A helicopter dynamic route planning method and system based on a composite cost function
Patent Information
- Application Number
- CN202610808354.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-05
- Publication Date
- 2026-08-28
AI Technical Summary
[0003]（1）地形数据滞后且不完整：传统依赖的卫星影像、高程数据、基础矢量数据或者航拍地图无法及时反映灾后地貌的剧烈变化（如塌方、堰塞湖等），且缺乏对临时风险源（如不稳定山体、泥石流滑坡）的感知，导致规划路线多用底图数据与实际情况严重脱节
[0059] 1. Dynamic and accurate situational awareness: This invention relies on a dynamic programming-driven multi-source heterogeneous data fusion and real-time update mechanism to construct a high-precision three-dimensional model that can accurately reflect the dynamic evolution of the post-disaster environment, providing real-time and reliable dynamic input for subsequent decision-making and planning.
Smart Images
Figure CN122653237A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of flight path planning technology, and more specifically to a helicopter dynamic flight path planning method and system based on a composite cost function. Background Technology
[0002] Currently, in the event of natural disasters (such as earthquakes, floods, and landslides) or major accidents, the use of helicopters for personnel search and rescue, material delivery, and casualty evacuation is a crucial emergency rescue method. However, the complex and ever-changing terrain after a disaster typically presents the following severe challenges:
[0003] (1) Lagging and incomplete terrain data: Traditional satellite imagery, elevation data, basic vector data or aerial maps cannot reflect the drastic changes in the landform after the disaster (such as landslides, barrier lakes, etc.) in a timely manner, and lack the perception of temporary risk sources (such as unstable mountains, debris flow and landslides), resulting in the use of base map data for planned routes being seriously out of sync with the actual situation.
[0004] (2) Severe lack of dynamic route planning capability: During mission execution, when encountering sudden obstacles, secondary disasters, landing point adjustments, or temporary airspace control, the existing system lacks the ability to reconstruct the global route in real time and cannot dynamically integrate new sensed information and provide closed-loop feedback to flight control. The response relies entirely on the pilot's experience to make temporary judgments and handle situations, which not only increases the operational workload but also leads to route deviations, delays in rescue windows, and even secondary risks. This "static planning + manual emergency response" model directly weakens the helicopter's adaptability and survivability in disaster environments.
[0005] Therefore, how to achieve real-time dynamic route planning through real-time fusion of multi-source data and coupling with cost functions is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0006] In view of the above problems, this invention is proposed to provide a helicopter dynamic route planning method and system based on a composite cost function to overcome or at least partially solve the above problems. By integrating "situational awareness, intelligent planning and dynamic adjustment" into a single route planning system, and through real-time fusion of multi-source data and coupling with cost functions, real-time dynamic route planning is achieved, thereby improving the safety, efficiency and reliability of helicopter rescue in disaster relief.
[0007] To achieve the above objectives, the present invention adopts the following technical solution:
[0008] In a first aspect, embodiments of the present invention provide a helicopter dynamic route planning method based on a composite cost function, comprising:
[0009] Acquire multi-source data of the target area and fuse them to generate a dynamic 3D terrain model;
[0010] Based on the target area, a takeoff point and multiple potential landing points are established;
[0011] All landing points are evaluated based on a comprehensive evaluation cost function for landing point adaptability to obtain the optimal landing point.
[0012] Based on the takeoff point and the optimal landing point, and combined with the flight complexity cost function, the current optimal exploration area is obtained;
[0013] Based on the current optimal exploration area and the deep coupling cost function, candidate flight nodes are selected.
[0014] The optimal flight node for the current exploration area is obtained based on the candidate flight nodes;
[0015] The current optimal flight path is obtained based on the takeoff point, the optimal flight node, and the optimal landing point;
[0016] The flight is based on the current optimal route, and subsequent routes are dynamically updated in case of anomalies.
[0017] Preferably, generating a dynamic 3D terrain model specifically includes:
[0018] The target area's basic GIS data, post-disaster remote sensing images, geological early warning data, real-time meteorological data, on-site sensor data, and UAV aerial images are acquired and used together as the multi-source data.
[0019] Based on the multi-source data, a fusion operation of unified coordinate system, complementary filtering and 3D reconstruction, dynamic layer labeling and updating is performed to generate the dynamic 3D terrain model containing basic terrain, static obstacles and dynamic risk sources.
