Unmanned aerial vehicle path dynamic optimization method and device based on load distribution and medium
By constructing payload distribution data and evaluating the three-axis center of gravity position, combined with a path reconstruction mechanism and a joint optimization objective function, the problem of flight instability caused by uneven payload in UAV path planning was solved, dynamic path optimization was achieved, and flight safety and robustness were improved.
Patent Information
- Application Number
- CN202511489750.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-17
- Publication Date
- 2026-02-10
AI Technical Summary
Existing UAV path planning methods have failed to effectively address issues such as flight oscillations, heading deviations, and control failures caused by uneven payload distribution. In particular, when delivering to multiple points or mixing different types of cargo, they are unable to adapt to changes in flight status in real time, affecting flight safety and path reliability.
By collecting cargo information to construct load distribution data, calculating the three-axis center of gravity position and evaluating flight stability, introducing a path reconstruction triggering mechanism, dynamically adjusting the flight path based on the joint path optimization objective function and heuristic strategy, and integrating energy consumption and stability indicators to achieve dynamic path optimization.
It enables dynamic path planning for UAVs under varying load conditions, improving flight safety and system robustness, and ensuring path stability and efficiency.
Smart Images
Figure CN121500748A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of intelligent logistics and unmanned aerial vehicle flight control technology, and particularly relates to a method, device and medium for dynamically optimizing a path of an unmanned aerial vehicle based on load distribution. BACKGROUND
[0002] With the development of low-altitude intelligent logistics, unmanned aerial vehicles are widely used in city distribution, emergency delivery, mountain transportation and other scenarios. In actual cargo-carrying flight, the task path planning of the unmanned aerial vehicle is not only affected by the geographical environment and airspace control, but also closely related to the weight, volume and distribution of the goods in the cargo compartment. Different ways of loading goods will cause the center of gravity position of the unmanned aerial vehicle to change during flight, thereby affecting its attitude control, energy consumption level and flight stability. Therefore, the path planning of the unmanned aerial vehicle under the condition of load is an important link to ensure flight stability.
[0003] Most of the existing path planning methods of unmanned aerial vehicles are to generate the shortest path or the most energy-saving path by using heuristic search, graph optimization or deep learning algorithms based on static maps and aircraft dynamics models. However, this method is implemented under the assumption that the load mass is uniformly distributed during flight, and does not model dynamic load changes. Therefore, in the case of asymmetric loading of goods or mid-way delivery, problems such as flight oscillation, heading deviation and even control failure often occur, which seriously affects flight safety and path reliability. Moreover, in the application of multi-point delivery or mixed loading of different goods, the distribution of goods in space may be highly uneven, causing the center of gravity of the unmanned aerial vehicle to change continuously during flight. If the path planning is still set according to fixed parameters, it will be difficult to adapt to changes in flight state in real time, limiting the realization of efficient, safe and fine scheduling. SUMMARY
[0004] To solve the above technical problems, one or more embodiments of the present application provide a method, device and medium for dynamically optimizing a path of an unmanned aerial vehicle based on load distribution.
[0005] One or more embodiments of the present application adopt the following technical solutions: One or more embodiments of the present application provide a method for dynamically optimizing a path of an unmanned aerial vehicle based on load distribution, the method comprising: collecting information of goods corresponding to a current task of a to-be-optimized unmanned aerial vehicle, to construct load distribution data of the to-be-optimized unmanned aerial vehicle based on the information of the goods; calculating a three-axis center of gravity position of the to-be-optimized unmanned aerial vehicle according to the load distribution data, to construct a flight stability evaluation index of the to-be-optimized unmanned aerial vehicle through the center of gravity position; wherein the flight stability evaluation index is used to quantitatively evaluate the stability of the unmanned aerial vehicle during flight through a stability parameter; Based on the flight stability assessment indicators, determine whether path reconstruction of the UAV to be optimized is triggered; If so, the optimal flight path of the UAV to be optimized is determined based on a pre-set joint path optimization objective function and a heuristic strategy; wherein, the pre-set joint path optimization objective function is constructed based on the mission requirement information and flight environment information of the UAV to be optimized, and the heuristic strategy is used to adjust the flight path of the UAV to be optimized to obtain the optimal flight path.
