Automatic equipment control method, computing equipment and computer readable storage medium

Abstract

The invention discloses an automatic equipment control method. The method comprises the following steps: acquiring current automatic equipment state data and environment sensing data; determining a planned path in a future prediction time window according to the automatic equipment state data and the environment perception data; according to the planned path, determining a target control instruction sequence for the automatic equipment in the prediction time window through the constructed model prediction controller; wherein the model prediction controller executes the following operations: dynamically adjusting weight parameters in a target function of the model prediction controller through a preset optimization algorithm, dividing a prediction time window into a plurality of sub-intervals by adopting a multiple shooting algorithm, and solving a control instruction sequence of each sub-interval in parallel based on the target function, according to the control instruction sequence of each subinterval, a target control instruction sequence is generated through connection constraint; and executing corresponding control operation on the automatic equipment based on the target control instruction sequence. Therefore, the stability and the safety of the automatic equipment can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of automatic equipment technology, and in particular to an automatic equipment control method, a computing device, and a computer-readable storage medium. Background Technology

[0002] In open-pit mining environments, automated equipment such as unmanned mining trucks, automated guided vehicles, and automated robots need to perform tasks such as path tracking, obstacle avoidance, and speed control in complex terrain. However, due to the variable environment in mining areas, including steep slopes, sharp bends, and soft surfaces, traditional autonomous driving methods in mining areas mainly rely on rule-based control, PID control, or experience-based path tracking algorithms. These methods suffer from poor adaptability, high computational complexity, and low control accuracy when facing complex terrain, high dynamic loads, and real-time task scheduling. Summary of the Invention

[0003] The purpose of this application is to provide an automatic equipment control method, a computing device, and a computer-readable storage medium to at least solve the problems in the related art.

[0004] To achieve the above objectives: In a first aspect, embodiments of this application provide an automatic equipment control method, including: Acquire current status data of automated equipment and environmental perception data; Based on the status data of the automated equipment and the environmental perception data, a planned path is determined within the future prediction time window; According to the planned path, the model predictive controller determines the target control command sequence for the automated equipment within the prediction time window; wherein, the model predictive controller performs the following operations: dynamically adjusts the weight parameters in the objective function of the model predictive controller through a preset optimization algorithm, and divides the prediction time window into multiple sub-intervals using a multi-shot algorithm, solves the control command sequence of each sub-interval in parallel based on the objective function, and generates the target control command sequence through connection constraints based on the control command sequence of each sub-interval; The automatic equipment performs corresponding control operations based on the target control command sequence.

[0005] In one possible implementation, generating the target control command sequence based on the control command sequence of each sub-interval includes: By processing the connection constraints through quadratic programming to integrate the control command sequences of the various sub-intervals, the globally continuous target control command sequence is determined. In one possible implementation, the step of performing corresponding control operations on the automated device based on the target control command sequence includes: In response to the target control command sequence including a direction control command, the direction control command is sent to the electronic steering system so that the electronic steering system performs a direction adjustment operation on the automatic device according to the direction control command; In response to the target control command sequence including a braking control command, the braking control command is sent to the electronic braking system so that the electronic braking system performs a braking operation on the automatic device according to the braking control command; In response to the target control command sequence including drive control commands, the drive control commands are sent to the drive control system so that the drive control system performs a speed adjustment operation on the automatic equipment according to the drive control commands.

[0006] In one possible implementation, the step of performing corresponding control operations on the automated device based on the target control command sequence further includes: In response to the detection of an abnormality in the validity of the target control command sequence, a preset safety operation mechanism is triggered; the preset safety operation mechanism includes at least one of the following operations: deceleration, emergency braking, and alarm.

[0007] In one possible implementation, the preset optimization algorithm includes at least one of the following algorithms: quantum particle swarm optimization algorithm, genetic algorithm, and simulated annealing algorithm.

[0008] In one possible implementation, the automated equipment status data includes at least one of the following: acceleration, angular velocity, velocity, and pose; The environmental perception data includes at least one of the following: road terrain data, obstacle data, and road structure data.

