the unmanned forklift to generate precise positioning information; a dynamic model of the unmanned forklift is established according to the state data of the unmanned forklift, and an optimization problem is defined according to the precise positioning information, combined with the dynamic model and path planning results, and an optimal control sequence is solved by a nonlinear optimization algorithm; the control input at the current moment is extracted according to the optimal control sequence, and applied to the driving and steering systems of the unmanned forklift to perform intelligent control, and the beneficial effects produced include:

[0052] 1. High-precision positioning: The preset position optimization algorithm is used to correct the position data. By calculating the geometric deviation measurement and dynamic residual enhancement, the total cost function is formed and minimized, which enhances the system's adaptability to environmental changes and sensor noise, improves the positioning accuracy of the forklift, and ensures that it can achieve accurate navigation and positioning in a dynamic and complex storage environment;

[0053] 2. Efficient path planning and tracking control: Based on precise positioning information and the established dynamic model, combined with the path planning results, the optimal control sequence is solved by defining the optimization problem and using the nonlinear optimization algorithm. This method can plan future control inputs in advance within the prediction step length, ensuring that the forklift can travel efficiently and smoothly along the predetermined path, reducing path tracking errors, and improving the efficiency and reliability of logistics operations.

[0054] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0056] Figure 1 A flowchart of an intelligent control method for an unmanned forklift is shown as an exemplary embodiment of the present invention;

[0057] Figure 2 The figure is a schematic structural diagram of an unmanned forklift intelligent control system according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0059] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0060] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0061] Embodiment 1

[0062] An intelligent control method for unmanned forklift, such as Figure 1 As shown, including:

[0063] By deploying multi-dimensional sensors to build a perception layer, the status data, location data and static environment feature location data of the unmanned forklift can be obtained;

[0064] According to the position data of the unmanned forklift and the position data of the static environment characteristics, the position data of the unmanned forklift is corrected by using a preset position optimization algorithm to generate accurate positioning information;

[0065] A dynamic model of the unmanned forklift is established according to the state data of the unmanned forklift, an optimization problem is defined according to the precise positioning information, in combination with the dynamic model and the path planning result, and an optimal control sequence is solved using a nonlinear optimization algorithm;

[0066] The control input at the current moment is extracted according to the optimal control sequence and applied to the driving and steering systems of the unmanned forklift for intelligent control.

[0067] The present invention is further configured such that the multi-dimensional sensor includes a laser radar, a camera, an ultrasonic sensor, an inertial measurement unit and an ultra-wideband positioning base station, and the status data includes linear speed, driving torque, friction torque, angular velocity and steering angle. Specifically, in the intelligent control method of an unmanned forklift, accurately perceiving the environment and the state of the forklift itself is the basis for achieving efficient and precise control. To this end, the present invention further stipulates the composition of the multi-dimensional sensor, including a laser radar, a camera, an ultrasonic sensor, an inertial measurement unit (IMU) and an ultra-wideband (UWB) positioning base station. These sensors work together to comprehensively collect the status data, position data, and static environmental characteristic position data of the unmanned forklift. The status data includes linear speed, which indicates the speed of the forklift in a straight line and reflects the movement status of the forklift; driving torque, which indicates the torque acting on the forklift drive system and is used to control the acceleration and deceleration of the forklift; friction torque, which indicates the friction torque between the forklift tires and the ground, affects the movement stability and handling performance of the forklift; angular velocity, which indicates the rotation speed of the forklift and reflects the steering state and rotation dynamics of the forklift; steering angle, which indicates the steering angle of the forklift's front wheels, is used to control the forklift's steering behavior and affects the forklift's driving path.

[0068] The present invention is further configured to correct the position data of the unmanned forklift using a preset position optimization algorithm, including:

[0069] Starting from the initial moment, the position data of the unmanned forklift in the time series is obtained according to the time step t (x 1 (t),x 2 (t)) and static environment feature position data (l 1 (t),l 2(t)), calculate the measured distance s(t) between the unmanned forklift and the static environment feature; specifically, the static environment feature represents the coordinate position of the fixed landmark feature point in the storage environment, and the coordinate position is known. Since the position is represented by a two-dimensional plane, the calculation logic of the measured distance between the unmanned forklift and the static environment feature is the Euclidean distance;

