Moving trajectory monitoring system, method, device and equipment for intelligent picking and hanging unmanned vehicle, storage medium and program product

Abstract

The invention relates to a running track monitoring system, method and device for an intelligent picking and hanging unmanned vehicle, computer equipment, a readable storage medium and a program product, and relates to the technical field of running track monitoring. According to the invention, the dynamic environment adaptability of picking and hanging the unmanned vehicle can be improved. The system comprises an environment field intensity topological mapping subsystem which is used for generating a dynamic field intensity topological graph according to dynamic field intensity nodes; the track potential energy evolution prediction subsystem is used for determining the potential energy accumulation consumption and the field intensity disturbance propagation trend of each path when the intelligent picking and hanging unmanned vehicle moves according to the potential energy difference, and generating a potential energy track prediction cloud according to the potential energy accumulation consumption and the field intensity disturbance propagation trend; the collaborative field resonance optimization subsystem is used for injecting a micro-regulation signal to a target topological node through a reverse field excitation generator according to the existence condition of a target area so as to change environment field intensity distribution; and according to the changed environment field intensity distribution, guiding the intelligent picking and hanging unmanned vehicle to carry out natural form separation or spontaneous track adjustment.

Description

Technical Field

[0001] This application relates to the field of operational trajectory monitoring technology, and in particular to an operational trajectory monitoring system, method, device, computer equipment, computer-readable storage medium, and computer program product for intelligent detachable unmanned vehicles. Background Technology

[0002] With the rapid development of intelligent manufacturing and smart logistics, unmanned vehicles are increasingly being used in warehousing, ports, and factories. Since unmanned vehicles frequently need to perform cargo attaching and unattaching operations, accurate monitoring of their operating trajectories is one of the core technologies for ensuring operational safety and efficiency.

[0003] Traditional autonomous vehicle systems often rely on preset paths or simple environmental perception, considering only geometric paths while ignoring the influence of the physical field of the environment. Multi-vehicle trajectory planning relies on centralized scheduling or fixed avoidance rules, resulting in poor adaptability to dynamic environments and difficulty in meeting the high-precision trajectory tracking requirements in dynamic scenarios. Summary of the Invention

[0004] Based on this, it is necessary to provide a system, method, device, computer equipment, computer-readable storage medium, and computer program product for monitoring the operating trajectory of an intelligent unmanned vehicle that can be attached and detached, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a trajectory monitoring system for an intelligent detachable unmanned vehicle, the system comprising: an environmental field strength topology mapping subsystem, a trajectory potential energy evolution prediction subsystem, and a cooperative field resonance optimization subsystem; the trajectory potential energy evolution prediction subsystem is communicatively connected to the environmental field strength topology mapping subsystem and the cooperative field resonance optimization subsystem, respectively.

[0006] The environmental field strength topology mapping subsystem is used to acquire multi-source heterogeneous physical signals generated by the intelligent detachable unmanned vehicle during operation, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes.

[0007] The trajectory potential energy evolution prediction subsystem is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it is moving based on the potential energy difference; and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and the field strength disturbance propagation trend.

[0008] The cooperative field resonance optimization subsystem is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through a reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

[0009] In one embodiment, the cooperative field resonance optimization subsystem includes: a predictive cloud topology projection component, a field interference resonance detection component, and a reverse field modulation component;

[0010] The predicted cloud topology projection component is used to map the field strength region of the cloud predicted by the potential energy trajectory back to the topology node, generate a spatiotemporal projection topology map, and superimpose node load values ​​and region motion vectors on the dynamic field strength topology map.

[0011] The field interference resonance detection component is used to select a key transmission path connecting the motion direction of the intelligent unmanned vehicles according to the spatiotemporal projection topology map when there are overlapping nodes in the projection areas of the two intelligent unmanned vehicles and the intersection of the time windows is not empty; and generate an interference resonance spectrum according to the key transmission path.

[0012] The reverse field modulation component is used to extract the original frequency domain features, attenuation gradient, and path node signal strength of conflict nodes based on the node parameters of the interference resonance spectrum and the dynamic field strength topology map; generate an inverse modulation signal based on the original frequency domain features and the attenuation gradient, and generate a resonance enhancement signal based on the path node signal strength; generate a field modulation instruction set based on the inverse modulation signal and the resonance enhancement signal; the field modulation instruction set is used to guide the intelligent detachment unmanned vehicle to perform natural shape separation or spontaneous trajectory adjustment.

[0013] In one embodiment, the field interference resonance detection component includes: a spatiotemporal conflict sub-component, a motion path coupling sub-component, and a path efficiency evaluation sub-component;

[0014] The spatiotemporal conflict sub-component is used to detect whether there is spatiotemporal overlap of multiple vehicles in the spatiotemporal projection topology map. If there is spatiotemporal overlap of multiple vehicles, a conflict intensity factor is calculated based on the spatiotemporal overlap of multiple vehicles. A conflict node tag set is generated based on the spatial location of the intelligent detachable unmanned vehicle, the associated vehicle identifier, and the conflict intensity factor.

[0015] The motion path coupling sub-component is used to extract the main motion vector of the intelligent detaching and attaching unmanned vehicle based on the spatiotemporal projection topology map; generate key transmission paths based on the main motion vector through vector coherence extension; and generate a multi-vehicle coupling path set of the intelligent detaching and attaching unmanned vehicle based on the key transmission paths.

[0016] The path efficiency evaluation sub-component is used to calculate the path efficiency value for each path based on the multi-vehicle coupled path set and the spatiotemporal projection topology map. If the efficiency value is less than a preset threshold and the average load value of the path is not less than the average load value of the three-hop neighborhood surrounding the path, then a bottleneck path tag set is generated based on the conflict node tag set.

[0017] In one embodiment, the path efficiency evaluation sub-component includes: a path conduction resistance generation module, an efficiency field strength coupling module, and a neighborhood load balancing detection module;

[0018] The path conduction resistance generation module is used to extract the load value of each node sequentially along the path node sequence according to the multi-vehicle coupled path set and the spatiotemporal projection topology map, calculate the conduction resistance product through the resistance accumulator, and generate a path resistance feature set based on the conduction resistance product;

[0019] The efficiency field strong coupling module is used to calculate the path efficiency index based on the path resistance feature set, by using the conduction resistance product and the total number of path nodes, and to generate an efficiency field intensity index based on the path efficiency index.

[0020] The neighborhood load balancing detection module is used to determine the path average load value based on the efficiency field emphasis table and the spatiotemporal projection topology map; obtain the calculated neighborhood average load value; and generate a load deviation identifier set based on the path average load value and the calculated neighborhood average load value.

[0021] In one embodiment, the neighborhood load balancing detection module includes: a path load equivalent transformation submodule, a topology neighborhood wavefront expansion submodule, and a neighborhood load agglomeration submodule;

[0022] The path load equivalent transformation submodule is used to generate a path equivalent load set according to the efficiency field emphasis table and the resistance product-load equivalence law.

