Multiple access interference management method and device based on communication perception integration

Abstract

The invention relates to the technical field of information management, and discloses a multi-access interference management method and device based on communication perception integration, and the method comprises the steps: carrying out environment perception through a sensor group on an autonomous mobile machine service platform, and obtaining environment perception data; performing network service quality detection on each autonomous mobile machine service platform to obtain network quality characteristics, performing data integration processing on the environment sensing data according to the network quality characteristics to obtain a sensing network data set, and performing digital modeling according to the sensing network data set to obtain a live simulation model; according to the method, communication and sensing functions can be effectively integrated, the communication quality and stability are improved, and the cooperative work capability of an autonomous mobile machine service platform is enhanced; the problem in the prior art that the overall performance of the system is affected by interference generated between multiple devices when the multiple devices communicate at the same time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to a multiple access interference management method and device based on communication perception integration. Background Art

[0002] With the rapid development of unmanned aerial vehicles (UAV) and autonomous mobile robots (such as robot dogs), these autonomous mobile machine service platforms are playing an increasingly important role in various applications, including but not limited to environmental monitoring, logistics and transportation, agricultural management, and security patrols. In order to realize these applications, machine service platforms not only need efficient autonomous navigation and collaborative working capabilities, but also reliable communication and perception capabilities to perform tasks in dynamic and complex environments.

[0003] However, in practical applications, machine service platform arrays (consisting of multiple autonomous mobile machine service platforms) face multiple challenges, one of which is the problem of multiple access interference management. Multiple access interference refers to the interference between multiple devices when they communicate simultaneously in a wireless communication network, resulting in a decrease in communication quality and affecting the overall performance of the system. This interference is especially significant in the high-density deployment and collaborative work scenarios of autonomous mobile machine service platforms. Summary of the invention

[0004] The purpose of the present invention is to provide a multiple access interference management method and device based on integrated communication perception, aiming to solve the problem in the prior art that the interference generated between multiple devices when communicating simultaneously affects the overall performance of the system.

[0005] The present invention is implemented in this way. In a first aspect, the present invention provides a multiple access interference management method based on integrated communication perception, comprising: Acquiring array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and driving the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; Performing environmental perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array to obtain environmental perception data of each of the autonomous mobile machine service platforms; Performing network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; Performing data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms to obtain a perception network data set; The information feedback of the digital modeling of the machine service platform array is processed according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to feedback the real-time information of the machine service platform array after eliminating interference information.

[0006] In a second aspect, the present invention provides a multiple access interference management device based on integrated communication perception, which is used to implement a multiple access interference management method based on integrated communication perception as described in any one of the first aspects, including: An information acquisition module, used to acquire array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and drive the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; An environment perception module, used to perform environment perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, so as to obtain environment perception data of each of the autonomous mobile machine service platforms; A network detection module, used to perform network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; A data integration module, configured to perform data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms, so as to obtain a perception network data set; An information simulation module is used to process information feedback of digitally modeling the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to provide real-time information feedback to the machine service platform array after eliminating interference information.

[0007] The present invention provides a multiple access interference management method based on communication perception integration, which has the following beneficial effects: The present invention uses a sensor group on an autonomous mobile machine service platform to perform environmental perception and obtain environmental perception data, performs network service quality detection on each autonomous mobile machine service platform to obtain network quality characteristics, performs data integration processing on the environmental perception data according to the network quality characteristics to obtain a perception network data set, performs digital modeling based on the perception network data set to obtain a real-time simulation model, eliminates interference information and provides real-time information feedback. This method can effectively integrate communication and perception functions, improve communication quality and stability, enhance the collaborative working ability of the autonomous mobile machine service platform, and solves the problem in the prior art that interference generated by multiple devices when communicating simultaneously affects the overall performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a schematic diagram of the steps of a multiple access interference management method based on integrated communication perception provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a multiple access interference management device based on integrated communication perception provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0010] The implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0011] Reference Figure 1 , Figure 2 As shown, a preferred embodiment of the present invention is provided.

[0012] In a first aspect, the present invention provides a multiple access interference management method based on communication perception integration, comprising: S1: acquiring array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and driving the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; S2: performing environmental perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array to obtain environmental perception data of each of the autonomous mobile machine service platforms; S3: Performing network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; S4: performing data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms to obtain a perception network data set; S5: Processing information feedback of digital modeling of the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to feedback real-time information of the machine service platform array after eliminating interference information.

[0013] Specifically, in step S1 of the embodiment provided by the present invention, the performance information of each platform in the array (such as a drone or a robot dog) is obtained. The performance information includes the individual characteristics of the platforms (for example, battery power, load capacity, sensor accuracy, speed, etc.) and the collaboration capabilities between them (such as communication capabilities, collaboration protocols, etc.). The performance data of each platform can be collected regularly or in real time through sensors, embedded computing systems, network communications, etc. to form a platform performance database. By continuously obtaining real-time performance information of each platform, the system can accurately understand the working status of each platform, thereby providing a reliable foundation for subsequent collaborative work. Based on this performance information, the advantages and disadvantages of each platform can be identified, and the subsequent task allocation can be optimized.

[0014] More specifically, based on the acquired array performance information, the platform array is driven to ensure that they work together efficiently in a specified area. This stage involves the design of multi-platform task allocation and collaboration strategies to ensure that each platform performs tasks in the best condition. For example, based on performance information, the platform with the most resources and the lightest load is allocated to perform complex perception tasks, or tasks with heavier workloads are allocated to platforms with greater load capacity. In addition, the collaboration strategies of each platform need to be dynamically adjusted to ensure that tasks are completed without conflict in a specific area.

[0015] More specifically, by evaluating the performance of each platform and designing a reasonable task allocation algorithm, it is ensured that each platform performs appropriate tasks within its optimal performance range. A collaborative control algorithm is introduced to ensure that multiple platforms can collaborate synchronously or on demand in the same area to avoid task conflicts or waste of resources between platforms. Through reasonable task allocation and platform drive, it is ensured that multiple autonomous platforms can perform at their best when working together and reduce conflicts in time and space. Through real-time monitoring and analysis of the performance of each platform, tasks can be intelligently allocated between platforms to ensure the execution accuracy and efficiency of each task.

[0016] More specifically, in actual applications, multiple platforms such as drone swarms and robot dog swarms need to jointly perform tasks in a designated area, such as map construction, area inspection, material transportation, etc. At this stage, by coordinating the position, speed, direction, task progress, etc. of each platform, it is ensured that the platform array can effectively divide the work and cooperate in the area. At the same time, based on the performance characteristics and task requirements of each platform, it may be necessary to dynamically adjust the coordination strategy to ensure real-time coordination and efficient work between platforms.

[0017] More specifically, combined with the platform's positioning and performance information, a path planning algorithm is used to ensure that the platform can effectively avoid obstacles and conduct dynamic coordination in space. A load balancing and task scheduling algorithm is used to adjust task allocation and inter-platform collaboration relationships in real time according to the platform's working status to ensure that tasks are completed on time. The platform can adjust its own movement trajectory in the area in real time to avoid collisions or obstruction of the work of other platforms. At the same time, it can flexibly adapt to changes in the external environment (such as the appearance of obstacles or adjustment of task priorities). Through the coordination and scheduling mechanism, multiple platforms can efficiently and seamlessly complete collaborative tasks, reduce redundant operations, and improve task execution efficiency.

