Complex environment-oriented ground-air cooperative sensing parameter adjustment method and system

Abstract

The invention relates to the technical field of ground-air parameter adjustment, in particular to a ground-air cooperative sensing parameter adjustment method and system oriented to a complex environment, and the method comprises the steps: obtaining multi-mode sensing data of a current environment, and receiving system task information; based on the multi-modal sensing data, analyzing to obtain complex state information of the current environment, and obtaining a historical sequence corresponding to the complex state information; according to the historical sequence, analyzing an environment state change trend within a set time; defining a collaborative parameter adjustment target according to the system task information, the complex state information and the environment state change trend; and according to the cooperative parameter adjustment target, generating a perception parameter set for adjusting the complex state information, and distributing the perception parameter set to the corresponding ground-air equipment to adjust the perception parameters. According to the method, the problem of adaptive adjustment of the ground-air cooperative sensing parameters in a complex dynamic environment is effectively solved, the perspectiveness of parameter adjustment is remarkably improved, and task-oriented accurate collaboration is realized.

Description

Technical Field

[0001] This invention relates to the field of ground-to-air parameter adjustment technology, and in particular to a method and system for adjusting ground-to-air collaborative sensing parameters for complex environments. Background Technology

[0002] Ground-air collaborative sensing refers to the combined operation of air and ground platforms, utilizing their onboard sensors to conduct multi-level and multi-view detection and monitoring of specific areas or targets, thereby forming a comprehensive and three-dimensional sensing capability. Among these, sensing parameter adjustment is the core technical link to ensure the effectiveness of collaborative sensing. It refers to a series of operations that dynamically optimize the pose, motion state, and specific working mode of each platform according to environmental and mission requirements.

[0003] Currently, one of the existing technical solutions for adjusting ground-to-air collaborative sensing parameters is based on preset rules and static configuration. The static configuration method based on preset rules is completely unable to cope with the rapidly changing and unexpected situations in complex environments. Its parameter adjustment strategy is rigid. Once the preset conditions do not match the actual situation, the sensing performance of the entire system will drop sharply. More importantly, the existing technical solutions do not take system task information as a core decision input. They cannot proactively and collaboratively reconstruct the parameter configuration strategies of all platforms according to the real-time intent of the task. The parameter adjustment behaviors of ground-to-air devices are independent of each other, making it difficult to form the optimal overall collaborative sensing performance.

[0004] Therefore, a method is needed that can proactively and collaboratively adjust parameters based on historical data and the system's task intent. Summary of the Invention

[0005] In view of at least one of the above technical problems, the present invention provides a method and system for adjusting ground-air cooperative sensing parameters for complex environments. By introducing a collaborative decision-making mechanism based on multi-dimensional environmental prediction and task analysis, the present invention can achieve forward-looking and global optimization adjustment of ground-air cooperative sensing parameters.

[0006] This invention provides a method for adjusting ground-air cooperative sensing parameters for complex environments, comprising the following steps:

[0007] Acquire multimodal sensing data of the current environment and receive system task information;

[0008] Based on the multimodal sensing data, the complex state information of the current environment is obtained by parsing, and the historical sequence corresponding to the complex state information is obtained.

[0009] Based on the historical sequence, analyze the trend of environmental state changes within a set time period;

[0010] Based on the system task information, the complex state information, and the environmental state change trend, define the collaborative parameter adjustment target;

[0011] Based on the adjustment target of the coordination parameters, a set of sensing parameters for adjusting the complex state information is generated, and the set of sensing parameters is distributed to the corresponding ground-to-air equipment to adjust the sensing parameters.

[0012] In some embodiments of the present invention, analyzing the trend of environmental state changes within a set time period based on the historical sequence includes:

[0013] The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term.

[0014] Short-term trend values ​​are calculated based on the short-term subsequences, medium-term trend values ​​are calculated based on the medium-term subsequences, and long-term trend values ​​are calculated based on the long-term subsequences.