[0020] The preferred method is to obtain the optimal landing point, which specifically includes:
[0021] The comprehensive evaluation cost function for landing site adaptability includes four primary indicators: terrain physical characteristics, airspace conditions, rescue convenience, and environmental risk.
[0022] Each of the primary indicators includes multiple secondary indicators;
[0023] Based on the analytic hierarchy process, weights are assigned to each of the secondary indicators to obtain the corresponding indicator weights;
[0024] Based on all the landing points, the corresponding indicator scores are obtained by quantifying all the secondary indicators.
[0025] The comprehensive suitability score for each landing point is obtained by weighted summation of all the indicator weights and the corresponding indicator scores.
[0026] The landing point corresponding to the highest comprehensive suitability score is selected as the optimal landing point.
[0027] Preferably, the terrain physical characteristics include multiple secondary indicators: ground slope, ground roughness, and ground bearing capacity;
[0028] The airspace conditions include several secondary indicators: assessment of the impact of approach / departure track obstacles and surrounding turbulence;
[0029] The rescue convenience includes several secondary indicators: the accessibility and cost between the landing point and multiple rescue points, and the convenience of helicopter hovering and transfer;
[0030] The environmental risks include several secondary indicators: distance from dynamic risk sources and population density.
[0031] The preferred approach is to obtain the current optimal exploration region, specifically including:
[0032] The flight complexity cost function is used to dynamically adjust the search direction of flight node expansion based on the relative position of the current flight segment and the target point and terrain features;
[0033] Based on the region between the takeoff point and the optimal landing point, the exploration direction of the flight node expansion is dynamically adjusted in conjunction with the flight complexity cost function, guiding the exploration of the current optimal exploration region that is safe, gentle, weather-stable, and points towards the optimal landing point.
[0034] Preferably, the method for obtaining candidate flight nodes is as follows:
[0035] All flight nodes to be tested are determined based on the current optimal exploration area;
[0036] Based on the flight node under test, the deep coupling cost function constraint verification of flight performance and terrain constraints is performed;
[0037] The test flight node that simultaneously passes the vertical gradient verification, ground clearance verification, horizontal safety verification, and maneuverability verification is selected as the candidate flight node.
[0038] Preferably, the passing criterion for the vertical gradient verification is: the ratio of the height difference of the regional terrain to the horizontal distance of the regional terrain is less than or equal to the maximum rate of ascent;
[0039] The passing standard for the near-ground clearance verification is: ground clearance greater than or equal to the minimum ground clearance;
[0040] The passing standard for the horizontal safety check is: the horizontal distance to the obstacle is greater than or equal to the safety distance;
[0041] The passing standard for the mobility test is: the turning radius is greater than or equal to the minimum turning radius.
[0042] The preferred method for obtaining the optimal flight node is as follows:
[0043] Based on the dynamic three-dimensional terrain model, the terrain undulation and slope change rate of the route path nodes are extracted to construct a terrain complexity cost function;
[0044] A risk attenuation field is constructed based on the risk sources in dynamic monitoring to form a dynamic environmental risk cost function;
[0045] A real-time meteorological impact cost function is constructed based on real meteorological data, including headwind / crosswind costs, visibility and precipitation impacts, and lightning and severe convection avoidance.
[0046] Based on the candidate flight nodes, the candidate flight node with the lowest terrain complexity, lowest environmental risk, and lowest meteorological impact is selected as the optimal flight node through the terrain complexity cost function, the dynamic environmental risk cost function, and the real-time meteorological impact cost function.
[0047] Preferably, subsequent routes are dynamically updated, specifically including:
[0048] Fly based on the current optimal route and acquire real-time environmental data during the flight;
[0049] Based on the comparison between the real-time environmental data and the dynamic three-dimensional terrain model, when a new obstacle is detected or the deviation from the preset flight path exceeds the safety threshold, an early warning is triggered and a local replanning is initiated.
[0050] During the local replanning, the process of obtaining the current optimal route is repeated with the current position as the new starting point, the flight route after the new starting point is updated, and the updated new route is generated.