[0018] It is understandable that the performance information of the platform array is obtained and monitored in real time to ensure that each platform performs the task in its best condition. According to the performance evaluation results of each platform, tasks are intelligently allocated and collaboration strategies are adjusted so that the platform array can work together efficiently and seamlessly. Multiple autonomous platforms can achieve precise and coordinated operations through path planning, obstacle avoidance and dynamic adjustment in a specified area to ensure that tasks can be completed efficiently. When the external environment changes (such as the appearance of obstacles, changes in platform performance, etc.), the platform can flexibly adjust the collaboration mode and work strategy to maintain the overall efficiency of the system. By optimizing and integrating the performance, perception capabilities and task collaboration of multiple autonomous platforms, the platform array can perform tasks in complex and dynamic environments, such as large-scale inspections, search and rescue, and other tasks, and can exert stronger comprehensive advantages than a single platform.

[0019] Specifically, in step S2 of the embodiment provided by the present invention, multiple sensors are pre-installed on each autonomous mobile machine service platform (such as a drone, a robot dog, etc.) to achieve multi-dimensional environmental perception. Common sensors include: visual sensors (such as RGB cameras, infrared cameras) for image capture and visual recognition of the environment, lidar for generating high-precision three-dimensional maps and sensing the spatial distribution of surrounding objects, ultrasonic sensors for close-range obstacle detection, temperature and humidity sensors for monitoring the temperature and humidity of the environment, gas sensors (such as CO2, methane, etc.) for sensing air quality or hazardous gases, and inertial measurement units (IMUs) for sensing the motion state of the platform to ensure accurate positioning and stability.

[0020] It is understandable that through the configuration of multiple sensors, the platform can perceive the environment in multiple dimensions, including vision, spatial position, climate, obstacles, etc., so as to obtain comprehensive environmental information. Different types of sensors complement each other, make up for the blind spots or limitations of a single sensor, and enhance the robustness and accuracy of the system.

[0021] More specifically, each platform uses its sensor group to perform environmental perception processing on the designated area and collect data in real time. The perception content includes but is not limited to: obstacle detection: identifying obstacles in the environment (such as buildings, trees, vehicles, etc.) and performing obstacle avoidance processing, regional terrain recognition: identifying and classifying terrain changes in the area (such as slopes, obstacles, open areas or narrow areas), climate data collection: obtaining environmental data such as temperature, humidity, and air pressure in the area, especially the impact on the mission in severe climates, environmental noise or harmful gas detection: if necessary, sensors can be used to collect air quality data, especially for emergency rescue or pollution detection tasks, real-time image and video acquisition: real-time images or videos in the area are obtained through visual sensors to assist in mission decision-making.

[0022] More specifically, the sensors of each platform collect data periodically or as needed. The sensors pre-process the collected raw data (such as noise filtering and image processing) and transmit the processed data to the central processing system or other platforms through wireless networks. The real-time data provided by the sensors can quickly feedback environmental changes and help the platform make adjustments based on actual conditions. The combination of lidar and visual sensors can achieve high-precision obstacle recognition and path planning in complex environments. The platform can adapt to different environmental changes (such as lighting changes, climate fluctuations, etc.) and automatically adjust action strategies based on perceived data.

[0023] More specifically, each autonomous platform transmits the collected environmental perception data to the central processing system through the communication system, or shares data with other platforms. The data collected by the sensors (such as images, lidar data, climate data, etc.) is transmitted through standardized protocols for subsequent processing, analysis and fusion. Wireless communication technologies (such as Wi-Fi, 4G / 5G, Mesh networks, etc.) are used to aggregate the perception data of each platform to a central node or other collaborative platform. Through data fusion technology, the perception data of different platforms are combined to form a global environmental perception map, thereby improving perception accuracy and operability.

[0024] More specifically, through data sharing, different platforms can collaborate with each other to form a more accurate global environmental perception map, avoid data isolation, and data from multiple platforms can work together, allowing the entire array to make more comprehensive and accurate judgments about complex environments.

[0025] More specifically, the environmental perception data collected from each platform is analyzed, modeled, and processed. Common applications include: identifying obstacles through image processing, lidar data analysis, and other methods, and adjusting the platform's motion trajectory in real time, generating mission planning based on perception data, for example, determining the optimal path for the platform, selecting appropriate collaboration strategies, analyzing climate change, gas concentrations, and sources of danger in the area, providing real-time environmental monitoring information, and helping decision makers take appropriate countermeasures. Through real-time processing and analysis of data, accurate environmental status can be obtained to ensure that the platform can make appropriate decisions in complex environments. Based on real-time environmental data, the platform can flexibly adjust mission planning and execution strategies to improve the effectiveness of mission execution.

[0026] It is understandable that through different types of sensors (vision, lidar, temperature and humidity sensors, etc.), the platform can perceive environmental information in multiple dimensions to ensure the acquisition of comprehensive and accurate environmental data. The sensors continuously collect environmental data in real time and transmit it to the processing system in a timely manner through wireless communication to ensure that the platform has the ability to respond quickly to environmental changes. With the help of lidar, vision sensors, etc., the platform can accurately identify obstacles and perform dynamic avoidance to ensure safe work in complex environments. By collecting environmental information (such as climate, gas concentration, noise, etc.), the platform can provide real-time environmental status reports to support the decision-making system to make accurate judgments, especially in emergency situations. Can provide key data.

[0027] Specifically, in step S3 of the embodiment provided by the present invention, the network connection part of each platform must have relevant hardware and software interfaces and be able to collect network quality data. Specifically, network monitoring tools need to be installed on the platform and ensure that they are connected to the communication modules of the platform (such as Wi-Fi, 5G, LoRa, Mesh networks, etc.) to detect and record network quality in real time, including but not limited to network delay monitoring tools, signal strength detection modules, bandwidth measurement modules, packet loss rate analysis modules, etc. The platform can monitor the quality of network connections with other platforms or external systems in real time to ensure a comprehensive grasp of the network status. Through the configuration of the network interface, the platform can support multiple network protocols and can collect multi-dimensional network data in real time.

[0028] More specifically, each platform collects the following network quality characteristic data regularly or on demand through its communication modules and sensor groups: Network delay: refers to the data transmission delay time between the platform and other platforms or servers, usually measured by Ping test or other delay detection methods, Signal strength: Measures the strength of the wireless signal, reflecting the connection quality between the platform and the communication base station, other platforms or external systems, Bandwidth usage: Records the current network bandwidth usage of the platform to evaluate whether there is a bandwidth bottleneck, Packet loss rate: Monitors the number of data packets lost in network communication. Usually a high packet loss rate means poor network quality or unstable communication, Bit error rate: Analyzes the ratio of transmission errors during data transmission. A high bit error rate indicates that there may be network failures or signal interference, Network stability: Detects whether the network is frequently interrupted, fluctuates, or has sudden network problems.