[0006] Optionally, in one or more embodiments of this application, before determining the optimal flight path of the UAV to be optimized based on a preset joint path optimization objective function and a heuristic strategy, the method further includes: Obtain the coordinate positions of each existing path point in the existing path planning of the UAV to be optimized; wherein each existing coordinate point corresponds to a time step of equal length; Based on the coordinate positions corresponding to each existing path point and the number of time steps corresponding to each existing coordinate point, the estimated energy consumption and flight time corresponding to the existing path planning are obtained. The estimated energy consumption, the flight time, and the flight stability evaluation index are fused together to obtain the preset joint path optimization objective function corresponding to the UAV to be optimized. Based on the coordinates of each existing path point, the starting position of the UAV to be optimized is determined. Based on the starting position and the time steps corresponding to each of the existing coordinate points, the constraints of the preset joint path optimization objective function are determined; wherein, the constraints include: start and end point constraints, maximum speed limit, and maximum acceleration limit.
[0007] Optionally, in one or more embodiments of this application, the step of fusing the estimated energy consumption, the flight time, and the flight stability evaluation index to obtain the preset joint path optimization objective function corresponding to the UAV to be optimized specifically includes: Based on a pre-set weight adjustment coefficient, the estimated energy consumption and flight time corresponding to the existing path planning are fused with the flight stability evaluation index to construct a pre-set joint path optimization objective function for the UAV to be optimized: ; in, , This is an energy consumption conversion factor used to square the displacement of adjacent path points. Converted to the corresponding energy consumption, To estimate energy consumption, For the first point in the existing path The coordinates of the path points. is the coordinate position of the first path point in the existing path points is the coordinate position of the path point of the step path, is the total flight time, is the total number of time steps, is the time step length; is the preset weight adjustment coefficient.
[0008] Optionally, in one or more embodiments of the present application, the optimal flight path of the to-be-optimized unmanned aerial vehicle is determined based on a preset joint path optimization objective function and a heuristic strategy, specifically comprising: based on the position coordinates of the current path point of the to-be-optimized unmanned aerial vehicle, the existing path planning is divided to obtain a head path and a tail path, and the position coordinates of the current path point are taken as an update starting point of path reconstruction; based on the heuristic strategy, the path points between the update starting point and the end point are searched to obtain an initial path sequence; on the basis of the initial path sequence, a flight state space vector of the to-be-optimized unmanned aerial vehicle is constructed, so as to fine-tune the coordinate positions of the path points in the initial path sequence in combination with the preset action space of the to-be-optimized unmanned aerial vehicle and the flight state vector, and obtain a to-be-optimized path sequence; based on the flight stability evaluation indexes corresponding to each path point in the to-be-optimized path sequence, a disturbance sensitive sub-path segment is constructed; the disturbance sensitive sub-path segment is reconstructed to obtain the optimal flight path of the to-be-optimized unmanned aerial vehicle.
[0009] Optionally, in one or more embodiments of the present application, the disturbance sensitive sub-path segment is reconstructed to obtain the optimal flight path of the to-be-optimized unmanned aerial vehicle, specifically comprising: a plurality of local disturbance candidate paths of the disturbance sensitive sub-path segment are obtained to determine the generation value corresponding to each local disturbance candidate path based on a preset joint path optimization objective function; based on the generation value corresponding to each local disturbance candidate path, it is determined that the disturbance sensitive sub-path segment with the minimum generation cost is a target path; if it is determined that the flight stability evaluation indexes corresponding to each path point in the target path are less than a preset index threshold, the target path is retained to replace the tail path to obtain the optimal flight path of the to-be-optimized unmanned aerial vehicle.
