Method and device for evaluating trajectory planning strategy, electronic equipment and storage medium
By simulating flight and evaluating trajectory planning strategies in a digital twin environment, the problem of insufficient accuracy of existing trajectory planning evaluation methods in complex environments is solved. This enables in-depth and dynamic reliability evaluation of trajectory planning strategies, ensuring the safe flight of airships in near space.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- AEROSPACE INFORMATION RES INST CAS
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-02
AI Technical Summary
Existing trajectory planning and evaluation methods are unable to accurately reflect the real-time platform status of stratospheric airships in the complex and ever-changing near-space environment, which may lead to the airship's inability to accurately track the planned trajectory and potentially cause mission failure.
By acquiring user-submitted trajectory planning tasks, the trajectory planning strategy is invoked to simulate flight in a digital twin environment, real-time platform status data is obtained, and the trajectory planning strategy is evaluated based on this data. The digital twin environment is used to conduct in-depth, dynamic, and high-fidelity reliability assessment.
Without compromising the safety of real airship operations, the performance of the trajectory planning strategy was fully verified, improving the credibility and engineering reference value of the evaluation results and ensuring the reliability and effectiveness of the trajectory planning strategy in complex environments.
Smart Images
Figure CN122133502A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of airship technology, and more particularly to a method, apparatus, electronic device, and storage medium for evaluating trajectory planning strategies. Background Technology
[0002] Near space typically refers to the airspace at an altitude of 20 to 100 kilometers above the ground. This airspace lies between the flight altitude of traditional aircraft and the orbital altitude of spacecraft, possessing unique strategic value. Stratospheric airships, as typical near-space vehicles, rely on the static buoyancy generated by rising gases to achieve ambulation. They possess significant advantages such as long endurance, large payload, and low energy consumption, enabling long-term ambulation and controlled flight in specific areas. They are widely used in surveillance and early warning, communication relay, navigation and positioning, and high-altitude scientific experiments. However, near space typically has a complex and variable wind field environment, and stratospheric airships also face multiple challenges during flight, including limited energy reserves and propulsion system constraints.
[0003] Before a stratospheric airship can perform a mission, trajectory planning is usually required. Existing trajectory planning evaluation methods mainly focus on the feasibility verification at the logical or geometric level, such as determining whether the planned trajectory can connect the starting point to the ending point, or verifying whether the trajectory path avoids known static obstacle areas.
[0004] However, stratospheric airships are significantly affected by the atmospheric environment and possess complex nonlinear dynamic characteristics. Relying solely on static assessments based on geometric paths or ideal environments often fails to accurately reflect the real-time platform status of the airship during actual flight. For example, while a planned trajectory may be theoretically feasible, under specific dynamic wind field disturbances or energy constraints, the airship may be unable to accurately track the trajectory, leading to mission failure. Summary of the Invention
[0005] In view of the problems existing in the prior art, the present invention provides a method, apparatus, electronic device and storage medium for evaluating trajectory planning strategies.
[0006] This invention provides a method for evaluating trajectory planning strategies, comprising: Retrieve user-submitted trajectory planning tasks; The trajectory planning result is obtained by invoking the trajectory planning strategy according to the trajectory planning task. Based on the trajectory planning results, the digital twin airship is controlled to perform simulated flight in the digital twin environment to obtain the real-time platform status data of the digital twin airship; The trajectory planning strategy is evaluated based on the real-time platform status data and the trajectory planning results.
[0007] According to the method for evaluating a trajectory planning strategy provided by the present invention, the step of obtaining a trajectory planning result by invoking the trajectory planning strategy according to the trajectory planning task includes: Based on the trajectory planning task, at least one of the trajectory planning strategies is called through an interface to obtain the trajectory planning result generated by each trajectory planning strategy according to the trajectory planning task.
[0008] According to the method for evaluating a trajectory planning strategy provided by the present invention, the evaluation of the trajectory planning strategy based on the real-time platform status data and the trajectory planning result includes: The evaluation rules are determined based on the task requirements of the trajectory planning task. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results.
[0009] According to the present invention, an evaluation method for a trajectory planning strategy is provided, wherein the evaluation of the trajectory planning strategy based on the evaluation rules, by comparing the real-time platform status data and the trajectory planning results, includes: Based on the evaluation rules, if the real-time platform status data and the trajectory planning results are compared, it is determined that the digital twin airship will be controlled to complete the trajectory planning task according to the trajectory planning results; Then, the flight time, energy consumption, and / or distance deviation of the digital twin aerostat performing the trajectory planning task are determined, and the trajectory planning strategy is evaluated based on the flight time, energy consumption, and / or distance deviation. The distance deviation is obtained by comparing the actual position of the digital twin aerostat with the target position of the trajectory planning result.