[0023] The topological neighborhood wavefront extension submodule is used to initiate third-order wavefront propagation starting from each node in the path based on the path equivalent load set, and to collect a pure neighborhood pool formed by all third-order nodes; and to generate a path neighborhood node library based on the pure neighborhood pool.

[0024] The neighborhood load agglomeration submodule is used to apply agglomeration operators to the load values ​​of all nodes in the pure neighborhood pool through the path neighborhood node library to generate a neighborhood load feature table.

[0025] In one embodiment, the neighborhood load agglomeration submodule includes: a neighborhood node load agglomeration unit, a spatial scale normalization unit, and a load feature binding unit;

[0026] The neighborhood node load aggregation unit is used to extract the load value of each node in the pure neighborhood pool based on the node load values ​​of the path neighborhood node library and the spatiotemporal projection topology graph, generate a neighborhood load product based on the load value through a load homogeneous coupler, and form a neighborhood load product set.

[0027] The spatial scale normalization unit is used to obtain the average neighborhood load value based on the neighborhood load product set and the total number of nodes in the pure neighborhood pool, using the load product-mean equivalence law; and to generate a normalized neighborhood load set based on the average neighborhood load value.

[0028] The load feature binding unit is used to bind the average load value of the neighborhood with the corresponding path identifier based on the normalized neighborhood load set, and add the neighborhood node size as a spatial scale reference to generate the neighborhood load feature table.

[0029] Secondly, this application also provides a method for monitoring the operating trajectory of an intelligent unmanned vehicle, applied to an intelligent unmanned vehicle operating trajectory monitoring system, the method comprising:

[0030] The system acquires multi-source heterogeneous physical signals generated during the operation of the intelligent unmanned vehicle, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes.

[0031] The difference in environmental field strength between adjacent nodes in the dynamic field strength topology is quantified into a potential energy difference; the potential energy accumulation and field strength disturbance propagation trend of each path of the intelligent unmanned vehicle during movement are determined based on the potential energy difference, and a potential energy trajectory prediction cloud is generated based on the potential energy accumulation and field strength disturbance propagation trend.

[0032] The potential energy trajectory prediction cloud is superimposed on the dynamic field strength topology map, and the existence of the target area is detected. Based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution. Based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

[0033] Thirdly, this application also provides a trajectory monitoring device for an intelligent unmanned vehicle, comprising:

[0034] The topology mapping module is used to acquire multi-source heterogeneous physical signals generated during the operation of the intelligent detachable unmanned vehicle, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes.

[0035] The trajectory prediction module is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it moves based on the potential energy difference, and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and the field strength disturbance propagation trend.

[0036] The resonance optimization module is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

[0037] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0038] The system acquires multi-source heterogeneous physical signals generated during the operation of an intelligent unmanned vehicle (UAV), including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances. It then fuses these signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes using this model, and generates a dynamic field strength topology map based on these nodes. The system quantifies the environmental field strength differences between adjacent nodes in the dynamic field strength topology map as potential energy differences. Based on these potential energy differences, it determines the cumulative potential energy consumption and field strength disturbance propagation trend of each path of the intelligent UAV during its movement, and generates a potential energy trajectory prediction cloud based on these trends. The potential energy trajectory prediction cloud is then superimposed onto the dynamic field strength topology map, and the existence of target areas is detected. Based on the existence of the target areas, a micro-adjustment signal is injected into the target topology nodes via a reverse field excitation generator to change the environmental field strength distribution. Finally, based on the changed environmental field strength distribution, the system guides the intelligent UAV to perform natural morphological separation or spontaneous trajectory adjustment.

[0039] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] The system acquires multi-source heterogeneous physical signals generated during the operation of an intelligent unmanned vehicle (UAV), including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances. It then fuses these signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes using this model, and generates a dynamic field strength topology map based on these nodes. The system quantifies the environmental field strength differences between adjacent nodes in the dynamic field strength topology map as potential energy differences. Based on these potential energy differences, it determines the cumulative potential energy consumption and field strength disturbance propagation trend of each path of the intelligent UAV during its movement, and generates a potential energy trajectory prediction cloud based on these trends. The potential energy trajectory prediction cloud is then superimposed onto the dynamic field strength topology map, and the existence of target areas is detected. Based on the existence of the target areas, a micro-adjustment signal is injected into the target topology nodes via a reverse field excitation generator to change the environmental field strength distribution. Finally, based on the changed environmental field strength distribution, the system guides the intelligent UAV to perform natural morphological separation or spontaneous trajectory adjustment.

[0041] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0042] The system acquires multi-source heterogeneous physical signals generated during the operation of an intelligent unmanned vehicle (UAV), including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances. It then fuses these signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes using this model, and generates a dynamic field strength topology map based on these nodes. The system quantifies the environmental field strength differences between adjacent nodes in the dynamic field strength topology map as potential energy differences. Based on these potential energy differences, it determines the cumulative potential energy consumption and field strength disturbance propagation trend of each path of the intelligent UAV during its movement, and generates a potential energy trajectory prediction cloud based on these trends. The potential energy trajectory prediction cloud is then superimposed onto the dynamic field strength topology map, and the existence of target areas is detected. Based on the existence of the target areas, a micro-adjustment signal is injected into the target topology nodes via a reverse field excitation generator to change the environmental field strength distribution. Finally, based on the changed environmental field strength distribution, the system guides the intelligent UAV to perform natural morphological separation or spontaneous trajectory adjustment.

[0043] The aforementioned intelligent unmanned vehicle trajectory monitoring system, method, device, computer equipment, computer-readable storage medium, and computer program products, through multi-source heterogeneous physical signal fusion technology, transform complex physical quantities such as non-visible frequency radiation and micro-vibration waves into a calculable environmental field strength topology map, realizing three-dimensional dynamic quantitative modeling of the operating environment; the signal strength, frequency domain characteristics, and other parameters recorded by each discrete node construct a spatial field strength distribution database accurate to the centimeter level. Based on potential energy field theory, the field strength difference is quantified into a calculable potential energy gradient, and the traditional path planning is upgraded to a prediction system containing spatiotemporal probability weights through a probabilistic cloud algorithm; the output in the form of a heatmap not only predicts the position coordinates, but also reflects the probability of motion trends within multiple future time windows through density distribution, making the prediction results have temporal continuity and spatial coverage. This application utilizes a distributed control mechanism based on the field resonance principle, enabling the system to proactively adjust the distribution of the environmental field strength to guide the unmanned vehicles to make adjustments. This indirect control method avoids the computational bottleneck of centralized scheduling. Each unmanned vehicle spontaneously adjusts its trajectory according to local field strength changes, thereby improving the dynamic environmental adaptability of the unmanned vehicles. This ensures collision avoidance reliability, detects overlapping areas / conflict points, improves group operation efficiency, optimizes path interference areas, and forms a decentralized collaborative control system. Attached Figure Description

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

[0045] Figure 1 This is a schematic diagram of the operation trajectory monitoring system of an intelligent unmanned vehicle in one embodiment;

[0046] Figure 2 This is a schematic diagram of the structure of the cooperative field resonance optimization subsystem in one embodiment;