[0010] Optionally, in one or more embodiments of the present application, the three-axis barycenter position of the to-be-optimized unmanned aerial vehicle is calculated according to the load distribution data, and the flight stability evaluation index of the to-be-optimized unmanned aerial vehicle is constructed through the barycenter position, specifically comprising: The load distribution data is processed according to a preset mass-weighted averaging strategy to obtain the three-axis center of gravity position of the UAV to be optimized. Based on the difference between the preset static design center of gravity position of the UAV to be optimized and the three-axis center of gravity position, the center of gravity offset of the UAV to be optimized is determined. The flight stability evaluation index of the UAV to be optimized is constructed by using the center of gravity offset and a preset allowable offset threshold; wherein, the flight stability evaluation index is: , To preset the allowed offset threshold, This is a stability penalty coefficient. This represents the offset of the center of gravity.
[0011] Optionally, in one or more embodiments of this application, determining whether to trigger path reconstruction of the UAV to be optimized based on the flight stability evaluation index specifically includes: Based on the maximum center of gravity offset of the UAV to be optimized, the threshold value corresponding to the flight stability evaluation index is determined; wherein, the threshold value is: , This represents the maximum center of gravity offset. If the flight stability assessment index is determined to be less than or equal to the index threshold, then path reconstruction of the UAV to be optimized will not be triggered. If the flight stability assessment index is determined to be greater than the index threshold, then path reconstruction of the UAV to be optimized is triggered.
[0012] Optionally, in one or more embodiments of this application, cargo information corresponding to the current task of the UAV to be optimized is collected to construct payload distribution data of the UAV to be optimized based on the cargo information, specifically including: The UAV collects and optimizes cargo information corresponding to its current mission based on a pre-set payload sensing device; wherein, the cargo information includes: cargo weight, cargo dimensions, and cargo three-dimensional position coordinates; The cargo information is sorted based on matrix columns to construct the payload distribution data of the UAV to be optimized; wherein each matrix column corresponds to cargo information of the same type.
[0013] One or more embodiments of this application provide a device for dynamic path optimization of unmanned aerial vehicles (UAVs) based on load distribution. The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described above.
[0014] One or more embodiments of this application provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute any of the methods described above.
[0015] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: By collecting cargo information corresponding to the current task to construct payload distribution data, subsequent path optimization can perceive the payload status and dynamically adjust the flight path. This facilitates accurate characterization of the local disturbance effect of payload center of gravity shift on the flight path, enabling dynamic path planning for the UAV. Quantifying the center of gravity position to construct flight stability assessment indicators objectively reflects the stability of the UAV during flight, providing a scientific basis for determining whether path reconfiguration is necessary. A path reconfiguration trigger mechanism is introduced to determine whether path adjustment is needed in real time based on the flight stability assessment indicators, and obtains the optimal flight path based on a pre-set joint path optimization objective function and a heuristic strategy. This integrates the time and energy cost functions in traditional path planning with flight stability indicators to form a multi-objective path optimization model. This model captures the global impact of payload state evolution on the entire flight process, dynamically selecting more stable and lower-risk new routes, thereby improving flight safety and system robustness. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this application 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 A flowchart illustrating a method for dynamic path optimization of unmanned aerial vehicles based on load distribution, provided in an embodiment of this application; Figure 2 A schematic diagram of a UAV path dynamic optimization device based on load distribution is provided for an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a non-volatile storage medium provided in an embodiment of this application. Detailed Implementation
[0017] This application provides a method, device, and medium for dynamic optimization of UAV paths based on load distribution.
[0018] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.
[0019] like Figure 1 As shown, this application provides a flowchart illustrating a method for dynamic path optimization of unmanned aerial vehicles (UAVs) based on payload distribution. Figure 1 As can be seen, in one or more embodiments of this application, a method for dynamic optimization of UAV path based on load distribution specifically includes the following steps: S101: Collect cargo information corresponding to the current task of the UAV to be optimized, and construct the payload distribution data of the UAV to be optimized based on the cargo information.