[0009] In one possible implementation, before determining the planned path within a future prediction time window based on the automated equipment status data and the environmental perception data, the process includes: The automatic equipment status data and the environmental perception data are preprocessed, and the preprocessing includes at least one of the following: data fusion, data alignment, and data filtering.

[0010] In one possible implementation, determining the planned path within a future prediction time window based on the automated equipment status data and the environmental perception data includes: The global reference path is optimized locally based on the status data of the automated equipment and the environmental perception data to obtain the planned path within the future prediction time window; the global reference path is obtained by global path planning based on preset tasks and map data.

[0011] In a second aspect, embodiments of this application provide a computing device, including: a processor and a memory storing a computer program, wherein when the processor runs the computer program, it implements the automatic device control method as described in any of the first aspects. Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the automatic equipment control method as described in any of the first aspects.

[0012] The automatic equipment control method, computing device, and computer-readable storage medium provided in this application include: acquiring current automatic equipment status data and environmental perception data; determining a planned path within a future prediction time window based on the automatic equipment status data and environmental perception data; determining a target control command sequence for the automatic equipment within the prediction time window based on the planned path using a constructed model predictive controller; wherein the model predictive controller performs the following operations: dynamically adjusting the weight parameters in the objective function of the model predictive controller using a preset optimization algorithm, and dividing the prediction time window into multiple sub-intervals using a multi-shot algorithm, solving the control command sequence of each sub-interval in parallel based on the objective function, and generating a target control command sequence based on the control command sequence of each sub-interval through connection constraints; and executing corresponding control operations on the automatic equipment based on the target control command sequence. Thus, in the process of automatic driving of automatic equipment based on MPC control, through parallel optimization of the multi-shot algorithm and adaptive weight adjustment of the preset optimization algorithm, high-precision trajectory tracking, robust dynamic response, and high real-time computing efficiency of the automatic equipment under complex working conditions can be achieved, effectively improving the stability and safety of the automatic equipment. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating the automatic equipment control method provided in an embodiment of this application.

[0014] Figure 2 This is a schematic diagram of the framework of the automatic equipment control method provided in the embodiments of this application.

[0015] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0016] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. In the following description relating to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements.

[0017] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0018] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, can be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Therefore, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0019] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, some steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or parts of the sub-steps or stages of other steps.

[0020] It should be noted that step designations such as S101 and S102 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S102 first and then S101, etc., but these should all be within the protection scope of this application.

[0021] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0022] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0023] See Figure 1 This application provides an automatic equipment control method, which can be executed by an automatic equipment control device provided in this application. The automatic equipment control device can be implemented in software and / or hardware, such as a processor or other computing device. The automatic equipment control method provided in this embodiment includes: Step S101: Obtain the current status data of the automated equipment and the environmental perception data.

[0024] In this embodiment, the automated equipment includes automated guided vehicles, robots, and autonomous vehicles such as driverless mining trucks, which can plan their own paths and move independently; no specific limitations are specified here. Automated equipment status data is used to characterize data related to the operational status of the automated equipment. This data may include at least one of the following: acceleration, angular velocity, velocity, and pose. Specifically, it can be collected through inertial measurement units, and / or positioning units, and / or electronic control units installed on the automated equipment. Environmental perception data is used to characterize data related to the driving environment of the automated equipment and may include at least one of the following: road terrain data, obstacle data, and road structure data. Road terrain data describes dynamic information about the physical characteristics of the ground surface and may include slope and aspect, surface material, and undulation (such as the depth or width of potholes and gullies). For example, slope and undulation can be collected by a lidar installed on the automated equipment, or surface material can be identified by a camera installed on the automated equipment. Obstacle data describes the distribution or status of obstacles affecting the safe passage of automated equipment. This data may include the type of obstacle and the distance to the obstacle. Specifically, obstacle data can be collected using millimeter-wave radar and / or cameras installed on the automated equipment. Road structure data describes static information about the road's geometric topology. This data may include lane topology data (such as lane lines and road centerlines), radius of curvature, road width, and shoulder boundaries. Specifically, lane lines, road width, and shoulder boundaries can be identified using cameras installed on the automated equipment, and the radius of curvature and road centerline can be determined using a positioning unit installed on the automated equipment in conjunction with a map showing the location of the automated equipment.

