Situation integrated multi-satellite mission planning design evaluation system and method

Abstract

The application provides a situation comprehensive multi-satellite task planning design evaluation system and method, belongs to the satellite system overall technical field, and aims to solve the problems of difficult evaluation of multi-satellite task planning efficiency and difficult verification of algorithm. The system comprises a task planning control plug-in, a perception data generation plug-in, a comprehensive situation processing plug-in, a system efficiency evaluation plug-in, and a comprehensive simulation deduction platform integrated with the foregoing plug-ins. The system builds a closed-loop verification environment for task planning-situation processing. The corresponding method comprises scene building, service configuration, running simulation and evaluation analysis. The application can simulate multi-algorithm concurrent execution, and quantitatively evaluate based on a multi-dimensional index system at the levels of coverage planning, task and situation, thereby providing reliable data support for task planning design.

Description

Technical Field

[0001] This invention relates to the field of satellite system technology, specifically to a situational awareness integrated multi-satellite mission planning, design, and evaluation system and method. Background Technology

[0002] The space-ground integrated satellite control model relies on ground stations, which has shortcomings in information timeliness, emergency mission response, and multi-satellite collaborative scheduling. In response, on-board mission planning technology has emerged, enabling satellites to move beyond complete reliance on ground control commands and generate action commands online based on dynamic, real-time observation needs, situational environment, and satellite on-orbit operational status. As satellite on-orbit missions have evolved from simple to complex, from open-loop to closed-loop, and from independent to coupled, the complexity of on-board mission planning in information closure and multi-mission execution has continuously increased, raising the difficulty of mission planning and design.

[0003] The mission planning and design process mainly includes requirements analysis, detailed design, and testing and verification. The rationality of the requirements analysis is crucial for the subsequent detailed system design. Currently, requirements analysis primarily focuses on defining and clarifying requirements for functionality, performance, hardware and software environment, and interfaces. However, due to limitations in development and testing support, it is difficult to directly support the implementation of complex future business scenarios. On one hand, there is a lack of system performance evaluation methods for multi-satellite mission planning in scenarios involving collaborative planning and execution with other mission systems. Current mission planning designs mainly measure the merits of algorithms in local processing stages and optimize them based on expert experience, ease of use, and security. When facing complex satellite constellation mission collaboration, the performance of the mission planning system is difficult to estimate, leaving significant room for optimization in the on-orbit performance of the designed mission planning. On the other hand, there is a lack of verification methods for mission planning algorithms that can comprehensively evaluate the spatiotemporal situation of satellites during mission execution. Current verification methods mainly test the correctness of interfaces, with limited ability to verify the effectiveness of the mission planning algorithm's control process in conjunction with the observation data generation process during mission execution. This makes it difficult to truly evaluate the performance in the entire business scenario.

[0004] Therefore, existing technologies face technical challenges in the design and verification of complex multi-satellite collaborative mission planning, such as the lack of system performance evaluation methods and difficulties in verifying related mission planning algorithms at the data level. There is an urgent need in the market for a solution that can comprehensively simulate spatiotemporal situation evolution, support the concurrent use of multiple algorithms, and conduct systematic performance evaluation. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to provide a situational comprehensive multi-satellite mission planning, design, and evaluation system and method. This system and method are intended to solve the technical problems in existing technologies, such as the lack of system effectiveness evaluation methods and the difficulty in verifying situational related algorithms in complex multi-satellite collaborative mission planning and design processes. The invention provides reliable data support and quantitative evaluation methods for mission planning and design.

[0006] A situational intelligence-integrated multi-satellite mission planning, design, and evaluation system provided by the present invention includes: The task planning and control plugin is used to implement the deployment, task triggering, task scheduling, and execution control of various types of task planning algorithms. A sensor data generation plugin is used to simulate and generate heterogeneous satellite multi-source sensor data to construct complex space situation scenarios that closely resemble reality. The integrated situation processing plugin is used to deploy the situation processing prototype software and process multi-source sensing data to generate integrated situation information. The system performance evaluation plugin is used to quantitatively evaluate multi-task planning algorithms based on a preset evaluation index system. The integrated simulation and deduction platform is used to integrate the task planning and control plugin, the perception data generation plugin, the integrated situation processing plugin, and the system performance evaluation plugin to build a closed-loop verification environment and support the construction of simulation scenarios and the operation of simulation deduction.