[0051] In a second aspect, embodiments of the present invention provide a helicopter dynamic route planning system based on a composite cost function, used to execute a helicopter dynamic route planning method based on a composite cost function as described in any of the first aspects, including: a terrain model generation module, a landing point screening module, an exploration area determination module, a candidate node determination module, an optimal route generation module, and a route dynamic update module;
[0052] The terrain model generation module is used to acquire multi-source data of the target area and fuse them to generate a dynamic three-dimensional terrain model;
[0053] The landing point screening module is used to set a takeoff point and multiple potential landing points based on the target area; and to evaluate all the landing points based on the landing point adaptability comprehensive evaluation cost function to obtain the optimal landing point.
[0054] The exploration area determination module is used to obtain the current optimal exploration area based on the takeoff point and the optimal landing point, combined with the flight complexity cost function;
[0055] The candidate node determination module is used to filter and obtain candidate flight nodes based on the current optimal exploration area and the deep coupling cost function;
[0056] The optimal route generation module is used to obtain the optimal flight node in the current exploration area based on the candidate flight nodes; and to obtain the current optimal route based on the takeoff point, the optimal flight node, and the optimal landing point.
[0057] The route dynamic update module is used to fly based on the current optimal route and dynamically update subsequent routes in case of anomalies.
[0058] As can be seen from the above technical solution, compared with the prior art, the present invention discloses a helicopter dynamic route planning method and system based on a composite cost function, which has the following beneficial effects:
[0059] 1. Dynamic and accurate situational awareness: This invention relies on a dynamic programming-driven multi-source heterogeneous data fusion and real-time update mechanism to construct a high-precision three-dimensional model that can accurately reflect the dynamic evolution of the post-disaster environment, providing real-time and reliable dynamic input for subsequent decision-making and planning.
[0060] 2. Optimal Route Planning Safety: This invention integrates real-time dynamic data to form a cost function that covers terrain, risk field, aircraft performance coupling constraints, weather, landing point and flight complexity. Through continuous global and local optimization, it generates the optimal route that meets flight safety requirements, significantly improving the reliability and practicality of the planning results.
[0061] 3. Strong ability to dynamically adjust flight routes: This invention introduces a dynamic planning online adjustment mechanism, enabling the system to perceive environmental changes and mission deviations in real time. It can dynamically correct flight routes and decision-making strategies during flight, enhance its adaptability to post-disaster uncertainties, and effectively ensure flight safety. Attached Figure Description
[0062] 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 embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0063] Figure 1This is a flowchart of a helicopter dynamic route planning method based on a composite cost function provided in an embodiment of the present invention.
[0064] Figure 2 This is a schematic diagram illustrating the principle of constructing a dynamic three-dimensional terrain model by fusing multi-source data in an embodiment of the present invention.
[0065] Figure 3 This is a flowchart of the candidate flight node acquisition method provided in this embodiment of the invention.
[0066] Figure 4 This is a flowchart of the method for dynamically updating subsequent flight routes provided in an embodiment of the present invention.
[0067] Figure 5 This is a schematic diagram of a helicopter dynamic route planning system based on a composite cost function provided in an embodiment of the present invention. Detailed Implementation
[0068] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0069] Example 1
[0070] like Figure 1 As shown, this embodiment of the invention discloses a helicopter dynamic route planning method based on a composite cost function, including the following steps. For ease of description, these steps are numbered S1 to S8, and these numbers are not used to limit the sequential relationship between the various steps of this invention:
[0071] S1 acquires multi-source data of the target area and fuses it to generate a dynamic three-dimensional terrain model.
[0072] Furthermore, such as Figure 2 As shown, generating a dynamic 3D terrain model specifically includes:
[0073] Acquire basic GIS data, post-disaster remote sensing images, geological early warning data, real-time meteorological data, on-site sensor data, and drone aerial images of the target area, and use them together as multi-source data;
[0074] By performing a fusion operation based on multi-source data—including a unified coordinate system, complementary filtering and 3D reconstruction, and dynamic layer labeling and updating—a dynamic 3D terrain model is generated, which includes basic terrain, static obstacles, and dynamic risk sources.
[0075] Furthermore, the received field sensor data is first annotated with base map images, and then the data is fused by spatiotemporal registration, Kalman filtering and feature stitching of the image data to generate a dynamic three-dimensional terrain model that includes basic terrain, static obstacles and dynamic risk sources.
[0076] Furthermore, the basic GIS data includes: digital elevation model (DEM), vector layers, vegetation, water bodies, buildings, and power lines; basic topography includes: elevation, surface type, and slope; static obstacles include: buildings and peaks; and dynamic risk sources include: landslides, floods, and new obstacles.