[0025] It should be noted that the automated equipment in this application embodiment may have an automated driving mode or automated driving function. For example, the automated equipment may be an automated driving mining truck (also known as an unmanned mining truck) working in the mining area.

[0026] Step S102: Determine the planned path within the future prediction time window based on the status data of the automatic equipment and the environmental perception data.

[0027] Since the automated equipment needs to be controlled automatically, a planned path within a future prediction time window needs to be determined based on the current status data of the automated equipment and environmental perception data. This planned path then guides the automated equipment's movement. The prediction time window can be set according to factors such as the automated equipment's speed and / or terrain complexity. For example, the faster the automated equipment travels, the shorter the prediction time window can be, while the slower the automated equipment travels, the longer the prediction time window can be. In this embodiment, a prediction time window of 3 to 8 seconds is used as an example.

[0028] In one embodiment, determining a planned path within a future prediction time window based on automated equipment status data and environmental perception data includes: Local trajectory optimization is performed on the global reference path based on the status data of automated equipment and environmental perception data to obtain the planned path within the future prediction time window; the global reference path is obtained by global path planning based on preset tasks and map data.

[0029] The preset task can be a driving task, a transportation task, etc., without specific limitations. Given the preset task (including starting point and destination information) and map data (i.e., map data corresponding to the area to be driven), global path planning can be performed based on the preset task and map data to obtain a global reference path from the starting point to the destination. Since the global reference path is not precise enough, for example, it cannot detect temporarily added obstacles on the road, and may not be able to control the automated equipment to drive safely based on the global reference path. Therefore, local trajectory optimization can be performed on the global reference path based on the automated equipment's status data and environmental perception data to obtain a planned path within the future prediction time window. For example, the Hybrid A* algorithm combined with map data can be used to plan a global reference path for the automated equipment from the starting point to the target point to meet the task requirements. Then, based on the global reference path, a smooth trajectory within the future prediction time window, i.e., the planned path, is generated using Bézier curves combined with a fifth-order polynomial to ensure continuous trajectory curvature and avoid steering wheel vibration. In this way, by optimizing the local trajectory of the global reference path using the status data of the automated equipment and the environmental perception data, a planned path can be obtained within the future prediction time window, which can improve the safety and efficiency of the planned path and enhance the driving stability of the automated equipment.

[0030] In one embodiment, before determining the planned path within a future prediction time window based on automated equipment status data and environmental perception data, the method includes: Preprocessing is performed on the status data of automated equipment and environmental perception data. The preprocessing includes at least one of the following: data fusion, data alignment, and data filtering.

[0031] It is understandable that the acquired automated equipment status data and environmental perception data may contain noise, missing values, or redundant information. Therefore, before determining the planned path within the future prediction time window based on the automated equipment status data and environmental perception data, preprocessing can be performed on the data to improve its reliability and accuracy. For example, for data fusion, an extended Kalman filter (EKF) can be used to fuse multi-sensor data to improve the accuracy and robustness of pose estimation in the automated equipment status data. For data alignment, time synchronization (ROS Time Synchronizer) can be used to align data collected separately by LiDAR, millimeter-wave radar, inertial measurement unit (IMU), and GPS to reduce errors caused by time deviations. For data filtering, the RANSAC algorithm can be used to remove false detection points from LiDAR, or a Butterworth low-pass filter can be used to process GPS signals to eliminate high-frequency noise. Thus, by preprocessing the automated equipment status data and environmental perception data, the reliability and accuracy of the data can be effectively improved, further enhancing the safety of automated equipment control.

