Intelligent control method and system for operation of rotary air magnetic ship

Abstract

The invention provides an intelligent control method and system for operation of a rotary-space magnetic ship, and the method comprises the steps: constructing a three-dimensional model of a surrounding virtual environment, fusing the three-dimensional model with imported map data, and generating a real-time updated environment model; based on the real-time updated environment model, an optimal path from the current position to the target position is planned, and obstacles are avoided; the planned path is converted into a specific control instruction to guide the running direction and speed of the air rotation magnet; the optimal path is continuously adjusted through real-time GPS positioning and environment scanning data feedback; in the running process of the air-spinning magnet, the change of the surrounding environment is continuously monitored; and when a potential collision risk is detected, the running direction is adjusted, and obstacles are avoided. The system comprises an environment model updating module, a path optimizing and adjusting module and an operation obstacle avoidance monitoring module. The technical effect of the system is improved, and the important significance of improving the environment sensing capacity, enhancing the safety, achieving accurate control, guaranteeing stable operation and the like is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of control and regulation of non-electrical variables, and in particular to an intelligent control method and system for the operation of a gyromagnetic ship. Background Art

[0002] POD powered vessels (Podded Propulsion Vessels) are vessels that use a pod propulsion system. This propulsion system integrates the motor and propeller in a rotatable pod that can be directly mounted on the outside of the hull, allowing the propeller and motor to rotate 360 ​​degrees, thereby achieving all-round propulsion and precise heading control of the ship. The heading control methods can be: full-turn propulsion, through the 360-degree rotation of the pod, the ship can achieve all-round propulsion, thereby accurately controlling the heading; power distribution, by adjusting the propulsion force and direction of different pods, complex heading control and maneuvering operations can be achieved; automatic control system, combined with GPS, laser scanning and environmental perception technology, the automatic control system can adjust the propulsion force and direction of the pod according to real-time data to achieve intelligent heading control and obstacle avoidance. However, these control methods have poor environmental perception accuracy and weak obstacle avoidance capabilities; they cannot automatically adjust the control strategy according to different environments and task requirements, resulting in poor adaptability.

[0003] Prior art 1. Application number: CN202410758928.X discloses a ship heading control method based on adaptive angular rate solution, including the following steps: real-time acquisition of the ship's heading, rudder angle and speed signal; online identification of the ship's motion equation to obtain the turning index at a specific speed and the steering index at a specific speed; dimensionless ship motion equation to obtain the dimensionless turning index and the dimensionless steering index; calculate the turning index at the real-time speed and the steering index at the real-time speed, and construct a heading state observation model to solve the adaptive angular rate; calculate the command rudder angle, and control the ship's heading according to the calculated command rudder angle. Although it is beneficial to reduce the steering frequency, reduce mechanical wear, and reduce cabin noise; but the lack of environmental perception leads to poor obstacle avoidance ability during the ship's navigation.

[0004] Prior art 2, application number: CN202411159851.0 discloses a large ship heading keeping control method based on composite function nonlinear feedback, through the difference between the preset heading and the actual heading, the first layer function expression and the second layer function expression in the composite function are obtained, and the heading difference after the second layer function in the composite function is obtained; finally, the rudder angle and the actual heading output by the controller are obtained to realize the heading keeping control of the large ship. Although it can be used for the heading keeping control of the super-large ship under the condition of considering the steering gear characteristics of the super-large ship and the wind and wave interference, the composite function nonlinear feedback technology is more robust than the simple function nonlinear feedback technology, and the adjustment time is shortened, the maximum yaw angle is reduced, the average yaw angle is reduced, the average rudder angle is reduced, and the average rudder angle change rate is shortened. At the same time, the energy consumption in the heading keeping process is reduced, and the comprehensive performance index is better, achieving the purpose of strong robustness and low energy consumption. However, its control process is relatively complicated, and higher requirements are put forward on the intelligent level of the ship's controller, which increases the navigation cost of the ship to a certain extent.

[0005] Prior art three, application number: CN202411121733.0 discloses an adaptive neural network unmanned ship heading control method with input quantization and output constraints, including: obtaining the surrounding environment and the sea conditions of other ships around, and establishing a mathematical model for the heading control of the unmanned ship; using a composite quantizer to quantize the control input in the control system, and using a linear analytical model to describe the input quantization process; based on the output constraint theory, designing the obstacle Lyapunov function to obtain the heading controller of the unmanned ship; based on the Lyapunov stability theory, it is proved that when no prior information of the quantized parameters is required, the stability of the designed adaptive neural network unmanned ship heading control system with input quantization and output constraints is stable, and all signals in the closed-loop control system are consistent and ultimately bounded. Although the heading performance of the unmanned ship can be improved. However, the adaptive adjustment of the heading is not achieved, which makes the intelligence level of the heading adjustment low on the one hand, and is not conducive to driving safety on the other hand.

[0006] At present, the existing technologies 1, 2 and 3 have poor environmental perception accuracy and weak obstacle avoidance capabilities; they cannot automatically adjust the control strategy according to different environments and task requirements, resulting in poor adaptability. Therefore, the present invention provides an intelligent control method and system for the operation of a rotating magnetic ship. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides an intelligent control method for the operation of a rotating magnetic ship, comprising the following steps:

[0008] Build a three-dimensional model of the surrounding virtual environment and generate a real-time updated environment model;

[0009] Based on the real-time updated environment model, an optimal path from the current location to the target location is planned;

[0010] When a potential collision risk is detected, the obstacle avoidance program is activated and the running direction is adjusted.

[0011] Optionally, the process of converting the planned optimal path into specific control instructions includes the following steps:

[0012] Based on the real-time updated environment model, the shortest path from the current position to the target position is calculated; the optimized path is decomposed into a series of small path segments, each of which corresponds to a control instruction;

[0013] According to the length and curvature of the path segment, the speed of the rotating air magnet on each path segment is planned; the path segment and speed planning are converted into specific control instructions and sent to the actuator of the rotating air magnet;

[0014] During the operation of the rotating magnetic field, the execution of the path and environmental changes are continuously monitored through the feedback of real-time GPS positioning and environmental scanning data; if path deviation or environmental changes are detected, the path planning and control command generation are re-performed.

[0015] Optionally, the process of calculating the shortest path from the current location to the target location includes the following steps:

[0016] Based on the real-time updated environment model, a graph structure is constructed, with the current position as the starting point and the target position as the end point;

[0017] Create a priority queue to store the nodes to be processed, and initialize the distances of all nodes to infinity and the distance of the starting point to 0; take out the node with the smallest distance from the priority queue, traverse all its adjacent nodes, and calculate the distance from the starting point through the current node to the adjacent node;

[0018] When the node taken out from the priority queue is the target location node, the algorithm stops; the initial path is generated by backtracking the parent node of each node, from the target location node to the starting point; the starting point of the initial path is used as the root node, random sampling is performed near the key point of the path, and new path nodes are generated by expanding from the nearest neighbor node to the random point direction;

[0019] The new path nodes are collided with obstacles in the environment; when the nodes in the rapidly explored random tree are close to the target position, backtracking is used to generate a new optimized path, i.e. the shortest path.

[0020] Optionally, each node represents a location, and the edge represents the connection between nodes, and is assigned corresponding weights.

[0021] Optionally, the process of calculating the distance from the starting point through the current node to the adjacent node includes the following steps:

[0022] Clarify the position of the current node and adjacent nodes; obtain the shortest known distance from the current node to the starting point;

[0023] Calculate the direct distance from the current node to the adjacent node; add the distance from the starting point to the current node and the distance from the current node to the adjacent node to get the total distance from the starting point through the current node to the adjacent node;

[0024] Compare the calculated total distance to the current distance of the neighboring nodes.

[0025] Optionally, if the total distance is less than the current distance of the adjacent node, the distance of the adjacent node is updated to the total distance, and the adjacent node is added to the priority queue; the above steps are repeated until the node taken out of the priority queue is the target position node, and the calculation stops.