[0077] Furthermore, post-disaster remote sensing imagery is used to identify large-scale surface changes; drone aerial imagery is used to acquire detailed topography of the target area.
[0078] Furthermore, this invention introduces a real-time update detection mechanism by generating a dynamic three-dimensional terrain model: continuously accessing UAV aerial survey images and sensor monitoring information, quickly marking and fusing new temporary risk sources such as landslides and rising water levels to form a new data model, ensuring that the data model is dynamically synchronized with the post-disaster environment, and completely solving the analysis bias caused by data lag.
[0079] S2 sets up takeoff points and multiple potential landing points based on the target area.
[0080] Furthermore, relevant commanders set up takeoff points, multiple potential landing sites to be assessed (such as flat open spaces, rooftops, stadiums, school playgrounds), and the location of rescue villages in the target area.
[0081] S3 evaluates all landing points based on the landing point adaptability comprehensive evaluation cost function to obtain the optimal landing point.
[0082] Furthermore, the optimal landing point is obtained, specifically including:
[0083] The cost function for the comprehensive assessment of landing site adaptability includes four primary indicators: terrain physical characteristics, airspace conditions, rescue convenience, and environmental risk.
[0084] Each primary indicator includes multiple secondary indicators;
[0085] We assign weights to each secondary indicator based on the analytic hierarchy process to obtain the corresponding indicator weights.
[0086] Based on all landing points, the corresponding indicator scores are obtained by quantifying all secondary indicators.
[0087] The comprehensive suitability score for each landing point is obtained by weighted summation of all indicator weights and corresponding indicator scores.
[0088] The landing point corresponding to the highest overall fit score is selected as the optimal landing point.
[0089] Furthermore, the physical characteristics of the terrain include several secondary indicators: ground slope, ground roughness, and ground bearing capacity;
[0090] Clearance conditions include several secondary indicators: assessment of the impact of approach / departure track obstacles and surrounding turbulence;
[0091] Rescue accessibility includes several secondary indicators: accessibility and cost between the landing site and multiple rescue points, and the ease of helicopter hovering and transfer;
[0092] Environmental risks include several secondary indicators: distance from dynamic risk sources and population density.
[0093] Furthermore, by using a comprehensive evaluation cost function for landing site adaptability, the subjective judgment of selecting the optimal landing site, which relies on experience, is transformed into an objective and reproducible scientific evaluation.
[0094] S4 obtains the current optimal exploration area based on the takeoff point and the optimal landing point, combined with the flight complexity cost function.
[0095] Furthermore, the current optimal exploration region is obtained, specifically including:
[0096] The flight complexity cost function is used to dynamically adjust the search direction of flight node expansion based on the relative position of the current flight segment and the target point and terrain features;
[0097] Based on the region between the takeoff point and the optimal landing point, and combined with the flight complexity cost function, the exploration direction of flight node expansion is dynamically adjusted to guide the exploration of the current optimal exploration area that is safe, flat, weather-stable, and points towards the optimal landing point. This significantly improves search efficiency and route feasibility under complex weather conditions and terrain.
[0098] Furthermore, in this embodiment, an 8-direction (2D) or 26-direction (3D) neighborhood is generated. Through adaptive direction adjustment, non-flying areas (no-fly zones, obstacles) are filtered out, and the expansion priority and search direction are adjusted according to the flight complexity cost function.
[0099] S5 selects candidate flight nodes based on the current optimal exploration area and the deep coupling cost function.
[0100] Furthermore, such as Figure 3 As shown, the method for obtaining candidate flight nodes is as follows:
[0101] All flight nodes to be tested are determined based on the current optimal exploration area;
[0102] Verification of the deep coupling cost function constraint between flight performance and terrain constraints based on the flight node under test;
[0103] The test flight nodes that pass the vertical gradient verification, ground clearance verification, horizontal safety verification, and maneuverability verification are selected as candidate flight nodes.
[0104] Furthermore, the passing criterion for vertical gradient verification is: the ratio of the height difference of the terrain to the horizontal distance of the terrain is less than or equal to the maximum rate of ascent.
[0105] The passing standard for ground clearance verification is: ground clearance greater than or equal to the minimum ground clearance;
[0106] The passing standard for horizontal safety verification is: the horizontal distance to the obstacle is greater than or equal to the safe distance;
[0107] The passing standard for mobility verification is: the turning radius is greater than or equal to the minimum turning radius.