[0070] According to the location data of the unmanned forklift (x 1 (t),x 2 (t)), static environment feature location data (l 1 (t),l 2 (t)) and the measured distance s(t) are used to calculate the geometric deviation metric of time step t; the present invention is further configured such that the calculation logic of the geometric deviation metric of time step t is: D(t)=((x 1 (t)-l 1 (t)) 2 +(x 2 (t)-l 2 (t)) 2 ) α -(s(t)) 2α , where D(t) is the geometric deviation measure at time step t, and α is the polynomial transformation order that controls the geometric difference. Specifically, the error between the current position of the unmanned forklift and the feature point of the static environment is evaluated by calculating the geometric deviation measure D(t) at time step t. The core idea is to perform a nonlinear transformation on the Euclidean distance between the actual position of the forklift and the position of the feature point, and compare it with the nonlinear transformation result of the distance s(t) measured by the sensor, so as to obtain a measure that reflects the degree of geometric deviation. By adjusting the polynomial transformation order α, the sensitivity of the deviation to different error sizes can be controlled. α is usually a positive real number greater than 0. When α>1, large errors will be amplified. When α<1, large errors are weakened, and more attention is paid to the difference between small and medium errors.

[0071] According to the calculation of the dynamic residual enhancement of time step t, the dynamic residual enhancement of all time steps is accumulated and added to obtain the total cost function; the calculation logic of the dynamic residual enhancement of time step t is: R(t) = (D(t)) 2 ·exp(δ·sin(β·s(t))), where R(t) is the dynamic residual enhancement at time step t, δ is the frequency parameter of the modulated sine function, and β is the scale parameter of the control exponential factor; the calculation logic of the total cost function is: Among them, C is the total cost function, and M is the number of time steps. Specifically, the dynamic residual enhancement R(t) is calculated based on the geometric deviation metric D(t). By introducing the exponential weighting term, the sensitivity to the error is enhanced, and the positioning optimization effect is improved. The dynamic residual enhancement R(t) of all time steps is accumulated and added to form the total cost function C. By minimizing the total cost function, the precise positioning information is obtained, and the high-precision positioning and stable control of the unmanned forklift are realized. The frequency parameter δ of the modulated sine function is selected according to the system's response requirements to dynamic changes to control the intensity of the influence of the exponential weighting. The value range is positive real numbers. The larger the δ, the more the influence of the exponential weighting is enhanced, making the residual more significant under specific conditions; the scale parameter β of the control exponential factor adjusts the frequency of the sine function to control the periodic change of the exponential weighting term. The value range is positive real numbers. The larger the β, the more the frequency of the sine function is increased, so that the exponential weighting term fluctuates more frequently in the measurement distance change.

[0072] By minimizing the total cost function, we can solve (x 1 (t),x 2 (t)) to obtain accurate positioning information. The present invention is further configured to solve (x 1 (t),x 2 (t)) to obtain precise positioning information, including:

[0073] Calculate the minimum total cost function C for the position variable x 1 (t) and x 2 The partial derivative of (t) and Specifically, By applying the total cost function C to the position variable x 1 (t) and x 2 (t) Calculate partial derivatives to obtain gradient information, which is used to guide the update direction of position variables;

[0074] Set initial estimates of location variables and And the number of iteration steps k = 0;

[0075] At each iteration k, the geometric deviation measure D is calculated (k) (t), dynamic residual enhancement R (k) (t) and partial derivatives and

[0076] According to the partial derivative and Update the position variable, Among them, η is the learning rate parameter, which is used to control the update step size; specifically, in each iteration, the position variable x is adjusted according to the current partial derivative information. 1 (t) and x 2 (t) is used to gradually reduce the value of the total cost function C. The learning rate parameter η is used to control the step size of the position variable update, which affects the convergence speed and stability of the optimization algorithm. Its value range is a positive real number less than 1.

[0077] Calculate the cost function value of the current iteration step, Determine whether the convergence condition is met|C (k+1) -C (k) |<∈, where ∈ is the preset convergence threshold;

[0078] When the change in the cost function between two consecutive iterations is less than the preset threshold ∈, the iteration process is terminated and the precise positioning information is output. By calculating partial derivatives and adopting an iterative update strategy, the system can be ensured to quickly and stably approach the optimal solution, thereby enhancing the robustness and adaptability of the system.