[0047] Figure 3 This is a schematic diagram of the structure of a field interference resonance detection component in one embodiment;

[0048] Figure 4 This is a schematic diagram of the path efficiency evaluation subcomponent in one embodiment;

[0049] Figure 5 This is a schematic diagram of the neighborhood load balancing detection module in one embodiment;

[0050] Figure 6 This is a schematic diagram of the neighborhood load aggregation submodule in one embodiment;

[0051] Figure 7 This is a flowchart illustrating the operation trajectory monitoring method of an intelligent unmanned vehicle in one embodiment;

[0052] Figure 8 This is a structural block diagram of the trajectory monitoring device for an intelligent unmanned vehicle in one embodiment;

[0053] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] In one embodiment, such as Figure 1As shown, an intelligent unmanned vehicle trajectory monitoring system 100 is provided. The system includes: an environmental field strength topology mapping subsystem 101, a trajectory potential energy evolution prediction subsystem 102, and a cooperative field resonance optimization subsystem 103; the trajectory potential energy evolution prediction subsystem 102 is communicatively connected to the environmental field strength topology mapping subsystem 101 and the cooperative field resonance optimization subsystem 103 respectively.

[0056] The environmental field strength topology mapping subsystem 101 is used to acquire multi-source heterogeneous physical signals generated by the intelligent unmanned vehicle during operation, including non-visible frequency radiation, micro-vibration waves and local airflow disturbances; it integrates visible frequency radiation, micro-vibration waves and multi-source heterogeneous physical signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes through the environmental field strength distribution model, and generates a dynamic field strength topology map based on the dynamic field strength nodes.

[0057] The trajectory potential energy evolution prediction subsystem 102 is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; based on the potential energy difference, it determines the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it is moving, and generates a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and field strength disturbance propagation trend.

[0058] The collaborative field resonance optimization subsystem 103 is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

[0059] Specifically, refer to Figure 1 The intelligent unmanned vehicle trajectory monitoring system 100 includes the following modules that are connected in sequence and work together:

[0060] The environmental field strength topology mapping subsystem 101 is used to acquire multi-source heterogeneous physical signals generated during the operation of the intelligent unmanned vehicle, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances. It integrates different multi-source heterogeneous physical signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes, and records the signal strength, frequency domain characteristics, and attenuation gradient of each node to generate a dynamic field strength topology map. The node association strength characterizes the spatial location correlation, the connection direction reflects the signal propagation path, and the topology structure reflects the environmental physical field distribution in real time.

[0061] The trajectory potential energy evolution prediction subsystem 102 is used to input the dynamic field strength topology map and quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into potential energy difference. The movement of the intelligent detaching and attaching unmanned vehicle is a transition behavior in the potential energy field. By calculating the cumulative consumption of potential energy and the propagation trend of field strength disturbance in each path, a trajectory evolution probability cloud is constructed and a potential energy trajectory prediction cloud is generated. The field strength region where the detaching and attaching unmanned vehicle is most likely to appear in a few future time windows is marked in thermal form. The density reflects the probability weight and the shape reflects the motion trend.

[0062] The collaborative field resonance optimization subsystem 103 is used to input the potential energy trajectory prediction cloud and its real-time dynamic field strength topology map. It overlays the potential energy trajectory prediction cloud of the intelligent unmanned vehicle onto the current real-time dynamic field strength topology, detects overlapping areas or conflict points of the prediction clouds and interference areas or efficiency bottlenecks of the field strength transmission path, and injects micro-adjustment signals into the target topology nodes through the reverse field excitation generator to actively change the local field strength distribution and guide the intelligent unmanned vehicle to naturally separate its form or spontaneously adjust its trajectory. That is, by generating a field optimization instruction set, the environmental field strength distribution is changed, so that the potential energy trajectory prediction clouds of each vehicle automatically avoid conflicts and optimize paths, and the intelligent unmanned vehicle will spontaneously adjust its trajectory after sensing the changed field strength.

[0063] In the aforementioned intelligent unmanned vehicle trajectory monitoring system 100, multi-source heterogeneous physical signal fusion technology is used to transform complex physical quantities such as non-visible frequency radiation and micro-vibration waves into a calculable environmental field strength topology map, realizing three-dimensional dynamic quantitative modeling of the working environment. The signal strength, frequency domain characteristics, and other parameters recorded by each discrete node construct a spatial field strength distribution database accurate to the centimeter level. Based on potential energy field theory, the field strength difference is quantified into a calculable potential energy gradient. The probabilistic cloud algorithm elevates traditional path planning to a prediction system containing spatiotemporal probability weights. The output in heatmap form not only predicts position coordinates but also reflects the probability of motion trends within multiple future time windows through density distribution, giving the prediction results temporal continuity and spatial coverage. A distributed control mechanism implemented through the field resonance principle enables the system to actively adjust the environmental field strength distribution to guide the behavior of the unmanned vehicle. This indirect control method avoids the computational bottleneck of centralized scheduling. Each unmanned vehicle spontaneously adjusts its trajectory according to local field strength changes, ensuring collision avoidance reliability, detecting overlapping areas / conflict points, improving group operation efficiency, optimizing path interference areas, and forming a decentralized collaborative control system. Furthermore, this solution also realizes a complete closed loop from physical signal perception to field strength modeling and from single-machine trajectory prediction to multi-machine collaborative optimization, providing a dynamically adjustable physical field control framework for intelligent unmanned vehicle group operations. It is based entirely on the indirect control of the environmental physical field, without relying on direct communication between vehicles, and achieves group collaboration by changing the field strength distribution of the shared environment, thus having better real-time performance and robustness.

[0064] In one embodiment, such as Figure 2 As shown, the cooperative field resonance optimization subsystem 103 includes: a predictive cloud topology projection component, a field interference resonance detection component, and a reverse field modulation component;

[0065] The predictive cloud topology projection component is used to predict the field strength region of the cloud based on the potential energy trajectory and map it back to the topology node, generate a spatiotemporal projection topology map, and superimpose node load values ​​and regional motion vectors on the dynamic field strength topology map.

[0066] The field interference resonance detection component is used when the projection areas of two intelligent unmanned vehicles overlap and the intersection of their time windows is not empty; based on the spatiotemporal projection topology map, it selects the key transmission path connecting the motion directions of the intelligent unmanned vehicles; and generates an interference resonance spectrum based on the key transmission path.

[0067] The reverse field modulation component is used to extract the original frequency domain features, attenuation gradient, and path node signal strength of conflict nodes based on the node parameters of the interference resonance spectrum and the dynamic field strength topology map; it generates an inverse modulation signal based on the original frequency domain features and attenuation gradient, and generates a resonance enhancement signal based on the path node signal strength; it generates a field modulation instruction set based on the inverse modulation signal and the resonance enhancement signal; the field modulation instruction set is used to guide the intelligent detaching unmanned vehicle to perform natural shape separation or spontaneous trajectory adjustment.