[0032] Step S103: Based on the planned path, the target control command sequence for the automated equipment within the prediction time window is determined by the constructed model predictive controller. The model predictive controller performs the following operations: dynamically adjusts the weight parameters in the objective function of the model predictive controller through a preset optimization algorithm, divides the prediction time window into multiple sub-intervals using a multi-shot algorithm, solves the control command sequence of each sub-interval in parallel based on the objective function, and generates the target control command sequence through connection constraints based on the control command sequence of each sub-interval.

[0033] In this embodiment, a model predictive controller incorporating a preset optimization algorithm and a multi-shot algorithm is constructed to predict control commands for automated devices. In one implementation, the preset optimization algorithm includes at least one of the following algorithms: quantum particle swarm optimization algorithm, genetic algorithm, and simulated annealing algorithm.

[0034] The following is a brief description of the composition of the model prediction controller in the embodiments of this application, using an unmanned mining truck as the automated equipment and the quantum particle swarm optimization algorithm as the preset optimization algorithm.

[0035] Model Predictive Control (MPC) is a control method based on rolling optimization and feedback correction, suitable for complex systems with nonlinear and dynamic constraints. Unmanned driving in mining areas faces challenges such as complex terrain (slopes, potholes, gravel) and dynamic nonlinearities (vehicle drift, tire slippage). Traditional MPC suffers from high computational complexity during the solution process, easily leading to decreased real-time performance or control instability. The modeling process of the model predictive controller in this embodiment mainly includes: (1) Determine the system state equations The kinematic model of the unmanned mining truck adopts the bicycle model, as shown below:

[0036] Where (x,y) represents the location of the mining card; v is the heading angle; v is the velocity; 'a' is the front wheel steering angle (control input); 'a' is the acceleration (control input); 'L' is the wheelbase.

[0037] (2) Determine the objective function The objective of MPC is to minimize yaw error, lateral error, and control input variation. The objective function is as follows:

[0038] in, This refers to lateral error; For heading error; and To control input changes; Q1, Q2, R1, R2, R3, and R4 are weight parameters.

[0039] To address the problems of slow convergence, high computational complexity, and susceptibility to local optima inherent in traditional MPC (Multi-Process Optimization) methods that directly solve for the optimal control command sequence across the entire prediction time window using a single-step optimization approach, this application introduces a multi-shooting algorithm. This algorithm divides the optimization problem into multiple sub-intervals and performs parallel optimization within each sub-interval to reduce computational burden. The optimization process is as follows: (1) Decompose the prediction time window T into N small intervals, i.e. ; (2) Establish system state equation constraints in each interval and calculate the optimal control command sequence for that interval; (3) Introduce connection constraints to ensure that the states of adjacent intervals are consistent: ; (4) Parallel computing is used to improve the solution efficiency. After each interval is optimized independently, the overall control command sequence is optimized by quadratic programming (QP) to reduce error accumulation.

[0040] The performance of MPC control depends on the appropriate selection of weight matrices Q and R. Traditional methods rely on manual, empirical parameter tuning, but due to the complex environment of mining areas, fixed parameters are difficult to adapt to different operating conditions. This application employs a quantum particle swarm optimization (QPSO) algorithm to adaptively adjust the weight matrix, thereby improving control performance. The specific process is as follows: (1) QPSO objective function The QPSO objective function is the same as the objective function for optimizing MPC, aiming to find the optimal weight combination Q* and R* that minimizes the error. The corresponding formula is: .

[0041] (2) QPSO iterative solution The iterative solution process of QPSO mainly includes: 1) Particle initialization: Set weight parameters Q and R as the particle swarm, and initialize the particle position and velocity.

[0042] 2) Update particle positions: .

[0043] 3) Calculate the fitness function and select the optimal weight parameters: .

[0044] 4) Iterate and optimize until convergence.