[0020] Because existing payload drone path planning largely assumes a uniform payload mass distribution during flight and fails to model dynamic payload changes, problems such as flight oscillations, heading deviations, and even control failures often occur in situations with asymmetrical cargo loading or mid-flight deliveries, severely impacting flight safety and path reliability. Particularly in multi-point deliveries or mixed cargo loading applications, the cargo distribution in space may be uneven, causing continuous shifts in the drone's center of gravity during flight. If path planning is still set with fixed parameters, it will be difficult to adapt to changes in flight status in real time, limiting the realization of efficient, safe, and precise scheduling. Therefore, in order to incorporate the spatial distribution information of the cargo payload into the path optimization process, enabling subsequent path optimization to perceive the payload status and dynamically adjust the flight path, this embodiment collects cargo information corresponding to the current task of the drone to be optimized in real time. Based on this cargo information, payload distribution data of the drone to be optimized is constructed, facilitating accurate characterization of the local disturbance effect of payload center of gravity shift on the flight path and achieving dynamic path planning for the drone.
[0021] Specifically, in one or more embodiments of this application, cargo information corresponding to the current task of the UAV to be optimized is collected, and payload distribution data of the UAV to be optimized is constructed based on the cargo information. The specific process includes the following: The payload information corresponding to the current task of the UAV is collected and optimized based on a pre-set payload sensing device. This payload information includes payload weight, dimensions, and three-dimensional position coordinates. Then, the payload information is sorted according to matrix columns to construct the payload distribution data for the UAV to be optimized; each matrix column corresponds to the same type of payload information. That is, assuming the UAV's cargo compartment is equipped with... A standard cargo unit, at any flight time The system collects the mass and spatial location of each cargo within the cargo hold using a load sensing system, and constructs a load distribution matrix in matrix form. : ; Each row corresponds to the load information of a cargo, with the first column being the mass. The remaining three columns represent three-dimensional spatial coordinates. This matrix serves as the core input for subsequent flight center of gravity calculations and path stability analysis.
[0022] S102: Calculate the three-axis center of gravity position of the UAV to be optimized based on the load distribution data, so as to construct the flight stability evaluation index of the UAV to be optimized through the center of gravity position; wherein, the flight evaluation stability index is used to quantitatively evaluate the stability of the UAV during flight through stability parameters.
[0023] To facilitate the calculation of the aircraft's current center of gravity position and to evaluate path feasibility using a stability penalty function to obtain flight stability assessment indicators, thereby accurately characterizing the local disturbance effect of load center of gravity offset on the flight path, this embodiment calculates the three-axis center of gravity position of the UAV to be optimized based on load distribution data. This center of gravity position is then used to construct the flight stability assessment indicators for the UAV to be optimized. The three-axis center of gravity position refers to the coordinates of the object's center of gravity relative to the three coordinate axes in three-dimensional space, and is typically used to describe the balance state of the UAV in space.
[0024] Specifically, in one or more embodiments of this application, the three-axis center of gravity position of the UAV to be optimized is calculated based on the load distribution data, thereby constructing a flight stability evaluation index for the UAV to be optimized based on the center of gravity position. The specific process includes the following steps: First, the payload distribution data is processed according to a pre-set mass-weighted averaging strategy to obtain the three-axis center of gravity positions of the UAV to be optimized. ;Right now: ;in, This refers to the number of payload items, i.e., the total number of goods carried by the drone at the current moment. For the first The goods at the time The quality; , , , for the first The goods at the time The three-dimensional spatial coordinates of the UAV correspond to the X, Y, and Z directions in the UAV's body coordinate system, respectively. For a moment The total mass of the goods; , , For a moment The overall load's three-dimensional centroid coordinates.
[0025] Then, based on the preset static design center of gravity position of the drone to be optimized... The difference between the center of gravity position and the position of the three-axis center of gravity is used to determine the center of gravity offset of the UAV to be optimized. By using the center of gravity offset and a preset allowable offset threshold, a flight stability evaluation index for the UAV to be optimized is constructed; the flight stability evaluation index is as follows: , To preset the allowed offset threshold, This is a stability penalty coefficient. This represents the offset of the center of gravity.