[0015] Based on the system task information, emergency factors are dynamically allocated to the short-term, medium-term, and long-term subsequences;

[0016] Based on the emergency factors and the corresponding short-term trend values, medium-term trend values, and long-term situation values, the trend of environmental state change is constructed.

[0017] In some embodiments of the present invention, constructing the environmental state change trend includes:

[0018] Construct the environmental state change trend T=[|S| α ·sign(S)]·[|M| β ·sign(M)]·[|L| γ ·sign(L)];

[0019] Wherein, S is the short-term trend value; M is the medium-term trend value; L is the long-term situation value; α is the emergency factor corresponding to the short-term subsequence, which is a constant; β is the emergency factor corresponding to the medium-term subsequence, which is a constant; γ is the emergency factor corresponding to the long-term subsequence, which is a constant, and α+β+γ=1.

[0020] In some embodiments of the present invention, the urgency factor is further dynamically adjusted in conjunction with the system task information:

[0021] The system task information is categorized into three types: rapid response, continuous monitoring, and resource sensitive.

[0022] If the system task information is a fast response type task, then increase the urgency factor α of the short-term subsequence;

[0023] If the system task information is a continuous monitoring task, then increase the urgency factor γ of the long-term subsequence;

[0024] If the system task information is a resource-sensitive task, then the urgency factor β of the intermediate subsequence is increased.

[0025] In some embodiments of the present invention, a collaborative parameter adjustment target is defined based on the system task information, the complex state information, and the environmental state change trend, including:

[0026] Based on the system task information, a task completion degree is established, and a collaborative decision-making space guided by the task completion degree is constructed in combination with the environmental state change trend.

[0027] Within the collaborative decision-making space, the complex state information is mapped into several perception performance constraints;

[0028] The perception parameters adjusted under the perception performance constraint to achieve the task completion rate are defined as the collaborative parameter adjustment target.

[0029] In some embodiments of the present invention, constructing a collaborative decision space oriented towards the task completion degree includes:

[0030] Based on the trend of environmental state changes, the evolution range of the complex state information within a future time window is selected.

[0031] The priority of each dimension of the perception parameters is determined based on the system task information, and the value range of each dimension is set.

[0032] The collaborative decision-making space is constructed using the parameter value range as a dimension, the evolution range as a dynamic feasible region, and the task completion degree as terrain height.

[0033] In some embodiments of the present invention, distributing the sensing parameter set to corresponding ground-to-air devices for adjusting the sensing parameters includes:

[0034] Based on the set of sensing parameters, a collaborative instruction is generated that includes parameter values, effective time, duration, and priority label.

[0035] Based on the local air-to-ground devices corresponding to the system task information, the collaborative instructions are distributed in the form of broadcasting or designated signatures.

[0036] After receiving the coordination command, the local air-to-ground equipment shall reply with a confirmation signal within a set time. If the confirmation signal is not replied with, a coordination anomaly signal shall be triggered.

[0037] In some embodiments of the present invention, the sensing parameter set includes platform-level parameters for controlling the spatial pose and motion state of ground-to-air equipment, and sensor-level parameters for controlling the operating mode of the sensing sensors.

[0038] This invention also provides a ground-air cooperative sensing parameter adjustment system for complex environments, comprising:

[0039] The receiving module acquires multimodal perception data of the current environment and receives system task information;

[0040] The environment analysis module, based on the multimodal sensing data, analyzes and obtains the complex state information of the current environment, and acquires the historical sequence corresponding to the complex state information;

[0041] The trend analysis module analyzes the trend of environmental state changes within a set time period based on the historical sequence.

[0042] The target definition module defines collaborative parameters to adjust the target based on the system task information, the complex state information, and the environmental state change trend.

[0043] The parameter adjustment module generates a set of sensing parameters for adjusting the complex state information based on the collaborative parameter adjustment target, and distributes the set of sensing parameters to the corresponding ground-to-air devices for adjusting the sensing parameters.