[0026] Optionally, the process of generating a new path node includes the following steps:

[0027] In narrow passages at critical turning points of the path, the sampling range is expanded to capture potential paths; in straight sections of the path, the sampling range is reduced;

[0028] Use historical path data to predict the optimal sampling point; select sampling points by learning historical data of path planning;

[0029] Combined with real-time environmental perception technology, it can obtain environmental information in real time and dynamically adjust the path planning strategy; in a dynamic environment, it can respond to changes in obstacles and update path nodes in real time; it can assign path planning tasks to multiple computing nodes and accelerate the path generation process through parallel computing.

[0030] Optionally, the process of converting the path segments and velocity plans into specific control instructions includes the following steps:

[0031] Decompose the path segment into a series of key nodes and intermediate nodes, extract the coordinate information and connection relationship of each node; calculate the speed requirement of each path segment based on the length and curvature of the path segment;

[0032] According to the curvature and connection relationship of the path segment, the steering angle of each node is calculated; according to the speed planning information, the acceleration change of each path segment is calculated; according to the length of the path segment and the speed planning, the speed control instruction of each path segment is generated.

[0033] Optionally, according to the optimized steering angle instruction, the rotating air magnetic actuator performs a steering operation; according to the optimized acceleration instruction, the rotating air magnetic actuator performs an acceleration change; according to the optimized speed control instruction, the rotating air magnetic actuator performs a speed change.

[0034] The present invention provides an intelligent control system for the operation of a rotating magnetic ship, comprising:

[0035] The environment model update module is responsible for building a three-dimensional model of the surrounding virtual environment and generating a real-time updated environment model;

[0036] The path optimization and adjustment module is responsible for planning an optimal path from the current location to the target location based on the real-time updated environment model;

[0037] Run the obstacle avoidance monitoring module, which is responsible for starting the obstacle avoidance program when a potential collision risk is detected.

[0038] The data import and environment modeling of the present invention realizes the fusion of multi-source data by importing pre-stored map data such as terrain and obstacle distribution, combined with real-time sensor data, and improves the accuracy and comprehensiveness of the environment model; constructs a three-dimensional model of the surrounding virtual environment, so that the rotating air magnet can understand the surrounding environment more intuitively and comprehensively, and provide basic data for path planning and obstacle avoidance; the generated environmental model is updated in real time, and can dynamically reflect environmental changes, ensuring that the rotating air magnet always makes decisions based on the latest environmental information during operation. Path planning and control instruction generation, based on the real-time updated environmental model, path planning is carried out, and an optimal path from the current position to the target position can be planned to avoid obstacles and ensure the efficiency and safety of the path; the planned path is converted into specific control instructions to guide the running direction and speed of the rotating air magnet, and realize the seamless connection between path planning and actual operation; through the feedback of real-time GPS positioning and environmental scanning data, the optimal path is continuously adjusted to ensure the dynamic adaptability and real-time nature of the path. Environmental perception and obstacle avoidance strategy continuously monitors changes in the surrounding environment during the operation of the rotating magnetic field to ensure comprehensive perception of the environment and timely detection of potential risks. When a potential collision risk is detected, the obstacle avoidance program is activated to adjust the direction of operation and avoid obstacles to ensure the safe operation of the rotating magnetic field.

[0039] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0042] Figure 1 This is a flow chart of the intelligent control method for the operation of a rotating magnetic ship in Example 1 of the present invention;

[0043] Figure 2 A process diagram of generating a real-time updated environment model in Embodiment 2 of the present invention;

[0044] Figure 3 A process diagram of converting a planned path into specific control instructions in Embodiment 3 of the present invention;

[0045] Figure 4 A process diagram for calculating the shortest path from the current position to the target position in Embodiment 4 of the present invention;

[0046] Figure 5 A process diagram of calculating the distance from the starting point through the current node to the adjacent node in Embodiment 5 of the present invention;

[0047] Figure 6 A process diagram for generating a new path node in Embodiment 6 of the present invention;

[0048] Figure 7 A process diagram of selecting sampling points in Embodiment 7 of the present invention;

[0049] Figure 8 is a process diagram of converting path segments and speed planning into specific control instructions in Example 8 of the present invention;

[0050] Fig. 9 A process diagram of calculating the steering angle of each node, that is, calculating the acceleration change of each path segment in Embodiment 9 of the present invention;

[0051] Fig.10 is a process diagram of starting the obstacle avoidance program in embodiment 10 of the present invention;

[0052] Fig.11 This is a block diagram of the intelligent control system for the operation of a rotating magnetic ship in Example 11 of the present invention. DETAILED DESCRIPTION

[0053] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0054] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0055] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0056] Example 1: Figure 1 As shown, an embodiment of the present invention provides an intelligent control method for the operation of a gyromagnetic ship, comprising the following steps:

[0057] S100: importing pre-stored map data containing information such as terrain and obstacle distribution; initializing the operating parameters of the rotating air magnet, setting the initial position and the target position; constructing a three-dimensional model of the surrounding virtual environment, integrating it with the imported map data, and generating a real-time updated environment model;

[0058] S200: Based on the real-time updated environmental model, it performs path planning and plans an optimal path from the current position to the target position to avoid obstacles; it converts the planned path into specific control instructions to guide the running direction and speed of the rotating air magnet; it continuously adjusts the optimal path through the feedback of real-time GPS positioning and environmental scanning data;

[0059] S300: During the operation of the rotating magnetic field, the system continuously monitors changes in the surrounding environment; when a potential collision risk is detected, the system starts the obstacle avoidance program, adjusts the direction of operation, and avoids obstacles.

[0060] The working principle and beneficial effects of the above technical solution are as follows: this embodiment first imports pre-stored map data containing information such as terrain and obstacle distribution; initializes the operating parameters of the rotating magnetic field, sets the initial position and target position; constructs a three-dimensional model of the surrounding virtual environment, merges it with the imported map data, and generates a real-time updated environmental model; secondly, based on the real-time updated environmental model, performs path planning to plan an optimal path from the current position to the target position to avoid obstacles; converts the planned path into specific control instructions to guide the running direction and speed of the rotating magnetic field; continuously adjusts the optimal path through real-time GPS positioning and feedback from environmental scanning data; finally, during the operation of the rotating magnetic field, continuously monitors changes in the surrounding environment; when a potential collision risk is detected, starts the obstacle avoidance program, adjusts the running direction, and avoids obstacles. Step S100 of the above scheme is data import and environmental modeling. By importing pre-stored map data such as terrain and obstacle distribution, combined with real-time sensor data, multi-source data fusion is achieved to improve the accuracy and comprehensiveness of the environmental model; a three-dimensional model of the surrounding virtual environment is constructed, so that the rotating air magnet can understand the surrounding environment more intuitively and comprehensively, providing basic data for path planning and obstacle avoidance; the generated environmental model is updated in real time, and can dynamically reflect environmental changes, ensuring that the rotating air magnet always makes decisions based on the latest environmental information during operation. Significance achieved: Through multi-source data fusion and real-time updated environmental models, the rotating air magnet can perceive the surrounding environment more accurately and provide reliable data support for intelligent decision-making; the real-time updated environmental model can cope with environmental changes, improve the robustness and adaptability of the system, and ensure the stable operation of the rotating air magnet in complex environments. Step S200: Path planning and control instruction generation. Based on the real-time updated environment model, path planning is performed to plan an optimal path from the current position to the target position, avoid obstacles, and ensure the efficiency and safety of the path; the planned path is converted into specific control instructions to guide the running direction and speed of the rotating air magnet, so as to achieve seamless connection between path planning and actual operation; through the feedback of real-time GPS positioning and environmental scanning data, the optimal path is continuously adjusted to ensure the dynamic adaptability and real-time performance of the path. Significance achieved: Intelligent path planning can optimize path selection, reduce unnecessary detours and delays, and improve the operating efficiency of the rotating air magnet; by avoiding obstacles and dynamically adjusting the path, the safety of the rotating air magnet during operation is ensured, and the risk of collision is reduced; the path planning is converted into specific control instructions to ensure that the rotating air magnet can run accurately according to the planned path, and improve the control accuracy and stability of the system. Step S300: Environmental perception and obstacle avoidance strategy. During the operation of the rotating air magnet, the changes in the surrounding environment are continuously monitored to ensure comprehensive perception of the environment and timely detection of potential risks; when a potential collision risk is detected, the obstacle avoidance program is started to adjust the running direction, avoid obstacles, and ensure the safe operation of the rotating air magnet.Significance achieved: Through continuous monitoring and obstacle avoidance algorithms, the rotating air magnet can avoid obstacles in time during operation, thereby improving the safety of the system; the application of the obstacle avoidance algorithm enables the rotating air magnet to respond to sudden environmental changes and enhance the adaptability and flexibility of the system; through timely obstacle avoidance, the stable operation of the rotating air magnet is ensured, reducing system failures and downtime caused by collisions.