[0108] S6 selects the optimal flight node for the current exploration area based on the candidate flight node selection.
[0109] Furthermore, the optimal flight node acquisition method is as follows:
[0110] The terrain undulation and slope change rate of the route path nodes are extracted based on the dynamic three-dimensional terrain model to construct the terrain complexity cost function.
[0111] A risk attenuation field is constructed based on the risk sources in dynamic monitoring to form a dynamic environmental risk cost function;
[0112] A real-time meteorological impact cost function is constructed based on real meteorological data, including headwind / crosswind costs, visibility and precipitation impacts, and lightning and severe convection avoidance.
[0113] Based on the candidate flight nodes, the candidate flight node with the lowest terrain complexity, lowest environmental risk, and lowest meteorological impact is selected as the optimal flight node through the terrain complexity cost function, dynamic environmental risk cost function, and real-time meteorological impact cost function.
[0114] Furthermore, the terrain complexity cost function guides aircraft to prioritize airspace with gentle terrain and small gradient changes, thereby effectively reducing flight vibration and energy consumption, and improving flight stability and efficiency.
[0115] Furthermore, the risk distance decreases in the dynamic environmental risk cost function, and the downwind area is given additional weight to ensure that the route stays away from dangerous areas.
[0116] Furthermore, real-time meteorological data includes: wind speed, wind direction, visibility, precipitation, lightning, etc.
[0117] The cost of headwind / crosswind is: dynamically adjusting energy consumption and time cost based on the wind speed and heading angle;
[0118] The impact of visibility and precipitation is as follows: low visibility or areas with heavy precipitation increase navigation uncertainty.
[0119] Lightning and severe convective weather avoidance measures include: marking high-risk areas on weather radar and imposing high penalties or prohibiting flights.
[0120] Furthermore, the landing site adaptability comprehensive evaluation cost function, the flight complexity cost function, the deep coupling cost function of flight performance and terrain constraints, the terrain complexity cost function, the dynamic environmental risk cost function, and the real-time weather impact cost function together constitute the composite cost function.
[0121] S7 obtains the current optimal route based on the takeoff point, optimal flight node, and optimal landing point.
[0122] Furthermore, if the current optimal flight node meets the termination conditions (reaching the destination / mission change / major environmental change triggering replanning), then the current optimal route is output; otherwise, continue.
[0123] Furthermore, the optimal flight path is generated by connecting the takeoff point with the optimal flight node one by one until it is connected with the optimal landing point.
[0124] S8 flies based on the current optimal route and dynamically updates subsequent routes in case of anomalies.
[0125] Furthermore, such as Figure 4 As shown, subsequent routes are dynamically updated, specifically including:
[0126] Fly based on the current optimal route and acquire real-time environmental data during the flight;
[0127] Based on the comparison between real-time environmental data and dynamic 3D terrain model, when a new obstacle is detected or the deviation from the preset flight path exceeds the safety threshold, an early warning is triggered and a local replanning is initiated.
[0128] During local replanning, the process of obtaining the current optimal route is repeated with the current position as the new starting point, the flight route after the new starting point is updated, and the updated new route is generated.
[0129] After the pilot confirms or the system confirms automatically, the flight will proceed according to the new route.
[0130] Furthermore, when flying along the current optimal flight path, if forward-looking radar detects new areas above the planned route that are at risk of tall building collapses, rockfalls, or mudslides, it immediately triggers local replanning, generating a safe new path to bypass the risk area and alerting the pilot. Simultaneously, if ground sensors report new ground fissures near the original landing point, the framework can quickly reassess the landing point and plan a new flight path to an alternative location.
[0131] Furthermore, this invention ultimately involves real-time data dynamic updates, modeling, global flight path dynamic planning and adjustment, and landing point optimization and selection. This method supports various complex post-disaster scenarios such as mountains, canyons, and urban ruins, forming a complete solution for helicopter ground approach and dynamic flight path planning analysis, significantly improving the response speed from disaster analysis to rescue deployment and the safety of the entire flight operation.