[0044] In some embodiments of the present invention, the trend analysis module includes:

[0045] The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term. The short-term trend value is calculated based on the short-term subsequence, the medium-term trend value is calculated based on the medium-term subsequence, and the long-term trend value is calculated based on the long-term subsequence.

[0046] The factor allocation unit, in conjunction with the system task information, dynamically allocates emergency factors to the short-term subsequence, medium-term subsequence, and long-term subsequence;

[0047] The trend construction unit constructs the environmental state change trend based on the emergency factor and the corresponding short-term tendency value, medium-term trend value and long-term situation value.

[0048] The beneficial effects of this invention are as follows: By introducing multi-timescale environmental state historical sequence analysis and dynamic trend prediction, this invention achieves the effect of shifting from passive response to active prediction of environmental changes, thereby improving the system's perception foresight and decision-making ability in complex dynamic environments; by dynamically coupling system task information with environmental trends and allocating trend urgency factors to different system task types, it improves the pertinence of system task execution and the efficiency of resource utilization, effectively solving the pain point that static parameter configuration cannot adapt to the diverse system task requirements. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present 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 only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating the method for adjusting ground-air cooperative sensing parameters in complex environments according to an embodiment of the present invention.

[0051] Figure 2 This is a flowchart illustrating the trend of environmental state changes over a set time period in an embodiment of the present invention;

[0052] Figure 3 This is a flowchart defining the target for adjusting the collaborative parameters in an embodiment of the present invention;

[0053] Figure 4 This is a flowchart illustrating the construction of a collaborative decision-making space oriented towards task completion in an embodiment of the present invention;

[0054] Figure 5 This is the process in this embodiment of the invention for distributing the sensing parameter set to the corresponding ground-to-air equipment to adjust the sensing parameter map. Detailed Implementation

[0055] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0056] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0058] This invention provides a method such as Figures 1 to 5 The method for adjusting ground-air cooperative sensing parameters for complex environments, as shown, includes the following steps:

[0059] Acquire multimodal sensing data of the current environment and receive system task information;

[0060] Based on multimodal sensing data, we can analyze and obtain complex state information of the current environment and acquire the historical sequence corresponding to the complex state information.

[0061] Based on historical sequences, analyze the trends in environmental state changes over a given time period;

[0062] Define the adjustment target for collaborative parameters based on system task information, complex state information, and environmental state change trends;

[0063] Based on the adjustment target of the coordination parameters, a set of sensing parameters for adjusting complex state information is generated, and the set of sensing parameters is distributed to the corresponding ground-to-air equipment to adjust the sensing parameters.

[0064] Multimodal perception data is acquired through various device nodes in the air-ground collaborative network. Specifically, visible light video streams can be acquired through optical cameras mounted on UAVs, infrared image sequences can be acquired through their infrared thermal imagers, electromagnetic environment data such as signal strength and interference noise can be acquired through spectrum monitoring sensors deployed on ground stations, and real-time wind speed and visibility data can be acquired through meteorological sensors. At the same time, system task information is received from the superior command system or manually input. System task information is a structured data object that includes at least one of the following: task type, geographical coordinates of the task area, core target of concern, task start / end time, and performance indicator requirements.

[0065] Data fusion and analysis methods, such as a lightweight convolutional neural network, are used to obtain complex state information of the current environment from multimodal sensing data. The system then retrieves historical information data recorded over a period of time, such as ten minutes, from the database to form a historical sequence. This process refines the raw, high-dimensional, and redundant sensor data into low-dimensional, key, and quantifiable complex state information, which is directly and strongly correlated with the performance of the sensing system. This greatly reduces the amount of data to be processed in subsequent steps, while making environmental information measurable and comparable, providing clear data objects for trend analysis. Furthermore, by analyzing the trend of environmental state changes based on the historical sequence, time series forecasting methods can be used, enabling the system to no longer passively respond to environmental changes but to gain the ability to predict the short-term state of the future.