[0010] According to the present invention, an evaluation method for a trajectory planning strategy is provided, wherein the evaluation of the trajectory planning strategy based on the evaluation rules, by comparing the real-time platform status data and the trajectory planning results, includes: The system state of the digital twin aerostat after executing the trajectory planning task is determined based on the real-time platform status data. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results, combined with the system status.
[0011] According to the present invention, an evaluation method for trajectory planning strategies is provided, wherein the evaluation rules are determined based on the requirements of the trajectory planning task and the dynamic requirements of the actual airship.
[0012] According to the evaluation method of trajectory planning strategy provided by the present invention, the digital twin environment is dynamically adjusted based on the environmental forecast data of the real flight area corresponding to the trajectory planning task.
[0013] The present invention also provides an evaluation device for trajectory planning strategies, comprising: The task acquisition module is used to acquire trajectory planning tasks published by users; The trajectory planning module is used to call the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result; The trajectory verification module is used to control the digital twin airship to perform simulated flight in the digital twin environment according to the trajectory planning results, and to obtain the real-time platform status data of the digital twin airship. The strategy evaluation module is used to evaluate the trajectory planning strategy based on the real-time platform status data and the trajectory planning results.
[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement an evaluation method for any of the trajectory planning strategies described above.
[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an evaluation method for trajectory planning strategies as described above.
[0016] This invention provides a method, apparatus, electronic device, and storage medium for evaluating trajectory planning strategies. It acquires user-submitted trajectory planning tasks, invokes trajectory planning strategies based on these tasks to obtain trajectory planning results, controls a digital twin aerostat to perform simulated flight in a digital twin environment based on the trajectory planning results, obtains real-time platform status data of the digital twin aerostat, evaluates the trajectory planning strategy based on the real-time platform status data and the trajectory planning results, and utilizes a digital twin environment to simulate and evaluate the trajectory planning strategy. This allows for in-depth, dynamic, and high-fidelity reliability assessment of the trajectory planning strategy, comprehensively verifying its performance without affecting the operational safety of the actual aerostat. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the evaluation method for trajectory planning strategies provided by the present invention.
[0019] Figure 2 This is a schematic diagram illustrating the application of the trajectory planning strategy evaluation method provided by the present invention.
[0020] Figure 3 This is a schematic diagram of the structure of the trajectory planning strategy evaluation device provided by the present invention.
[0021] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0023] The following is combined with Figures 1 to 4 The present invention describes an evaluation method, apparatus, electronic device, and storage medium for the trajectory planning strategy.
[0024] Figure 1 This is a flowchart illustrating the evaluation method for trajectory planning strategies provided by the present invention, as shown below. Figure 1 As shown, the method includes the following: Step 101: Obtain the trajectory planning task published by the user.
[0025] The trajectory planning task, also known as task information, refers to the configuration items created by the user to generate the flight trajectory of the airship. For example, the trajectory planning task can be a natural language task or a set of task parameters.
[0026] The set of mission parameters may include flight target data and flight constraint data, etc. For example, when the trajectory planning task is a set of mission parameters, the trajectory planning task may include mission start time, starting point location, target point location, planned flight duration, and no-fly zones, etc.
[0027] It should be noted that the execution entity in this embodiment can be the processor of the digital test system of the airship. The user can obtain the trajectory planning task created and published by the user through the interactive interface of the flight management module of the digital test system according to the determined task parameters and initial conditions.
[0028] Step 102: Invoke the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result.
[0029] The trajectory planning strategy refers to the scheme for generating the space travel path of an airship over a future period of time. For example, the trajectory planning strategy could be a trajectory planning algorithm for a stratospheric airship.
[0030] The trajectory planning result refers to the flight trajectory of the airship obtained by processing the trajectory planning task according to the trajectory planning strategy. For example, the trajectory planning result may include a flight trajectory consisting of multiple time series nodes, where each node corresponds to parameters such as the airship's position, altitude, velocity, and attitude at the corresponding time.
[0031] It should be noted that the trajectory planning task can be solved based on a preset trajectory planning strategy to generate trajectory planning results that meet the task constraints.
[0032] Step 103: Control the digital twin airship to perform simulated flight in the digital twin environment according to the trajectory planning results, and obtain the real-time platform status data of the digital twin airship.
[0033] The digital twin aerostat is a virtual aerostat deployed in the simulation computing environment of a ground station computer, establishing a one-to-one mapping relationship with the real aerostat. The real aerostat refers to a physical aerostat that is expected to apply the aforementioned trajectory planning strategy, deployed in the stratosphere of near space, and possesses autonomous flight control capabilities.