[0068] Specifically, the predictive cloud topology projection component is used to input the potential energy trajectory prediction cloud and real-time dynamic field strength topology map of the multi-attached unmanned vehicle; it maps the field strength region of each potential energy trajectory prediction cloud back to the topology node; and outputs a generated spatiotemporal projection topology map, superimposing two types of markers on the original dynamic field strength topology map: node load value and region motion vector; where the region node load value mapped back to the topology node = cloud density × number of nodes covered in the region; and the region motion direction = cloud shape. The field interference resonance detection component is used to input the spatiotemporal projection topology map. When there are overlapping nodes in the projection regions of two detached unmanned vehicles and the time window intersection is not empty, it selects the key transmission path connecting the motion directions of the multi-attached unmanned vehicles, generates an interference resonance spectrum, and marks the conflict point location, intensity, bottleneck path coordinates, and efficiency value; when there are overlapping nodes in the projection regions of two detached unmanned vehicles and the time window intersection is not empty, the conflict intensity = the sum of the load values ​​of the overlapping nodes; the path efficiency of the key transmission path = the product of the node load values ​​on the path / path length; if the efficiency < threshold and the path load > neighborhood mean, it is marked as a bottleneck. The inverse field modulation component is used to take into account the interferometric resonance spectrum and the node parameters of the real-time dynamic field strength topology map, extract the original frequency domain features and attenuation gradient of the conflicting nodes, generate the inverse modulation signal, extract the signal strength of the path nodes, generate the resonance enhancement signal, and form a field modulation instruction set, which includes a list of nodes to be modified and new parameter values.

[0069] This embodiment achieves potential field optimization and control for multi-moving body cooperative operations through multi-layer field parameter coupling processing. It converts the predicted cloud parameters of discrete density and morphology into quantifiable attributes of node loads and motion vectors in the topological network, establishing a bidirectional mapping relationship between trajectory prediction results and the underlying field strength structure, thus realizing the correlation between macroscopic motion trends and microscopic node states. Based on spatiotemporal overlap detection and path efficiency analysis, it accurately quantifies the conflict intensity and conduction bottleneck characteristics of multi-body interference. By accumulating load values ​​to calculate conflict intensity and combining it with path efficiency threshold judgment, a three-dimensional conflict characterization model including spatial location, time window, and energy conduction characteristics is formed. Based on the conflict characteristics, the frequency domain characteristics and attenuation gradient of the original field parameters are analyzed inversely to generate a composite control strategy including anti-phase modulation and resonance enhancement. While maintaining the field strength topology unchanged, conflict resolution and path optimization are achieved through node parameter adjustment, forming a complete control chain of conflict detection-parameter inversion-field strength reconstruction.

[0070] In summary, this embodiment achieves closed-loop processing from trajectory prediction to field parameter optimization, topological space conflict modeling of multi-moving body trajectories, automatic identification of transmission bottlenecks based on path efficiency analysis, and dynamic optimization of field strength parameters while maintaining network topology.

[0071] In one embodiment, such as Figure 3 As shown, the field interference resonance detection component includes: a spatiotemporal conflict sub-component, a motion path coupling sub-component, and a path efficiency evaluation sub-component;

[0072] The spatiotemporal conflict sub-component is used to detect whether there is spatiotemporal overlap of multiple vehicles in the spatiotemporal projection topology map. If there is spatiotemporal overlap of multiple vehicles, the conflict intensity factor is calculated based on the spatiotemporal overlap of multiple vehicles. Based on the spatial location of the intelligent detachable unmanned vehicle, the associated vehicle identifier, and the conflict intensity factor, a conflict node tag set is generated.

[0073] The motion path coupling sub-component is used to extract the main motion vector of the intelligent detaching and attaching unmanned vehicle based on the spatiotemporal projection topology map; generate key transmission paths based on the main motion vector through vector coherence extension; and generate a multi-vehicle coupling path set for the intelligent detaching and attaching unmanned vehicle based on the key transmission paths.

[0074] The path efficiency evaluation sub-component is used to calculate the path efficiency value for each path based on the multi-vehicle coupled path set and the spatiotemporal projection topology map. If the efficiency value is less than a preset threshold and the average load value of the path is not less than the average load value of the three-hop neighborhood surrounding the path, then a bottleneck path tag set is generated based on the conflict node tag set.

[0075] Specifically, in the cloud topology projection component, the regional node load value mapped back to the topology node = cloud density × number of nodes covered in the region; the regional movement direction = cloud shape; in the field interference resonance detection component, when there are overlapping nodes in the projection regions of two detached unmanned vehicles and the intersection of the time windows is not empty, the conflict intensity = the sum of the load values ​​of the overlapping nodes; the path efficiency of the key transmission path = the product of the load values ​​of the nodes on the path / the path length; if the efficiency < threshold and the path load > the neighborhood mean, it is marked as a bottleneck. The spatiotemporal conflict subcomponent traverses all nodes in the spatiotemporal projection topology map, detects whether there is spatiotemporal overlap between multiple vehicles. When a node is covered by at least two predicted cloud regions, and all predicted clouds covering the node share a common valid time window (time window identifiers are non-empty), the conflict intensity factor is calculated, and a conflict node tag set is generated. Each conflict node records its spatial location, conflict intensity factor, and associated vehicle identifier. The motion path coupling subcomponent takes the spatiotemporal projection topology map as input, extracts the main motion vector of each unloading / attaching vehicle, selects the node with the largest load value from the unloading / attaching vehicle's projection area, and the motion vector of this node is the main motion direction of the unloading / attaching vehicle. This is then generated through vector coherence extension. The critical transmission path starts from the main motion vector node and extends along the topological connection direction to form a set of coupled paths for multiple detachable unmanned vehicles. Each path records the starting / ending detachable unmanned vehicle identifiers and the sequence of nodes passed through. The path efficiency evaluation sub-component is used to input the set of coupled paths for multiple vehicles and the spatiotemporal projection topology map. It calculates the transmission resistance product for each path. The resistance product is equal to the product of the load values ​​of all nodes on the path. It calculates the path efficiency index, which is the resistance product divided by the total number of nodes on the path. Bottleneck determination is performed when the efficiency value is less than a preset threshold and the average load value of the path is not less than the average load value of the three-hop neighborhood surrounding the path. A bottleneck path marker set is generated. Each bottleneck path records the coordinate sequence, efficiency value, and load deviation.

[0076] In one embodiment, such as Figure 4 As shown, the path efficiency evaluation sub-component includes: a path conduction resistance generation module, an efficiency field strength coupling module, and a neighborhood load balancing detection module.

[0077] The path conduction resistance generation module is used to extract the load value of each node sequentially along the path node sequence according to the multi-vehicle coupled path set and the spatiotemporal projection topology map, calculate the conduction resistance product through the resistance accumulator, and generate a path resistance feature set based on the conduction resistance product;

[0078] The efficiency field strong coupling module is used to calculate the path efficiency index based on the path resistance feature set, by using the conduction resistance product and the total number of path nodes, and to generate an efficiency field intensity index based on the path efficiency index.