[0045] Specifically, firstly, based on the kinematic model of the automated equipment, a rolling-variable model predictive controller objective function is established with the goal of minimizing yaw error, lateral error, and control input variation. Next, the weight parameters in the objective function are dynamically adjusted using a preset optimization algorithm, and a multi-shot algorithm is employed to divide the prediction time window into multiple sub-intervals. Combined with the planned path, the control command sequence for each sub-interval is solved in parallel based on the objective function. Then, based on the control command sequence of each sub-interval, a target control command sequence is generated through connection constraints. The target control command sequence may include multiple control commands of different types, such as direction control commands and drive control commands. It should be noted that the connection constraints in this embodiment can be predefined and may include direction and steering angle constraints (such as the angle range of the direction and steering angle, the range of direction and steering angle changes between adjacent sub-intervals, etc.) and acceleration constraints (such as the range of acceleration, the range of acceleration changes between adjacent sub-intervals, etc.).

[0046] In this embodiment, QPSO and the Multi-Shooting algorithm are combined to optimize MPC. Specifically, QPSO is used for global search to optimize MPC control parameters, improving the algorithm's convergence speed. Simultaneously, the multi-shot method is combined to break down the optimization problem into multiple sub-interval task planning, reducing computational burden and accelerating the optimization process. Furthermore, this embodiment uses MPC to achieve unified processing of lateral control (such as steering wheel angle) and longitudinal control (such as braking) of automated equipment, achieving coupled lateral and longitudinal MPC control to ensure the stability of automated equipment under complex operating conditions.

[0047] In one embodiment, a target control command sequence is generated based on the control command sequence of each sub-interval through connection constraints, including: By using quadratic programming to process connection constraints and integrate the control command sequences of each sub-interval, a globally continuous target control command sequence is determined.

[0048] The potential for abrupt changes or discontinuities in the boundary states of adjacent sub-intervals can affect the stability and safety of automated equipment control. For example, if the final velocity of the preceding sub-interval was 10 m / s while the initial velocity of the current sub-interval is 12 m / s, a velocity step jump may occur, potentially triggering impact loads. Therefore, quadratic programming is needed to process the connection constraints and force the boundary states of adjacent sub-intervals to be consistent. This allows the control command sequences of each sub-interval to be merged into a globally continuous target control command sequence, ensuring the stability and safety of automated equipment control.

[0049] Step S104: Perform corresponding control operations on the automatic equipment based on the target control command sequence.

[0050] Among them, the control instructions contained in the target control instruction sequence can control the automatic equipment to perform corresponding operations, so as to realize the automatic equipment driving based on the automatic equipment status data and environmental perception data.

[0051] In one embodiment, performing corresponding control operations on the automated equipment based on a target control command sequence includes: In response to a target control command sequence including a direction control command, a direction control command is sent to the electronic steering system so that the electronic steering system performs a direction adjustment operation on the automatic equipment according to the direction control command; In response to a target control command sequence including a braking control command, a braking control command is sent to the electronic braking system so that the electronic braking system performs a braking operation on the automatic equipment according to the braking control command. In response to the target control command sequence including drive control commands, drive control commands are sent to the drive control system so that the drive control system performs speed adjustment operations on the automatic equipment according to the drive control commands.

[0052] The directional control commands can include the required steering angle of the front wheels of the automated equipment, or the required steering angle of the steering wheel corresponding to the required steering angle of the front wheels. When the target control command sequence includes directional control commands, directional control commands (such as front wheel steering angle commands) can be sent to the electronic steering system, so that the electronic steering system can perform directional adjustment operations on the automated equipment according to the directional control commands, that is, control the steering wheel of the automated equipment to turn at the corresponding angle to ensure stable steering of the automated equipment. When the target control command sequence includes braking control commands, braking control commands can be sent to the electronic braking system, so that the electronic braking system can perform braking operations on the automated equipment according to the braking control commands, such as reducing the acceleration of the automated equipment to a preset acceleration threshold or controlling the automated equipment to stop. When the target control command sequence includes drive control commands, drive control commands (such as acceleration commands) can be sent to the drive control system, so that the drive control system can perform speed adjustment operations on the automated equipment according to the drive control commands, such as the drive control system adjusting the output power of the engine or motor of the automated equipment, controlling the automated equipment to accelerate, decelerate, or drive at a constant speed, etc., to optimize energy efficiency. In this way, depending on the different control commands, the corresponding control system executes the control commands to perform corresponding control operations on the automatic equipment, thereby improving the convenience and accuracy of automatic equipment control.