[0079] The present invention is further configured to establish a dynamic model of the unmanned forklift according to the state data of the unmanned forklift, define an optimization problem according to the precise positioning information, combined with the dynamic model and the path planning result, and solve the optimal control sequence using a nonlinear optimization algorithm, including:

[0080] The linear motion equation and angular motion equation of the unmanned forklift are established; the present invention is further configured such that the linear motion equation of the unmanned forklift is: Where m is the total mass of the unmanned forklift, v(t) is the linear velocity of the unmanned forklift at time t, and F d (t) is the driving torque acting on the unmanned forklift at time t, F f (t) is the friction torque acting on the forklift at time t; the angular motion equation of the unmanned forklift is: Where I is the moment of inertia of the unmanned forklift about the center of mass, ω(t) is the angular velocity of the unmanned forklift at time t, L is the wheelbase of the unmanned forklift, θ(t) is the steering angle at time t, and C f is the friction coefficient between the tire and the ground; specifically, by establishing the linear motion equation and angular motion equation of the unmanned forklift, the motion characteristics of the forklift are modeled from the dynamic level, providing an accurate mathematical basis for the subsequent intelligent control algorithm. By separately modeling linear motion and angular motion, the dynamic behavior of the forklift in the forward direction and the turning direction can be described respectively; in the linear motion equation, the linear acceleration of the unmanned forklift is determined by the difference between the driving force and the friction force, and by controlling F d (t), precise control of the forklift speed can be achieved; It indicates the steering torque generated by the combined effect of steering angle and driving force. This item indicates that when the steering angle is not zero and there is driving force, the forklift will generate a turning torque to cause it to rotate; represents the nonlinear friction torque term related to angular velocity. Its cubic relationship increases the sensitivity to friction at high angular velocity. When the speed increases, the influence of friction torque becomes more significant, suppressing excessive angular velocity and ensuring steering stability. By adjusting the steering angle θ(t) and controlling the driving force F d (t), precise control of the forklift’s steering behavior can be achieved;

[0081] Discretize the continuous time module to obtain the discretized linear motion equation and angular motion equation; the discretized linear motion equation is: After rearrangement we get: Δt is the discretized time step; the discretized angular motion equation is: After rearrangement we get: Specifically, by discretizing the continuous-time dynamics model of the unmanned forklift, the discretized linear motion equations and angular motion equations suitable for the digital control system are obtained. The core purpose of the discretization process is to convert the continuous-time differential equations into discrete-time difference equations so as to realize real-time control and calculation in the digital controller;

[0082] The dynamic model is expressed in matrix form and the state update equation is constructed; the matrix form of the dynamic model is expressed as: Where X(t) is the state vector at time t, and u(t) is the control input vector at time t. The state update equation is: X(t+1)=A·X(t)+B·u(t)+N(X(t),u(t)), where A is the state transfer matrix, B is the control input matrix, N(X(t),u(t)) is a nonlinear interference term, Specifically, by establishing a state space model of the unmanned forklift, its dynamic behavior is described to achieve precise motion control and positioning optimization. The state space model consists of a state vector, a control input vector, a state transfer matrix, a control input matrix, and nonlinear interference terms. Through this model, the motion state of the unmanned forklift at each time step t can be systematically described, and the control input u(t) can be used to adjust the forklift's linear velocity v(t) and angular velocity ω(t), thereby achieving precise navigation and control;

[0083] At each control moment, an optimization problem with a finite time step length N is defined, and the optimal control sequence is obtained by minimizing the cost function within the next N steps using a nonlinear optimization algorithm.

[0084] The present invention is further configured to define an optimization problem with a finite time step length N at each control moment, and to obtain an optimal control sequence by minimizing the cost function within the next N steps and using a nonlinear optimization algorithm, including:

[0085] Define the objective function and constraints, and set the initial control sequence U 0 (t); The present invention is further configured such that the objective function is: Among them, J(U(t)) is the objective function of the control sequence U(t), x ref (t+k) is the reference state vector, is the path planning result, Q is the state error weight matrix, and R is the control input weight matrix; the constraints are: x(t+k+1)=A·x(t+k)+B·u(t+k)+N(x(t+k),u(t+k)), k=0,1,…,N-1, and the physical constraints of the control input: u min ≤u(t+k)≤u max ,k=0,1,…,N-1,where u min and u max are the minimum and maximum vectors of the control input respectively; specifically, the objective function J(U(t)) aims to minimize the state error of the unmanned forklift and the energy consumption of the control input. By weighted summing the state error and control input of the next N time steps, an optimization goal is formed. The constraints include: state transition constraint: the next state of the unmanned forklift is determined by the current state, control input and nonlinear interference; control input constraint: the control input must be within the physical limit to ensure the safety and stable operation of the system; initialize the control sequence U 0 (t), as the starting point of the optimization algorithm, the optimal control sequence is obtained by minimizing the objective function;