[0029] It is understandable that through comprehensive network quality indicator collection, the platform can obtain detailed information about the network in real time, providing data support for optimizing network performance and solving network problems. Through parameters such as packet loss rate, delay and signal strength, the platform can provide early warning when network quality deteriorates to avoid affecting task execution.

[0030] More specifically, the platform transmits the collected network quality data to the central control system or distributed network nodes through communication systems (such as Wi-Fi, 5G, Mesh networks, etc.) for centralized storage and processing. The central control system or dedicated monitoring system can receive network quality data from all platforms and display and monitor them in real time. Through a graphical interface or data dashboard, managers can intuitively understand the network status of the entire array, and can view the network quality characteristics of each autonomous platform in real time to ensure a clear understanding of the global network status. Through the real-time monitoring panel, users can view the trend of network quality changes and make timely adjustments.

[0031] More specifically, all collected network quality data will be analyzed and evaluated. Common analysis methods include: Trend analysis: Analyze the changing trends of data such as latency, packet loss rate, bandwidth, etc. to discover potential problems with network quality; Network quality scoring: Score the network quality of each platform, and comprehensively evaluate the stability and reliability of the network based on factors such as latency, bandwidth, packet loss rate, and signal strength; Anomaly detection and fault location: Based on the collected network data, the system can automatically detect network anomalies (such as packet loss, excessive latency, etc.) and locate the cause of the problem. Through data analysis, it can provide support for subsequent optimization decisions. For example, when the signal strength of a certain area is detected to drop, the system can adjust the platform's communication strategy. Through real-time data analysis, the system can quickly locate network problems and reduce task delays and service interruptions caused by network failures.

[0032] More specifically, when it is detected that the network quality of a certain platform or a certain area is poor, the system can restore the normal network status or reduce the impact through a series of optimization measures: Signal enhancement: By adjusting the communication parameters of the platform or adjusting the location of the network access point, the signal strength is improved; Load balancing: Through intelligent scheduling, the data traffic is reasonably distributed to the communication nodes with stronger signals and lower loads in the network to optimize bandwidth allocation; Path switching: When a communication link is found to be abnormal, the platform can restore the network connection through path switching (such as switching to another communication protocol or switching to a different base station); Fault recovery: If a serious network failure is detected (such as the disconnection between the platform and the network), the system will trigger an automatic recovery mechanism, such as restarting the communication module or reconnecting to the backup network; Through network optimization means, the platform can quickly restore the network connection to ensure the smooth progress of the task, optimize network traffic and paths, reduce network load, and improve the communication efficiency and reliability of the platform.

[0033] More specifically, network quality detection is not just a one-time task, it should be an ongoing process. The platform will generate network quality reports regularly or in real time. Administrators can view the network health of each platform through the report and make timely adjustments. The report content includes latency, packet loss rate, bandwidth, signal strength, network quality score, etc., to help managers analyze and evaluate network performance. Through long-term data monitoring and evaluation, the platform's network connection can be gradually optimized to avoid network problems affecting task execution. Through network quality reports, managers can grasp the network status of each platform at any time and provide a basis for decision-making.

[0034] It is understandable that through the detection and evaluation of multi-dimensional network quality characteristics such as latency, bandwidth, packet loss rate, signal strength, etc., the platform can fully understand the status of the network connection. Through the real-time monitoring system, it can grasp the changes in network quality at any time and take optimization measures as needed. Through data analysis and trend monitoring, it can identify potential problems before the network quality deteriorates and provide early warning to avoid communication interruptions during task execution. The platform has an intelligent network optimization and fault recovery mechanism, which can automatically adjust when network problems are detected to ensure that tasks are not interrupted. Through data analysis and network quality reports, managers can make scientific decisions to improve network quality and platform communication efficiency.

[0035] Specifically, in step S4 of the embodiment provided by the present invention, each autonomous mobile platform will continuously collect environmental perception data (such as vision, lidar, ultrasonic sensor data, etc.) and network quality feature data (such as delay, bandwidth, signal strength, etc.) during operation. First, it is necessary to ensure that each data source (perception data and network quality data) can be collected synchronously and have a unified timestamp. The environmental perception data includes information about the environment around the platform, such as obstacle location, motion status, map data, temperature and humidity, air pressure, etc. The network quality feature data includes real-time indicators of communication quality between platforms, such as network delay, packet loss rate, bandwidth, signal strength, etc., to ensure that data from different platforms have consistent timestamps to avoid data distortion or timing disorder, thereby providing a basis for subsequent data integration processing.

[0036] More specifically, the collected data usually contains noise, missing values ​​or outliers, and needs to be preprocessed and cleaned, mainly including: Noise filtering: Use filtering algorithms (such as Kalman filtering, mean filtering, etc.) to suppress noise in environmental perception data, Data filling: For missing data, you can use interpolation algorithms or model-based filling methods (such as KNN-based filling, time series analysis, etc.), Anomaly detection and elimination: Detect and remove abnormal data through statistical methods or machine learning models, and remove noise and abnormal data through data cleaning to ensure the accuracy of subsequent analysis, ensure the accuracy and completeness of environmental perception data, and make the output of the model more credible.

[0037] More specifically, the network quality feature data of each platform is associated and fused with the environmental perception data. To ensure that the perception data and network quality data can be combined, it is usually necessary to process them in the following ways: align the environmental perception data and network quality feature data through timestamps to ensure that the data at each time point can match, and map the network quality features (such as delay, packet loss rate, etc.) to the context of the perception data. For example, the sensor data of a certain platform may produce errors under high latency conditions. At this time, it is necessary to consider the impact of delay on the perception data, set weight values ​​for the network quality features of each platform, and dynamically adjust the weights according to the network quality. For example, when the network of a certain platform is poor, the perception data of the platform may be processed with low weight to reduce the impact on the data set. Through time alignment and feature mapping, the perception data and network quality data from different platforms can be effectively fused, so that the final data set contains more dimensional information. Through weighted fusion technology, the impact of poor network quality can be reduced and the accuracy and reliability of the data set can be improved.

[0038] More specifically, after data fusion, the perception data and network quality feature data of all platforms will be merged into a unified perception network data set. This data set needs to be processed in a specific format to facilitate subsequent analysis, storage and use. Common processing steps include: Data normalization: The perception data and network data of different platforms need to be normalized so that they can be compared under the same dimension. Data grouping and encoding: According to different platforms, different sensor types and data sources, the data are grouped and encoded. Each group of data should contain timestamp, platform ID, perception data and network quality features. Data storage: The integrated data is stored in an efficient database or distributed storage system for real-time query and analysis. Multiple heterogeneous data sources are formatted into a unified data structure to improve data processing efficiency. The integrated data is stored in a database to support efficient query and data extraction, ensuring the scalability and maintainability of the system.