[0026] This process employs a pre-set mass-weighted averaging strategy to process load distribution data, objectively reflecting the weight proportion of different loads in the overall UAV structure, thereby accurately calculating the three-axis center of gravity position. This physically-based calculation method ensures the accuracy of the center of gravity position results, providing reliable basic data for subsequent stability assessments. When the center of gravity offset exceeds a pre-set allowable offset threshold... At that time, the flight stability assessment index was evaluated using a stability penalty coefficient. This transforms the degree of offset into a quantifiable risk value. This allows stability assessments to move beyond qualitative judgments and enable quantitative analysis based on specific offset amounts, providing clear numerical data for subsequent path optimization and disturbance handling.
[0027] S103: Based on the flight stability evaluation index, determine whether to trigger the path reconstruction of the UAV to be optimized.
[0028] After obtaining the flight stability evaluation indicators of the UAV to be optimized based on the above steps, it can be determined whether the UAV to be optimized needs path reconstruction at a certain moment. In other words, during flight, it can be determined through a fixed period. Detection load distribution With center of gravity The flight stability assessment index is determined, and based on the flight stability assessment index, it is determined whether the path reconstruction of the UAV to be optimized is triggered.
[0029] Specifically, in one or more embodiments of this application, determining whether to trigger path reconstruction of the UAV to be optimized based on flight stability evaluation indicators includes the following process: First, based on the maximum center of gravity offset of the UAV to be optimized, the threshold values corresponding to the flight stability evaluation indicators are determined; where the threshold values are: , This represents the maximum center of gravity offset. If the flight stability assessment index is less than or equal to the index threshold, it indicates that the current flight of the UAV to be optimized is relatively stable, so path reconstruction for the UAV to be optimized is not triggered. However, if the flight stability assessment index is greater than the index threshold, then path reconstruction for the UAV to be optimized is triggered. In other words, during the flight of the UAV to be optimized, path reconstruction is performed at fixed intervals. Detection load distribution With center of gravity If at some point the following condition is met: The system then triggers a path reconfiguration mechanism. During this process, by monitoring changes in the payload center of gravity in real time, when the offset exceeds a stability threshold, the system triggers a path update strategy, dynamically selecting a more stable and lower-risk new route, which can improve flight safety and system robustness.
[0030] S104: If so, the optimal flight path of the UAV to be optimized is determined based on the preset joint path optimization objective function and heuristic strategy; wherein, the preset joint path optimization objective function is constructed based on the mission requirement information and flight environment information of the UAV to be optimized.
[0031] If, based on step S103 above, the flight stability assessment index is determined to be greater than the index threshold, then path reconstruction of the UAV to be optimized will be triggered. At this time, the optimal flight path of the UAV to be optimized needs to be determined according to the pre-set joint path optimization objective function and heuristic strategy. It should be noted that the pre-set joint path optimization objective function is constructed based on the mission requirement information and flight environment information of the UAV to be optimized.
[0032] Furthermore, in one or more embodiments of this application, before determining the optimal flight path of the UAV to be optimized based on a preset joint path optimization objective function and a heuristic strategy, the method further includes the following process: First, obtain the coordinates of each existing path point in the existing path plan of the UAV to be optimized; each existing coordinate point corresponds to a time step of equal length. Then, based on the coordinates of each existing path point and the number of time steps corresponding to each existing coordinate point, obtain the estimated energy consumption and flight time corresponding to the existing path plan. Next, fuse the estimated energy consumption and flight time with the flight stability evaluation index to obtain the pre-set joint path optimization objective function for the UAV to be optimized. In a feasible embodiment, fusing the estimated energy consumption, flight time, and flight stability evaluation index to obtain the pre-set joint path optimization objective function for the UAV to be optimized specifically includes the following process: First, based on the pre-set weight adjustment coefficients, the estimated energy consumption and flight time corresponding to the existing path planning are integrated with the flight stability evaluation index to construct the pre-set joint path optimization objective function for the UAV to be optimized: ; in, , This is an energy consumption conversion factor used to square the displacement of adjacent path points. Converted to the corresponding energy consumption, To estimate energy consumption, For the first point in the existing path The coordinates of the path points. For the first point in the existing path The coordinates of the path points. Total flight time The total number of time steps. The time step length; The pre-set weight adjustment coefficients are used. This process integrates the time and energy cost functions in traditional path planning with flight stability indicators to form a multi-objective path optimization model, which helps to capture the global impact of payload state evolution on the entire flight process.