[0086] At the current state point, the nonlinear dynamic model is Taylor expanded, the first-order terms are retained, and the linearized model is obtained; the nonlinear dynamic model is Taylor expanded, the first-order terms are retained, and the linearized model is obtained: x(t+k+1)≈A·x(t+k)+B·u(t+k)+J(t+k)·Δx(t+k), where J is the Jacobian matrix, which represents the partial derivative of the nonlinear term with respect to the state; specifically, the nonlinear dynamic model of the unmanned forklift is linearized to simplify the design and implementation of the control and optimization algorithms. The specific steps include Taylor expanding the nonlinear model at the current state point, retaining the first-order terms, and obtaining the linearized model. The linearized model is convenient for applying linear control theory, thereby realizing high-precision positioning and intelligent control of the unmanned forklift. The core idea of ​​this process is to use linear approximation to simplify complex nonlinear dynamic behaviors, so that the control algorithm has higher computational efficiency and feasibility while maintaining high accuracy; the Jacobian matrix is ​​a matrix that describes the linear approximation of a nonlinear function at a certain point. It is a prior art and will not be described here; by performing Taylor expansion on the nonlinear dynamic model of the unmanned forklift and retaining the first-order terms, a linearized model is obtained. This invention successfully simplifies the complex nonlinear system description, making the motion control and optimization of the unmanned forklift more efficient and accurate. The linearized model is not only suitable for advanced linear control strategies, but also significantly improves the computational efficiency and real-time response capabilities of the system;

[0087] Based on the linearized model, the quadratic approximation objective function and constraints are constructed. The sequential quadratic programming algorithm is used to iteratively solve the quadratic approximation problem and update the control increment until the objective function converges. The control input at the current moment is extracted from the optimal control sequence and applied to the dynamic model. According to the dynamic model and control input, the state of the forklift is updated. Based on the linearized model, the quadratic approximation objective function and constraints are constructed: Among them, J approx (ΔU(t)) is the objective function of quadratic approximation, ΔU(t) is the control input increment vector, H is the Hessian matrix, g is the gradient vector, Specifically, by constructing a quadratic approximation objective function and constraints based on the linearized model, the Sequential Quadratic Programming (SQP) algorithm is used to iteratively solve the quadratic approximation problem and update the control increment until the objective function converges. Finally, the control input at the current moment is extracted from the optimal control sequence and applied to the dynamic model. The state of the forklift is updated according to the dynamic model and the control input. The whole process aims to achieve high-precision positioning and intelligent control of unmanned forklifts. By constructing a quadratic approximation objective function and constraints based on the linearized model, the Sequential Quadratic Programming (SQP) algorithm is used to achieve high-precision positioning and intelligent control of unmanned forklifts in complex dynamic warehousing environments. Specifically, the nonlinear dynamic model is linearized through Taylor expansion to simplify the control and optimization problems; the quadratic approximation objective function J is constructed. approx (ΔU(t)) and related constraints make the optimization problem suitable for efficient quadratic programming methods. The SQP algorithm iteratively solves the quadratic approximation problem and gradually updates the control increment until the objective function converges, thereby obtaining the optimal control input; through a systematic optimization control method, it significantly improves the operating performance, positioning accuracy and safety of unmanned forklifts in automated logistics systems, and has broad application prospects and significant technical advantages.

[0088] Embodiment 2

[0089] See also Figure 2 , the exemplary unmanned forklift intelligent control system includes:

[0090] Perception module: Build a perception layer by deploying multi-dimensional sensors to obtain the status data, location data, and static environment feature location data of the unmanned forklift;

[0091] Positioning module: Based on the position data of the unmanned forklift and the static environment feature position data, the preset position optimization algorithm is used to correct the position data of the unmanned forklift to generate accurate positioning information;

[0092] Solution module: establish a dynamic model of the unmanned forklift according to the state data of the unmanned forklift, define an optimization problem according to the precise positioning information, combined with the dynamic model and the path planning result, and solve the optimal control sequence using a nonlinear optimization algorithm;

[0093] Control module: extracts the control input at the current moment according to the optimal control sequence, and applies it to the driving and steering systems of the unmanned forklift for intelligent control.