[0034] Real-time platform status data refers to a time-series multi-dimensional data set reflecting the actual operational status of the digital twin aerostat in the digital twin environment, including its physical state, energy state, mission state, and environmental interaction state. For example, real-time platform status data may include at least one of the following: the aerostat's actual flight position, flight altitude, speed, attitude angle, energy consumption data, and environmental interaction status.
[0035] It should be noted that during the simulated flight, control commands can be applied to the digital twin airship according to the trajectory planning results, and corresponding real-time platform status data can be collected in real time.
[0036] Step 104: Evaluate the trajectory planning strategy based on the real-time platform status data and the trajectory planning results.
[0037] It should be noted that real-time platform status data can be compared and analyzed with trajectory planning results to calculate trajectory tracking error, attitude stability index, energy consumption index, and safety index, and an evaluation result of the trajectory planning strategy can be generated based on preset evaluation rules. The evaluation result can be used to characterize the feasibility and stability of the trajectory planning strategy under the current task and environmental conditions.
[0038] In one embodiment, based on the evaluation results, the trajectory planning strategy can be adjusted in terms of parameters or updated in terms of strategy to achieve iterative optimization of the trajectory planning strategy.
[0039] The trajectory planning strategy evaluation method provided in this invention obtains the trajectory planning task published by the user, calls the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result, controls the digital twin airship to perform simulated flight in the digital twin environment according to the trajectory planning result, obtains the real-time platform status data of the digital twin airship, evaluates the trajectory planning strategy based on the real-time platform status data and the trajectory planning result, and uses the digital twin environment to simulate flight and evaluate the trajectory planning strategy. This method can perform in-depth, dynamic and high-fidelity reliability evaluation of the trajectory planning strategy, and comprehensively verify the performance of the trajectory planning strategy without affecting the operational safety of the real airship.
[0040] In some embodiments, the digital twin environment is dynamically adjusted based on environmental forecast data of the actual flight area corresponding to the trajectory planning task.
[0041] Understandably, in this embodiment, by introducing environmental forecast data from the actual flight area to dynamically adjust the digital twin environment, the digital twin environment can realistically reflect the time-varying characteristics of key environmental factors such as wind field distribution, temperature changes, pressure gradient, and radiation conditions in the target flight airspace at different times. Compared to using static or idealized environmental models, this embodiment enables the simulated flight results of the trajectory planning strategy to more closely resemble real flight conditions, significantly improving the credibility and engineering reference value of the evaluation results.
[0042] Furthermore, in this embodiment, matching the digital twin environment with the real flight area corresponding to the trajectory planning task enables the evaluation of the trajectory planning strategy to no longer be a general or abstract simulation verification, but a targeted evaluation for specific tasks, specific airspaces and specific time windows. This is beneficial for differentiated comparison and optimization of trajectory planning schemes for different flight areas or different execution periods during the task release stage, thereby improving the accuracy of task decision-making.
[0043] Based on the above embodiments, the step of invoking the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result includes: Based on the trajectory planning task, at least one of the trajectory planning strategies is called through an interface to obtain the trajectory planning result generated by each trajectory planning strategy according to the trajectory planning task.
[0044] On the one hand, different mission scenarios have different requirements for stratospheric airships, resulting in different trajectory planning algorithms for stratospheric airships. On the other hand, even under the same mission scenario, there are currently a variety of trajectory planning algorithms for stratospheric airships, such as sampling-based trajectory planning strategies, search-based trajectory planning strategies, optimization-based trajectory planning strategies, or learning-based trajectory planning strategies, specifically including optimal control algorithms, model predictive control algorithms, intelligent optimization algorithms, and artificial intelligence-based methods.
[0045] It should be noted that after pre-configuring at least one different trajectory planning strategy, each strategy can be invoked through a unified strategy interface. Each strategy processes the trajectory planning task independently according to its own planning principles, thereby generating the corresponding trajectory planning result. The different trajectory planning strategies are encapsulated through a unified strategy interface, which facilitates the invocation and execution of different strategies under the same input conditions.
[0046] For example, when facing trajectory planning tasks with different task scenarios, a trajectory planning strategy can be evaluated by calling an interface. When facing trajectory planning tasks with the same task scenario, multiple different trajectory planning strategies can be called sequentially for evaluation according to the same trajectory planning task.
[0047] Understandably, by calling at least one trajectory planning strategy through an interface, it is possible to flexibly match an appropriate trajectory planning strategy for the different mission scenarios faced by the stratospheric aerostat. This on-demand calling mechanism enables the evaluation of the effectiveness of different trajectory planning strategies, simplifies the verification and evaluation process of different trajectory planning strategies for aerostats in the complex stratospheric environment, and solves the technical problem that the verification process of a single trajectory planning strategy cannot take into account different mission scenarios.