[0079] The neighborhood load balancing detection module is used to determine the path average load value based on the efficiency field emphasis table and the spatiotemporal projection topology map; obtain the calculated neighborhood average load value; and generate a load deviation identifier set based on the path average load value and the calculated neighborhood average load value.

[0080] Specifically, the path conduction resistance generation module is used to input a multi-vehicle coupled path set and a spatiotemporal projection topology map, extract the load value of each node sequentially along the path node sequence, calculate the conduction resistance product through a resistance accumulator, generate a path resistance feature set, and associate the resistance product value of each path; the efficiency field strong coupling module is used to input the path resistance feature set, calculate the path efficiency index by combining the conduction resistance product with the total number of path nodes, form an efficiency field emphasis table, and record the efficiency value and spatial span of each path; the neighborhood load balancing detection module is used to input the efficiency field emphasis table and the spatiotemporal projection topology map, obtain the average load value of the path, obtain the outer three-hop neighborhood, extend three layers of adjacent nodes outward along the topology connection direction with the path node as the center, collect the load values ​​of all nodes in the neighborhood; obtain and calculate the average load value of the neighborhood, generate a load deviation identifier set, and mark the comparison status of the average load and the neighborhood load of each path.

[0081] The path efficiency evaluation sub-component in this embodiment constructs a multi-dimensional path efficiency quantitative evaluation system through the cascaded processing of three modules; it forms a progressive evaluation process from resistance calculation, efficiency standardization and environmental balance verification, and outputs three types of data: resistance feature set, efficiency field intensity scale, and load deviation identifier set. It provides a triple criterion for path optimization: resistance intensity, efficiency level and local load balance, and systematically identifies potential bottleneck paths with high resistance, low efficiency or load imbalance.

[0082] In one embodiment, such as Figure 5 As shown, the neighborhood load balancing detection module includes: a path load equivalent transformation submodule, a topology neighborhood wavefront expansion submodule, and a neighborhood load agglomeration submodule;

[0083] The path load equivalent transformation submodule is used to generate a path equivalent load set based on the efficiency field emphasis table and the resistance product-load equivalence law.

[0084] The topological neighborhood wavefront extension submodule is used to initiate third-order wavefront propagation starting from each node in the path based on the path equivalent load set, and to collect a pure neighborhood pool formed by all third-order nodes; and to generate a path neighborhood node library based on the pure neighborhood pool.

[0085] The Neighborhood Load Agglomeration Submodule is used to apply agglomeration operators to the load values ​​of all nodes in the pure neighborhood pool through the path neighborhood node library to generate a neighborhood load feature table.

[0086] Specifically, the path load equivalent transformation submodule is used to input the efficiency field intensity scale, apply the resistance product-load equivalence law, generate a path equivalent load set, and associate the average load value of each path; the topological neighborhood wavefront expansion submodule is used to input the path equivalent load set, start third-order wavefront propagation with each node of the path as the starting point, the first order visits the directly adjacent nodes along the topological connection direction, the second order visits the directly adjacent nodes from the first-order node, and the third order visits the directly adjacent nodes from the second-order node, collecting all third-order nodes to form a pure neighborhood pool, forming a path neighborhood node library, and recording the neighborhood node set corresponding to each path; the neighborhood load agglomeration submodule is used to input the path neighborhood node library, apply the agglomeration operator to the load values ​​of all nodes in the neighborhood pool, generate a neighborhood load feature table, and associate the average load value of each path with the neighborhood.

[0087] The neighborhood load balancing detection module in this embodiment achieves quantitative analysis of path load status and neighborhood feature extraction in the network topology through the collaborative work of three sub-modules. The path load equivalence transformation sub-module transforms the original efficiency field emphasis table into a comparable equivalent load set using the resistance product-load equivalence law, eliminating dimensional differences in the physical characteristics of different paths and providing standardized input for subsequent analysis. The topology neighborhood wavefront expansion sub-module employs a third-order wavefront propagation algorithm to accurately define the topological influence range of each path; it constructs a pure neighborhood pool through a hierarchical diffusion mechanism, avoiding both local topological blind spots and noise interference caused by over-expansion. The neighborhood load agglomeration sub-module performs operator agglomeration on the neighborhood node library, generating a two-dimensional representation containing both path local load and neighborhood load characteristics. This feature table quantifies and reflects: the path's own load level (average load value) and the load status of the surrounding topological environment (neighborhood average load value).

[0088] In summary, this embodiment forms a complete load analysis pipeline. The final output neighborhood load feature table can support load hotspot detection, load balance assessment, and topology congestion propagation analysis. Overall, it realizes the transformation from raw scheduling data to a topology-aware load feature space, providing a structured quantitative basis for subsequent load scheduling decisions.

[0089] In one embodiment, such as Figure 6 As shown, the neighborhood load agglomeration submodule includes: a neighborhood node load agglomeration unit, a spatial scale normalization unit, and a load feature binding unit.

[0090] The neighborhood node load aggregation unit is used to extract the load value of each node in the pure neighborhood pool based on the node load values ​​of the path neighborhood node library and the spatiotemporal projection topology graph, generate the neighborhood load product based on the load value through the load homogeneous coupler, and form a set of neighborhood load products.

[0091] The spatial scale normalization unit is used to obtain the average neighborhood load value based on the neighborhood load product set and the total number of nodes in the pure neighborhood pool, through the load product-mean equivalence law; and to generate a normalized neighborhood load set based on the average neighborhood load value.

[0092] The load feature binding unit is used to bind the average load value of the neighborhood with the corresponding path identifier based on the normalized neighborhood load set, and to attach the neighborhood node size as a spatial scale reference to generate a neighborhood load feature table.

[0093] Specifically, the neighborhood node load aggregation unit is used to input the node load values ​​of the path neighborhood node library and the spatiotemporal projection topology graph, traverse each node in the neighborhood pool, extract its load value, generate a neighborhood load product through a load homogeneous coupler, and generate a neighborhood load product set, with each path associated with a single load product value; the spatial scale normalization unit is used to input the neighborhood load product set and the total number of nodes in the neighborhood pool, apply the load product-mean equivalence law to obtain the neighborhood average load value, form a normalized neighborhood load set, and record the neighborhood average load value of each path; the load feature binding unit is used to input the normalized neighborhood load set, bind the neighborhood average load value with the corresponding path identifier, attach the neighborhood node size as a spatial scale reference, and generate a neighborhood load feature table, which includes the path identifier, the neighborhood average load value, and the number of neighborhood nodes.