[0132] Example 2
[0133] like Figure 5 As shown, based on the same inventive concept, this embodiment of the invention also provides a helicopter dynamic route planning system based on a composite cost function, including: a terrain model generation module, a landing point screening module, an exploration area determination module, a candidate node determination module, an optimal route generation module, and a route dynamic update module;
[0134] The terrain model generation module is used to acquire multi-source data of the target area and fuse them to generate a dynamic three-dimensional terrain model;
[0135] The landing point selection module is used to set the takeoff point and multiple potential landing points based on the target area; it evaluates all landing points based on the landing point suitability comprehensive evaluation cost function to obtain the optimal landing point;
[0136] The exploration area determination module is used to determine the current optimal exploration area based on the takeoff point and the optimal landing point, combined with the flight complexity cost function;
[0137] The candidate node determination module is used to filter and obtain candidate flight nodes based on the current optimal exploration area and the deep coupling cost function;
[0138] The optimal route generation module is used to obtain the optimal flight node in the current exploration area based on the candidate flight node selection; and to obtain the current optimal route based on the take-off point, the optimal flight node, and the optimal landing point.
[0139] The route dynamic update module is used to fly based on the current optimal route and dynamically update subsequent routes in case of anomalies.
[0140] Furthermore, in this embodiment, the functional implementation methods of each functional module correspond one-to-one with the methods described above, and will not be repeated here.
[0141] Example 3
[0142] Based on the same inventive concept, the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory stores instructions, characterized in that the instructions are loaded and executed by the processor to implement a helicopter dynamic route planning method based on a composite cost function as in Embodiment 1.
[0143] Based on the same inventive concept, the present invention also provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;
[0144] Memory, used to store computer programs;
[0145] When the processor executes the program stored in the memory, it can implement a helicopter dynamic route planning method based on a composite cost function, as shown in Example 1.
[0146] The electronic device may include a processor, a communications interface, a memory, and a communication bus, wherein the processor, communications interface, and memory communicate with each other via the communication bus. The processor can call logical instructions in the memory to execute a helicopter dynamic flight path planning method based on a composite cost function as described in Embodiment 1.
[0147] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and 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 of 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.
[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.
[0149] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A helicopter dynamic flight path planning method based on a composite cost function, characterized in that, include: Acquire multi-source data of the target area and fuse them to generate a dynamic 3D terrain model; Based on the target area, a takeoff point and multiple potential landing points are established; All landing points are evaluated based on a comprehensive evaluation cost function for landing point adaptability to obtain the optimal landing point. Based on the takeoff point and the optimal landing point, and combined with the flight complexity cost function, the current optimal exploration area is obtained; Based on the current optimal exploration area and the deep coupling cost function, candidate flight nodes are selected. The optimal flight node for the current exploration area is obtained based on the candidate flight nodes; The current optimal flight path is obtained based on the takeoff point, the optimal flight node, and the optimal landing point; The flight is based on the current optimal route, and subsequent routes are dynamically updated in case of anomalies.
2. The helicopter dynamic route planning method based on a composite cost function as described in claim 1, characterized in that, Generate dynamic 3D terrain models, specifically including: The target area's basic GIS data, post-disaster remote sensing images, geological early warning data, real-time meteorological data, on-site sensor data, and UAV aerial images are acquired and used together as the multi-source data. Based on the multi-source data, a fusion operation of unified coordinate system, complementary filtering and 3D reconstruction, dynamic layer labeling and updating is performed to generate the dynamic 3D terrain model containing basic terrain, static obstacles and dynamic risk sources.
3. The helicopter dynamic route planning method based on a composite cost function as described in claim 2, characterized in that, Obtaining the optimal landing point specifically includes: The comprehensive evaluation cost function for landing site adaptability includes four primary indicators: terrain physical characteristics, airspace conditions, rescue convenience, and environmental risk. Each of the primary indicators includes multiple secondary indicators; Based on the analytic hierarchy process, weights are assigned to each of the secondary indicators to obtain the corresponding indicator weights; Based on all the landing points, the corresponding indicator scores are obtained by quantifying all the secondary indicators. The comprehensive suitability score for each landing point is obtained by weighted summation of all the indicator weights and the corresponding indicator scores. The landing point corresponding to the highest comprehensive suitability score is selected as the optimal landing point.
4. The helicopter dynamic route planning method based on a composite cost function as described in claim 3, characterized in that, The terrain physical characteristics include several secondary indicators: ground slope, ground roughness, and ground bearing capacity; The airspace conditions include several secondary indicators: assessment of the impact of approach / departure track obstacles and surrounding turbulence; The rescue convenience includes several secondary indicators: the accessibility and cost between the landing point and multiple rescue points, and the convenience of helicopter hovering and transfer; The environmental risks include several secondary indicators: distance from dynamic risk sources and population density.