[0094] It should be noted that the unmanned forklift intelligent control system provided in the above embodiment and the unmanned forklift intelligent control method provided in the above embodiment belong to the same concept, and the specific way in which each module and unit performs the operation has been described in detail in the method embodiment, which will not be repeated here. In actual application, the unmanned forklift intelligent control system provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0095] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0096] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0097] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0098] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent control method for an unmanned forklift, characterized in that: include: By deploying multi-dimensional sensors to build a perception layer, the status data, location data and static environment feature location data of the unmanned forklift can be obtained; According to the position data of the unmanned forklift and the position data of the static environment characteristics, the position data of the unmanned forklift is corrected by using a preset position optimization algorithm to generate accurate positioning information; A dynamic model of the unmanned forklift is established according to the state data of the unmanned forklift, an optimization problem is defined according to the precise positioning information, in combination with the dynamic model and the path planning result, and an optimal control sequence is solved using a nonlinear optimization algorithm; The control input at the current moment is extracted according to the optimal control sequence and applied to the driving and steering systems of the unmanned forklift for intelligent control.

2. The intelligent control method for an unmanned forklift according to claim 1 is characterized in that: Multi-dimensional sensors include lidar, cameras, ultrasonic sensors, inertial measurement units and ultra-wideband positioning base stations, and status data include linear speed, driving torque, friction torque, angular velocity and steering angle.

3. The intelligent control method for an unmanned forklift according to claim 2 is characterized in that: The position data of the unmanned forklift is corrected using the preset position optimization algorithm, including: Starting from the initial moment, the position data (x1(t), x2(t)) of the unmanned forklift and the position data (l1(t), l2(t)) of the static environment feature in the time series are obtained according to the time step t, and the measured distance s(t) between the unmanned forklift and the static environment feature is calculated; Calculate the geometric deviation metric at time step t based on the position data of the unmanned forklift (x1(t), x2(t)), the static environment feature position data (l1(t), l2(t)) and the measured distance s(t); According to the calculation of the dynamic residual enhancement of time step t at time step t, the dynamic residual enhancement of all time steps is accumulated and summed to obtain the total cost function; By minimizing the total cost function and solving the value of (x1(t), x2(t)), we can obtain accurate positioning information.

4. The intelligent control method for unmanned forklift according to claim 3 is characterized in that: The calculation logic of the geometric deviation metric at time step t is: D(t) = ((x1(t)-l1(t)) 2 +(x2(t)-l2(t)) 2 ) α -(s(t)) 2α , where D(t) is the geometric deviation measure at time step t, and α is the polynomial transformation order that controls the geometric difference; The calculation logic of dynamic residual enhancement at time step t is: R(t) = (D(t)) 2 exp(δ·sin(β·s(t))), where R(t) is the dynamic residual enhancement at time step t, δ is the frequency parameter of the modulating sine function, and β is the scale parameter of the control exponential factor; The calculation logic of the total cost function is: Among them, C is the total cost function and M is the number of time steps.

5. The intelligent control method for unmanned forklift according to claim 4 is characterized in that: By minimizing the total cost function, we can solve the value of (x1(t), x2(t)) to obtain accurate positioning information, including: Calculate the partial derivatives of the minimized total cost function C with respect to the position variables x1(t) and x2(t) and Set initial estimates of location variables and And the number of iteration steps k = 0; At each iteration k, the geometric deviation measure D is calculated (k) (t), dynamic residual enhancement R (k) (t) and partial derivatives and According to the partial derivative and Update the position variable, Among them, η is the learning rate parameter, which is used to control the update step size; Calculate the cost function value of the current iteration step, Determine whether the convergence condition is met|C (k+1) -C (k) |<∈, where ∈ is the preset convergence threshold; When the change in the cost function between two consecutive iterations is less than the preset threshold ∈, the iteration process is terminated and the precise positioning information is output.