[0039] More specifically, after data integration, the resulting perception network data set can be used for further analysis and processing. The main tasks include: Network impact analysis: Analyze the impact of different network qualities on environmental perception data; for example, in the case of high latency, the perception data may be misaligned in time, resulting in position deviations, etc.; Task planning and scheduling: Based on perception data and network quality, dynamically adjust the execution strategy of platform tasks. For example, when the network quality of a platform is poor, the scheduling system can select other platforms to take on more tasks to avoid task failures or delays. Based on the integrated data, apply machine learning models for anomaly detection, identify potential errors or abnormal behaviors in environmental perception data, and make timely adjustments.

[0040] More specifically, by analyzing the data set, we can provide a scientific basis for collaboration and task scheduling between platforms to ensure the smooth execution of tasks. By analyzing the impact of network quality on perception data, we can optimize the collection and processing strategies of perception data for different network environments.

[0041] More specifically, when the system finds problems with network quality or environmental perception data, the feedback mechanism will send optimization instructions to each platform based on preset rules or the output of the machine learning model; for example: if the network quality affects the accuracy of the perception data, it can be optimized by optimizing the network path, adjusting the bandwidth, increasing the signal gain, etc. Based on the analysis results, the system can adjust the working mode of the perception module (such as adjusting the sampling frequency of the sensor or adjusting the perception accuracy) to reduce data errors. When the system finds problems with the network or perception data, it can provide timely feedback and optimization adjustments to ensure data quality. Through continuous optimization and adjustment, the system can maintain efficient and stable operation under different network environments and perception conditions.

[0042] It can be understood that by fusing environmental perception data with network quality data, a perception network data set containing rich information is formed, which can comprehensively reflect the status and environmental conditions of the platform. Through data preprocessing, fusion and weighting technology, the impact of noise and anomalies on the data is reduced, and the accuracy and reliability of the data set are improved. Through integrated data analysis, the task scheduling, network usage and perception strategies of the platform can be optimized in real time to ensure efficient collaboration and task execution between platforms. According to the network quality of the platform, the weight and influence of the perception data can be automatically adjusted to maintain the stability and efficiency of the system in different network environments.

[0043] Specifically, in step S5 of the embodiment provided by the present invention, the acquired perception network data set, including environmental perception data, platform status information and network quality characteristics, is used to perform preliminary screening and cleaning of the data. The goal of this process is to remove irrelevant, noisy or incomplete data in order to better establish a real-life simulation model. The cleaning process includes: filtering out lost data, erroneous data, duplicate data and outliers, performing time synchronization and spatial alignment on the data to ensure that the perception data and the status information of the platform array can be accurately matched, removing interfering data, improving the accuracy of subsequent modeling, and aligning the data in time and space to ensure consistency and timeliness of the data, laying the foundation for subsequent analysis.

[0044] More specifically, the cleaned perception network dataset is used to establish a digital model of the platform array through modeling methods (such as those based on physical models, machine learning, neural networks, etc.). This digital model will integrate the physical characteristics of the platform, perception data and network quality, simulate the working status and behavior of the entire array, and establish physical connection models, motion models, task collaboration models, etc. between platforms. The perception data and platform status data are used to train machine learning models (such as deep neural networks, support vector machines, etc.) to predict and simulate the behavior of the platform array. Intelligent algorithms, such as reinforcement learning and multi-agent collaboration algorithms, are introduced into the model to enhance the adaptability of the platform array. Through digital modeling, a highly accurate virtual model of the machine service platform array is formed that can reflect the dynamic behavior of the array. Through the model, real-time behavior prediction and status simulation can be performed to provide support for subsequent decision-making.

[0045] More specifically, various interference information (such as noise, signal loss, sensor failure, etc.) often appears during the operation of the platform array. These interferences will affect the accuracy and stability of the model. Therefore, based on the digital model, a set of interference identification and elimination mechanisms needs to be designed: using anomaly detection algorithms (such as statistical threshold detection, anomaly detection technology in machine learning models, etc.) to identify the interference components in the data, and once the interference information is identified, it is immediately filtered out, corrected or replaced. Commonly used methods include interpolation algorithms (such as Lagrange interpolation), Kalman filters, or advanced denoising algorithms (such as wavelet transform, deep learning denoising, etc.). The model makes real-time adjustments to the exclusion of interference information to ensure that the platform array can continue to operate stably under interference conditions, effectively identify and remove interference information, improve the accuracy and stability of the model, and enhance the adaptability of the platform array to the interference environment to ensure that it can still operate stably in complex environments.

[0046] More specifically, after removing the interference information, the constructed digital model is simulated in real time. Through this simulation model, the operating status of the platform array can be fed back in real time and its behavior can be optimized. At this time, the simulation model can predict the performance of the platform array under different working conditions and perform the following steps: update the simulation model in real time according to the perception network data set to ensure that the model can reflect the real-time status of the current array. Based on the simulation results, the array status is evaluated and the system behavior at the next moment is predicted. The evaluation results will be used to dynamically adjust the control strategy of the platform array. Through the simulation feedback mechanism, the behavior of each platform in the array is adjusted in real time. For example, when a platform is detected to be in a poor network state, its task allocation is adjusted or its tasks are transferred to other platforms. Through the live simulation model, the working status of each platform in the array can be fed back in real time to ensure the accuracy and efficiency of task execution. According to the feedback of the simulation model, the working strategy and task scheduling of the platform array can be flexibly adjusted to improve the task completion.

[0047] More specifically, the constructed real-time simulation model needs to be verified and optimized to ensure that it can accurately reflect the behavior of the platform array in the real environment. Verification and optimization are carried out through the following steps: verify the accuracy and effectiveness of the simulation model through the simulation environment, check whether it can accurately predict the array behavior, adjust and optimize the model parameters according to the verification results, and improve its performance in specific scenarios. During the actual operation process, the model is optimized online in combination with real-time perception data and feedback information to gradually improve the accuracy and adaptability of the model. Through verification and optimization, the accuracy of the simulation model is further improved so that it can better adapt to the complex actual environment. Through online optimization, it is ensured that the model can maintain efficient and stable performance in different environments.

[0048] It is understandable that through digital modeling and interference elimination, a high-precision live simulation model can be generated to reflect the behavior of the platform array in real time and optimize the task execution strategy. Through the identification and elimination of interference information, the platform array can maintain stable operation when facing different types of interference, enhancing the robustness of the system. Through real-time simulation and feedback mechanisms, the behavior of the platform array can be dynamically adjusted, resource allocation and task scheduling can be optimized, and the work efficiency of the system can be improved. The feedback provided by the live simulation model provides a basis for the intelligent decision-making of the platform array, helping the platform to make more reasonable work arrangements and task decisions.

[0049] The present invention provides a multiple access interference management method based on communication perception integration, which has the following beneficial effects: The present invention uses a sensor group on an autonomous mobile machine service platform to perform environmental perception and obtain environmental perception data, performs network service quality detection on each autonomous mobile machine service platform to obtain network quality characteristics, performs data integration processing on the environmental perception data according to the network quality characteristics to obtain a perception network data set, performs digital modeling based on the perception network data set to obtain a real-time simulation model, eliminates interference information and provides real-time information feedback. This method can effectively integrate communication and perception functions, improve communication quality and stability, enhance the collaborative working ability of the autonomous mobile machine service platform, and solves the problem in the prior art that interference generated by multiple devices when communicating simultaneously affects the overall performance of the system.