5. The helicopter dynamic route planning method based on a composite cost function as described in claim 4, characterized in that, The current optimal exploration region is obtained, specifically including: The flight complexity cost function is used to dynamically adjust the search direction of flight node expansion based on the relative position of the current flight segment and the target point and terrain features; Based on the region between the takeoff point and the optimal landing point, the exploration direction of the flight node expansion is dynamically adjusted in conjunction with the flight complexity cost function, guiding the exploration of the current optimal exploration region that is safe, gentle, weather-stable, and points towards the optimal landing point.
6. The helicopter dynamic route planning method based on a composite cost function as described in claim 5, characterized in that, The method for obtaining the candidate flight node is as follows: All flight nodes to be tested are determined based on the current optimal exploration area; Based on the flight node under test, the deep coupling cost function constraint verification of flight performance and terrain constraints is performed; The test flight node that simultaneously passes the vertical gradient verification, ground clearance verification, horizontal safety verification, and maneuverability verification is selected as the candidate flight node.
7. The helicopter dynamic route planning method based on a composite cost function as described in claim 6, characterized in that, The passing standard for the vertical gradient verification is: the ratio of the height difference of the regional terrain to the horizontal distance of the regional terrain is less than or equal to the maximum rate of ascent. The passing standard for the near-ground clearance verification is: ground clearance greater than or equal to the minimum ground clearance; The passing standard for the horizontal safety check is: the horizontal distance to the obstacle is greater than or equal to the safety distance; The passing standard for the mobility test is: the turning radius is greater than or equal to the minimum turning radius.
8. The helicopter dynamic route planning method based on a composite cost function as described in claim 6, characterized in that, The optimal flight node is obtained as follows: Based on the dynamic three-dimensional terrain model, the terrain undulation and slope change rate of the route path nodes are extracted to construct a terrain complexity cost function; A risk attenuation field is constructed based on the risk sources in dynamic monitoring to form a dynamic environmental risk cost function; A real-time meteorological impact cost function is constructed based on real meteorological data, including headwind / crosswind costs, visibility and precipitation impacts, and lightning and severe convection avoidance. Based on the candidate flight nodes, the candidate flight node with the lowest terrain complexity, lowest environmental risk, and lowest meteorological impact is selected as the optimal flight node through the terrain complexity cost function, the dynamic environmental risk cost function, and the real-time meteorological impact cost function.
9. The helicopter dynamic route planning method based on a composite cost function as described in claim 8, characterized in that, Dynamically update subsequent routes, specifically including: Fly based on the current optimal route and acquire real-time environmental data during the flight; Based on the comparison between the real-time environmental data and the dynamic three-dimensional terrain model, when a new obstacle is detected or the deviation from the preset flight path exceeds the safety threshold, an early warning is triggered and a local replanning is initiated. During the local replanning, the process of obtaining the current optimal route is repeated with the current position as the new starting point, the flight route after the new starting point is updated, and the updated new route is generated.
10. A helicopter dynamic flight path planning system based on a composite cost function, used to execute a helicopter dynamic flight path planning method based on a composite cost function as described in any one of claims 1-9, characterized in that, include: The system includes a terrain model generation module, a landing point selection module, an exploration area determination module, a candidate node determination module, an optimal route generation module, and a route dynamic update module. The terrain model generation module is used to acquire multi-source data of the target area and fuse them to generate a dynamic three-dimensional terrain model; The landing point screening module is used to set the takeoff point and multiple potential landing points based on the target area; All landing points are evaluated based on a comprehensive evaluation cost function for landing point adaptability to obtain the optimal landing point. The exploration area determination module is used to obtain the current optimal exploration area based on the takeoff point and the optimal landing point, combined with the flight complexity cost function; The candidate node determination module is used to filter and obtain candidate flight nodes based on the current optimal exploration area and the deep coupling cost function; The optimal route generation module is used to obtain the optimal flight node in the current exploration area based on the candidate flight nodes; and to obtain the current optimal route based on the takeoff point, the optimal flight node, and the optimal landing point. The route dynamic update module is used to fly based on the current optimal route and dynamically update subsequent routes in case of anomalies.