[0053] In one embodiment, performing corresponding control operations on the automated equipment based on a target control command sequence further includes: In response to the detection of an abnormality in the validity of the target control command sequence, a preset safety operation mechanism is triggered; the preset safety operation mechanism includes at least one of the following operations: deceleration, emergency braking, and alarm.

[0054] Before or during the execution of corresponding control operations on automated equipment based on a target control command sequence, the system can detect whether the validity of the target control command sequence is abnormal. For example, it can detect whether the validity of each control command included in the target control command sequence is abnormal. If the validity of any control command in the target control command sequence is abnormal, then the validity of the target control command sequence is determined to be abnormal. For instance, if the target control command sequence includes a front wheel steering command, and the steering angle corresponding to the front wheel steering command exceeds a preset mechanical limit, it indicates that the validity of the front wheel steering command is abnormal, and an alarm message is output. As another example, if the target control command sequence includes an acceleration command, and the acceleration value corresponding to the acceleration command exceeds a preset mechanical limit, it indicates that the validity of the acceleration command is abnormal. If a collision risk is predicted based on the distance to the obstacle, an emergency braking operation can be performed. Thus, by triggering a preset safety operation mechanism when an abnormality in the validity of the target control command sequence is detected, the safety of automated equipment control is improved.

[0055] In summary, the automatic equipment control method provided in this application reduces computational burden, improves computational efficiency and scalability, and ensures real-time control by using the Multi-Shooting method for parallel solution. The QPSO method for global search and adaptive adjustment of weight parameters reduces trajectory tracking errors, making the automatic equipment drive more accurately and smoothly, and adapting to different working conditions such as slopes and curves, thus improving stability and robustness. In other words, the automatic equipment control method provided in this application, during the automatic driving process of MPC-based control of automatic equipment, achieves high-precision trajectory tracking, robust dynamic response, and high real-time computational efficiency for automatic equipment under complex working conditions through parallel optimization of the multi-shooting algorithm and adaptive weight adjustment of the preset optimization algorithm, effectively improving the stability and safety of the automatic equipment.

[0056] Based on the same inventive concept as the foregoing embodiments, the automatic equipment control method provided in this embodiment will be illustrated by a specific example below. In this example, the automatic equipment is an unmanned mining truck (hereinafter referred to as a mining truck).

[0057] See Figure 2 The automatic equipment control method provided in this embodiment mainly includes: (1) Data collection Data acquisition primarily involves collecting environmental perception data (including road terrain data, road structure data, obstacles, etc.) and vehicle status data (including angular velocity, velocity, acceleration, etc.) from the mining area, providing reliable input data for subsequent path planning and MPC predictive control. Specifically, environmental perception data such as road structure, obstacle distribution, and driving boundaries in the mining area can be acquired through LiDAR, millimeter-wave radar, and cameras. Vehicle status data such as acceleration, angular velocity, velocity, and pose can be collected through inertial measurement units (IMU), GPS / RTK, and onboard electronic control units (ECUs) to ensure real-time monitoring of the mining truck's movement status. Furthermore, high-precision maps can be used to calibrate the mining truck's position.

[0058] (2) Data processing Considering that the collected data may contain noise, missing values, or redundant information, the collected data can be fused and optimized to improve its reliability and accuracy. For example, extended Kalman filtering (EKF) can be used to fuse multi-sensor data to improve the accuracy and robustness of pose estimation; time synchronization (ROS TimeSynchronizer) can be used to align data collected by LiDAR, millimeter-wave radar, IMU, and GPS to reduce errors caused by time deviations; the RANSAC algorithm can be used to remove false detection points in LiDAR; and a Butterworth low-pass filter can be used to process GPS signals to eliminate high-frequency noise.