[0066] Under the constraints of system task information, current complex state information, and predicted future environmental state change trends, an optimal performance solution is found and defined as the collaborative parameter adjustment target. This target can follow a predefined rule base or be derived through an optimization algorithm that is calculated and verified. Ultimately, it clearly indicates the direction that the system needs to adjust in order to achieve. Then, the collaborative parameter adjustment target is used to generate a set of sensing parameters that need to be adjusted based on the current complex state information. This set is simultaneously distributed to the sensing control unit of ground or air equipment via wireless communication links and adjusted accordingly. This significantly improves the intelligence level, overall efficiency, and mission reliability of the ground-air collaborative sensing system in complex dynamic environments.

[0067] In some embodiments of the present invention, such as Figure 2 As shown, based on historical sequences, the trend of environmental state changes within a set time period is analyzed, including:

[0068] The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term.

[0069] Short-term trend values ​​are calculated based on short-term subsequences, medium-term trend values ​​are calculated based on medium-term subsequences, and long-term trend values ​​are calculated based on long-term subsequences.

[0070] Based on system task information, emergency factors are dynamically allocated to short-term, medium-term, and long-term subsequences;

[0071] Based on the emergency factors and their corresponding short-term trend values, medium-term trend values, and long-term situation values, the trend of environmental status change is constructed.

[0072] The system maintains a cyclic database that continuously stores historical sequences composed of complex state information vectors. When trend analysis is required, the system divides the historical sequence into three subsequences according to a preset time window configuration. The short-term subsequence covers the most recent very short time period and is used to capture instantaneous fluctuations and rapid disturbances in the environment. The medium-term subsequence covers a slightly longer medium-term time period and is used to identify the continuous trends and change patterns of the environment. The long-term subsequence covers the longest long-term time period and is used to determine the macro background situation and baseline level of the environment.

[0073] Next, representative sub-trend values ​​are calculated for each of the three sub-sequences. For the short-term sub-sequence, a short-term tendency value is calculated, which is mainly used to quantify the direction (forward or backward) and urgency of the latest changes. For the medium-term sub-sequence, a medium-term trend value is calculated, which is mainly used to quantify the intensity and stability of changes within the medium-term time period. For the long-term sub-sequence, a long-term situation value is calculated, which is mainly used to assess the absolute baseline level of the environment. Based on the received system task information, urgency factors are dynamically assigned to the above three sub-trends to lay the foundation for adaptive task scheduling. Finally, the calculated short-term tendency value, medium-term trend value, and long-term situation value are combined with their respective assigned urgency factors to construct a comprehensive environmental state change trend. By transforming the original historical data sequence into an environmental state change trend rich in semantic information and strongly correlated with system task information, a solid foundation is laid for realizing the transformation from passive response to proactive anticipation.

[0074] Based on the above embodiments, an environmental state change trend is constructed, including:

[0075] Construct the environmental state change trend T=[|S| α ·sign(S)]·[|M| β ·sign(M)]·[|L| γ ·sign(L)];

[0076] Where S is the short-term trend value; M is the medium-term trend value; L is the long-term trend value; α is the emergency factor corresponding to the short-term subsequence, which is a constant; β is the emergency factor corresponding to the medium-term subsequence, which is a constant; γ is the emergency factor corresponding to the long-term subsequence, which is a constant, and α+β+γ=1.