[0007] Preferably, the task planning control plugin supports the deployment of multiple types of task planning algorithm schemes, including heuristic rule-based sorting algorithms, exact algorithms, metaheuristic intelligent algorithms, and machine learning-based algorithms, and assigns each algorithm instance a globally unique coded identifier containing algorithm framework type, algorithm type information, and version number.

[0008] Preferably, the sensing data generation plugin integrates typical target models, spatial environment models, and multiple noise models to model the measurement errors of different sensors, so as to simulate and generate multi-source sensing data that takes into account the randomness of target detection, environmental parameters, and interference noise.

[0009] Preferably, the integrated situation processing plugin covers functional modules including information source management, data registration, data association, information fusion, feature extraction, and situation generation, and supports hot-swapping and version management of internal processing algorithms.

[0010] Preferably, the evaluation index system on which the system performance evaluation plugin is based is a multi-dimensional evaluation index system, including indicators at the planning level, task level, and situation level. The planning-level indicators include planning duration and number of information exchanges; the task-level indicators include target coverage, satellite load, and task completion rate; and the situation-level indicators include situation update cycle and situation update timeliness.

[0011] A situational intelligence-integrated multi-satellite mission planning, design, and evaluation method provided by the present invention, implemented based on the system, includes: By loading various plugins into the integrated simulation platform, adding hypothetical entities such as satellites, targets, and environments, and configuring parameters, the basic simulation scenario is built. Configure task planning and situation handling services on the relevant entities; The simulation is run to enable multiple entities to concurrently complete task planning, task execution and situation processing. During task execution, the input data for situation processing is obtained through the perception data generation service, and the situation processing results are distributed and maintained based on the information link status. After the simulation is completed, the simulation results are recorded and analyzed by the system performance evaluation plugin to provide data reference for task planning and design.

[0012] Preferably, in the step of configuring the task planning service, different types or versions of task planning algorithms are allowed to be configured on different entities to simulate and verify collaborative scenarios in which multiple task planning algorithms are executed concurrently.

[0013] Preferably, during the simulation, the situation information generated by the integrated situation processing plugin is distributed to the task planning and control plugin through the simulated communication link to verify the task planning algorithm that can trigger emergency replanning and realize adaptive adjustment of task planning under dynamic spatiotemporal situation.

[0014] Preferably, a noise model, an environmental attenuation model, and a random data loss model are introduced during the generation of sensing data to restore the characteristics of real on-orbit observation sensing data.

[0015] Preferably, in the evaluation and analysis phase, the system performance of different task planning algorithms is quantitatively compared from three dimensions: planning efficiency, task execution effect, and spatiotemporal situation, and a visual comparison report is generated.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention constructs a closed-loop verification environment for concurrent multi-task planning algorithms and situational data processing, which solves the problems of single simulation environment and difficulty in evaluating the adaptability of algorithms under complex information interaction in traditional verification methods. It can effectively evaluate the adaptability of algorithms under complex information interaction at the spatiotemporal situational data level.

[0017] 2. This invention proposes a pluggable "4+1" system architecture, which enables flexible scaling up and down of the simulation dimension of the verification environment through flexible configuration and hot-swapping of plug-ins, thereby enhancing the scalability and applicability of the system.

[0018] 3. This invention establishes a multi-dimensional quantitative evaluation index system covering multiple levels such as planning, mission, and situation, realizing a comprehensive and objective evaluation of the effectiveness of mission planning schemes, providing reliable technical support for multi-satellite system mission planning and design, and helping to improve the overall effectiveness of cross-departmental heterogeneous satellite resource allocation schemes. Attached Figure Description

[0019] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram illustrating the composition of a situational intelligence-integrated multi-satellite mission planning, design, and evaluation system provided in an embodiment of the present invention. Figure 2 This is a flowchart illustrating a situational intelligence-based multi-satellite mission planning, design, and evaluation method provided in an embodiment of the present invention. Detailed Implementation

[0020] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0021] Example 1 According to the present invention, a situational intelligence-integrated multi-satellite mission planning, design, and evaluation system is provided, such as... Figure 1 As shown, it includes a comprehensive simulation and simulation platform and four pluggable functional plug-ins, namely: a task planning and control plug-in, a perception data generation plug-in, a comprehensive situation processing plug-in, and a system performance evaluation plug-in. By simulating the task layer and data layer of a heterogeneous multi-satellite collaborative scenario, it realizes the generation of spatiotemporal situation data and the verification of task interaction logic, and integrates situation fusion and other data processing links to simulate and evaluate the application performance of multi-task planning algorithms concurrently.