[0061] To sum up, the intelligent control method for the operation of a gyromagnetic ship in this embodiment not only improves the technical effect of the system, but also achieves important significance such as improving environmental perception capability, enhancing safety, achieving precise control and ensuring stable operation.

[0062] Example 2: Figure 2 As shown, based on Example 1, the process of generating a real-time updated environment model provided by the embodiment of the present invention includes the following steps:

[0063] S1011: processing the map data in layers according to different levels of detail to generate terrain and obstacle models of different precisions; using spatial interpolation to fill in gaps and details in the map data to generate a continuous and smooth three-dimensional spatial model; simplifying the generated three-dimensional model through an optimization algorithm to remove redundant information;

[0064] Among them, the expression for filling the gaps and details in the map data using spatial interpolation is:

[0065]

[0066] The Kriging equations are used to solve the weight coefficient λ i , which has the following form:

[0067]

[0068] Where Z(x0) represents the interpolation result at the map data position x0, Z(x i ) indicates that at the known position x in the map data i The measured value at i represents the weight coefficient, which is determined by the Kriging equations; C(x i ,x j ) is the position x i and x j The covariance function between x1,x2,…,x n is a known position, x0 is an unknown position in the map data, and interpolation is performed at the map data position; x i and x j is the index of the known location of the map data;

[0069] Get the vertex coordinates v of the 3D model i and v j; Calculate the quadratic error matrix Q for each vertex; For each pair of adjacent vertices v i and v j , calculate the merge cost E(v i ,v j ); using equation E(v i ,v j )=(v i +v j ) T Q(v i +v j ) Calculate the merging cost; select the vertex pair with the smallest merging cost to merge; update the model, remove the merged vertices, and update the quadratic error matrix Q of the relevant vertices; repeat the above steps until the predetermined simplification goal is achieved (such as the number of vertices is reduced to a certain extent);

[0070] S1012: Collect dynamic data of the current environment including real-time position and obstacle changes through real-time GPS positioning and environment scanning equipment; match and align the collected dynamic data with the pre-processed static map data;

[0071] Among them, Kalman filtering is used to fuse dynamic data and static map data to improve the accuracy and reliability of positioning. For example, in an urban environment, GPS signals may be interfered by obstructions such as tall buildings and trees, resulting in increased positioning errors. By integrating with static map data, the system can better understand the current environment and provide more accurate positioning services.

[0072]

[0073] Pk|k=(IK k H k ) k|k-1

[0074] In the formula, represents the state prediction, F k represents the state transfer matrix, B k represents the control input matrix, u k represents the control input vector, P k|k-1 represents the prediction error covariance matrix, Q k represents the process noise covariance matrix, K k represents the Kalman gain, H k represents the observation matrix, R k represents the observation noise covariance matrix, z k represents the observation vector, represents state update, Pk|k represents the updated error covariance matrix; the first step of using Kalman filtering is to predict the state, based on the state estimate at the previous moment And the state transfer matrix F k , predict the current state When predicting the state, the error covariance matrix P is also required k|k-1 , calculate the Kalman gain K k , determines the impact of new observation data on state update; using observation data z k And Kalman gain, correct the predicted state to get the final state estimate It is actually the process of matching and aligning dynamic data with static map data;

[0075] S1013: using a fusion algorithm, the dynamic data is fused with the static map data to generate a real-time updated environment model; the fusion algorithm includes steps such as data weight allocation, data smoothing processing, and conflict detection and resolution;

[0076] Among them, the Bayesian fusion equation is used to calculate the weight of each data source based on the prior probability and likelihood; the prior probability assumes that the accuracy of static map data is higher and gives a higher prior probability; the marginal probability is the overall probability of new evidence without considering the impact of the hypothesis; the posterior probability is the updated confidence in the hypothesis after considering the new evidence;

[0077] Assume there are multiple hypotheses H1, H2, ..., H n and multiple evidences E1,E2,…,E m , the following extended Bayesian formula can be used:

[0078]

[0079] Where: P(H i |E1,E2,…,E m ) means that given multiple evidences E1, E2, …, E m When H i The posterior probability; P(E1,E2,…,E m |H i )·P(H i ) means that under the assumption that H i When established, multiple pieces of evidence E1, E2, …, E m The joint probability, P(H i ) indicates the hypothesis H i The prior probability, P(E1,E2,…,E m ) represents multiple pieces of evidence E1, E2, …, E m The joint marginal probability of

[0080] Data smoothing: Use the Kalman smoothing equation to smooth dynamic data and reduce the impact of noise;

[0081] predict:

[0082]

[0083] χ k+1|k =f(χ k|k ,u k )

[0084]

[0085] renew:

[0086]

[0087] γ k+1 =h(χ k+1|k )

[0088]

[0089] smooth:

[0090]

[0091] Where: σ is the unscented transformation function, used to generate σ points, W i (m) and W i (c) is the weight of point σ, n is the dimension of the state vector; χ k|k represents the estimated value of the state at time step k, represents some transformation or update of the state estimate, which is the state vector and the covariance matrix Pk|k, χ k+1|k Indicates the estimated value of the state based on time step k at time step k+1, f(χ k|k ,u k ) represents the state transfer function, which describes how the system state transfers from one time step to the next time step, u k is the control input; represents the prior estimate of the state at time step k+1, P k+1|k represents the prior covariance matrix of the state estimate at time step k+1, Q k represents the covariance matrix of process noise; χ k+1|k represents the prior estimate of the state at time step k+1, γ k+1 represents the prediction of the measured value at time step k+1, represents the estimated value of the measurement at time step k+1, P zz,k+1 represents the covariance matrix of the measured value prediction at time step k+1, P xz,k+1represents the cross-covariance matrix between the state estimate and the measurement prediction at time step k+1, K k+1 represents the Kalman gain, which is used to weigh the weight of the predicted value and the measured value. represents the posterior estimate of the state at time step k+1, P k+1|k+1 represents the posterior covariance matrix of the state estimate at time step k+1, R k represents the covariance matrix of the measurement noise; represents the smoothed state estimate based on all available data at time step k, C k represents the smoothing gain, which is used to feed future information back to the current estimate, F k represents the state transfer matrix;

[0092] Use the least squares optimization equation to resolve conflicts between dynamic data and static map data to ensure the accuracy and consistency of the model;

[0093]

[0094] Where: y i represents the i-th measurement value, f(x i ) represents the model prediction value, and m represents the number of measured values.