[0048] Furthermore, by pre-configuring multiple types of trajectory planning strategies and encapsulating them using a unified interface, it is possible to synchronously or asynchronously acquire the planned trajectories of multiple strategies under the same task scenario input conditions. This provides a basis for comparing the performance of different algorithms in the complex dynamic environment of the stratosphere, thereby enabling a more objective and multi-dimensional evaluation of the advantages and disadvantages of each strategy, and providing data support for algorithm selection in practical tasks.
[0049] Based on any of the above embodiments, the evaluation of the trajectory planning strategy based on the real-time platform status data and the trajectory planning result includes: The evaluation rules are determined based on the task requirements of the trajectory planning task. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results.
[0050] It should be noted that stratospheric airships have long mission cycles, typically measured in months or years, and their endurance during missions relies heavily on their energy systems. Therefore, in addition to addressing changes in the complex external environment, the trajectory planning strategy for stratospheric airships also needs to balance the long-term feasibility of internal energy management strategies. Furthermore, the motion of stratospheric airships exhibits strong nonlinearity and hysteresis; thus, the trajectory planning strategy must be deeply coupled with complex dynamic models, requiring verification of the dynamic feasibility and mission requirements of the trajectory planning results.
[0051] The task requirements for trajectory planning refer to a set of technical indicators and constraints determined based on the pre-set mission objectives of the stratospheric airship, combined with its current platform status and external environmental information, to limit, guide, and evaluate the trajectory planning process.
[0052] For example, the task requirements for trajectory planning may include target point transfer, area dwell, and fixed-point dwell.
[0053] Among them, the evaluation rules refer to the pre-set criteria used to quantitatively or qualitatively measure whether the trajectory planning results generated by the trajectory planning strategy meet the task requirements and platform physical limitations.
[0054] In some embodiments, the evaluation rules are determined based on the requirements of the trajectory planning task and the dynamic requirements of the actual airship.
[0055] For example, the dynamic requirements of a real airship may include the dynamic characteristics of the real airship and energy cycle logic, etc.
[0056] It is understandable that, in this embodiment, by introducing the dynamic requirements of a real airship to construct evaluation rules and comparing the real-time platform status data with the trajectory planning results in a closed loop, it is possible to accurately identify whether the planned trajectory exceeds the dynamic limits or response capabilities of the airship, thereby effectively avoiding the problem of untraceable planned paths caused by the disconnect between the trajectory planning strategy and the dynamic model, and ensuring that every trajectory planning result generated by the trajectory planning strategy is executable at the physical level.
[0057] Furthermore, based on the feedback of real-time status data, this embodiment can construct a complete closed-loop evaluation system. Compared with offline simulation, this comparative evaluation method can reflect the real performance of the strategy in the real, complex and ever-changing stratospheric wind field environment. It provides data support for ranking the merits of multiple trajectory planning strategies, and provides feedback signals for the adaptive adjustment of parameters of each trajectory planning strategy, thereby improving the success rate of using trajectory planning strategies to control the airship to perform tasks.
[0058] In an optional embodiment, the trajectory planning result may also include corresponding evaluation indicators, such as trajectory length, smoothness, energy consumption estimation, safety distance, or computation time, for subsequent comparison or screening of different trajectory planning results.
[0059] Based on any of the above embodiments, the step of evaluating the trajectory planning strategy by comparing the real-time platform status data and the trajectory planning result based on the evaluation rules includes: Based on the evaluation rules, if the real-time platform status data and the trajectory planning results are compared, it is determined that the digital twin airship will be controlled to complete the trajectory planning task according to the trajectory planning results; Then, the flight time, energy consumption, and / or distance deviation of the digital twin aerostat performing the trajectory planning task are determined, and the trajectory planning strategy is evaluated based on the flight time, energy consumption, and / or distance deviation. The distance deviation is obtained by comparing the actual position of the digital twin aerostat with the target position of the trajectory planning result.
[0060] The evaluation rules may include evaluation indicators, which may be specifically formulated according to the requirements of the stratospheric flight test mission and the characteristics of the airship platform. These indicators may include mission completion, cost, system safety, etc.
[0061] It should be noted that when the mission requirement of the airship is target point transfer, the distance deviation between the actual position of the digital twin airship and the target position of the trajectory planning result within the flight time specified in the trajectory planning mission can be used to determine whether the digital twin airship has completed the trajectory planning mission based on the trajectory planning result.
[0062] When the mission requirement of the airship is regional or fixed-point stationing, the flight time of the digital twin airship within the normal range can be used to determine whether the flight time specified in the trajectory planning task has been reached, based on the trajectory planning results.
[0063] It should be noted that if, based on the evaluation rules, the real-time platform status data and trajectory planning results are compared, and it is determined that the digital twin airship, controlled according to the trajectory planning results, failed to complete the trajectory planning task, then the corresponding evaluation results can be obtained directly.