[0022] The integrated simulation and deduction platform serves as the foundation and scheduling center of the entire system, responsible for integrating and managing all functional plugins, providing the basic environment and operational control for simulation. It is understood that this integrated simulation and deduction platform integrates the aforementioned plugins, constructs a closed-loop verification environment, supports dynamic simulation, process playback, and result analysis of multi-satellite missions, target observations, and communication transmissions, and realizes simulation scenario construction and simulation deduction operation. Specifically, users can create and configure simulation scenarios through the platform's graphical interface or script interface. This process includes adding various hypothetical entities, such as satellites, ground stations, and observation targets (which can be fixed ground targets, moving targets, or space targets, etc.). After adding satellite entities, multiple versions of plugin services are flexibly configured for each entity. Different versions of plugin services are set with version identifiers and loading conditions. During the simulation and deduction process, the dynamic loading and switching of plugin services are achieved by interpreting the loading conditions of each identifier. Loading condition rules include, but are not limited to, the number of scenario entities, the number of connected edges in the communication network, the estimated simulation running time limit, and the memory usage ratio limit. In particular, a mission planning and control plugin is configured based on the limitation of the number of satellite entities, taking into account different constraint dimensions, so as to flexibly expand and shrink the simulation dimension of the mission scenario.

[0023] The core function of the mission planning and control plugin is to simulate mission planning software in satellite or ground control systems, enabling the deployment, triggering, scheduling, and execution control of various mission planning algorithms. The mission planning decision-making business logic controls the calculation methods for mission allocation and scheduling. It uses standardized inputs such as satellite capability parameters, orbital parameters, mission execution sequences, payload subsystem operating modes, information synchronization interaction types, and mission planning-related parameters, and standardized outputs such as satellite mission execution sequences and planning processing logs to construct the interface for mission planning decision implementation. Information synchronization interaction types include, but are not limited to, asynchronous information, locked interaction objects, and dynamic grouping interaction.

[0024] In its implementation, the task planning and control plugin exhibits high flexibility and scalability. Regarding algorithm deployment, the plugin adopts an interface-oriented design and encapsulates each stage of task planning (such as task triggering, task planning decision-making, information synchronization and interaction, and task planning result execution) based on a strategy design pattern. This allows different types of task planning algorithms to be seamlessly integrated as independent strategies. The supported algorithm types are extensive, including but not limited to: 1) heuristic-based sorting algorithms, such as simple sorting algorithms based on rules like highest priority, earliest observation time, and most balanced satellite load; 2) precise algorithms, such as those employing branch and bound, pruning strategies, or dynamic programming, suitable for solving small-scale problems; 3) metaheuristic intelligent algorithms, the mainstream method for handling complex large-scale planning problems, such as greedy algorithms, tabu search, simulated annealing, genetic algorithms, ant colony algorithms, particle swarm optimization, and their hybrid forms; 4) machine learning-based algorithms, such as using reinforcement learning (e.g., Q-learning, deep Q-networks) to enable satellites to autonomously learn planning strategies, or using decision trees and clustering algorithms for task allocation. Furthermore, to effectively manage and differentiate the numerous deployed algorithms, the mission planning and control plugin assigns each algorithm instance a globally unique coded identifier, version number, and simulated parameter data description. This facilitates unified management and performance comparison of different algorithm schemes deployed on real-world satellite and ground systems. The identifier's coding rules can be designed to include information such as the algorithm framework type, specific algorithm type, natively deployed satellite architecture, and creation time, ensuring accurate tracking and differentiation when multiple algorithms are executed concurrently. The version number follows the standardized format of major version number-minor version number-revision number, facilitating tracking algorithm iterations and performance comparison. Regarding the mission triggering mechanism, the mission planning and control plugin supports various flexible triggering methods to simulate diverse planning needs in the real world. Triggering conditions may include: 1) Time-cycle triggering, such as replanning every 10 minutes; 2) Command annotation triggering, simulating the ground station sending new planning commands; 3) Event-driven triggering, such as immediately triggering emergency replanning when the integrated situation processing plugin generates a high-threat situation event or receives guidance data packets from other satellites; 4) State change triggering, such as when a task is completed or fails, or when the satellite's own energy, storage, or other states change significantly. These conditions can also be logically combined to form complex triggering rules. At the execution level of the planning results, the mission planning and control plugin simulates the satellite's processing logic for the planning results. It receives the mission execution sequence generated by the mission planning algorithm and handles conflicts in the mission execution queue according to the actual situation of the satellite. For example, when a new high-priority mission needs to be inserted, the processing logic may be: if the time window allows, do not delete any existing missions; or delete low-priority missions according to priority to free up resources; or combine new and old missions through local re-optimization to achieve the optimal solution.The task planning and control plugin manages algorithms and calls services through the interface of the integrated simulation platform. It provides a parameter configuration interface for the corresponding algorithm based on the algorithm's identifier, version number, and parameter data description.