[0094] In the above embodiments, the neighborhood load agglomeration submodule of this embodiment achieves quantitative extraction and standardized characterization of topological neighborhood load features through a three-layer processing structure. Its technical significance is as follows: The neighborhood node load aggregation unit, based on the spatiotemporal projection topology graph, uses a load homogeneous coupler to nonlinearly aggregate the node load values ​​within the neighborhood pool, generating a load product. This transforms discrete node load states into continuous and comparable scalar values, preserving the overall load intensity characteristics of the neighborhood. The spatial scale normalization unit, through the load product-mean equivalence law, eliminates the difference in node cardinality between neighborhood pools of different sizes. The output normalized neighborhood load set ensures that: neighborhood loads with different topological densities are comparable; and the load product value is mapped to the unit node dimension. The triplet feature table generated by the load feature binding unit (path identifier / neighborhood average load value / number of neighboring nodes) provides: path-level load environment quantification indicators, neighborhood spatial scale metadata, and the number of nodes reflecting the topological influence radius, supporting subsequent load balancing algorithms for weighted calculation.

[0095] In summary, this embodiment outputs spatially consistent neighborhood load characteristics, providing the following analysis dimensions for the upper-layer system: absolute neighborhood load strength, load distribution density, and path-neighborhood load correlation.

[0096] Furthermore, the load feature binding unit also includes a path load feature matching subunit, a physical field feature binding subunit, and a spatiotemporal reference reinforcement subunit. The path load feature matching subunit is used to input the normalized neighborhood load set and the total number of neighborhood pool nodes, perform spatial scale anchoring on each path to obtain the neighborhood spatial density index, generate a density-anchored load set, and record triples for each path. The physical field feature binding subunit is used to input the density-anchored load set, extract the path identifier from the triples as the primary key, combine the neighborhood average load value and the spatial density index into a field strength feature vector, establish a bidirectional mapping relationship from path identifier to feature vector, and form a path-field strength feature mapping table containing the path identifier and its corresponding field strength feature vector. The spatiotemporal reference reinforcement subunit is used to input the path-field strength feature mapping table, activate the density index mechanism in the feature vector, and generate a neighborhood load feature table containing three elements: path identifier, neighborhood average load value, and neighborhood spatial density index. When the spatial density index is not less than a preset threshold, a high confidence marker is automatically added to the neighborhood average load value; when the spatial density index is not greater than the threshold, a spatial compensation factor is automatically added to the neighborhood average load value.

[0097] In one embodiment, the environmental field strength topology mapping subsystem includes: a signal intrinsic mode separation module, a spatial attenuation anchoring module, and a field strength node self-organization module.

[0098] The signal intrinsic mode separation module is used to enable multi-source heterogeneous physical signals with different physical properties to modulate each other under the target energy level threshold through cross-medium coupled resonant sieve; the high-frequency oscillation of the radiation signal triggers the resonant frequency of micro-vibration, and the resonant frequency forms an energy envelope with the airflow disturbance rate; the output generates eigenmode feature clusters, each feature cluster containing three types of signal coupling parameters: radiation oscillation main frequency, vibration resonant bandwidth, and airflow envelope phase;

[0099] The spatial attenuation anchoring module is used to input intrinsic mode feature clusters, and to establish an implicit mapping between feature attenuation paths and spatial locations by detecting the parameter attenuation degree of the same feature cluster at different spatial sampling points, including the attenuation slope of the radiation dominant frequency amplitude, the vibration bandwidth contraction rate, and the airflow phase offset; the output generates a spatial fingerprint of the attenuation path, where each path records the combination of attenuation gradients of the feature cluster from the signal source to the sampling point, forming a unique identifier of the spatial location;

[0100] The field strength node self-organizing module is used to input the attenuation path space fingerprint. When the terminal gradient combination of two feature attenuation paths satisfies the coherent convergence condition, node merging is triggered. The merged node inherits the source features of the two paths and generates dynamic field strength nodes. The connection strength between nodes is determined by the overlap of the attenuation paths in the attenuation path space fingerprint: the more overlapping gradient parameters, the higher the connection weight. The connection direction is determined by the sum of the attenuation gradient vectors. The output self-organizes to form a dynamic field strength topology graph. The node density in the dynamic field strength topology graph reflects the physical field complexity, and the connection direction network constitutes the main channel for signal transmission.

[0101] In-node storage of dynamic field strength nodes: Signal strength = source radiation amplitude × terminal vibration bandwidth; Frequency domain characteristics = modulation product of airflow envelope phase on radiation main frequency; Attenuation gradient = vector product of terminal vibration contraction rate and radiation attenuation slope.

[0102] In this embodiment, the environmental field strength topology mapping subsystem achieves structured modeling of complex physical fields through a multi-level signal processing chain. The signal intrinsic mode separation module transforms three types of heterogeneous signals—radiation, vibration, and airflow—into energy-correlated feature clusters through a cross-medium coupling resonance mechanism, establishing a quantized coupling relationship between signals. The spatial attenuation anchoring module utilizes the spatial attenuation characteristics of feature parameters to transform abstract physical signals into locatable spatial fingerprints, achieving unique encoding of spatial locations through attenuation gradient combinations. The field strength node self-organization module dynamically constructs a network topology reflecting the true distribution of the physical field based on the coherent convergence condition of the attenuation path. The node merging mechanism preserves signal source characteristics, and the calculation methods for connection weights and directions accurately reproduce the signal propagation path. In the final generated dynamic field strength topology graph, the node density automatically adapts to environmental complexity, and the connection network accurately represents the main signal propagation channels. The storage of composite parameters of signal strength, frequency domain characteristics, and attenuation gradient within nodes achieves a unified quantized expression of multi-dimensional physical fields, providing a complete field strength model that includes spatial correlation, signal propagation, and environmental dynamics. This embodiment solves the problem of spatial fusion of multi-source heterogeneous signals by transforming unstructured physical signals into a topological network with strict mathematical definition through a processing chain of signal coupling, spatial anchoring, and node self-organization.

[0103] In one embodiment, the trajectory potential energy evolution prediction subsystem includes: a field strength gradient potential well generation module, a perturbation wavefront tracking module, and a trajectory probability cloud synthesis module.

[0104] The field strength gradient potential well generation module is used to traverse adjacent nodes along the topological connection direction of the dynamic field strength topology graph, extract the three parameter differences between nodes: intensity potential difference, frequency domain coupling degree, and gradient compliance, and substitute the three parameters into the potential well generation function; the output generates a directed potential well network, and each topological connection is transformed into a weighted directed edge. The weight value is the potential energy difference, which reflects the difficulty of energy transition from the source node to the target node.

[0105] Intensity potential difference = target node signal strength / source node signal strength; Frequency domain coupling degree = |source node frequency domain characteristic - target node frequency domain characteristic Gradient compliance = dot product of the source node decay gradient vector and the direction of the connection; Potential well generation function: Potential difference = intensity potential difference × frequency domain coupling × gradient compliance;

[0106] The disturbance wavefront tracking module is used to input a directed potential well network and activate a virtual disturbance source at the current position node of the detaching and attaching unmanned vehicle. Its vibration mode is bound to the current operating state of the detaching and attaching unmanned vehicle. Through the wavefront propagation simulator, the disturbance is made to spread along the potential well network. The output generates a disturbance propagation path tree. The root of the tree is the current position of the detaching and attaching unmanned vehicle, the branches record the cumulative consumption and time delay of each path, and the leaf nodes cover the reachable field strength area.