[0095] The working principle and beneficial effects of the above technical solution are as follows: the present embodiment firstly processes the map data in layers according to different levels of detail to generate terrain and obstacle models of different precisions; uses spatial interpolation to fill in the gaps and details in the map data to generate a continuous and smooth three-dimensional spatial model; uses an optimization algorithm to simplify the generated three-dimensional model and remove redundant information; secondly, uses real-time GPS positioning and environmental scanning equipment to collect dynamic data of the current environment including real-time position and obstacle changes; matches and aligns the collected dynamic data with the pre-processed static map data; finally, uses a fusion algorithm to fuse the dynamic data with the static map data to generate a real-time updated environmental model; the fusion algorithm includes steps such as data weight allocation, data smoothing, and conflict detection and resolution. Step S1011 of the above solution is layered processing and model optimization. Through layered processing, terrain and obstacle models of different precisions can be generated, which enables the model to remain efficient and accurate in different application scenarios; spatial interpolation fills in the gaps in the map data to ensure the continuity and smoothness of the three-dimensional spatial model; and the optimization algorithm removes redundant information, making the model more concise and efficient. Significance: Step S1012 ensures the quality and efficiency of the basic model and provides a solid foundation for real-time updates; the environmental model not only performs well under static conditions, but also remains stable and reliable in dynamic changes. Step S1012 Dynamic data acquisition and matching: real-time GPS positioning and dynamic data collected by environmental scanning equipment provide real-time location and obstacle change information of the current environment; the matching and alignment of these dynamic data with static map data ensures the real-time and accuracy of the model. Significance: The environmental model can reflect environmental changes in real time, whether it is moving obstacles or environmental changes, they can be captured and updated in time; this is especially important for applications that require real-time environmental perception, such as autonomous driving and drone navigation. Step S1013 Data fusion and real-time update: the fusion algorithm seamlessly combines dynamic data with static map data to generate a real-time updated environmental model; data weight distribution ensures that the importance of different data sources is reasonably reflected, data smoothing reduces data noise, and conflict detection and resolution mechanisms ensure data accuracy and consistency. Significance: The model is given the ability to update in real time, so that the environmental model can continuously adapt to environmental changes, which not only improves the practicality and reliability of the model, but also provides strong support for various applications that require real-time environmental perception.

[0096] In summary, this embodiment builds an efficient, accurate and real-time updated environment model, providing solid technical support for various complex application scenarios.

[0097] Example 3: Figure 3 As shown, based on Example 1, the process of converting the planned path into a specific control instruction provided by the embodiment of the present invention includes the following steps:

[0098] S201: Calculate the shortest path from the current position to the target position based on the real-time updated environment model; decompose the optimized path into a series of small path segments, each path segment corresponds to a control instruction;

[0099] S202: planning the speed of the rotating magnetic field on each path segment according to the length and curvature of the path segment; converting the path segment and speed planning into specific control instructions, including steering angle, acceleration and speed, etc., and sending them to the actuator of the rotating magnetic field;

[0100] S203: During the operation of the rotating magnetic field, the execution of the path and environmental changes are continuously monitored through the feedback of real-time GPS positioning and environmental scanning data; if path deviation or environmental changes are detected, the path planning and control command generation are re-performed.

[0101] The working principle and beneficial effects of the above technical solution are as follows: First, based on the real-time updated environmental model, this embodiment calculates the shortest path from the current position to the target position; decomposes the optimized path into a series of small path segments, each path segment corresponds to a control instruction; secondly, according to the length and curvature of the path segment, plans the speed of the rotating air magnet on each path segment; converts the path segment and speed planning into specific control instructions, including steering angle, acceleration and speed, etc., and sends them to the actuator of the rotating air magnet; finally, during the operation of the rotating air magnet, the execution of the path and environmental changes are continuously monitored through the feedback of real-time GPS positioning and environmental scanning data; if path deviation or environmental change is detected, re-path planning and control instruction generation. Step S201 of the above scheme is path decomposition and control instruction generation, which decomposes the optimized path into a series of small path segments, each path segment corresponds to a control instruction; the decomposition method makes the path planning more refined and can better cope with subtle changes in complex environments; the control instruction corresponding to each path segment contains specific information such as steering angle, acceleration and speed, ensuring that the rotating air magnet can accurately execute path planning. Significance: By decomposing the path into small path segments, the rotating air magnet can execute each path segment more accurately and reduce the possibility of path deviation; path decomposition and control instruction generation enable the system to flexibly respond to environmental changes and adjust the operation strategy in a timely manner. Step S202 speed planning and instruction encoding, according to the length and curvature of the path segment, plan the speed of the rotating air magnet on each path segment; speed planning takes into account factors such as acceleration limitation and energy consumption optimization to ensure the operating efficiency and safety of the rotating air magnet on different path segments; convert the path segment and speed planning into specific control instructions, including steering angle, acceleration and speed, etc., and send them to the actuator of the rotating air magnet. Instruction encoding ensures that the control instructions can be accurately transmitted to the actuator. Significance: By reasonably planning the speed, the rotating air magnet can maximize the operating efficiency and reduce the operating time and energy consumption while ensuring safety; instruction encoding ensures the accurate transmission of control instructions, reduces the risk of misoperation and failure, and improves the overall reliability of the system. Step S203 real-time feedback and dynamic adjustment, through the feedback of real-time GPS positioning and environmental scanning data, constantly monitor the execution of the path and environmental changes; real-time feedback enables the system to obtain the current status and environmental information in a timely manner; if the path deviation or environmental change is detected, the system will re-plan the path and generate control instructions, and dynamic adjustment ensures that the rotating air magnet always runs along the optimal path. Significance: Real-time feedback and dynamic adjustment enable the rotating air magnet to adapt to environmental changes, adjust the operation strategy in time, and ensure the real-time and effectiveness of path planning; through dynamic adjustment, the system can respond quickly to emergencies, reduce accident risks, and improve the robustness and safety of the system.

[0102] In summary, this embodiment plays an irreplaceable technical effect in the process of converting the planned path into specific control instructions, and has important significance for the performance and reliability of the system. Path decomposition and control instruction generation improve the accuracy of path execution and the flexibility of the system; speed planning and instruction encoding optimize the operating efficiency and system reliability; real-time feedback and dynamic adjustment enhance the system's adaptability and robustness. Together, they ensure the efficient and safe operation of the gyromagnet in complex environments.

[0103] Example 4: Figure 4 As shown, based on Example 3, the process of calculating the shortest path from the current position to the target position provided by the embodiment of the present invention includes the following steps:

[0104] S2011: Based on the real-time updated environment model, including information such as obstacles and terrain, a graph structure is constructed; each node represents a location, and the edge represents the connection between nodes, and is assigned a corresponding weight; the current location is set as the starting point, and the target location is set as the end point;

[0105] S2012: Create a priority queue to store the nodes to be processed, and initialize the distances of all nodes to infinity and the distance of the starting point to 0; take out the node with the smallest distance from the priority queue (initialized as the starting point), traverse all its adjacent nodes, and calculate the distance from the starting point through the current node to the adjacent node; if the calculated distance is less than the current distance of the adjacent node, update the distance of the adjacent node and add the adjacent node to the priority queue;

[0106] S2013: When the node taken out from the priority queue is the target position node, the algorithm stops; the initial path is generated by backtracking the parent node of each node, from the target position node to the starting point; the starting point of the initial path is used as the root node, random sampling is performed near the key point of the path, and the node is expanded from the nearest neighbor node to the random point to generate a new path node;

[0107] S2014: The new path node is collided with the obstacles in the environment; if there is no collision, the new node is added to the fast exploration random tree; when the node in the fast exploration random tree is close to the target position, backtracking is used to generate a new optimized path, that is, the shortest path.