[0025] The perception data generation plugin is crucial for building a closed-loop simulation environment. Its function is to simulate the observation process of satellite sensors on targets during mission execution and generate near-realistic perception data, which serves as input for subsequent situational awareness processing and assessment. During simulation, the integrated simulation platform calculates which targets are currently within its field of view based on the satellite's real-time position, attitude, and onboard sensor parameters, thus establishing perception relationships. Once these relationships are established, the perception data generation plugin is activated. At this point, the plugin acquires detailed information related to the perception relationship, including the satellite's precise orbital data, the type of payload measurement (e.g., optical imaging, radar detection, signals intelligence interception), and the target's precise position, attitude, size, material, and other characteristic data. Subsequently, the plugin begins simulating the real perception process. This process is not a simple reproduction of the target's real data but rather involves introducing various uncertainty and error models to simulate the actual perception process. Specifically, the plugin integrates typical target models (such as radar cross-section models and infrared radiation characteristic models for different aircraft), space environment models (such as atmospheric attenuation and refraction models of electromagnetic waves, the influence of sunlight angle on optical imaging, and random occlusion models of clouds or terrain on observation), and various noise models. Among these, the noise model is crucial, modeling the measurement errors of different sensors. For example, it introduces shot noise and readout noise for optical sensors, and thermal noise and clutter models for radar sensors. Through the combined effect of these models, the sensing data generation plugin completes and corrects the ideal observation data (i.e., the spatial target position and characteristic parameters in the sensor coordinate system), generating raw measurement data with errors and uncertainties. To further improve the realism of the simulation, the sensing data generation plugin also simulates possible interruptions in data transmission and processing. For example, through random sampling, it simulates the loss of some sensing data during a continuous observation process due to onboard processor overload or a momentary downlink interruption. The resulting sensing data stream can truly reflect the randomness and incompleteness of satellite multi-source sensing in complex electromagnetic and physical environments.

[0026] The integrated situational awareness processing plugin simulates the acquisition and processing of mission execution results and status data by onboard or ground-based centers. This plugin receives sensing data from one or more satellites and processes it into comprehensive situational awareness information that can assess the effectiveness of the mission planning system. Users can designate one or more entities (such as a central processing satellite or a ground station) as the situational awareness processing center in the integrated simulation platform and deploy this plugin on them. The plugin typically contains a series of functional modules, such as source management, data registration, data association, information fusion, feature extraction, and situational awareness generation. Specifically, the source management module controls the range of sources corresponding to the receivable data and verifies the correctness based on the deployment status of the sensing data generation plugin service and the communication link topology configuration status. The data registration module simulates the process of estimating the bias of a multi-sensor system, corrects the mismatch between the measurement results of each sensor in the spatiotemporal dimension, and normalizes the target observation time. The data association module simulates the association processing of data to achieve correct matching between the target information obtained by each sensor. The information fusion module simulates the fusion processing of multi-source information to make various sensors complement each other and further improve information quality. The feature extraction module simulates the process of extracting target motion features from target information, including the target's velocity, acceleration, kinetic energy, and potential energy. The situation generation module integrates the information generated by the above modules to form comprehensive display information, providing computational data input for the system effectiveness evaluation plugin service. It should be noted that this generated comprehensive situation information is distributed through the communication network topology simulated by the comprehensive simulation platform and passed to the task planning and control plugin that needs this information, thus forming a closed loop of perception-processing-decision. The integrated situation processing plugin also supports hot-swapping and version management of internal processing algorithms, allowing researchers to easily replace and evaluate different data fusion or situation assessment algorithms.