[0050] Preferably, the step of obtaining array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and driving the machine service platform array to perform collaborative work in a designated area according to the array performance information comprises: S11: performing information identification of array constituent units of the machine service platform array to obtain array numbers of each autonomous mobile machine service platform in the machine service platform array; S12: Retrieving individual performance information and collaborative performance information of each autonomous mobile machine service platform from a designated database based on the array number of each autonomous mobile machine service platform; wherein the individual performance information and collaborative performance information of each autonomous mobile machine service platform in the machine service platform array together constitute the array performance information of the machine service platform array; S13: Acquire area type information of a designated area of ​​the machine service platform array to be used for collaborative work; S14: analyzing the adaptability of the array working range and the array working discrete form of the machine service platform array according to the area type information, so as to obtain the array working range adaptability characteristic distribution and the array working discrete form adaptability characteristic distribution of the machine service platform array corresponding to the specified area; S15: analyzing the theoretical optimal collaborative working mode of the machine service platform array according to the array working range adaptation characteristic distribution and the array working discrete form adaptation characteristic distribution, so as to obtain the initial working mode of the machine service platform array corresponding to the designated area; S16: Allocate work tasks to each of the autonomous mobile machine service platforms in the machine service platform array based on the initial work mode, so that each of the autonomous mobile machine service platforms can work collaboratively in a designated area according to the allocated work tasks.

[0051] Specifically, the machine service platform array is identified, and the array number of each autonomous mobile machine service platform is determined and recorded to ensure that the identity and location of each machine service platform in the array are clear, thereby achieving more accurate control and management.

[0052] More specifically, based on the array number of each autonomous mobile machine service platform, its individual performance information and collaborative performance information are retrieved from the designated database to obtain detailed performance data of each machine service platform (such as speed, load capacity, endurance, etc.) and their performance in collaboration (such as synchronization capability, communication delay, etc.), providing basic data for subsequent task allocation and collaborative work.

[0053] More specifically, obtaining the area type information (such as terrain, area, obstacle distribution, etc.) of the designated area where the machine service platform array is to perform collaborative work and understanding the environmental characteristics of the work area will help to formulate more effective work strategies and avoid potential operational risks.

[0054] More specifically, based on the regional type information, the adaptability of the machine service platform array in terms of array working range and array working discrete form is analyzed to obtain the distribution of array working range adaptation characteristics and the distribution of array working discrete form adaptation characteristics, and to evaluate the feasibility and adaptability of the machine service platform array in a specific area, thereby ensuring the reasonable distribution and efficient operation of the machine service platform in terms of working range and working form.

[0055] More specifically, according to the above-mentioned adaptive feature distribution, the theoretical optimal collaborative working mode of the machine service platform array is analyzed to obtain the initial working mode, and the optimal collaborative working mode is designed based on the analysis results to maximize the overall performance of the array and the task completion efficiency.

[0056] More specifically, based on the initial working mode, work tasks are assigned to each autonomous mobile machine service platform in the machine service platform array so that they can work together in a designated area according to the assigned tasks, ensuring that each machine service platform has a clear task, optimizing resource utilization, and improving overall work efficiency and task completion quality.

[0057] It can be understood that by obtaining the number and performance information, accurate identification and effective scheduling of each autonomous mobile machine service platform can be achieved. Through adaptive analysis and work mode optimization, efficient collaborative work of the machine service platform array in the designated area can be ensured. On the basis of a full analysis of the area type information, a reasonable work mode can be planned to reduce operational risks and improve the reliability and safety of the system. Through reasonable task allocation, the resources of each machine service platform (such as electricity and load capacity) can be optimally utilized to avoid waste of resources. The system has the ability to make dynamic adjustments based on actual working conditions, thereby improving the flexibility and adaptability of the system.

[0058] Preferably, the step of performing environmental perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array to obtain environmental perception data of each of the autonomous mobile machine service platforms includes: S21: activating the environment recognition sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, and performing environmental perception of the environment in which the autonomous mobile machine service platform is located through the environment recognition sensor group to obtain external environment data of the autonomous mobile machine service platform; wherein the environment recognition sensor group includes an image sensor, an infrared sensor, and an acoustic sensor; S22: Start the array positioning sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, and collect information about the relative positioning of the autonomous mobile machine service platform with respect to the other autonomous mobile machine service platforms through the array positioning sensor group to obtain the array positioning data of the autonomous mobile machine service platform in the machine service platform array; wherein the array positioning sensor group includes a laser radar sensor, an inertial measurement sensor, and a wireless signal ranging sensor; S23: fusing the external environment data of the autonomous mobile machine service platform with the array positioning data to obtain the environment perception data of the autonomous mobile machine service platform.

[0059] Specifically, the pre-set environmental recognition sensor group on the autonomous mobile machine service platform is started, including image sensors, infrared sensors and acoustic wave sensors. The image sensor captures and records visual information of the surrounding environment, such as object shape, color, texture, etc. The infrared sensor detects heat sources and temperature changes, and is used to perceive thermal imaging data in the environment. The acoustic wave sensor reflects information through sound waves, detects and identifies sound wave patterns and obstacles in the environment, and obtains comprehensive environmental perception data, including visual, temperature and acoustic wave information, to ensure multi-dimensional and high-precision environmental perception.

[0060] More specifically, the array positioning sensor group pre-set on the autonomous mobile machine service platform is started, including a lidar sensor, an inertial measurement sensor and a wireless signal ranging sensor. The lidar sensor measures the distance and shape of surrounding objects through laser scanning to establish a high-precision three-dimensional environmental model. The inertial measurement sensor (IMU) measures the acceleration, angular velocity and azimuth of the machine, and provides motion status and posture information. The wireless signal ranging sensor measures the relative distance using the change in wireless signal strength to achieve high-precision positioning of the relative position, obtain the relative position and motion status between the autonomous mobile machine service platform and other platforms, and ensure the high accuracy and real-time nature of the positioning data.

[0061] More specifically, the external environment data and array positioning data of the autonomous mobile machine service platform are fused, and the data from image, infrared and acoustic wave sensors are integrated to form a unified environmental perception map. The lidar, inertial measurement and wireless signal ranging data are combined to form an accurate relative position and motion state map. Through data fusion technology, the accuracy and reliability of environmental perception and positioning data are improved, and comprehensive environmental perception data of the autonomous mobile machine service platform is generated.

[0062] It is understandable that through the combination of image, infrared and acoustic wave sensors, the visual, temperature and acoustic information of the environment can be fully perceived, the comprehensiveness and accuracy of perception can be improved, and laser radar, inertial measurement and wireless signal ranging technology can be combined to achieve high-precision relative positioning and motion state detection, ensure the coordination of the platform array, and through efficient data processing and fusion algorithms, the real-time update of environmental perception and positioning data can be achieved to ensure the real-time response capability of the autonomous mobile machine service platform. Based on real-time data, the path and behavior of the autonomous mobile machine service platform can be automatically adjusted to improve the flexibility and adaptability of task execution. The redundant design of multiple sensors improves the reliability of the system. Even if a sensor fails, it can be compensated by the data of other sensors to ensure the stable operation of the overall system. Through data fusion technology, the impact of single sensor data errors can be reduced to improve the overall fault tolerance of environmental perception and positioning.