[0077] The output of the constructed environmental state change trend T is the product of the inputs. When an input changes slightly, especially when its magnitude is very large or very small, it will have a multiplicative effect on the output, amplifying or reducing it. In the real world, environmental factors do not change in isolation. For example, rainfall during rush hour increases the likelihood of traffic paralysis, and sudden strong winds in turbulent areas significantly increase the overall hazard. Therefore, in complex environments, using product calculations can amplify the effect of a trend at one scale that suddenly issues a strong danger signal, allowing it to immediately dominate the final fusion result T. This makes the system react extremely quickly and avoids missing the optimal decision window. Furthermore, the addition of the sign function (sign)... It can capture the consistency of input results, which is useful for handling the direction of trends separately. When the short-term trend value S, the medium-term trend value M, and the long-term situation value L all point to the same conclusion in the corresponding actual system task information, the absolute value of the product result, the environmental state change trend T, will be very large, indicating that the environmental change is certain and generating a very strong signal that the system needs to make significant parameter adjustments. The short-term trend value S can be obtained by calculating the arithmetic mean of the short-term subsequence using the first difference. The medium-term trend value M can be obtained by linearly fitting the medium-term subsequence and using the fitting slope as the medium-term trend value M. The long-term situation value L can be obtained by calculating the relative rate of change of the long-term subsequence with respect to the initial value.

[0078] Furthermore, the absolute value of the environmental state change trend T represents the intensity of the trend; the larger the absolute value, the stronger and more certain the trend. The sign of the environmental state change trend T represents the direction of the overall trend: a positive sign indicates the environment is developing in a more challenging or worsening direction, while a negative sign indicates the environment is developing in a more favorable direction. The construction of the environmental state change trend T enables the system to have a superlinear response capability to short-term sudden risks, greatly improving safety and achieving a deep integration of task strategy and situational analysis. This allows the system to make different parameter adjustments for different complex environments. The environmental state change trend T generated by multiplication and fusion is a scalar with both direction and intensity, providing an extremely clear and quantitative decision-making basis for subsequent parameter adjustments, ultimately driving the ground-air cooperative system to achieve advanced and precise adaptive adjustments in dynamic environments.

[0079] Based on the above embodiments, the urgency factor is also dynamically adjusted in conjunction with system task information:

[0080] System task information is categorized into three types: rapid response, continuous monitoring, and resource sensitive.

[0081] If the system task information is a fast-response task, then increase the urgency factor α of the short-term subsequence;

[0082] If the system task information is a continuous monitoring task, then increase the urgency factor γ of the long-term subsequence;

[0083] If the system task information is a resource-sensitive task, then increase the urgency factor β of the intermediate subsequence.

[0084] Rapid response tasks, such as target emergence tracking and emergency disaster monitoring, focus on short-term changes and require the system to react in a very short time. Continuous monitoring tasks, such as routine regional patrols and long-term situation building, emphasize stability and long-term data consistency. Resource-sensitive tasks, such as operating in energy-saving mode and multi-task coordination under limited resources, emphasize the efficiency and balance of resource use. Different system task information requires different response capabilities. By driving the allocation of emergency factors through task type, trend analysis can better match the actual task needs, avoid the possibility of overgeneralization, and more quickly focus on the environmental change dimensions that are most important to the current task, thereby improving response speed and execution accuracy.

[0085] In some embodiments of the present invention, such as Figure 3 As shown, based on system task information, complex state information, and environmental state change trends, the coordination parameter adjustment targets are defined, including:

[0086] Based on system task information, a task completion rate is established, and a collaborative decision-making space oriented towards task completion rate is constructed by combining the trend of environmental state changes.

[0087] Within the collaborative decision-making space, complex state information is mapped into several perception performance constraints;

[0088] The perception parameters that are adjusted under the constraint of perception performance to achieve the desired task completion rate are defined as the collaborative parameter adjustment target.

[0089] First, based on the core intent of the system's task information, a quantifiable task completion index is established as the ultimate guide for all parameter adjustments. Then, combined with predictions of future environmental trends, a multi-dimensional collaborative decision-making space is constructed. Each dimension of this space represents an adjustable perception parameter, its value range dynamically defined by the predicted environmental evolution. The value terrain within the space is depicted by the task completion index, representing the expected effectiveness of different parameter combinations for task achievement. Within this decision-making space, the current complex real-time environmental state is transformed into specific perception effectiveness constraints. These constraints act like obstacle zones in the space, identifying parameter areas that are infeasible or inefficient due to current environmental limitations. Within the feasible range after excluding obstacle zones, the optimal parameter combination that maximizes task completion is sought, and this combination is explicitly defined as the target of this collaborative parameter adjustment. This ensures that the parameter adjustment strategy is not isolated or static, achieving precise, adaptive, and globally optimal closed-loop decision-making from task requirements to parameter execution. This significantly improves the intelligent perception parameter adjustment level and task execution efficiency of the ground-air collaborative system in complex dynamic environments.