[0027] The system performance evaluation plugin provides an objective and quantitative assessment of the entire simulation process and the performance of the task planning algorithm. After the simulation, the plugin automatically collects and analyzes detailed logs and output data recorded during the operation of the integrated simulation platform, task planning and control plugin, and integrated situation processing plugin. The core of the evaluation lies in a pre-set multi-dimensional evaluation index system, which comprehensively measures the merits of the task planning scheme from different levels. The multi-dimensional evaluation index system includes: 1) Planning-level indicators: focusing on the efficiency and cost of the planning algorithm itself. For example: planning duration, number of information interactions, and average latency of planning result transmission. 2) Task-level indicators: focusing on the execution effect of the planning scheme and the quality of task completion. For example: target priority weighted coverage, target coverage, satellite load balance, cooperative satellite angle, task completion rate, and task completion timeliness. 3) Situation-level indicators: focusing on the contribution of planning activities to situation awareness capabilities. For example: average latency of task execution message transmission, situation update cycle, situation update timeliness, situation continuity maintenance rate, situation data diversity, and average latency of situation information transmission. To facilitate use and expansion, this plugin provides detailed configuration items for each indicator, including indicator definition, indicator type, indicator satisfaction value, indicator tolerance value, and indicator satisfaction interval attributes. Furthermore, the calculation logic for the indicators can be constructed using scripting languages ​​such as Python and dynamically loaded and invoked by the plugin. This design allows users to easily customize new evaluation indicators without recompiling the entire system. Finally, the system performance evaluation plugin summarizes, statistically analyzes, and visualizes the calculation results of all indicators, generating a comprehensive simulation results report. This provides designers with strong data support for comparing the advantages and disadvantages of different mission planning algorithms, optimizing algorithm parameters, and improving satellite system design.

[0028] Example 2 This embodiment will combine Figure 2 This invention provides a detailed description of the complete method and process for conducting a typical multi-satellite mission planning, design, and evaluation using the system provided by this invention. Figure 2 This is a flowchart illustrating a situational intelligence multi-satellite mission planning, design, and evaluation method in one embodiment of the present invention.

[0029] The evaluation method mainly includes scenario setup step S1, configuration task planning service step S2, configuration situation processing service step S3, simulation operation step S4, and evaluation and analysis step S5.

[0030] First, the scenario setup step S1 is executed. The user first starts the integrated simulation platform, which loads the necessary core services and basic plugins. Next, the user begins constructing a specific simulation scenario. For example, assuming the goal of this evaluation is to verify the performance of two different mission planning algorithms in Earth observation missions, the user needs to add a series of scenario entities. First, add satellite entities. The user can choose from a pre-built satellite model library or define a new custom satellite model. Second, add target entities. The user defines a series of observation target areas on the virtual Earth surface. Third, configure the environment model. The user selects the required environment model, for example, enabling the atmospheric attenuation model and cloud image model to simulate the impact of weather on optical observations. Fourth, configure simulation parameters. The user sets the simulation start time, end time, and simulation step size. After completing these configurations, a basic simulation scenario is built. All this configuration information is saved as a scenario file for easy reuse or modification later.