[0063] Preferably, the step of performing network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms includes: S31: Performing network quality detection on each of the autonomous mobile machine service platforms based on a predetermined network quality detection indicator to obtain detection parameters of each of the autonomous mobile machine service platforms corresponding to the network quality detection indicator; wherein the network quality detection indicator includes delay, bandwidth, packet loss rate, jitter, and signal strength; S32: Performing a weighted comprehensive analysis on the detection parameters of each of the autonomous mobile machine service platforms corresponding to the network quality detection index according to a weight model to obtain network quality characteristics of each of the autonomous mobile machine service platforms.

[0064] Specifically, determine the network quality detection indicators, which include latency, bandwidth, packet loss rate, jitter and signal strength. Latency: the time required for a data packet to reach the destination from the source. Bandwidth: the amount of data that can be transmitted per unit time. Packet loss rate: the proportion of data packets lost during transmission. Jitter: the rate of change of data packet transmission delay. Signal strength: the strength of the wireless signal, usually expressed in dBm. Clarify the key parameters of network quality detection and provide standards for subsequent detection and analysis.

[0065] More specifically, based on predetermined network quality detection indicators, network quality detection is performed on each autonomous mobile machine service platform to obtain various detection parameters, the ping command or other delay detection tools are used to measure the round-trip time of the data packet, and a bandwidth testing tool (such as iPerf) is used to measure the maximum data transmission volume per unit time. The packet loss rate is calculated by sending a large number of data packets and recording the number of lost data packets. The delay variation between consecutive data packets is analyzed and the jitter value is calculated. The strength of the wireless signal is measured through a wireless network adapter or a signal strength detection tool. The specific detection parameters of each autonomous mobile machine service platform under different network quality detection indicators are obtained to provide basic data for subsequent analysis.

[0066] More specifically, according to the weight model, a weighted comprehensive analysis is performed on the detection parameters of the network quality detection indicators corresponding to each autonomous mobile machine service platform. The weight of each network quality detection indicator is determined according to the application scenario and requirements. For example, the weights of delay and jitter can be increased according to the real-time requirements of the task. For example: the delay weight is 0.3, the bandwidth weight is 0.2, the packet loss rate weight is 0.2, the jitter weight is 0.2, and the signal strength weight is 0.1. Each detection parameter is multiplied by the corresponding weight, and then the weighted sum is performed to obtain the comprehensive network quality score of each autonomous mobile machine service platform. The formula is: comprehensive network quality score = (delay parameter × delay weight) + (bandwidth parameter × bandwidth weight) + (packet loss rate parameter × packet loss rate weight) + (jitter parameter × jitter weight) + (signal strength parameter × signal strength weight). Through weighted comprehensive analysis, the network quality characteristics of each autonomous mobile machine service platform are obtained, and a comprehensive network quality evaluation is provided to provide a basis for task allocation and system optimization.

[0067] It is understandable that through the detection of multiple dimensions such as delay, bandwidth, packet loss rate, jitter and signal strength, the network quality is comprehensively evaluated, and the detection parameters are weightedly analyzed using a weight model to generate high-precision network quality characteristics. Through real-time network quality detection, the current network status of each autonomous mobile machine service platform is timely obtained. According to the comprehensive network quality characteristics, task allocation and path planning are dynamically adjusted to improve the flexibility and adaptability of the system. Through comprehensive analysis of various parameters, network bottlenecks and failure points are identified, and measures are taken in advance to improve the reliability and stability of the system. According to network quality characteristics, resource allocation is optimized to ensure that key tasks give priority to high-quality network resources. Based on network quality characteristics, tasks are reasonably allocated to avoid platforms with poor network quality from performing key tasks and improve overall efficiency. Through comprehensive evaluation of network quality characteristics, network configuration and parameters are optimized in a targeted manner to improve the overall performance of the system.

[0068] Preferably, the step of performing data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms to obtain a perception network data set includes: S41: Based on the array positioning data of each of the autonomous mobile machine service platforms in the machine service platform array, a comprehensive analysis is performed on the overall position distribution status of each of the autonomous mobile machine service platforms in the machine service platform array to obtain an array distribution topology structure of the machine service platform array; wherein the array distribution topology structure includes a plurality of topological nodes and a topological relationship between each of the topological nodes; S42: performing an environmental perception relationship analysis on the array distributed topology structure according to the array performance information to obtain an environmental perception information interaction relationship between each of the topological nodes in the array distributed topology structure, and constructing an information perception feature network of the array distributed topology structure based on the environmental perception information interaction relationship between each of the topological nodes in the array distributed topology structure; S43: Substituting the network quality characteristics of each of the autonomous mobile machine service platforms into the array distribution topology structure to obtain an information quality characteristic network of the machine service platform array; S44: Allocating tasks for information perception of a designated area to the array distribution topology structure according to the information perception feature network and the information quality feature network, so as to obtain a perception task feature network composed of information perception tasks of each of the topological nodes in the array distribution topology structure; S45: dividing, marking and combining the external environment data of the autonomous mobile machine service platform corresponding to each of the topological nodes according to the perception task feature network to obtain a perception network data set of the machine service platform array.

[0069] Specifically, obtain positioning data: obtain array positioning data from each autonomous mobile machine service platform in the machine service platform array, conduct a comprehensive analysis of the overall location distribution status of the entire machine service platform array, and construct an array distribution topology structure, which includes several topological nodes and the topological relationships between the nodes.

[0070] More specifically, array performance information is obtained, such as sensor data and mobility performance of each platform. According to the array performance information, the environmental perception information interaction relationship between each topological node in the topological structure is analyzed. Based on the above information interaction relationship, a network describing the information perception characteristics of the topological structure is constructed. The network quality characteristics (such as bandwidth, delay, packet loss rate, etc.) of each autonomous mobile machine service platform are substituted into the array distribution topology structure to obtain a network describing the information quality characteristics of the machine service platform array.

[0071] More specifically, according to the information perception feature network and the information quality feature network, the information perception tasks of the designated areas are allocated to the array distribution topology structure, forming a network composed of the information perception tasks of each topological node.

[0072] More specifically, according to the perception task feature network, the external environment data of the autonomous mobile machine service platform corresponding to each topological node is divided, labeled and combined, and finally a perception network dataset of a complete machine service platform array is obtained.

[0073] It can be understood that by comprehensively analyzing positioning data and environmental perception information, ensuring the accuracy of data integration, effectively utilizing information perception feature networks and information quality feature networks, and improving data processing efficiency, the system resources can be reasonably allocated through the task allocation step to ensure that each autonomous mobile machine service platform performs perception tasks in the most appropriate area, and constructing a perception task feature network, which helps to better manage and schedule tasks. The use of information interaction relationships and network quality characteristics maximizes environmental perception capabilities, enabling the platform to more accurately perceive and respond to changes in the external environment, and provide an accurate and efficient perception network data set to help further analysis and decision-making.