6. The intelligent control method for an unmanned forklift according to claim 2, characterized in that: A dynamic model of the unmanned forklift is established according to the state data of the unmanned forklift, an optimization problem is defined according to the precise positioning information, combined with the dynamic model and the path planning result, and an optimal control sequence is solved using a nonlinear optimization algorithm, including: Establish the linear and angular motion equations of the unmanned forklift; Discretize the continuous time module to obtain discretized linear motion equations and angular motion equations; Represent the dynamic model in matrix form and construct the state update equation; At each control moment, an optimization problem with a finite time step length N is defined, and the optimal control sequence is obtained by minimizing the cost function within the next N steps using a nonlinear optimization algorithm.

7. The intelligent control method for an unmanned forklift according to claim 6, characterized in that: The linear motion equation of the unmanned forklift is: Where m is the total mass of the unmanned forklift, v(t) is the linear velocity of the unmanned forklift at time t, and F d (t) is the driving torque acting on the unmanned forklift at time t, F f (t) is the friction torque acting on the forklift at time t; The angular motion equation of the unmanned forklift is: Where I is the moment of inertia of the unmanned forklift about the center of mass, ω(t) is the angular velocity of the unmanned forklift at time t, L is the wheelbase of the unmanned forklift, θ(t) is the steering angle at time t, and C f is the friction coefficient between the tire and the ground; The discretized linear equation of motion is: After rearrangement we get: Δt is the discretized time step; The discretized angular motion equation is: After rearrangement we get: The matrix form of the kinetic model is expressed as: Where X(t) is the state vector at time t, and u(t) is the control input vector at time t; The state update equation is: X(t+1)=A·X(t)+B·u(t)+N(X(t),u(t)), where A is the state transfer matrix, B is the control input matrix, N(X(t),u(t)) is a nonlinear interference term, 8. The intelligent control method for an unmanned forklift according to claim 7, characterized in that: At each control moment, an optimization problem with a finite time step length N is defined. By minimizing the cost function in the next N steps, the optimal control sequence is obtained using a nonlinear optimization algorithm, including: Define the objective function and constraints, and set the initial control sequence U0(t); At the current state point, the nonlinear dynamic model is Taylor expanded, the first-order terms are retained, and the linearized model is obtained; Based on the linearized model, the quadratic approximation objective function and constraints are constructed. The sequential quadratic programming algorithm is used to iteratively solve the quadratic approximation problem and update the control increment until the objective function converges. The control input at the current moment is extracted from the optimal control sequence and applied to the dynamic model. The state of the forklift is updated according to the dynamic model and the control input.

9. The intelligent control method for an unmanned forklift according to claim 8, characterized in that: The objective function is: Among them, J(U(t)) is the objective function of the control sequence U(t), x ref (t+k) is the reference state vector, is the path planning result, Q is the state error weight matrix, and R is the control input weight matrix; The constraints are: x(t+k+1)=A·x(t+k)+B·u(t+k)+N(x(t+k),u(t+k)), k=0,1,…,N-1, and the physical constraints of the control input: u min ≤u(t+k)≤u max ,k=0,1,…,N-1,where u min and u max are the minimum and maximum vectors of the control input respectively; The nonlinear dynamic model is Taylor expanded, and the first-order terms are retained to obtain the linearized model: x(t+k+1)≈A·x(t+k)+B·u(t+k)+J(t+k)·Δx(t+k), where J is the Jacobian matrix, which represents the partial derivative of the nonlinear term with respect to the state; Based on the linearized model, construct the objective function and constraints of quadratic approximation: Among them, J approx (ΔU(t)) is the objective function of quadratic approximation, ΔU(t) is the control input increment vector, H is the Hessian matrix, H = R + B T QB; g is the gradient vector, g = B T Q(x(t+k)-x ref (t+k)).

10. An unmanned forklift intelligent control system, used to implement an unmanned forklift intelligent control method according to any one of claims 1 to 9, characterized in that: include: Perception module: Build a perception layer by deploying multi-dimensional sensors to obtain the status data, location data, and static environment feature location data of the unmanned forklift; Positioning module: Based on the position data of the unmanned forklift and the static environment feature position data, the preset position optimization algorithm is used to correct the position data of the unmanned forklift to generate accurate positioning information; Solution module: establish a dynamic model of the unmanned forklift according to the state data of the unmanned forklift, define an optimization problem according to the precise positioning information, combined with the dynamic model and the path planning result, and solve the optimal control sequence using a nonlinear optimization algorithm; Control module: extracts the control input at the current moment according to the optimal control sequence, and applies it to the driving and steering systems of the unmanned forklift for intelligent control.

Images