[0090] Based on the above embodiments, such as Figure 4 As shown, a collaborative decision-making space oriented towards task completion is constructed, including:

[0091] Based on the trend of environmental state changes, the evolution range of complex state information within a future time window is selected.

[0092] Determine the priority of each dimension of the perception parameters based on the system task information, and set the parameter value range for each dimension.

[0093] A collaborative decision-making space is constructed using the parameter value range as the dimension, the evolution range as the dynamic feasible region, and the task completion degree as the terrain height.

[0094] By defining the possible evolution range of key environmental elements within a specific future time window based on the trend of environmental state changes, a dynamic boundary with time foresight is defined for decision-making. On this basis, the received task information is comprehensively analyzed to accurately determine the adjustment priority of each perception parameter. Based on the core requirements of the task and the expected changes in the environment, a reasonable and adaptive value range is set for each parameter dimension. These parameter value ranges are used as the basic dimensions of the space, the predicted range of environmental evolution is used as the feasible domain for dynamic adjustment, and the task completion degree achievable by different parameter combinations is projected as the terrain height in the space, thereby constructing a multi-dimensional collaborative decision-making space containing rich decision-making information. The complex mapping relationship between parameter selection, environmental evolution, and task effectiveness is shown, enabling the system to comprehensively consider all constraints and objectives within a unified and intuitive framework. This provides a crucial visualization and computational foundation for subsequently finding the globally optimal collaborative parameter adjustment target.

[0095] In some embodiments of the present invention, such as Figure 5 As shown, the sensing parameter set is distributed to the corresponding ground-to-air equipment for adjustment of the sensing parameters, including:

[0096] Based on the perception parameter set, generate collaborative instructions that include parameter values, effective time, duration and priority labels;

[0097] Based on the local air-to-ground devices corresponding to the system task information, collaborative instructions are distributed in the form of broadcasting or designated signatures.

[0098] After receiving the coordination command, the air-to-ground equipment in each location shall reply with a confirmation signal within a set time. If no confirmation signal is replied, a coordination anomaly signal will be triggered.

[0099] The generated set of sensing parameters is encapsulated into structured collaborative instructions. These instructions not only contain specific parameter values ​​but also specify the effective time, expected duration, and execution priority label for each parameter, thus forming a complete and time-sequential operational guide. Based on the equipment list involved in the mission information, the collaborative instructions are distributed to the corresponding ground or air equipment terminals via wireless communication networks, either broadcast globally or using digital signatures to designate specific devices. After receiving the instructions, each air-ground device must provide a confirmation signal within a preset time window to confirm successful reception and parsing. If any device fails to respond with a confirmation signal within the specified time, the system will immediately trigger a collaborative anomaly signal, alerting the control center to the risk of communication interruption or equipment failure, so as to promptly initiate redundant scheduling or troubleshooting procedures. This ensures the reliable transmission and synchronous execution of parameter adjustment instructions and significantly enhances the stability and reliability of the entire ground-air collaborative system in complex environments through collaborative anomaly signals.

[0100] In some embodiments of the present invention, the sensing parameter set includes platform-level parameters for controlling the spatial pose and motion state of ground-to-air equipment, and sensor-level parameters for controlling the operating mode of the sensing sensors.