[0108] The working principle and beneficial effects of the above technical solution are as follows: This embodiment first constructs a graph structure based on a real-time updated environmental model, including information such as obstacles and terrain; each node represents a position, and the edge represents the connection between nodes, and is assigned a corresponding weight; the current position is set as the starting point, and the target position is set as the end point; secondly, a priority queue is created to store the nodes to be processed, and the distances of all nodes are initialized to infinity, and the distance of the starting point is 0; the node with the smallest distance (initially the starting point) is taken out from the priority queue, and all its adjacent nodes are traversed, and the distance from the starting point through the current node to the adjacent node is calculated. ; If the calculated distance is less than the current distance of the adjacent node, the distance of the adjacent node is updated and the adjacent node is added to the priority queue; then when the node taken out of the priority queue is the target position node, the algorithm stops; by backtracking the parent node of each node, backtracking from the target position node to the starting point, an initial path is generated; taking the starting point of the initial path as the root node, random sampling is performed near the key point of the path, and a new path node is generated from the nearest neighbor node to the random point direction; finally, the new path node is collided with the obstacles in the environment; if there is no collision, the new node is added to the fast exploration random tree. When the node in the fast exploration random tree is close to the target position, a new optimized path, i.e., the shortest path, is generated by backtracking. Step S2011 of the above scheme provides a basic framework for path planning, ensuring that path search can be systematically performed in a complex environment; through the graph structure, environmental information is systematically processed, providing a clear logical basis for path search and optimization. S2012 ensures that the node with the shortest distance is processed each time through the priority queue, so as to efficiently expand the shortest path tree and avoid unnecessary node traversal; by continuously updating the node distance, it ensures that the path search process is always carried out in the direction of the shortest path, thereby improving the efficiency and accuracy of the path search. Step S2013 generates the initial path and performs random sampling. When the node taken out from the priority queue is the target position node, the algorithm stops; by backtracking the parent node of each node, backtracking from the target position node to the starting point, the initial path is generated; with the starting point of the initial path as the root node, random sampling is performed near the key points of the path, and the new path node is generated from the nearest neighbor node to the random point direction. Significance: The initial path from the starting point to the target position is generated, which provides a basis for path optimization; random sampling increases the diversity and flexibility of the path, avoids the singleness and rigidity in path planning, and provides more possibilities for subsequent path optimization. Step S2014 ensures the safety and feasibility of the path through collision detection, avoiding potential safety hazards in path planning; by quickly exploring the expansion and backtracking of the random tree, the shortest and safest path is generated, improving the efficiency and accuracy of path planning.

[0109] In summary, this embodiment realizes the shortest path planning from the current location to the target location, which not only improves the efficiency and accuracy of path planning, but also ensures the safety and feasibility of the path; through systematic graph structure construction, efficient priority queue path search, diversified random sampling and safe collision detection, the optimal path is finally generated, which meets the various needs of path planning.

[0110] Example 5: Figure 5 As shown, based on Example 4, the process of calculating the distance from the starting point through the current node to the adjacent node provided in the embodiment of the present invention includes the following steps:

[0111] S20121: Clear the position of the current node and adjacent nodes; obtain the shortest known distance from the current node to the starting point;

[0112] S20122: Calculate the direct distance from the current node to the adjacent node; add the distance from the starting point to the current node and the distance from the current node to the adjacent node to obtain the total distance from the starting point through the current node to the adjacent node;

[0113] S20123: Compare the calculated total distance with the current distance of the adjacent node; if the total distance is less than the current distance of the adjacent node, update the distance of the adjacent node to the total distance, and add the adjacent node to the priority queue; repeat the above steps until the node taken out of the priority queue is the target position node, and the calculation stops.

[0114] The working principle and beneficial effects of the above technical solution are as follows: the present embodiment first clarifies the position of the current node and the adjacent node; obtains the known shortest distance from the current node to the starting point; secondly, calculates the direct distance from the current node to the adjacent node; adds the distance from the starting point to the current node and the distance from the current node to the adjacent node to obtain the total distance from the starting point through the current node to the adjacent node; finally, compares the calculated total distance with the current distance of the adjacent node; if the total distance is less than the current distance of the adjacent node, the distance of the adjacent node is updated to the total distance, and the adjacent node is added to the priority queue; repeats the above steps until the node taken out of the priority queue is the target position node, and the calculation stops. Step S20121 of the above scheme clarifies the position of the current node and the adjacent node; obtains the known shortest distance from the current node to the starting point, and provides basic data for distance calculation by clarifying the node position and the known shortest distance. Significance: Ensure that the starting point and current node information of the calculation process are accurate, and provide reliable data support for the steps. Step S20122 calculates the direct distance by the Euclidean distance formula, and combines the known shortest distance to accurately calculate the total distance. Significance: Ensure that the calculated total distance is accurate, providing a reliable basis for distance comparison and path update. Step S20123 ensures that the path information is always optimal by comparing and updating the distance; efficient node processing is achieved by introducing the priority queue. Significance: Ensure that the final generated path is the shortest, improving the efficiency and accuracy of path planning; by using the priority queue, the execution efficiency of the algorithm is optimized, making the path planning process more efficient.

[0115] In summary, this embodiment can accurately calculate the distance from the starting point through the current node to the adjacent node, and update the path information as needed to ensure that the final generated path is the shortest; together, efficient and accurate path planning is achieved.

[0116] Example 6: Figure 6 As shown, based on Example 4, the process of generating a new path node provided by the embodiment of the present invention includes the following steps:

[0117] S20131: In narrow passages at critical turning points of the path, expand the sampling range to capture potential paths; in straight sections of the path, reduce the sampling range;

[0118] S20132: Use historical path data to predict the optimal sampling point; select sampling points by learning historical data of path planning;

[0119] S20133: Combine real-time environmental perception technology to obtain environmental information in real time and dynamically adjust path planning strategies; in a dynamic environment, respond to changes in obstacles and update path nodes in real time; assign path planning tasks to multiple computing nodes and accelerate the path generation process through parallel computing.

[0120] The working principle and beneficial effects of the above technical solution are as follows: first, in the narrow passage at the key turning point of the path, the sampling range is expanded to capture potential paths; in the straight part of the path, the sampling range is reduced; secondly, the historical path data is used to predict the optimal sampling point; the sampling point is selected by learning the historical data of path planning; finally, the real-time environment perception technology is combined to obtain environmental information in real time and dynamically adjust the path planning strategy; in a dynamic environment, the path nodes are updated in real time in response to the changes of obstacles; the path planning tasks are assigned to multiple computing nodes, and the path generation process is accelerated through parallel computing. Step S20131 of the above scheme is adaptively adjusted to the sampling range. At the key turning point of the path (such as a narrow passage), the sampling range is expanded to capture more potential paths and avoid omissions and errors in path planning; in the straight part of the path, the sampling range is reduced to reduce unnecessary calculations and improve the efficiency of path planning. The significance achieved: by adaptively adjusting the sampling range, path planning can better adapt to the needs of different environments, whether it is a complex or simple path; while ensuring the accuracy of path planning, by reducing unnecessary calculations, the utilization of computing resources is optimized and the efficiency of the overall system is improved. Step S20132: Based on the intelligent sampling point selection of historical data, the optimal sampling point is predicted by the machine learning algorithm using the historical path data, which can select the sampling point more accurately and improve the quality of path generation; by intelligently selecting the sampling point, the number of sampling points is reduced and the efficiency of path planning is improved. Significance achieved: By learning the historical data, the path planning can select the sampling point more intelligently, reduce human intervention and improve the automation level of path planning; by intelligently selecting the sampling point, the generated path is more optimized to meet the needs of different application scenarios. Step S20133: Dynamic environment perception and distributed path planning, combined with real-time environment perception technology, can obtain environmental information in real time and dynamically adjust the path planning strategy to ensure the real-time and safety of the path; in a dynamic environment, it can quickly respond to the changes of obstacles, update the path nodes in real time and ensure the robustness of the path; assign the path planning task to multiple computing nodes, accelerate the path generation process through parallel computing, and improve the efficiency of path planning. Significance achieved: Through dynamic environment perception, path planning can better adapt to changes in the dynamic environment and improve the adaptability and flexibility of path planning; through distributed computing, the efficiency of path planning is improved to meet the path planning needs of large-scale complex environments; through real-time updating of path nodes and parallel computing, the overall performance of the system is improved to ensure the efficiency and safety of path planning.

[0121] In summary, the process of generating new path nodes in this embodiment not only improves the accuracy, efficiency and real-time performance of path planning, but also enhances the intelligence, adaptability and robustness of path planning, so that path planning can better meet the needs of different application scenarios and improve the overall performance of the system and user experience.