[0074] Preferably, the step of allocating tasks for information perception of a designated area to the array distribution topology structure according to the information perception feature network and the information quality feature network to obtain a perception task feature network composed of information perception tasks of each of the topological nodes in the array distribution topology structure includes: S441: performing initial allocation of topological node perception ranges to a designated area where the machine service platform array is located based on the information perception feature network, so as to obtain initial perception tasks of each of the topological nodes in the array distribution topology structure; S442: performing node task upload quality evaluation on the initial perception task of each topological node in the array distributed topological structure according to the information quality characteristic network, so as to obtain the perception quality parameters of the initial perception task of each topological node and the overall perception quality characteristics of the array distributed topological structure; S443: optimizing the allocation of initial perception tasks of each of the topological nodes in the array distributed topological structure based on the overall perception quality characteristics of the array distributed topological structure and the perception quality parameters of each of the topological nodes, so as to obtain optimized perception tasks of each of the topological nodes; S444: marking the optimized perception task as an initial perception task, and returning to the step of performing node task upload quality evaluation on the initial perception task of each of the topological nodes in the array distributed topological structure according to the information quality feature network to obtain the perception quality parameters of the initial perception tasks of each of the topological nodes and the overall perception quality characteristics of the array distributed topological structure, and repeating the above steps in a loop until the initial perception task with the best perception quality parameters and overall perception quality characteristics is obtained; S445: taking each initial perception task with the best perception quality parameter and the overall perception quality feature as the information perception task of each topological node in the array distribution topology structure to obtain a perception task feature network.

[0075] Specifically, the information perception feature network is used to initially allocate the topological node perception range to the designated area where the machine service platform array is located, determine the initial perception task of each topological node in the array distributed topology structure, and perform node task upload quality evaluation on the initial perception task of each topological node to obtain the perception quality parameters of the initial perception task of each topological node, and obtain the overall perception quality characteristics of the array distributed topology structure.

[0076] More specifically, the initial perception tasks of each topological node in the array distribution topology structure are allocated and optimized based on the overall perception quality characteristics and the node perception quality parameters to obtain the optimized perception tasks of each topological node, mark the optimized perception tasks as the initial perception tasks, mark the optimized perception tasks as the new initial perception tasks, return to the node task upload quality assessment step, repeat the above process, perform iterative optimization, and stop the loop when the best perception quality parameters and overall perception quality characteristics are obtained.

[0077] More specifically, the best initial perception task of each topological node is taken as its information perception task, and finally a perception task feature network composed of these optimized information perception tasks is obtained.

[0078] It can be understood that the rationality and effectiveness of task allocation are ensured through the initial allocation and quality assessment steps. Through multiple optimizations and iterations, the effect of task allocation is gradually improved until the optimal state is reached. The perception quality parameters of each topological node and the overall perception quality characteristics are comprehensively considered to ensure the high quality of the perception data. The final perception task feature network has the best perception quality parameters to ensure the accuracy and reliability of the data. Through iterative optimization, the system can dynamically adjust the perception task allocation to adapt to different environments and conditions. The optimized perception task feature network improves the robustness and stability of the system under different network conditions. By constructing the perception task feature network, the management and scheduling of the autonomous mobile machine service platform are simplified, making the task allocation process more transparent and controllable, and improving the predictability of system operation.

[0079] Preferably, the step of performing information feedback processing of digital modeling of the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array includes: S51: performing information analysis processing on array distribution and environmental conditions on the perception network data set to obtain machine service platform array distribution information and machine service platform array environmental information fed back by the perception network data set; S52: Digital modeling of the array body and the environment of the machine service platform array is performed on the machine service platform array according to the machine service platform array distribution information and the machine service platform array environment information, so as to obtain a real-time simulation model corresponding to the machine service platform array.

[0080] Specifically, through the perception network, various data about the machine service platform array are collected, including location data, status data, environmental data, etc., the perception network data set is parsed, the location information, motion trajectory, etc. of the machine service platform are extracted, and array distribution information is formed. The environmental data in the perception network data set is parsed to obtain environmental information including terrain, weather, obstacles, etc.

[0081] More specifically, a location information model of the machine service platform is established based on the array distribution information. A state model of the machine service platform (such as power, load, etc.) is established based on the state data. A terrain model is established based on the terrain data in the environmental information. An obstacle model is established based on the obstacle data in the environmental information. A meteorological condition model of the environment is established based on the meteorological data.

[0082] More specifically, the array ontology model is integrated with the environmental model to form a unified digital model. The digital model is run to simulate the operation of the machine service platform array in the actual environment. The digital model is updated in real time according to the latest perception network data set to ensure the accuracy and real-time performance of the simulation.

[0083] It can be understood that through the detailed analysis of the perception network dataset, accurate information about the machine service platform array and the environment can be obtained. Through detailed modeling steps, the refinement and accuracy of the model can be ensured, providing a reliable basis for subsequent simulation. The digital model can be updated in real time according to the latest perception data to ensure that the simulation results are highly consistent with the actual situation. Through comprehensive modeling, a comprehensive simulation of the machine service platform array and its environment can be achieved.

[0084] Reference Figure 2 As shown, in a second aspect, the present invention provides a multiple access interference management device based on integrated communication perception, which is used to implement a multiple access interference management method based on integrated communication perception as described in any one of the first aspects, including: An information acquisition module, used to acquire array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and drive the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; An environment perception module, used to perform environment perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, so as to obtain environment perception data of each of the autonomous mobile machine service platforms; A network detection module, used to perform network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; A data integration module, configured to perform data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms, so as to obtain a perception network data set; An information simulation module is used to process information feedback of digitally modeling the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to provide real-time information feedback to the machine service platform array after eliminating interference information.

[0085] In this embodiment, for the specific implementation of each module in the above-mentioned device embodiment, please refer to the above-mentioned method embodiment, which will not be described in detail here.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multiple access interference management method based on integrated communication perception, characterized in that: include: Acquiring array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and driving the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; Performing environmental perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array to obtain environmental perception data of each of the autonomous mobile machine service platforms; Performing network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; Performing data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms to obtain a perception network data set; The information feedback of the digital modeling of the machine service platform array is processed according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to feedback the real-time information of the machine service platform array after eliminating interference information.

2. The multiple access interference management method based on communication perception integration according to claim 1, characterized in that: The steps of obtaining array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and driving the machine service platform array to perform collaborative work in a designated area according to the array performance information include: Identifying information of array constituent units of the machine service platform array to obtain array numbers of each autonomous mobile machine service platform in the machine service platform array; Based on the array number of each autonomous mobile machine service platform, the individual performance information and the collaborative performance information of each autonomous mobile machine service platform are retrieved from a designated database; wherein the individual performance information and the collaborative performance information of each autonomous mobile machine service platform in the machine service platform array together constitute the array performance information of the machine service platform array; Obtaining area type information of a designated area for the machine service platform array to work collaboratively; Analyzing the adaptability of the array working range and the array working discrete form of the machine service platform array according to the area type information, so as to obtain the array working range adaptability characteristic distribution and the array working discrete form adaptability characteristic distribution of the machine service platform array corresponding to the specified area; Analyzing the theoretical optimal collaborative working mode of the machine service platform array according to the array working range adaptation characteristic distribution and the array working discrete form adaptation characteristic distribution, so as to obtain the initial working mode of the machine service platform array corresponding to the designated area; Based on the initial working mode, work tasks are allocated to each of the autonomous mobile machine service platforms in the machine service platform array, so that each of the autonomous mobile machine service platforms can work collaboratively in a designated area according to the allocated work tasks.