[0031] Subsequently, step S2, configuring the task planning service, is executed. After the scenario is built, the simulated entities need to be endowed with intelligence, i.e., task planning services need to be configured for them. This step is mainly accomplished through the task planning control plugin. In this embodiment, to compare the two algorithms, the user will configure different task planning algorithms for the two sub-constellations. For example, a metaheuristic intelligent algorithm based on genetic algorithms is uniformly configured for the first sub-constellation consisting of 12 satellites (hereinafter referred to as Group A). ​​On the interface of the task planning control plugin, the user selects the algorithm for each satellite in Group A and configures its relevant parameters, such as population size, crossover probability, mutation probability, etc. These parameters belong to the task planning decision-related parameters. For the second sub-constellation (hereinafter referred to as Group B), the user configures a distributed planning algorithm based on multi-agent reinforcement learning. In this algorithm, each satellite acts as an intelligent agent, communicating and negotiating with each other to jointly complete task allocation. The user needs to configure information synchronization interaction-related parameters for this purpose, for example, selecting the dynamic group interaction mode and setting the communication range and information exchange protocol. In addition, users need to configure the same task planning triggering parameters for both groups, for example, setting it to "trigger periodically every 300 seconds, and trigger immediately when a new task request with priority 'urgent' is received." Simultaneously, configure the execution parameters for the planning results, such as selecting a strategy to resolve conflicts by priority. By configuring different task planning algorithms and parameters on different entities, this system can flexibly construct complex verification scenarios where multiple task planning algorithms run concurrently and compete against each other.

[0032] Next, step S3, configuring the situation processing service, is executed. This step is completed through the integrated situation processing plugin. In multi-satellite collaborative scenarios, situation information fusion can be completed on-board or at ground stations, both of which can be simulated by this system. In this example, it is assumed that Group A and Group B each have a central satellite responsible for processing the sensing data collected by other satellites within their respective groups. In the integrated simulation platform, the user selects satellite 1 of Group A and satellite 13 of Group B, loading and configuring the integrated situation processing plugin service for them. In the configuration interface, the user needs to set the maximum range of information sources; for example, the situation processing service of satellite 1 in Group A only receives sensing data from satellites 2 to 12 in Group A. The user can also configure the functional aspects of situation processing in detail, such as choosing to use the joint probabilistic data association algorithm for data association and extended Kalman filtering for information fusion. Through this configuration, the system simulates the deployment location and information link relationships of the real situation processing system. When the simulation runs, after ordinary satellites complete their observations, the sensing data they generate will be sent to the corresponding central satellite for processing through the communication link simulated by the platform.

[0033] Then, the simulation process proceeds to step S4. After completing all configurations, the user clicks the "Start Simulation" button, and the integrated simulation platform begins to advance the simulation time according to the set time step. During the simulation, multiple entities concurrently execute their respective tasks. Specifically, the process is as follows: First, the task planning and control plugin is activated according to the triggering rules configured in step S2. Satellites in groups A and B respectively call their configured genetic algorithms and reinforcement learning algorithms to generate their respective task execution sequences. Subsequently, the satellites adjust their attitudes according to the received task sequences, controlling their sensors to align with the designated targets. The integrated simulation platform then determines whether the satellites' sensors have successfully covered the targets based on the satellites' motion and attitude. Once the coverage relationship is established, the perception data generation plugin is triggered, simulating the sensor observation process and generating perception data containing errors and noise. This perception data is sent to satellites A1 and B13 via simulated communication links. The integrated situation processing plugins on these two satellites receive the data and perform fusion processing to generate integrated situation information. For example, if multiple satellites observe localized high temperatures in a forest area, the situation processing plugin may generate a situation event indicating a suspected fire area expansion. Newly generated integrated situational information (such as new high-priority target areas) is distributed to other satellites in the group. When the mission planning and control plugin receives such important situational updates, it may trigger an emergency replanning, enabling the satellites to dynamically respond to environmental changes. The entire simulation process is a continuous loop of the above steps, executed concurrently, forming a complete closed loop of planning-execution-sensing-processing-replanning.