[0064] For example, if the digital twin airship fails to complete the trajectory planning task based on the trajectory planning results, its evaluation result can be directly determined as failing or unqualified based on the preset relationship.
[0065] For example, taking the mission requirement of an airship as a target point transfer, the starting point, target point, and planned flight duration can be determined through the mission parameters of the trajectory planning task. The starting point and target point are located at different positions, and the airship transfers from the starting point to the target point according to the set planned flight duration. In this mission scenario, evaluation indicators may include, but are not limited to, target reachability and energy consumption costs.
[0066] Specifically, within a time range where the flight duration is less than or equal to the planned flight duration, the distance deviation between the current position and the target position of the digital twin aerostat can be calculated in real time to determine whether it is within the planned distance deviation range. If the distance deviation is within the planned distance deviation range, the target is determined to be reachable; if the distance deviation is not within the planned distance deviation range, the target is determined to be unreachable, and the trajectory planning strategy needs improvement.
[0067] Within a timeframe where the flight duration is less than or equal to the planned flight duration, if the target is determined to be reachable, the target arrival time and total energy consumption can be obtained. The score for this trajectory planning strategy can then be calculated using the following formula. : in, It is the time to achieve the goal. It refers to energy consumption. and It is its corresponding weight coefficient, and .
[0068] Energy consumption refers to the total amount of energy consumed.
[0069] In some embodiments, and The evaluation rules can be customized according to actual needs. If speed is the primary concern, then specific settings can be configured. If energy consumption is a greater concern, then a setting can be made. .
[0070] Different trajectory planning strategies should be validated under identical task parameters. When all strategies achieve the target reachability, the score is calculated accordingly. The smaller the value, the better the trajectory planning strategy performs in target point transfer scenarios.
[0071] Taking the mission requirement of an aerostat being area-based loiter as an example, the starting point, target point, loiter radius, and planned flight duration can be determined through mission parameters of trajectory planning. Setting the starting point and target point to be the same location establishes the center of the loiter area. The loiter radius can be determined based on actual operational needs. Within the planned flight duration, the aerostat maintains flight within the area defined by the center point determined by the starting or target point and the loiter radius. In this mission scenario, the evaluation metric can be set as mission completion rate.
[0072] Specifically, within a time range where the flight duration is less than or equal to the planned flight duration, the distance deviation between the current position of the digital twin aerostat and the target point can be calculated in real time. Based on this distance deviation and the loitering radius, it can be monitored in real time whether the aerostat is within the boundary of the loitering area. If the digital twin aerostat goes out of bounds, its out-of-bounds time is recorded; if the digital twin aerostat does not go out of bounds, the distance within the boundary between the current position of the digital twin aerostat and the target point is calculated in real time, and its average value and standard deviation are calculated. The score of the trajectory planning strategy is then determined using the following formula. : in, It is the out-of-bounds time of the digital twin levitation device. It is the average distance within the boundary. It is the standard deviation of the distance within the boundary. , and It is its corresponding weight coefficient, and .
[0073] In some embodiments, a shorter out-of-bounds time for the digital twin aerostat indicates a shorter out-of-bounds time and greater safety; a smaller distance between the current position of the digital twin aerostat and the target point calculated in real time indicates a larger safety margin and better performance; a smaller standard deviation of the in-bounds distance indicates more stable control of the aerostat. The evaluation rules can be adjusted according to the actual focus. , and Customize it.
[0074] For example, if whether or not the boundary is considered the most critical evaluation parameter, it can be set to... .
[0075] Different trajectory planning strategies should be validated under identical task parameters. When all strategies achieve the target reachability, the score is calculated accordingly. The smaller the value, the better the trajectory planning strategy performs in regional dwell task scenarios.
[0076] Taking the mission requirement of aerostats to remain stationary at a fixed point as an example, the starting point, target point, stationary radius, and planned flight duration can be determined through the mission parameters of the trajectory planning task. Specifically, setting the starting point and target point to be at the same location creates the center of the stationary area. The stationary radius is set to 0. The aerostat will remain stationary at the starting point, or target point, throughout the planned flight duration.
[0077] Specifically, within the time range where the flight duration is less than or equal to the planned flight duration, the distance deviation between the current position of the digital twin aerostat and the target point of fixed-point stationary can be calculated in real time, and its average value and standard deviation can be calculated. The score of the trajectory planning strategy can then be determined using the following formula. : in, It is the average distance deviation between the current position of the digital twin aerobatic system and the target point where it is stationary. It is the standard deviation of the distance between the current position of the digital twin aerobatic system and the target point where it is stationary. and It is its corresponding weight coefficient, and .