3. The multiple access interference management method based on communication perception integration as claimed in claim 1, characterized in that: The steps of performing environmental perception processing on a designated area by using a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array to obtain environmental perception data of each of the autonomous mobile machine service platforms include: Starting the environment recognition sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, and performing environmental perception of the environment in which the autonomous mobile machine service platform is located through the environment recognition sensor group to obtain external environment data of the autonomous mobile machine service platform; wherein the environment recognition sensor group includes an image sensor, an infrared sensor, and an acoustic sensor; Start the array positioning sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, and collect information about the relative positioning of the autonomous mobile machine service platform with respect to the other autonomous mobile machine service platforms through the array positioning sensor group to obtain the array positioning data of the autonomous mobile machine service platform in the machine service platform array; wherein the array positioning sensor group includes a laser radar sensor, an inertial measurement sensor, and a wireless signal ranging sensor; The external environment data of the autonomous mobile machine service platform and the array positioning data are fused to obtain the environment perception data of the autonomous mobile machine service platform.

4. The multiple access interference management method based on communication perception integration as claimed in claim 1, characterized in that: The step of performing network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms includes: Performing network quality detection on each of the autonomous mobile machine service platforms based on a predetermined network quality detection indicator to obtain detection parameters of each of the autonomous mobile machine service platforms corresponding to the network quality detection indicator; wherein the network quality detection indicator includes delay, bandwidth, packet loss rate, jitter, and signal strength; A weighted comprehensive analysis is performed on the detection parameters of each of the autonomous mobile machine service platforms corresponding to the network quality detection index according to the weight model to obtain the network quality characteristics of each of the autonomous mobile machine service platforms.

5. The multiple access interference management method based on communication perception integration as claimed in claim 3, characterized in that: The step of performing data integration processing on the environmental perception data of each autonomous mobile machine service platform according to the network quality characteristics of each autonomous mobile machine service platform to obtain a perception network data set includes: According to the array positioning data of each of the autonomous mobile machine service platforms in the machine service platform array, a comprehensive analysis is performed on the overall position distribution status of each of the autonomous mobile machine service platforms in the machine service platform array to obtain an array distribution topology structure of the machine service platform array; wherein the array distribution topology structure includes a plurality of topological nodes and a topological relationship between each of the topological nodes; Performing an environmental perception relationship analysis on the array distributed topology structure according to the array performance information to obtain an environmental perception information interaction relationship between each of the topological nodes in the array distributed topology structure, and constructing an information perception feature network of the array distributed topology structure based on the environmental perception information interaction relationship between each of the topological nodes in the array distributed topology structure; Substituting the network quality characteristics of each of the autonomous mobile machine service platforms into the array distribution topology structure to obtain an information quality characteristic network of the machine service platform array; Allocating tasks for information perception of a designated area of ​​the array distribution topology structure according to the information perception feature network and the information quality feature network to obtain a perception task feature network composed of information perception tasks of each of the topological nodes in the array distribution topology structure; The external environment data of the autonomous mobile machine service platform corresponding to each of the topological nodes is divided, marked and combined according to the perception task feature network to obtain a perception network data set of the machine service platform array.

6. The multiple access interference management method based on communication perception integration as claimed in claim 5, characterized in that: The steps of allocating tasks for information perception of a designated area of ​​the array distribution topology structure according to the information perception feature network and the information quality feature network to obtain a perception task feature network composed of information perception tasks of each topological node in the array distribution topology structure include: Based on the information perception feature network, an initial allocation of topological node perception ranges is performed on a designated area where the machine service platform array is located, so as to obtain an initial perception task of each topological node in the array distribution topology structure; Performing node task upload quality evaluation on the initial perception task of each topological node in the array distributed topological structure according to the information quality feature network, so as to obtain the perception quality parameters of the initial perception task of each topological node and the overall perception quality characteristics of the array distributed topological structure; Based on the overall perception quality characteristics of the array distribution topology structure and the perception quality parameters of each topology node, the initial perception task of each topology node in the array distribution topology structure is optimized to obtain the optimized perception task of each topology node; Marking the optimized perception task as an initial perception task, and returning to the step of performing node task upload quality evaluation on the initial perception task of each of the topological nodes in the array distributed topological structure according to the information quality feature network to obtain the perception quality parameters of the initial perception tasks of each of the topological nodes and the overall perception quality characteristics of the array distributed topological structure, and repeating the above steps in a loop until the initial perception task with the best perception quality parameters and overall perception quality characteristics is obtained; The initial perception tasks of the perception quality parameters with the best effects and the overall perception quality characteristics are used as the information perception tasks of each of the topological nodes in the array distribution topology structure to obtain a perception task feature network.

7. The multiple access interference management method based on communication perception integration as claimed in claim 1, characterized in that: The step of performing information feedback processing on digital modeling of the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array includes: Performing information analysis processing on array distribution and environmental conditions on the perception network data set to obtain machine service platform array distribution information and machine service platform array environmental information fed back by the perception network data set; According to the machine service platform array distribution information and the machine service platform array environment information, the array body and the environment of the machine service platform array are digitally modeled to obtain a real-time simulation model corresponding to the machine service platform array.

8. A multiple access interference management device based on integrated communication perception, characterized in that: A method for multiple access interference management based on integrated communication perception, used to implement any one of claims 1 to 7, comprising: An information acquisition module, used to acquire array performance information of a machine service platform array composed of a plurality of autonomous mobile machine service platforms, and drive the machine service platform array to perform collaborative work in a designated area according to the array performance information; wherein the autonomous mobile machine service platform is a drone or a robot dog; An environment perception module, used to perform environment perception processing on a designated area through a sensor group pre-set on each of the autonomous mobile machine service platforms in the machine service platform array, so as to obtain environment perception data of each of the autonomous mobile machine service platforms; A network detection module, used to perform network service quality detection on each of the autonomous mobile machine service platforms in the machine service platform array to obtain network quality characteristics of each of the autonomous mobile machine service platforms; A data integration module, configured to perform data integration processing on the environmental perception data of each of the autonomous mobile machine service platforms according to the network quality characteristics of each of the autonomous mobile machine service platforms, so as to obtain a perception network data set; An information simulation module is used to process information feedback of digitally modeling the machine service platform array according to the perception network data set to obtain a real-time simulation model corresponding to the machine service platform array; wherein the real-time simulation model is used to provide real-time information feedback to the machine service platform array after eliminating interference information.

Images