[0034] Finally, the evaluation and analysis step S5 is executed. The simulation ends when the set end time is reached or when it is manually stopped by the user, and the system performance evaluation plugin begins operation. This plugin first collects massive amounts of data recorded during the simulation from various parts of the system, including mission planning logs, mission execution logs, communication logs, resource consumption logs of all satellites, and fusion result logs from the integrated situation processing plugin. Then, the system performance evaluation plugin calls corresponding indicator operators (such as Python scripts) to calculate these data according to a preset evaluation index system. For example: To calculate target coverage, the script reads the observation records of all targets, counts the number of times each target was successfully observed and its duration, and then calculates the coverage based on the total number of targets. To calculate planning duration, the script analyzes the mission planning logs, finds the start and end timestamps of each planning session, calculates the time difference, and provides the average, maximum, and minimum values. To calculate the timeliness of situation updates, the script compares the timestamp of the actual event occurrence with the timestamp when the event is written into the integrated situation information, and calculates the average delay. Finally, the system performance evaluation plugin presents the calculation results of all evaluation indicators for Group A (using a genetic algorithm) and Group B (using a reinforcement learning algorithm) in various visualization formats such as tables, graphs, and radar charts, and generates a detailed simulation result report. By comparing and analyzing this report, the advantages and disadvantages of the two algorithms on different indicators can be clearly revealed. For example, it may be found that the genetic algorithm has a shorter planning time but a slightly lower target coverage; while the reinforcement learning algorithm, although slower in initial planning, performs better in dynamic task response and task completion timeliness. Through the analysis of these evaluation results, designers can verify the feasibility of the task planning algorithm or the indicators of the prototype satellite system, obtain valuable data references, and thus guide the next optimization direction. If necessary, users can also return to step S1 or S2, modify the satellite parameters or algorithm parameters, and conduct a new round of iterative simulation experiments until a satisfactory design solution is found.

[0035] Example 3 This embodiment details the method and process for performing a typical multi-algorithm concurrent verification and performance evaluation using the system provided by this invention. The method and process mainly include the following steps: plug-in service implementation (A1), scenario setup and configuration (A2), and simulation and evaluation analysis (A3).

[0036] First, execute step A1 of the plugin service implementation. Create or open a mission planning and control operator in the mission planning and control plugin, and define the external interface of the mission planning and control operator. The interface content includes parameter names, parameter types, normal values, etc. Then, design the content based on the usage modes of various satellites across different systems, and develop or translate the mission planning and control code according to the input and output parameters. After development, the code can be debugged based on test data. Save the debugged mission planning and control operator to the library for use when building simulation scenarios.

[0037] Next, perform scenario setup and configuration step A2. Simulate a multi-satellite combined mission scenario across different systems, adding satellites, target entities, and communication transmission link topologies, and configuring typical environmental and simulation parameters. Implement mission planning and control operators based on different mission systems, configure the mission planning and control plugins and their triggering conditions for each entity, and simulate real business processes such as single-satellite observation mission planning, multi-satellite collaborative mission planning, integrated space-ground observation mission planning, and on-board autonomous data transmission mission planning.

[0038] Finally, execute step A3, which involves simulation and evaluation analysis. After configuring simulation parameters, the simulation begins. During the simulation, each entity's corresponding plugin controls the concurrent execution of multiple task planning algorithms. The planning process is based on simulated real triggering conditions, situational awareness results, and inter-satellite interaction information. Simulation evaluation provides a direct analysis of the adaptability of each task planning algorithm in typical combined usage scenarios. For example, it may be found that the autonomous data transmission task planning cycle parameter is too long, resulting in untimely data transmission and inability to close the task flow; the algorithm logic used in multi-satellite collaborative task planning is overly dependent on communication, leading to uneven allocation of tasks to some satellites; the design of the waiting time for receiving inter-satellite interaction information in multi-satellite collaborative task planning is unreasonable, resulting in unobserved transits; and the design for conflict resolution in single-satellite observation task planning and integrated satellite-ground observation task planning is insufficient, leading to task execution failures and broken target information links. Through the analysis of these phenomena and other evaluation results, designers can verify the adaptability of combined business processes or task planning algorithms in complex scenarios, thereby optimizing the design.

[0039] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0040] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A situational awareness-integrated multi-satellite mission planning, design, and evaluation system, characterized in that, include: The task planning and control plugin is used to implement the deployment, task triggering, task scheduling, and execution control of various types of task planning algorithms. A sensor data generation plugin is used to simulate and generate heterogeneous satellite multi-source sensor data to construct complex space situation scenarios that closely resemble reality. The integrated situation processing plugin is used to deploy the situation processing prototype software and process multi-source sensing data to generate integrated situation information. The system performance evaluation plugin is used to quantitatively evaluate multi-task planning algorithms based on a preset evaluation index system. The integrated simulation and deduction platform is used to integrate the task planning and control plugin, the perception data generation plugin, the integrated situation processing plugin, and the system performance evaluation plugin to build a closed-loop verification environment and support the construction of simulation scenarios and the operation of simulation deduction.