[0033] Then, to ensure the path optimization results conform to the aircraft's physical characteristics and safety requirements, the following constraints are introduced based on the objective function. First, the starting position of the UAV to be optimized is determined based on the coordinates of each existing path point. Then, the constraints of the pre-set joint path optimization objective function are determined based on the starting position and the time steps corresponding to each existing coordinate point. These constraints include: start and end point constraints, maximum speed limit, and maximum acceleration limit. Specifically, the start and end point constraints are as follows: , The maximum speed limit is: ;in The maximum linear velocity of the aircraft; the maximum acceleration limit is: ,in This indicates the maximum allowable acceleration of the aircraft, used to suppress violent maneuvers and maintain a stable flight attitude; This indicates the starting position of the drone, which is the starting point for path optimization; This represents the target location of the UAV, i.e., the endpoint of the path optimization; the optimized path must satisfy the condition that the first point equals the starting point. The final point equals the final point. This is to ensure that the drone departs from the predetermined location and accurately arrives at the target location.
[0034] Specifically, in one or more embodiments of this application, the optimal flight path of the UAV to be optimized is determined based on a preset joint path optimization objective function and a heuristic strategy, including: Based on the coordinates of the current path points of the drone to be optimized, the existing path planning is divided into a head path and a tail path. The coordinates of the current path points are then used as the starting point for path reconstruction. For example: the current path Based on the position coordinates of the current path point at the moment the drone triggers path reconstruction, the current path can be divided into two segments: the head. Tail It will be replaced, thus at the current position Recalculate the new tail path as a new starting point. .
[0035] When recalculating the new tail path, a heuristic strategy is used to search for path points between the starting and ending points to obtain an initial path sequence. For example, a genetic algorithm can be used to search for the shortest path from the starting point to the ending point to generate the initial path sequence. Then, based on the initial path sequence, the flight state space vector of the UAV to be optimized is constructed. ,in, Current position; The current focus; This is due to a shift in the center of gravity. The Euclidean distance between the current position and the destination is used to fine-tune the coordinates of path points in the initial path sequence based on the flight state vector and the preset action space of the UAV to be optimized, thus obtaining the path sequence to be optimized. This preset action space consists of 9 local directions, including 8 unit direction actions and 1 hovering action, used by the reinforcement learning policy network to output path adjustment commands, i.e., using the policy network... Output adjustment action Fine-tuning is performed on nodes in the path with a high risk of offset, generating a reinforcement learning-optimized path. This serves as the path sequence to be optimized. Then, based on the flight stability evaluation indices corresponding to each path point in the path sequence, disturbance-sensitive sub-path segments are constructed. That is, the path sequence to be optimized... Based on this, identify the path points that satisfy... The moment Construct disturbance-sensitive sub-path segments This allows for the reconstruction of disturbance-sensitive sub-path segments, yielding the optimal flight path for the UAV to be optimized.
[0036] This process divides the original path into a head and a tail based on the current path point position. The tail path is then replanned using the current position as the new starting point. This preserves already executed valid path segments and allows for rapid response to dynamic changes, preventing the entire path from failing due to local issues and significantly improving the flexibility and efficiency of path adjustment. Furthermore, using heuristic strategies such as genetic algorithms to search for the initial path sequence quickly finds a relatively optimal path from the start point to the destination in complex environments, providing a reasonable initial solution for subsequent optimization, reducing the waste of computational resources caused by blind searches, and ensuring the basic feasibility of the path. In addition, the flight state space vector integrates key information such as position, center of gravity, center of gravity offset, and distance to the destination, comprehensively reflecting the core states of the UAV during flight. This multi-dimensional state description allows the reinforcement learning strategy to more accurately perceive the flight environment and its own state, providing sufficient basis for path fine-tuning. Through the design of the action space in nine local directions, combined with the policy network, fine-tuning of position nodes with high offset risks allows for targeted optimization of key nodes with stability risks in the path, improving the stability and safety of the path while maintaining its overall structure. Based on flight stability assessment indicators, sensitive sub-path segments to disturbances are identified, and multiple candidate paths are generated for cost evaluation and replacement. This allows for focusing on the key parts of the path most susceptible to disturbances, achieving precise optimization of local paths, and further improving the overall path's anti-interference capability and stability.