[0107] The energy consumed in each transition = 1 / target edge potential energy difference; when the wavefront reaches a new node, the cumulative consumption value and arrival delay are recorded; when the wavefront branches intersect at the node, the path with the minimum cumulative consumption is retained;

[0108] The trajectory probability cloud synthesis module is used to input the disturbance propagation path tree, extract the cumulative consumption value and time delay of the leaf nodes in the path tree, and substitute them into the spatiotemporal probability mapping relationship; aggregate the leaf nodes belonging to the same time window according to probability weight, and cluster them by field strength region; if there is an uninterrupted potential well connection between two nodes and the rate of change of potential energy difference is less than the threshold, they are merged into the same field strength region; generate a prediction cloud according to the region morphology; output the potential energy trajectory prediction cloud, each time window corresponds to a set of probability clouds, the physical location of the cloud is defined by the field strength region, and the motion trend is intuitively expressed by the cloud morphology;

[0109] Cloud density = sum of probability weights of nodes within the region; Cloud morphology = consistency of the direction of potential energy difference between nodes at the region boundary; Cloud prediction based on potential energy trajectory, probability weight = (cumulative consumption of leaf nodes). Time window assignment = latency / preset time resolution; region morphology generates predicted clouds, cloud density = sum of probability weights of nodes within the region; cloud morphology = consistency of the potential energy difference direction of nodes at the region boundary.

[0110] In this embodiment, spatiotemporal probabilistic prediction of the trajectory of a moving object in a dynamic potential energy field is achieved through multi-module collaboration. After transforming the physical field topology into a directed potential energy network, a prediction model with spatiotemporal evolution characteristics is constructed by combining the perturbation propagation mechanism and probability cloud synthesis. After fusion, a three-layer coupling mechanism is formed: First, a potential energy transition network is established through field strength gradient analysis to quantify the energy transfer probability between nodes; second, wavefront propagation is used to simulate the perturbation diffusion process to dynamically generate a path tree containing energy consumption and time delay information; finally, physical parameters are transformed into a visual prediction cloud through spatiotemporal probability mapping to realize a computable expression of trajectory trends.

[0111] In summary, this embodiment extends traditional field strength analysis to a three-dimensional parameter system that includes frequency domain coupling and gradient vectors; it uses virtual perturbation source binding technology to realize the dynamic correlation between motion state and field strength evolution; and it maintains the physical consistency of prediction results through a region clustering algorithm constrained by potential energy difference. This realizes a paradigm shift from static field strength analysis to dynamic trajectory prediction, providing a physically interpretable decision-making basis for autonomous mobile systems.

[0112] In one embodiment, such as Figure 7 As shown, a method for monitoring the operating trajectory of an intelligent unmanned vehicle is provided, which is then applied to... Figure 1 Taking the intelligent unmanned vehicle's operation trajectory monitoring system 100 as an example, the following steps are included:

[0113] Step S701: Acquire the multi-source heterogeneous physical signals of non-visible frequency radiation, micro-vibration waves, and local airflow disturbances generated during the operation of the intelligent unmanned vehicle; fuse the visible frequency radiation, micro-vibration waves, and multi-source heterogeneous physical signals into a unified environmental field strength distribution model; discretize the space into dynamic field strength nodes through the environmental field strength distribution model; and generate a dynamic field strength topology map based on the dynamic field strength nodes.

[0114] Step S702: Quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path when the intelligent detaching unmanned vehicle is moving based on the potential energy difference, and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and field strength disturbance propagation trend.

[0115] Step S703: The potential energy trajectory prediction cloud is superimposed on the dynamic field strength topology map, and the existence of the target area is detected; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

[0116] The aforementioned method for monitoring the operational trajectory of intelligent unmanned vehicles employs a distributed control mechanism based on the principle of field resonance. This mechanism enables the system to proactively adjust the distribution of the environmental field strength to guide the unmanned vehicles to make adjustments. This indirect control method avoids the computational bottleneck of centralized scheduling. Each unmanned vehicle spontaneously adjusts its trajectory according to local field strength changes, thereby improving the dynamic environmental adaptability of the unmanned vehicles. This ensures collision avoidance reliability, detects overlapping areas / conflict points, improves group operation efficiency, optimizes path interference areas, and forms a decentralized collaborative control system.

[0117] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0118] Based on the same inventive concept, this application also provides an intelligent unmanned vehicle trajectory monitoring device for implementing the above-mentioned intelligent unmanned vehicle trajectory monitoring method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more intelligent unmanned vehicle trajectory monitoring device embodiments provided below can be found in the limitations of the intelligent unmanned vehicle trajectory monitoring method described above, and will not be repeated here.

[0119] In one exemplary embodiment, such as Figure 8 As shown, a device for monitoring the operating trajectory of an intelligent unmanned vehicle is provided, which may include:

[0120] The topology mapping module 801 is used to acquire multi-source heterogeneous physical signals generated during the operation of the intelligent detachable unmanned vehicle, including non-visible frequency radiation, micro-vibration waves and local airflow disturbances; it integrates visible frequency radiation, micro-vibration waves and multi-source heterogeneous physical signals into a unified environmental field strength distribution model, discretizes the space into dynamic field strength nodes through the environmental field strength distribution model, and generates a dynamic field strength topology map based on the dynamic field strength nodes.

[0121] The trajectory prediction module 802 is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it is moving based on the potential energy difference, and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and field strength disturbance propagation trend.

[0122] The resonance optimization module 803 is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, it injects micro-adjustment signals into the target topology node through the reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, it guides the intelligent detaching unmanned vehicle to perform natural shape separation or spontaneously adjust its trajectory.

[0123] Specific limitations regarding the trajectory monitoring device for intelligent unmanned vehicles can be found in the above-mentioned limitations on the trajectory monitoring method for intelligent unmanned vehicles, and will not be repeated here. Each module in the aforementioned trajectory monitoring device for intelligent unmanned vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0124] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for monitoring the operating trajectory of an intelligent detachable unmanned vehicle. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0125] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0127] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0128] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0130] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0131] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0132] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A system for monitoring the operational trajectory of an intelligent unmanned vehicle, characterized in that, The system includes: an environmental field strength topology mapping subsystem, a trajectory potential energy evolution prediction subsystem, and a cooperative field resonance optimization subsystem; the trajectory potential energy evolution prediction subsystem is communicatively connected to the environmental field strength topology mapping subsystem and the cooperative field resonance optimization subsystem, respectively. The environmental field strength topology mapping subsystem is used to acquire multi-source heterogeneous physical signals generated by the intelligent detachable unmanned vehicle during operation, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes. The trajectory potential energy evolution prediction subsystem is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it is moving based on the potential energy difference; and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and the field strength disturbance propagation trend. The cooperative field resonance optimization subsystem is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through a reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

2. The system according to claim 1, characterized in that, The cooperative field resonance optimization subsystem includes: a predictive cloud topology projection component, a field interference resonance detection component, and a reverse field modulation component; The predicted cloud topology projection component is used to map the field strength region of the cloud predicted by the potential energy trajectory back to the topology node, generate a spatiotemporal projection topology map, and superimpose node load values ​​and region motion vectors on the dynamic field strength topology map. The field interference resonance detection component is used to select a key transmission path connecting the motion direction of the intelligent unmanned vehicles according to the spatiotemporal projection topology map when there are overlapping nodes in the projection areas of the two intelligent unmanned vehicles and the intersection of the time windows is not empty; and generate an interference resonance spectrum according to the key transmission path. The reverse field modulation component is used to extract the original frequency domain features, attenuation gradient, and path node signal strength of conflict nodes based on the node parameters of the interference resonance spectrum and the dynamic field strength topology map; generate an inverse modulation signal based on the original frequency domain features and the attenuation gradient, and generate a resonance enhancement signal based on the path node signal strength; generate a field modulation instruction set based on the inverse modulation signal and the resonance enhancement signal; the field modulation instruction set is used to guide the intelligent detachment unmanned vehicle to perform natural shape separation or spontaneous trajectory adjustment.