2. The situational awareness integrated multi-satellite mission planning, design, and evaluation system according to claim 1, characterized in that, The task planning control plugin supports the deployment of multiple types of task planning algorithm schemes, including heuristic-based sorting algorithms, exact algorithms, metaheuristic intelligent algorithms, and machine learning-based algorithms, and assigns each algorithm instance a globally unique coded identifier containing algorithm framework type, algorithm type information, and version number. The task planning and control plugin adopts an interface-oriented design and encapsulates each stage of task planning based on the strategy design pattern.

3. The situational awareness integrated multi-satellite mission planning, design, and evaluation system according to claim 1, characterized in that, The perception data generation plugin integrates typical target models, spatial environment models, and multiple noise models to model the measurement errors of different sensors, so as to simulate and generate multi-source perception data that takes into account the randomness of target detection, environmental parameters, and interference noise.

4. The situational awareness integrated multi-satellite mission planning, design, and evaluation system according to claim 1, characterized in that, The integrated situation processing plugin covers functional modules including information source management, data registration, data association, information fusion, feature extraction, and situation generation. The source management module is responsible for controlling the range of sources corresponding to the receivable data, and for verifying the correctness of the plugin service deployment status and communication link topology configuration status based on the sensing data. The data registration module is responsible for simulating the process of estimating the bias of the multi-sensor system, correcting the mismatch between the measurement results of each sensor in the spatiotemporal dimension, and normalizing the target observation time. The data association module is responsible for simulating the association processing of data to achieve correct matching between target information obtained by each sensor; The information fusion module is responsible for simulating the fusion processing of multi-source information; The feature extraction module is responsible for simulating the process of extracting the motion features of the target from the target information. The motion features include the target's velocity, acceleration, kinetic energy, and potential energy. The situation generation module is responsible for integrating and processing the information generated by the above modules to form comprehensive display information, providing calculation data input for the system effectiveness evaluation plug-in service.

5. The situational awareness integrated multi-satellite mission planning, design, and evaluation system according to claim 1, characterized in that, The evaluation index system upon which the system effectiveness evaluation plugin is based is a multi-dimensional evaluation index system, including indicators at the planning level, task level, and situation level. The planning-level indicators include planning duration and number of information exchanges; the task-level indicators include target coverage, satellite load, and task completion rate; and the situation-level indicators include situation update cycle and situation update timeliness.

6. A situational awareness-integrated multi-satellite mission planning, design, and evaluation method, characterized in that, Based on the system implementation of any one of claims 1-5, it includes: By loading various plugins into the integrated simulation platform, adding hypothetical entities such as satellites, targets, and environments, and configuring parameters, the basic simulation scenario is built. Configure task planning and situation handling services on the relevant entities; The simulation is run to enable multiple entities to concurrently complete task planning, task execution and situation processing. During task execution, the input data for situation processing is obtained through the perception data generation service, and the situation processing results are distributed and maintained based on the information link status. After the simulation is completed, the simulation results are recorded and analyzed by the system performance evaluation plugin to provide data reference for task planning and design.

7. The situational awareness integrated multi-satellite mission planning, design, and evaluation method according to claim 1, characterized in that, In the step of configuring the task planning service, different types or versions of task planning algorithms can be configured on different entities to simulate and verify collaborative scenarios in which multiple task planning algorithms are executed concurrently.

8. The situational awareness integrated multi-satellite mission planning, design, and evaluation method according to claim 1, characterized in that, During the simulation, the situation information generated by the integrated situation processing plugin is distributed to the task planning and control plugin through the simulated communication link to verify the task planning algorithm that can trigger emergency replanning and realize the adaptive adjustment of task planning under dynamic spatiotemporal situation.

9. The situational awareness integrated multi-satellite mission planning, design, and evaluation method according to claim 1, characterized in that, Noise models, environmental attenuation models, and random data loss models are introduced during the generation of sensing data to restore the characteristics of real on-orbit observation sensing data.

10. The situational awareness integrated multi-satellite mission planning, design, and evaluation method according to claim 1, characterized in that, In the evaluation and analysis phase, the system effectiveness of different task planning algorithms is quantitatively compared from three dimensions: planning efficiency, task execution effect, and spatiotemporal situation, and a visual comparison report is generated.

Images