[0122] Example 7: Figure 7 As shown, based on Example 6, the process of selecting a sampling point provided in this embodiment of the present invention includes the following steps:

[0123] S201321: Collect a large amount of path data from past path planning tasks, including path nodes, environmental information, i.e., obstacle locations, etc.; annotate the collected data and mark key path nodes and sampling points;

[0124] S201322: Extract key features from the marked key path nodes and sampling points, such as path length, curvature, obstacle distance, i.e., environmental complexity, etc., to select the features that have the greatest impact on path planning; perform statistical analysis on the extracted features, calculate the mean, variance, i.e., correlation, and other statistical quantities of each feature, and find out the relationship between the features;

[0125] S201323: Identify common path patterns and sampling point distribution patterns in historical data through pattern recognition; select optimal sampling points based on the results of statistical analysis and pattern recognition to generate new path nodes.

[0126] The working principle and beneficial effects of the above technical solution are as follows: the present embodiment first collects a large amount of path data from past path planning tasks, including path nodes, environmental information, i.e., obstacle locations, etc.; annotates the collected data, and marks key path nodes and sampling points; secondly, extracts key features from the marked key path nodes and sampling points, such as path length, curvature, obstacle distance, i.e., environmental complexity, etc., to screen out the features that have the greatest impact on path planning; performs statistical analysis on the extracted features, calculates the mean, variance, i.e., correlation, and other statistics of each feature, and finds out the relationship between the features; finally, identifies the common path patterns and sampling point distribution patterns in historical data through pattern recognition; selects the optimal sampling points based on the results of statistical analysis and pattern recognition to generate new path nodes. Step S201321 of the above solution is data collection and annotation. By collecting a large amount of path data, the system can obtain rich historical path information, providing a solid foundation for analysis; annotating the data, especially marking key path nodes and sampling points, can help the system more accurately identify and understand important nodes in the path. Significance: It provides necessary data support for feature extraction and pattern recognition, ensuring the comprehensiveness and accuracy of the analysis; through annotation, the system can better identify the key nodes in the path, which is crucial for optimizing path planning. Step S201322 Feature extraction and statistical analysis: By extracting key features such as path length, curvature, obstacle distance, etc., the system can screen out the features that have the greatest impact on path planning, thereby improving the efficiency of path planning; calculating the mean, variance, and correlation of each feature helps the system understand the relationship between features and further optimize the path planning strategy. Significance: Through feature screening and statistical analysis, the path features can be understood more accurately, thereby optimizing path planning and reducing unnecessary calculations and resource consumption; statistical analysis helps the system understand the relationship between features, which is very important for generating more reasonable path planning strategies. Step S201323 Pattern recognition and sampling point selection: Through pattern recognition, common path patterns and sampling point distribution patterns in historical data can be discovered, thereby better predicting future path needs; according to the results of statistical analysis and pattern recognition, the optimal sampling points are selected to generate more reasonable and efficient path nodes. Significance: Pattern recognition helps the system predict future path requirements, so that path planning can be done in advance, improving the predictability and accuracy of path planning; selecting the optimal sampling points can generate more efficient path nodes, reduce the time and resource consumption of path planning, and improve overall efficiency.

[0127] In summary, the process of selecting sampling points in this embodiment realizes the optimization and efficient generation of path planning through data collection, feature extraction, statistical analysis and pattern recognition, which is of great significance for improving the accuracy and efficiency of path planning.

[0128] Example 8: Figure 8As shown, based on Example 3, the process of converting the path segment and speed planning into specific control instructions provided by the embodiment of the present invention includes the following steps:

[0129] S2021: Decompose the path segment into a series of key nodes and intermediate nodes, extract the coordinate information and connection relationship of each node; calculate the speed requirement of each path segment according to the length and curvature of the path segment;

[0130] S2022: Calculate the steering angle of each node according to the curvature and connection relationship of the path segment; calculate the acceleration change of each path segment according to the speed planning information; generate the speed control instruction of each path segment according to the length of the path segment and the speed planning;

[0131] S2023: According to the optimized steering angle instruction, the actuator of the rotating air magnet performs a steering operation; according to the optimized acceleration instruction, the actuator of the rotating air magnet performs an acceleration change; according to the optimized speed control instruction, the actuator of the rotating air magnet performs a speed change.

[0132] The working principle and beneficial effects of the above technical solution are as follows: this embodiment first decomposes the path segment into a series of key nodes and intermediate nodes, and extracts the coordinate information and connection relationship of each node; calculates the speed requirement of each path segment according to the length and curvature of the path segment; secondly, calculates the steering angle of each node according to the curvature and connection relationship of the path segment; calculates the acceleration change of each path segment according to the speed planning information; generates the speed control instruction for each path segment according to the length and speed planning of the path segment; finally, according to the optimized steering angle instruction, the actuator of the rotating air magnet performs the steering operation; according to the optimized acceleration instruction, the actuator of the rotating air magnet performs the acceleration change; according to the optimized speed control instruction, the actuator of the rotating air magnet performs the speed change. Step S2021 of the above scheme is path segment decomposition and speed requirement calculation; by decomposing the path segment into a series of key nodes and intermediate nodes, the system can more precisely control the motion trajectory of the rotating air magnet; the coordinate information and connection relationship of each node provide basic data for the calculation; according to the length and curvature of the path segment, the speed requirement of each path segment is calculated to ensure that the rotating air magnet can maintain a suitable speed on different path segments, avoiding unstable movement or inefficiency caused by too fast or too slow speed. Significance achieved: Through precise path decomposition, the rotating air magnet can more accurately follow the planned path and reduce errors; reasonable speed planning can ensure that the rotating air magnet travels at the optimal speed on different path segments, improving overall movement efficiency. Step S2022: Steering angle and acceleration calculation. According to the curvature and connection relationship of the path segment, the steering angle of each node is calculated to ensure that the rotating air magnet can smoothly transition when turning to avoid loss of control or wear caused by sharp turns. According to the speed planning information, the acceleration change of each path segment is calculated to ensure that the rotating air magnet can smoothly transition during acceleration and deceleration to avoid impact or energy waste caused by excessive acceleration changes. According to the length and speed planning of the path segment, the speed control instruction of each path segment is generated to ensure that the rotating air magnet can travel at the planned speed on the entire path. Significance achieved: Through accurate calculation of steering angle and acceleration, the rotating air magnet can remain stable during turning and speed change, reducing vibration and wear; reasonable acceleration change and speed control can reduce unnecessary energy consumption and improve the endurance of the rotating air magnet. Step S2023 executes the mechanism operation. According to the optimized steering angle instruction, the actuator of the rotating air magnet executes the steering operation to ensure that the rotating air magnet can accurately complete the turning action; according to the optimized acceleration instruction, the actuator of the rotating air magnet executes the acceleration change to ensure that the rotating air magnet can smoothly transition during the acceleration and deceleration process; according to the optimized speed control instruction, the actuator of the rotating air magnet executes the speed change to ensure that the rotating air magnet can travel at the planned speed on the entire path.Significance achieved: Through the precise operation of the actuator, the rotating air magnet can complete the task according to the planned path and speed requirements, improving the accuracy and reliability of control; smooth movement and precise control can enhance the user's operating experience and reduce operational errors or discomfort caused by inaccurate control.

[0133] In summary, this embodiment achieves precise, smooth and efficient motion control, thereby improving the overall task completion quality and user experience.

[0134] Example 9: Fig. 9 As shown, based on Example 8, the process of calculating the steering angle of each node, that is, calculating the acceleration change of each path segment, provided in the embodiment of the present invention includes the following steps:

[0135] S20221: Obtain the coordinate information and connection relationship of the key nodes and intermediate nodes of the path segment, calculate the distance and angle difference between adjacent nodes, and determine the curvature of the path segment; fit the path segment to an arc, calculate the central angle of the arc, and use the coordinate vectors of adjacent nodes to calculate the angle between the vectors; calculate the tangent angle of the curve through the control points of the Bezier curve;

[0136] S20222: Determine an initial speed and a target speed of each path segment according to the length and speed requirement of the path segment;

[0137] S20223: Use the uniform acceleration motion formula to calculate acceleration and optimize acceleration changes; use model predictive control to adjust acceleration in real time.