[0078] In some embodiments, the evaluation rules can be adjusted according to the actual emphasis. , Customization is possible. For example, if it is believed that closer to the target point yields better results, then settings can be configured... .
[0079] Different trajectory planning strategies should be validated under identical task parameters. When all strategies achieve the target reachability, the score is calculated accordingly. The smaller the value, the better the trajectory planning strategy performs in fixed-point dwell task scenarios.
[0080] Based on any of the above embodiments, the step of evaluating the trajectory planning strategy by comparing the real-time platform status data and the trajectory planning result based on the evaluation rules includes: The system state of the digital twin aerostat after executing the trajectory planning task is determined based on the real-time platform status data. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results, combined with the system status.
[0081] System status refers to a set of assessment indicators that affect the safety, stability, and sustainable operation capability of the aerostat's architecture. For example, system status may include the pressure differential state of the capsule, the strength of the load structure, the energy reserve state, and the thermal control balance state.
[0082] It should be noted that the system state of the digital twin airship after executing the trajectory planning task can be determined by using real-time platform state data simulated by the digital twin model after the trajectory planning task is performed, through dynamic evolution simulation and feature extraction processing.
[0083] Understandably, compared to simplifying the airship to a single point for trajectory planning, this embodiment determines the system state of the digital twin airship after performing the trajectory planning task based on real-time platform status data, and incorporates this system state into the trajectory planning strategy evaluation process. This means that the evaluation of the trajectory planning strategy is no longer based solely on geometric reachability or kinematic optimality, but rather incorporates system safety indicators into a unified evaluation framework, thereby reducing the risk of the trajectory planning results damaging the airship's own architecture during the engineering implementation phase.
[0084] Furthermore, in this embodiment, based on real-time platform state data obtained from digital twin model simulation, combined with dynamic evolution simulation and feature extraction processing, the system state after executing the trajectory planning task is determined, enabling the evaluation process to truly reflect the dynamic response characteristics of the airship under actual operating conditions. By comparing and analyzing the system state with the trajectory planning results, the evaluation bias caused by relying solely on static models or ideal assumptions can be significantly reduced, improving the accuracy and reliability of the trajectory planning strategy evaluation results.
[0085] Based on any of the above embodiments, obtaining the trajectory planning result by invoking the trajectory planning strategy according to the trajectory planning task includes: Based on the trajectory planning task, environmental forecast data of the flight area of the real airship and real-time platform status data of the digital twin airship are obtained. The flight guidance data of the digital twin airship is obtained based on the real-time platform status data of the digital twin airship and the environmental forecast data; Executable flight control commands are generated based on the flight guidance data; the executable flight control commands are used to control the flight of the digital twin aerostat.
[0086] Among them, the environmental forecast data of the flight area of the real airship is a set of multi-dimensional environmental parameters that are determined according to the trajectory planning task, support the trajectory planning and guidance of the real airship, and cover the flight area of the real airship.
[0087] It should be noted that after determining the trajectory planning task, the task requirements can be obtained by parsing the trajectory planning task. Based on the task requirements, various commonly used data sources can be called to obtain environmental forecast data of multiple elements such as wind field, irradiance, and cloud cover required for the trajectory planning task.
[0088] For example, the trajectory planning module of the digital test system of the airship can receive and parse the trajectory planning task to obtain the task requirements, generate an environmental data query request according to the task requirements, and call various commonly used data sources to obtain the environmental forecast data of multiple elements such as wind field, irradiance, and cloud required for the trajectory planning task through the environmental data query request of the airship's digital test system, and send the multi-element environmental forecast data to the trajectory planning module.
[0089] Understandably, by fusing real-time platform status data reflecting the current physical, energy, and mission status of the digital twin aerostat with multi-dimensional environmental parameters covering the flight area, the generated flight guidance data can not only be based on ideal trajectory planning under external weather conditions, but also fully consider the actual feasibility of the digital twin aerostat in terms of current energy reserves and attitude response capabilities. This reduces the risk of flight failure due to mismatch between the aerostat's platform status and environmental conditions, and improves the robustness of the aerostat's autonomous control in complex airspace environments.
[0090] In some embodiments, after evaluating the trajectory planning strategy based on the real-time platform status data and the trajectory planning results, the evaluation results can be visualized to improve the user experience in terms of information feedback.
[0091] Figure 2 This is an application diagram illustrating the airship flight control method provided by the present invention, such as... Figure 2 As shown, in order to illustrate the function of the airship flight control method provided in this embodiment, a specific example is provided below.
[0092] In this embodiment, the airship flight control method can be applied to Figure 2 The interactive module of the evaluation system for the trajectory planning strategy shown.