[0101] The generated and issued sensing parameter set is a hierarchical and comprehensive set of control commands, encompassing all key parameters from macroscopic platform control to microscopic sensor tuning. This parameter set specifically includes two main categories: the first is platform-level parameters, primarily used to regulate the spatial attitude and motion state of the air-to-ground equipment itself, such as basic motion indicators like the aircraft's or ground vehicle's altitude, speed, hovering position, attitude angle, heading trajectory, and maneuvering mode; the second is sensor-level parameters, mainly used to manage the operating modes and acquisition strategies of various sensing sensors, such as the focal length, resolution, frame rate, and shooting angle of optical cameras, the temperature sensitivity and scanning range of infrared thermal imagers, the detection frequency and beamwidth of radars, and the gain and filtering settings of signal receiving equipment. This sensing parameter set can simultaneously perform collaborative optimization and integrated control of the platform's macroscopic attitude and the sensors' microscopic sensing behavior, ensuring both optimal layout of the observation perspective and high-quality acquisition of sensing data, thus laying a solid foundation for efficient air-to-ground collaborative sensing from a hardware perspective.

[0102] This invention also provides a ground-air cooperative sensing parameter adjustment system for complex environments, comprising:

[0103] The receiving module acquires multimodal perception data of the current environment and receives system task information;

[0104] The environment analysis module, based on multimodal perception data, analyzes and obtains the complex state information of the current environment, and acquires the historical sequence corresponding to the complex state information;

[0105] The trend analysis module analyzes the changing trends of environmental conditions within a set time period based on historical sequences.

[0106] The target definition module defines collaborative parameters to adjust targets based on system task information, complex state information, and environmental state change trends.

[0107] The parameter adjustment module generates a set of sensing parameters for adjusting complex state information based on the collaborative parameter adjustment target, and distributes the set of sensing parameters to the corresponding ground and air devices for adjusting the sensing parameters.

[0108] The adjustment system described above in this invention can effectively realize a method for adjusting ground-air collaborative sensing parameters for complex environments. The technical effects it can achieve are as described in the above embodiments, and will not be repeated here.

[0109] In some embodiments of the present invention, the trend analysis module includes:

[0110] The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term. Short-term trend values ​​are calculated based on the short-term subsequences, medium-term trend values ​​are calculated based on the medium-term subsequences, and long-term trend values ​​are calculated based on the long-term subsequences.

[0111] The factor allocation unit dynamically allocates emergency factors to short-term, medium-term, and long-term subsequences based on system task information.

[0112] The trend construction unit constructs the trend of environmental status change based on the emergency factors and their corresponding short-term tendency values, medium-term trend values ​​and long-term situation values.

[0113] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the methods provided by the present invention, which will not be elaborated here.

[0114] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for adjusting ground-air cooperative sensing parameters for complex environments, characterized in that, Includes the following steps: Acquire multimodal sensing data of the current environment and receive system task information; Based on the multimodal sensing data, the complex state information of the current environment is obtained by parsing, and the historical sequence corresponding to the complex state information is obtained. Based on the historical sequence, analyze the trend of environmental state changes within a set time period; Based on the system task information, the complex state information, and the environmental state change trend, define the collaborative parameter adjustment target; Based on the adjustment target of the coordination parameters, a set of sensing parameters for adjusting the complex state information is generated, and the set of sensing parameters is distributed to the corresponding ground-to-air equipment to adjust the sensing parameters.

2. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 1, characterized in that, Based on the historical sequence, analyze the trend of environmental state changes within a set time period, including: The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term. Short-term trend values ​​are calculated based on the short-term subsequences, medium-term trend values ​​are calculated based on the medium-term subsequences, and long-term trend values ​​are calculated based on the long-term subsequences. Based on the system task information, emergency factors are dynamically allocated to the short-term, medium-term, and long-term subsequences; Based on the emergency factors and the corresponding short-term trend values, medium-term trend values, and long-term situation values, the environmental state change trend is constructed.

3. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 2, characterized in that, Constructing the trend of environmental state changes includes: Construct the environmental state change trend T=[|S| α ·sign(S)]·[|M| β ·sign(M)]·[|L| γ ·sign(L)]; Wherein, S is the short-term trend value; M is the medium-term trend value; L is the long-term situation value; α is the emergency factor corresponding to the short-term subsequence, which is a constant; β is the emergency factor corresponding to the medium-term subsequence, which is a constant; γ is the emergency factor corresponding to the long-term subsequence, which is a constant, and α+β+γ=1.

4. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 3, characterized in that, It also includes dynamically adjusting the urgency factor based on the system task information: The system task information is categorized into three types: rapid response, continuous monitoring, and resource sensitive. If the system task information is a fast response type task, then increase the urgency factor α of the short-term subsequence; If the system task information is a continuous monitoring task, then increase the urgency factor γ of the long-term subsequence; If the system task information is a resource-sensitive task, then the urgency factor β of the intermediate subsequence is increased.

5. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 1, characterized in that, Based on the system task information, the complex state information, and the environmental state change trend, define the collaborative parameter adjustment target, including: Based on the system task information, a task completion degree is established, and a collaborative decision-making space guided by the task completion degree is constructed in combination with the environmental state change trend. Within the collaborative decision-making space, the complex state information is mapped into several perception performance constraints; The perception parameters adjusted under the perception performance constraint to achieve the task completion rate are defined as the collaborative parameter adjustment target.

6. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 5, characterized in that, Constructing a collaborative decision-making space oriented towards the completion degree of the aforementioned task, including: Based on the trend of environmental state changes, the evolution range of the complex state information within a future time window is selected. The priority of each dimension of the perception parameters is determined based on the system task information, and the value range of each dimension is set. The collaborative decision-making space is constructed using the parameter value range as a dimension, the evolution range as a dynamic feasible region, and the task completion degree as terrain height.

7. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 1, characterized in that, Distributing the sensing parameter set to the corresponding ground-to-air equipment to adjust the sensing parameters includes: Based on the set of sensing parameters, a collaborative instruction is generated that includes parameter values, effective time, duration, and priority label. Based on the local air-to-ground devices corresponding to the system task information, the collaborative instructions are distributed in the form of broadcasting or designated signatures. After receiving the coordination command, the local air-to-ground equipment shall reply with a confirmation signal within a set time. If the confirmation signal is not replied with, a coordination anomaly signal shall be triggered.

8. The method for adjusting ground-air cooperative sensing parameters for complex environments according to claim 1, characterized in that, The set of sensing parameters includes platform-level parameters for controlling the spatial pose and motion state of ground-to-air equipment, and sensor-level parameters for controlling the operating mode of sensing sensors.

9. A ground-air cooperative sensing parameter adjustment system for complex environments, characterized in that, include: The receiving module acquires multimodal perception data of the current environment and receives system task information; The environment analysis module, based on the multimodal sensing data, analyzes and obtains the complex state information of the current environment, and acquires the historical sequence corresponding to the complex state information; The trend analysis module analyzes the trend of environmental state changes within a set time period based on the historical sequence. The target definition module defines collaborative parameters to adjust the target based on the system task information, the complex state information, and the environmental state change trend. The parameter adjustment module generates a set of sensing parameters for adjusting the complex state information based on the collaborative parameter adjustment target, and distributes the set of sensing parameters to the corresponding ground-to-air devices for adjusting the sensing parameters.

10. The ground-air cooperative sensing parameter adjustment system for complex environments according to claim 9, characterized in that, The trend analysis module includes: The historical sequence is divided into subsequences corresponding to three time scales: short-term, medium-term, and long-term. The short-term trend value is calculated based on the short-term subsequence, the medium-term trend value is calculated based on the medium-term subsequence, and the long-term trend value is calculated based on the long-term subsequence. The factor allocation unit, in conjunction with the system task information, dynamically allocates emergency factors to the short-term subsequence, medium-term subsequence, and long-term subsequence; The trend construction unit constructs the environmental state change trend based on the emergency factor and the corresponding short-term tendency value, medium-term trend value and long-term situation value.

Images