[0138] The working principle and beneficial effects of the above technical solution are as follows: the present embodiment first obtains the coordinate information and connection relationship of the key nodes and intermediate nodes of the path segment, calculates the distance and angle difference between adjacent nodes, and determines the curvature of the path segment; fits the path segment to a circular arc, calculates the center angle of the circular arc, and uses the coordinate vectors of adjacent nodes to calculate the angle between vectors; calculates the tangent angle of the curve through the control points of the Bezier curve; secondly, determines the initial speed and target speed of each path segment according to the length and speed requirements of the path segment; finally, uses the uniform acceleration motion formula to calculate the acceleration and optimize the acceleration change; uses model predictive control to adjust the acceleration in real time. Step S20221 of the above solution is the geometric analysis and fitting of the path segment. By obtaining the coordinate information of the key nodes and intermediate nodes of the path segment and calculating the distance and angle difference between adjacent nodes, the curvature of the path segment can be accurately determined; fits the path segment to a circular arc, calculates the center angle of the circular arc, and uses the control points of the Bezier curve to calculate the tangent angle of the curve. These operations can provide detailed geometric information of the path segment. Significance: It provides basic data for speed and acceleration calculation, ensures the accuracy of path planning, enables the robot or vehicle to travel smoothly along the predetermined path, and reduces unnecessary vibration and energy consumption. Step S20222 Speed ​​planning: Determine the initial speed and target speed of each path segment according to the length and speed requirements of the path segment, which helps to achieve a smooth transition of speed and avoid sudden acceleration or deceleration. Significance: Reasonable speed planning can improve driving comfort and safety, while optimizing energy consumption and extending the service life of the equipment. Step S20223 Acceleration calculation and optimization: Calculate the acceleration using the uniform acceleration motion formula, and adjust the acceleration in real time through model predictive control (MPC) to ensure that the acceleration changes are smooth and meet the path requirements. Significance: It ensures the dynamic performance of the vehicle or robot during driving, enabling it to respond quickly to path changes while maintaining smooth and safe operation; by optimizing acceleration changes, it can further reduce energy consumption and improve the overall efficiency of the system.

[0139] In summary, this embodiment constitutes a complete path planning and control process, which not only improves the accuracy of path following, but also optimizes the dynamic performance and energy efficiency during driving, and has important application value in the fields of autonomous driving, robot navigation, etc.

[0140] Example 10: Fig.10 As shown, based on Example 1, the process of starting the obstacle avoidance program provided by the embodiment of the present invention includes the following steps:

[0141] S301: Based on the real-time perceived environment model, the relative distance and speed between the rotating magnetic field and the obstacle are calculated to evaluate the potential collision risk; according to the severity of the collision risk, the risk is divided into low, medium and high levels;

[0142] S302: When a high risk is detected, path replanning is initiated. Based on the current environment model and the operating status of the rotating air magnetic field, a path is replanned to avoid obstacles. According to the risk level and environmental complexity, obstacle avoidance strategies are selected, such as emergency braking, lateral avoidance and detour.

[0143] S303: Convert the selected obstacle avoidance strategy into specific control instructions, and adjust the running direction and speed of the rotating magnetic field in real time.

[0144] The working principle and beneficial effects of the above technical solution are as follows: This embodiment first calculates the relative distance and speed between the rotating air magnet and the obstacle based on the real-time perceived environmental model to evaluate the potential collision risk; according to the severity of the collision risk, the risk is divided into low, medium and high levels; secondly, when a high risk is detected, the path replanning is started, and a path to avoid obstacles is replanned based on the current environmental model and the operating status of the rotating air magnet; according to the risk level and environmental complexity, an obstacle avoidance strategy is selected, such as emergency braking, lateral avoidance and detour, etc.; finally, the selected obstacle avoidance strategy is converted into a specific control instruction to adjust the running direction and speed of the rotating air magnet in real time. Step S301 of the above scheme is collision risk assessment. Through the real-time perceived environmental model, the relative distance and speed between the rotating air magnet and the obstacle are accurately calculated to ensure the accuracy of the risk assessment; according to the severity of the collision risk, the risk is divided into low, medium and high levels, providing a clear basis for the selection of obstacle avoidance strategies. Significance: Through accurate risk assessment, potential collision risks can be identified in advance, providing a time window for taking effective obstacle avoidance measures, significantly improving the operational safety of the rotating air magnet; the division of risk levels enables the system to adopt corresponding obstacle avoidance strategies according to different risk levels, optimize the decision-making process, and improve obstacle avoidance efficiency. Step S302 path replanning and strategy selection, based on the current environmental model and the operating status of the rotating air magnet, the path is replanned in real time to ensure that the planned path can avoid obstacles; according to the risk level and environmental complexity, appropriate obstacle avoidance strategies are selected, such as emergency braking, lateral avoidance, detour, etc., to ensure the flexibility and efficiency of obstacle avoidance. Significance: Through dynamic path planning and multi-strategy selection, the rotating air magnet can flexibly respond to various complex environments and ensure that the optimal obstacle avoidance path can be found in different situations; reasonable strategy selection can reduce unnecessary obstacle avoidance actions, improve the operating efficiency of the rotating air magnet, and ensure that it can avoid obstacles quickly and smoothly. Step S303 generates control instructions, converts the selected obstacle avoidance strategy into specific control instructions, adjusts the running direction and speed of the rotating air magnet in real time, and ensures that it can avoid obstacles smoothly and quickly; through the closed-loop feedback mechanism, the obstacle avoidance effect is monitored in real time, and the control instructions are further fine-tuned according to the actual operation conditions to ensure the accuracy and stability of the obstacle avoidance process. Significance: Through real-time control adjustment, the rotating air magnet can accurately execute the obstacle avoidance strategy to ensure smooth and safe operation in complex environments; the introduction of the feedback mechanism enables the system to monitor the obstacle avoidance effect in real time, adjust the control instructions in time, and improve the stability and reliability of the obstacle avoidance process.

[0145] In summary, the obstacle avoidance program of the rotating air magnet in this embodiment can not only evaluate the collision risk in real time and accurately, but also flexibly select and execute obstacle avoidance strategies to ensure that it can operate efficiently and safely in complex environments. The obstacle avoidance program not only improves the operating safety of the rotating air magnet, but also enhances its reliability and adaptability in practical applications, and has important technical significance and application value.

[0146] Example 11: Fig.11 As shown, based on the embodiments 1 to 10, the intelligent control system for the operation of a gyromagnetic ship provided by the embodiment of the present invention comprises:

[0147] The environment model update module is responsible for importing pre-stored map data containing information such as terrain and obstacle distribution; initializing the operating parameters of the rotating air magnetic field, setting the initial position and target position; building a three-dimensional model of the surrounding virtual environment, integrating it with the imported map data, and generating a real-time updated environment model;

[0148] The path optimization and adjustment module is responsible for path planning based on the real-time updated environmental model, planning an optimal path from the current position to the target position to avoid obstacles; converting the planned path into specific control instructions to guide the running direction and speed of the rotating air magnet; and continuously adjusting the optimal path through real-time GPS positioning and environmental scanning data feedback;

[0149] The obstacle avoidance monitoring module is responsible for continuously monitoring changes in the surrounding environment during the operation of the rotating magnetic field; when a potential collision risk is detected, the obstacle avoidance program is started to adjust the running direction and avoid obstacles.