[0093] The interaction module may include a visual interface, which can be used to obtain the trajectory planning task published by the user. Then, based on the trajectory planning task, at least one trajectory planning strategy can be called through the interface to obtain the trajectory planning result. Based on the trajectory planning task, the digital twin airship can be started and the real-time platform status data of the digital twin airship can be obtained. The trajectory planning results and real-time platform status data can be sent to the flight guidance module to obtain the guidance data generated by the flight guidance module based on the trajectory planning results and real-time platform status data. The guidance data can then be sent to the flight control module to obtain the flight control commands generated by the flight control module based on the flight guidance data and the preset flight control algorithm. The flight control module sends flight control commands to the digital twin aerostat to control the digital twin aerostat to perform simulated flight in the digital twin environment, and obtains the real-time platform status data sent by the digital twin aerostat to the interaction module; then the trajectory planning results and real-time platform status data are sent to the effect evaluation module to obtain the evaluation results obtained by the effect evaluation module based on the evaluation indicators on the trajectory planning results and real-time platform status data. Finally, the evaluation results are visualized and provided to the user.
[0094] The aforementioned modules may be located on one or more ground monitoring computers or servers; one or more ground monitoring computers or servers may be connected to one or more network switches to enable data interaction between nodes in a distributed deployment.
[0095] It is understood that the trajectory planning strategy evaluation method provided in this embodiment of the invention, by applying a hierarchical architecture of planning, guidance, control, and digital twin airships, can achieve cross-disciplinary and full-element verification of the trajectory planning strategy of stratospheric airships, and simulate the actual application environment of the trajectory planning strategy of stratospheric airships to the greatest extent, so that the strategy can be fully verified.
[0096] Furthermore, users can set up task scenarios to verify multiple task scenarios such as regional residency and access to specific regions, as well as conduct full-process testing and verification from the start to the end of the task, thus solving the problem of insufficient task-oriented algorithm verification methods.
[0097] Furthermore, by using standard interface protocols, different trajectory planning strategies can be integrated into the algorithm verification system. Combined with various evaluation metrics, the effectiveness of different trajectory planning strategies can be assessed, simplifying the verification and evaluation process for trajectory planning strategies of different stratospheric airships. The evaluation metrics can be designed based on the mission requirements and platform characteristics of the stratospheric airship. After obtaining the evaluation results of the trajectory planning strategies, these results can be directly fed back to the algorithm designers through visualization, reducing the difficulty of iterative optimization of the trajectory planning strategies.
[0098] The trajectory planning strategy evaluation device provided by the present invention will be described below. The trajectory planning strategy evaluation device described below and the trajectory planning strategy evaluation method described above can be referred to in correspondence.
[0099] Figure 3 This is a schematic diagram of the structure of the trajectory planning strategy evaluation device provided by the present invention, as shown below. Figure 3 As shown, the device includes: The task acquisition module 310 is used to acquire trajectory planning tasks published by users. The trajectory planning module 320 is used to call the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result; The trajectory verification module 330 is used to control the digital twin airship to perform simulated flight in the digital twin environment according to the trajectory planning result, and obtain the real-time platform status data of the digital twin airship. The strategy evaluation module 340 is used to evaluate the trajectory planning strategy based on the real-time platform status data and the trajectory planning results.
[0100] Based on any of the above embodiments, the trajectory planning module 320 is used to call at least one of the trajectory planning strategies through an interface according to the trajectory planning task, and obtain the trajectory planning result generated by each trajectory planning strategy according to the trajectory planning task.
[0101] Based on any of the above embodiments, the strategy evaluation module 330 is used to determine evaluation rules according to the task requirements of the trajectory planning task; and to evaluate the trajectory planning strategy by comparing the real-time platform status data and the trajectory planning results based on the evaluation rules.
[0102] Based on any of the above embodiments, the strategy evaluation module 330 is configured to: if, based on the evaluation rules, compare the real-time platform status data and the trajectory planning result, and determine that the digital twin aerostat is controlled to complete the trajectory planning task according to the trajectory planning result; then determine the flight duration, energy consumption, and / or distance deviation of the digital twin aerostat performing the trajectory planning task, and evaluate the trajectory planning strategy based on the flight duration, the energy consumption, and / or the distance deviation; wherein, the distance deviation is obtained by comparing the actual position of the digital twin aerostat with the target position of the trajectory planning result.
[0103] Based on any of the above embodiments, the strategy evaluation module 330 is used to determine the system state of the digital twin aerostat after it performs the trajectory planning task based on the real-time platform state data; and to evaluate the trajectory planning strategy by comparing the real-time platform state data and the trajectory planning result, and combining the system state, based on the evaluation rules.
[0104] Based on any of the above embodiments, the evaluation rules are determined according to the requirements of the trajectory planning task and the dynamic requirements of the actual airship.