[0059] (3) Trajectory planning Trajectory planning primarily involves generating safe and efficient driving paths based on the mining truck's driving tasks, environmental perception data, and vehicle status data. This includes global path planning and local trajectory optimization. Global path planning uses the Hybrid A* algorithm combined with a high-precision mining area map to plan the globally optimal path from the starting point to the destination. Local trajectory optimization, based on the global path, uses Bézier curves combined with a fifth-order polynomial to generate a smooth trajectory—the planned path—to improve driving stability.

[0060] (4) MPC Predictive Control The path planned based on the trajectory needs to output smoother and more reasonable control commands, thereby enabling the mining truck to generate a more stable and efficient trajectory. However, traditional MPC uses direct single-step optimization, which may converge slowly or even fail to solve due to the complex terrain and nonlinear dynamics of the mining area. This embodiment automatically constructs and solves an MPC control model, i.e., a model predictive controller, optimized by combining the QPSO algorithm and the Multi-Shooting algorithm. The specific implementation process of the QPSO algorithm and the Multi-Shooting algorithm can be found in the description of the aforementioned embodiment, and will not be repeated here. In this embodiment, by introducing the Multi-Shooting algorithm, the optimization time domain (i.e., the prediction time window) is divided into multiple sub-intervals, and the optimal control command sequence for each sub-interval is solved separately to reduce computational burden and improve optimization efficiency. Furthermore, when solving for control commands, the QPSO algorithm is used to adaptively adjust the weight matrices Q (state weights) and R (control input weights). Finally, the constructed model predictive controller enhances the robustness, real-time performance, and adaptability of the mining truck control.

[0061] (5) Execution of control commands The calculation results generated by the model predictive controller need to be transmitted to the mining truck through actuators to complete operations such as steering control, acceleration control, and braking control. For example, the electronic steering system (EPS) can receive the front wheel steering angle command calculated by the MPC and adjust the steering wheel angle to ensure stable steering of the mining truck; the electronic braking system (EBS) can perform precise braking according to the braking control command calculated by the MPC to ensure safe stopping or deceleration of the mining truck; the drive control system (DCS) can adjust the engine or motor power according to the drive control command calculated by the MPC to control the acceleration or constant speed of the mining truck and optimize energy efficiency.

[0062] In addition, it can detect the validity of control commands and trigger safety mechanisms in abnormal situations, such as emergency braking or switching to manual mode.

[0063] (6) Monitoring and optimization To ensure the stable operation of the mining truck in complex mining environments, this embodiment can also monitor and optimize the control of the mining truck in real time, continuously evaluate the status of the mining truck, and adjust control commands according to environmental changes.

[0064] In summary, the vehicle control method provided in the above embodiments utilizes real-time parallel optimization computation based on the Multi-Shooting method. This involves solving the MPC problem in parallel segments using the Multi-Shooting method, which reduces computational complexity and improves solution efficiency. This enables the unmanned driving system to achieve real-time trajectory optimization and control in complex mining environments. Simultaneously, QPSO is introduced for global optimization to improve trajectory tracking accuracy. This involves combining the QPSO algorithm with the MPC solution capability, optimizing control parameters through global search to avoid local optima, and improving trajectory tracking accuracy, ensuring the stable operation of the unmanned mining truck in dynamic environments. Furthermore, an adaptive weight adjustment strategy enhances system adaptability. This involves using QPSO for adaptive adjustment of MPC weights, enabling the predictive control model to dynamically optimize parameters according to different operating conditions, improving the stability and robustness of the unmanned driving system in environments with slopes, curves, and complex obstacles.

[0065] Based on the same inventive concept as the foregoing embodiments, this embodiment of the invention provides a computing device, such as... Figure 3 As shown, the computing device includes: a processor 310 and a memory 311 storing computer programs; wherein, Figure 3 The processor 310 shown in the diagram does not indicate that there is only one processor 310, but only indicates the positional relationship of the processor 310 relative to other devices. In practical applications, there can be one or more processors 310; similarly, Figure 3The memory 311 shown in the diagram has the same meaning, that is, it is only used to indicate the positional relationship of memory 311 relative to other devices. In practical applications, there can be one or more memories 311. When the processor 310 runs the computer program, the above-described automatic device control method is implemented.