3. The system according to claim 2, characterized in that, The field interference resonance detection component includes: a spatiotemporal conflict sub-component, a motion path coupling sub-component, and a path efficiency evaluation sub-component; The spatiotemporal conflict sub-component is used to detect whether there is spatiotemporal overlap of multiple vehicles in the spatiotemporal projection topology map. If there is spatiotemporal overlap of multiple vehicles, a conflict intensity factor is calculated based on the spatiotemporal overlap of multiple vehicles. A conflict node tag set is generated based on the spatial location of the intelligent detachable unmanned vehicle, the associated vehicle identifier, and the conflict intensity factor. The motion path coupling sub-component is used to extract the main motion vector of the intelligent detaching and attaching unmanned vehicle based on the spatiotemporal projection topology map; generate key transmission paths based on the main motion vector through vector coherence extension; and generate a multi-vehicle coupling path set of the intelligent detaching and attaching unmanned vehicle based on the key transmission paths. The path efficiency evaluation sub-component is used to calculate the path efficiency value for each path based on the multi-vehicle coupled path set and the spatiotemporal projection topology map. If the efficiency value is less than a preset threshold and the average load value of the path is not less than the average load value of the three-hop neighborhood surrounding the path, then a bottleneck path tag set is generated based on the conflict node tag set.

4. The system according to claim 3, characterized in that, The path efficiency evaluation sub-component includes: a path conduction resistance generation module, an efficiency field strength coupling module, and a neighborhood load balancing detection module. The path conduction resistance generation module is used to extract the load value of each node sequentially along the path node sequence according to the multi-vehicle coupled path set and the spatiotemporal projection topology map, calculate the conduction resistance product through the resistance accumulator, and generate a path resistance feature set based on the conduction resistance product; The efficiency field strong coupling module is used to calculate the path efficiency index based on the path resistance feature set, by using the conduction resistance product and the total number of path nodes, and to generate an efficiency field intensity index based on the path efficiency index. The neighborhood load balancing detection module is used to determine the path average load value based on the efficiency field emphasis table and the spatiotemporal projection topology map; obtain the calculated neighborhood average load value; and generate a load deviation identifier set based on the path average load value and the calculated neighborhood average load value.

5. The system according to claim 4, characterized in that, The neighborhood load balancing detection module includes: a path load equivalent transformation submodule, a topology neighborhood wavefront expansion submodule, and a neighborhood load agglomeration submodule; The path load equivalent transformation submodule is used to generate a path equivalent load set according to the efficiency field emphasis table and through the resistance product-load equivalence law. The topological neighborhood wavefront extension submodule is used to initiate third-order wavefront propagation starting from each node in the path based on the path equivalent load set, and to collect a pure neighborhood pool formed by all third-order nodes; and to generate a path neighborhood node library based on the pure neighborhood pool. The neighborhood load agglomeration submodule is used to apply agglomeration operators to the load values ​​of all nodes in the pure neighborhood pool through the path neighborhood node library to generate a neighborhood load feature table.

6. The system according to claim 5, characterized in that, The neighborhood load aggregation submodule includes: a neighborhood node load aggregation unit, a spatial scale normalization unit, and a load feature binding unit; The neighborhood node load aggregation unit is used to extract the load value of each node in the pure neighborhood pool based on the node load values ​​of the path neighborhood node library and the spatiotemporal projection topology graph, generate a neighborhood load product based on the load value through a load homogeneous coupler, and form a neighborhood load product set. The spatial scale normalization unit is used to obtain the average neighborhood load value based on the neighborhood load product set and the total number of nodes in the pure neighborhood pool, using the load product-mean equivalence law; and to generate a normalized neighborhood load set based on the average neighborhood load value. The load feature binding unit is used to bind the average load value of the neighborhood with the corresponding path identifier based on the normalized neighborhood load set, and add the neighborhood node size as a spatial scale reference to generate the neighborhood load feature table.

7. A method for monitoring the operating trajectory of an intelligent unmanned vehicle, characterized in that, A trajectory monitoring system for intelligent unmanned vehicles, the method comprising: The system acquires multi-source heterogeneous physical signals generated during the operation of the intelligent unmanned vehicle, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes. The difference in environmental field strength between adjacent nodes in the dynamic field strength topology is quantified into a potential energy difference; the potential energy accumulation and field strength disturbance propagation trend of each path of the intelligent unmanned vehicle during movement are determined based on the potential energy difference, and a potential energy trajectory prediction cloud is generated based on the potential energy accumulation and field strength disturbance propagation trend. The potential energy trajectory prediction cloud is superimposed on the dynamic field strength topology map, and the existence of the target area is detected. Based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution. Based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

8. A device for monitoring the operating trajectory of an intelligent unmanned vehicle, characterized in that, The device includes: The topology mapping module is used to acquire multi-source heterogeneous physical signals generated during the operation of the intelligent detachable unmanned vehicle, including non-visible frequency radiation, micro-vibration waves, and local airflow disturbances; it integrates the visible frequency radiation, the micro-vibration waves, and the multi-source heterogeneous physical signals into a unified environmental field strength distribution model; it discretizes the space into dynamic field strength nodes through the environmental field strength distribution model; and it generates a dynamic field strength topology map based on the dynamic field strength nodes. The trajectory prediction module is used to quantify the difference in environmental field strength between adjacent nodes in the dynamic field strength topology map into a potential energy difference; determine the potential energy accumulation consumption and field strength disturbance propagation trend of each path of the intelligent detaching unmanned vehicle when it moves based on the potential energy difference, and generate a potential energy trajectory prediction cloud based on the potential energy accumulation consumption and the field strength disturbance propagation trend. The resonance optimization module is used to overlay the potential energy trajectory prediction cloud onto the dynamic field strength topology map and detect the existence of the target area; based on the existence of the target area, a micro-adjustment signal is injected into the target topology node through the reverse field excitation generator to change the environmental field strength distribution; based on the changed environmental field strength distribution, the intelligent detaching unmanned vehicle is guided to perform natural shape separation or spontaneously adjust its trajectory.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method of claim 7.

Images