[0150] The working principle and beneficial effects of the above technical solution are as follows: the environmental model updating module of this embodiment imports pre-stored map data containing information such as terrain and obstacle distribution; initializes the operating parameters of the rotating magnetic field, sets the initial position and target position; constructs a three-dimensional model of the surrounding virtual environment, integrates it with the imported map data, and generates a real-time updated environmental model; the path optimization and adjustment module performs path planning based on the real-time updated environmental model, and plans an optimal path from the current position to the target position to avoid obstacles; converts the planned path into specific control instructions to guide the running direction and speed of the rotating magnetic field; continuously adjusts the optimal path through real-time GPS positioning and feedback from environmental scanning data; runs the obstacle avoidance monitoring module during the operation of the rotating magnetic field to continuously monitor changes in the surrounding environment; when a potential collision risk is detected, starts the obstacle avoidance program, adjusts the running direction, and avoids obstacles. The environmental model update module of the above scheme realizes the fusion of multi-source data by importing pre-stored map data such as terrain and obstacle distribution, combined with real-time sensor data, to improve the accuracy and comprehensiveness of the environmental model; constructs a three-dimensional model of the surrounding virtual environment, so that the rotating air magnet can understand the surrounding environment more intuitively and comprehensively, and provide basic data for subsequent path planning and obstacle avoidance; the generated environmental model is updated in real time, and can dynamically reflect environmental changes, ensuring that the rotating air magnet always makes decisions based on the latest environmental information during operation. Significance achieved: Through multi-source data fusion and real-time updated environmental models, the rotating air magnet can perceive the surrounding environment more accurately and provide reliable data support for intelligent decision-making; the real-time updated environmental model can cope with environmental changes, improve the robustness and adaptability of the system, and ensure the stable operation of the rotating air magnet in complex environments. The path optimization and adjustment module performs path planning based on the real-time updated environmental model. It can plan an optimal path from the current position to the target position, avoid obstacles, and ensure the efficiency and safety of the path; convert the planned path into specific control instructions to guide the running direction and speed of the rotating air magnet, and realize the seamless connection between path planning and actual operation; through the feedback of real-time GPS positioning and environmental scanning data, the optimal path is continuously adjusted to ensure the dynamic adaptability and real-time nature of the path. Significance achieved: Intelligent path planning can optimize path selection, reduce unnecessary detours and delays, and improve the operating efficiency of the rotating air magnet; by avoiding obstacles and dynamically adjusting the path, the safety of the rotating air magnet during operation is ensured, and the risk of collision is reduced; the path planning is converted into specific control instructions to ensure that the rotating air magnet can run accurately according to the planned path, and improve the control accuracy and stability of the system. During the operation of the rotating air magnet, the obstacle avoidance monitoring module continuously monitors the changes in the surrounding environment to ensure a comprehensive perception of the environment and timely discover potential risks; when a potential collision risk is detected, the obstacle avoidance program is started to adjust the running direction, avoid obstacles, and ensure the safe operation of the rotating air magnet.Significance achieved: Through continuous monitoring and obstacle avoidance algorithms, the rotating air magnet can avoid obstacles in time during operation, thereby improving the safety of the system; the application of the obstacle avoidance algorithm enables the rotating air magnet to respond to sudden environmental changes and enhance the adaptability and flexibility of the system; through timely obstacle avoidance, the stable operation of the rotating air magnet is ensured, reducing system failures and downtime caused by collisions.

[0151] To sum up, the intelligent control system for rotating magnetic ship operation in this embodiment not only improves the technical effect of the system, but also achieves important significance such as improving environmental perception ability, enhancing safety, realizing precise control and ensuring stable operation.

[0152] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of equivalent technologies of the present invention, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent control method for the operation of a rotating magnetic ship, characterized in that: The following steps are involved: Build a three-dimensional model of the surrounding virtual environment and generate a real-time updated environment model; Based on the real-time updated environment model, an optimal path from the current location to the target location is planned; When a potential collision risk is detected, the obstacle avoidance program is activated and the running direction is adjusted.

2. The intelligent control method for the operation of a rotating magnetic ship according to claim 1, characterized in that: The process of converting the planned optimal path into specific control instructions includes the following steps: Based on the real-time updated environment model, the shortest path from the current position to the target position is calculated; the optimized path is decomposed into a series of small path segments, each of which corresponds to a control instruction; According to the length and curvature of the path segment, the speed of the rotating air magnet on each path segment is planned; the path segment and speed planning are converted into specific control instructions and sent to the actuator of the rotating air magnet; During the operation of the rotating magnetic field, the execution of the path and environmental changes are continuously monitored through the feedback of real-time GPS positioning and environmental scanning data; if path deviation or environmental changes are detected, the path planning and control command generation are re-performed.

3. The intelligent control method for the operation of a rotating magnetic ship according to claim 2, characterized in that: The process of calculating the shortest path from the current location to the target location includes the following steps: Based on the real-time updated environment model, a graph structure is constructed, with the current position as the starting point and the target position as the end point; Create a priority queue to store the nodes to be processed, and initialize the distances of all nodes to infinity and the distance of the starting point to 0; take out the node with the smallest distance from the priority queue, traverse all its adjacent nodes, and calculate the distance from the starting point through the current node to the adjacent node; When the node taken out from the priority queue is the target position node, the algorithm stops; the initial path is generated by backtracking the parent node of each node and backtracking from the target position node to the starting point; Taking the starting point of the initial path as the root node, random sampling is performed near the key points of the path, and new path nodes are generated by expanding from the nearest neighbor node to the random point. The new path nodes are collided with obstacles in the environment; when the nodes in the rapidly explored random tree are close to the target position, backtracking is used to generate a new optimized path, i.e. the shortest path.

4. The intelligent control method for the operation of a rotating magnetic ship according to claim 3, characterized in that: Each node represents a location, and the edge represents the connection between nodes, and is assigned corresponding weights.

5. The intelligent control method for the operation of a rotating magnetic ship according to claim 3, characterized in that: The process of calculating the distance from the starting point through the current node to the adjacent node includes the following steps: Clarify the position of the current node and adjacent nodes; obtain the shortest known distance from the current node to the starting point; Calculate the direct distance from the current node to the adjacent node; add the distance from the starting point to the current node and the distance from the current node to the adjacent node to get the total distance from the starting point through the current node to the adjacent node; Compare the calculated total distance to the current distance of the neighboring nodes.

6. The intelligent control method for the operation of a rotating magnetic ship according to claim 5, characterized in that: If the total distance is less than the current distance of the adjacent node, the distance of the adjacent node is updated to the total distance, and the adjacent node is added to the priority queue; repeat the above steps until the node taken out of the priority queue is the target position node, and the calculation stops.

7. The intelligent control method for the operation of a rotating magnetic ship according to claim 3, characterized in that: The process of generating a new path node includes the following steps: In narrow passages at critical turning points of the path, the sampling range is expanded to capture potential paths; in straight sections of the path, the sampling range is reduced; Use historical path data to predict the optimal sampling point; select sampling points by learning historical data of path planning; Combined with real-time environmental perception technology, it can obtain environmental information in real time and dynamically adjust the path planning strategy; In a dynamic environment, the path nodes are updated in real time in response to changes in obstacles; the path planning tasks are assigned to multiple computing nodes, and the path generation process is accelerated through parallel computing.

8. The intelligent control method for the operation of a rotating magnetic ship according to claim 3, characterized in that: The process of converting path segments and velocity plans into specific control instructions includes the following steps: Decompose the path segment into a series of key nodes and intermediate nodes, extract the coordinate information and connection relationship of each node; calculate the speed requirement of each path segment based on the length and curvature of the path segment; Calculate the steering angle of each node based on the curvature and connectivity of the path segments; According to the speed planning information, the acceleration change of each path segment is calculated; according to the length and speed planning of the path segment, the speed control instruction of each path segment is generated.

9. The intelligent control method for the operation of a rotating magnetic ship according to claim 8, characterized in that: According to the optimized steering angle instruction, the actuator of the rotating air magnet performs the steering operation; according to the optimized acceleration instruction, the actuator of the rotating air magnet performs the acceleration change; according to the optimized speed control instruction, the actuator of the rotating air magnet performs the speed change.

10. An intelligent control system for rotating magnetic ship operation, characterized in that: Include: The environment model update module is responsible for building a three-dimensional model of the surrounding virtual environment and generating a real-time updated environment model; The path optimization and adjustment module is responsible for planning an optimal path from the current location to the target location based on the real-time updated environment model; Run the obstacle avoidance monitoring module, which is responsible for starting the obstacle avoidance program when a potential collision risk is detected.

Images