[0066] The computing device may also include at least one network interface 312. The various components of the computing device are coupled together via a bus system 313. It is understood that the bus system 313 is used to implement communication between these components. In addition to a data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 313.

[0067] The memory 311 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0068] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a computer-readable storage medium storing a computer program. The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc. When the computer program stored in the computer-readable storage medium is executed by a processor, it implements the above-described automatic device control method. For the specific steps implemented when the computer program is executed by the processor, please refer to [link to relevant documentation]. Figure 1 The description of the illustrated embodiments will not be repeated here.

[0069] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0070] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An automatic equipment control method, characterized in that, The method includes: Acquire current status data of automated equipment and environmental perception data; Based on the status data of the automated equipment and the environmental perception data, a planned path is determined within the future prediction time window; According to the planned path, the model predictive controller determines the target control command sequence for the automated equipment within the prediction time window; wherein, the model predictive controller performs the following operations: dynamically adjusts the weight parameters in the objective function of the model predictive controller through a preset optimization algorithm, and divides the prediction time window into multiple sub-intervals using a multi-shot algorithm, solves the control command sequence of each sub-interval in parallel based on the objective function, and generates the target control command sequence through connection constraints based on the control command sequence of each sub-interval; The automatic equipment performs corresponding control operations based on the target control command sequence.

2. The method according to claim 1, characterized in that, The step of generating the target control command sequence based on the control command sequence of each sub-interval includes: By processing the connection constraints through quadratic programming to integrate the control command sequences of the various sub-intervals, the globally continuous target control command sequence is determined.

3. The method according to claim 1 or 2, characterized in that, The step of performing corresponding control operations on the automated equipment based on the target control command sequence includes: In response to the target control command sequence including a direction control command, the direction control command is sent to the electronic steering system so that the electronic steering system performs a direction adjustment operation on the automatic device according to the direction control command; In response to the target control command sequence including a braking control command, the braking control command is sent to the electronic braking system so that the electronic braking system performs a braking operation on the automatic device according to the braking control command; In response to the target control command sequence including drive control commands, the drive control commands are sent to the drive control system so that the drive control system performs a speed adjustment operation on the automatic equipment according to the drive control commands.

4. The method according to claim 3, characterized in that, The step of performing corresponding control operations on the automated equipment based on the target control command sequence further includes: In response to the detection of an abnormality in the validity of the target control command sequence, a preset safety operation mechanism is triggered; the preset safety operation mechanism includes at least one of the following operations: deceleration, emergency braking, and alarm.

5. The method according to claim 1, characterized in that, The preset optimization algorithm includes at least one of the following algorithms: quantum particle swarm optimization algorithm, genetic algorithm, and simulated annealing algorithm.

6. The method according to claim 1, characterized in that, The status data of the automated equipment includes at least one of the following: acceleration, angular velocity, velocity, and pose; The environmental perception data includes at least one of the following: road terrain data, obstacle data, and road structure data.

7. The method according to claim 6, characterized in that, Before determining the planned path within the future prediction time window based on the automated equipment status data and the environmental perception data, the process includes: The automatic equipment status data and the environmental perception data are preprocessed, and the preprocessing includes at least one of the following: data fusion, data alignment, and data filtering.

8. The method according to claim 6, characterized in that, The step of determining the planned path within a future prediction time window based on the automated equipment status data and the environmental perception data includes: The global reference path is optimized locally based on the status data of the automated equipment and the environmental perception data to obtain the planned path within the future prediction time window; the global reference path is obtained by global path planning based on preset tasks and map data.

9. A computing device, characterized in that, include: The processor and the memory storing a computer program implement the automatic equipment control method according to any one of claims 1 to 8 when the processor runs the computer program.

10. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the automatic equipment control method according to any one of claims 1 to 8.

Images