[0105] Based on any of the above embodiments, the digital twin environment is dynamically adjusted according to the environmental forecast data of the real flight area corresponding to the trajectory planning task.
[0106] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute an evaluation method for a trajectory planning strategy. This method includes: acquiring a trajectory planning task published by a user; invoking the trajectory planning strategy according to the trajectory planning task to obtain a trajectory planning result; controlling a digital twin aerostat to perform simulated flight in a digital twin environment based on the trajectory planning result to obtain real-time platform status data of the digital twin aerostat; and evaluating the trajectory planning strategy based on the real-time platform status data and the trajectory planning result.
[0107] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0108] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the evaluation method of the trajectory planning strategy provided by the above methods. The method includes: obtaining a trajectory planning task published by a user; invoking the trajectory planning strategy according to the trajectory planning task to obtain a trajectory planning result; controlling a digital twin aerostat to perform simulated flight in a digital twin environment according to the trajectory planning result to obtain real-time platform status data of the digital twin aerostat; and evaluating the trajectory planning strategy based on the real-time platform status data and the trajectory planning result.
[0109] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements an evaluation method for the trajectory planning strategy provided by the above methods. The method includes: acquiring a trajectory planning task published by a user; invoking the trajectory planning strategy according to the trajectory planning task to obtain a trajectory planning result; controlling a digital twin aerostat to perform simulated flight in a digital twin environment according to the trajectory planning result to obtain real-time platform status data of the digital twin aerostat; and evaluating the trajectory planning strategy based on the real-time platform status data and the trajectory planning result.
[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for evaluating trajectory planning strategies, characterized in that, include: Retrieve user-submitted trajectory planning tasks; The trajectory planning result is obtained by invoking the trajectory planning strategy according to the trajectory planning task. Based on the trajectory planning results, the digital twin airship is controlled to perform simulated flight in the digital twin environment to obtain the real-time platform status data of the digital twin airship; The trajectory planning strategy is evaluated based on the real-time platform status data and the trajectory planning results.
2. The evaluation method for trajectory planning strategies according to claim 1, characterized in that, The step of obtaining the trajectory planning result by invoking the trajectory planning strategy according to the trajectory planning task includes: Based on the trajectory planning task, at least one of the trajectory planning strategies is called through an interface to obtain the trajectory planning result generated by each trajectory planning strategy according to the trajectory planning task.
3. The evaluation method for trajectory planning strategies according to claim 1, characterized in that, The evaluation of the trajectory planning strategy based on the real-time platform status data and the trajectory planning results includes: The evaluation rules are determined based on the task requirements of the trajectory planning task. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results.
4. The evaluation method for trajectory planning strategies according to claim 3, characterized in that, The evaluation of the trajectory planning strategy based on the evaluation rules, by comparing the real-time platform status data and the trajectory planning results, includes: Based on the evaluation rules, if the real-time platform status data and the trajectory planning results are compared, it is determined that the digital twin airship will be controlled to complete the trajectory planning task according to the trajectory planning results; Then, the flight time, energy consumption, and / or distance deviation of the digital twin aerostat performing the trajectory planning task are determined, and the trajectory planning strategy is evaluated based on the flight time, energy consumption, and / or distance deviation. The distance deviation is obtained by comparing the actual position of the digital twin aerostat with the target position of the trajectory planning result.
5. The evaluation method for trajectory planning strategies according to claim 3, characterized in that, The evaluation of the trajectory planning strategy based on the evaluation rules, by comparing the real-time platform status data and the trajectory planning results, includes: The system state of the digital twin aerostat after executing the trajectory planning task is determined based on the real-time platform status data. Based on the evaluation rules, the trajectory planning strategy is evaluated by comparing the real-time platform status data and the trajectory planning results, combined with the system status.
6. The evaluation method for trajectory planning strategies according to claim 3, characterized in that, The evaluation rules are determined based on the requirements of the trajectory planning task and the dynamic requirements of the actual airship.
7. The evaluation method for trajectory planning strategies according to claim 3, characterized in that, The digital twin environment is dynamically adjusted based on environmental forecast data of the actual flight area corresponding to the trajectory planning task.
8. An evaluation device for trajectory planning strategies, characterized in that, include: The task acquisition module is used to acquire trajectory planning tasks published by users; The trajectory planning module is used to call the trajectory planning strategy according to the trajectory planning task to obtain the trajectory planning result; The trajectory verification module is used to control the digital twin airship to perform simulated flight in the digital twin environment according to the trajectory planning results, and to obtain the real-time platform status data of the digital twin airship. The strategy evaluation module is used to evaluate the trajectory planning strategy based on the real-time platform status data and the trajectory planning results.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the evaluation method of the trajectory planning strategy as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the evaluation method of the trajectory planning strategy as described in any one of claims 1 to 7.