[0037] Specifically, in one or more embodiments of this application, the disturbance-sensitive sub-path segments are reconstructed to obtain the optimal flight path of the UAV to be optimized, specifically including: Multiple local perturbation candidate paths are obtained for the perturbation-sensitive sub-path segments. The cost value corresponding to each local perturbation candidate path is determined based on a pre-defined joint path optimization objective function. If, based on the cost values corresponding to each local perturbation candidate path, the perturbation-sensitive sub-path segment with the minimum cost is determined as the target path, then the target path... The following objective optimization problem must be satisfied: ; Then, if the flight stability evaluation index corresponding to each path point in the target path is determined to be less than the preset index threshold, the target path is retained to replace the tail path that needs to be replaced, thereby obtaining the optimal flight path of the UAV to be optimized.
[0038] This process generates multiple candidate paths for local disturbances and calculates their costs, enabling the exploration of optimal local path solutions from multiple perspectives. This avoids the optimization limitations caused by a single path selection, ensuring that the selected target path has a significant cost advantage. Furthermore, the target path must satisfy a pre-defined joint path optimization problem, guaranteeing that the path minimizes flight energy consumption and flight time while ensuring mission completion (i.e., reachability of the start and end points), and effectively avoids instability risks caused by payload center of gravity shifts, making the optimization results more closely aligned with actual flight requirements. After selecting the minimum-cost path, the flight stability evaluation indicators of each path point are further verified to ensure they are below pre-defined thresholds, forming a dual screening mechanism. This ensures that the final replaced path segment is not only economical and efficient but also meets the core requirements of flight safety. By replacing the parts of the tail path that need optimization, the reconstructed path can seamlessly connect with the head path, ensuring the continuity and integrity of the entire flight path and avoiding flight interruptions or connection problems that may arise from path adjustments.
[0039] Furthermore, it should be noted that the initial path planning for the drone to be optimized can also be implemented based on this process. First, the cargo information for the current mission is collected, including the mass, dimensions, and three-dimensional coordinates of each item within the cargo hold, constructing a payload distribution dataset. Then, based on the payload distribution data, the current center of gravity position of the aircraft is calculated, thereby constructing a flight stability assessment index. Next, according to mission requirements and the current flight environment, a joint path optimization objective function is constructed, comprehensively considering path energy consumption, flight time, and flight stability, and an optimal path is generated through a heuristic algorithm. During flight based on this optimal path, changes in cargo status and the aircraft's center of gravity position are continuously monitored. Once a center of gravity shift exceeds a set safety threshold, a dynamic path update module is immediately triggered to replan the flight path to ensure flight safety and energy efficiency. The final output is a flight trajectory that balances payload stability and path optimization, suitable for complex drone logistics applications with frequent load changes or multi-point delivery tasks.
[0040] like Figure 2 As shown in the diagram, this application provides a structural schematic of a drone path dynamic optimization device based on load distribution. Figure 2 As can be seen, in one or more embodiments of this application, a UAV path dynamic optimization device based on load distribution includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described above.
[0041] like Figure 3 As shown in the diagram, this application provides a structural schematic of a non-volatile storage medium, which consists of... Figure 3 It is understood that, in one or more embodiments of this application, a non-volatile storage medium stores computer-executable instructions 301, which are capable of executing any of the methods described above.
[0042] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0043] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0044] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0045] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0046] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, a network interface, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0047] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0049] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0050] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0051] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0052] The above description is merely one or more embodiments of this application and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to one or more embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this application should be included within the scope of this application.
Claims
1. A method for dynamic path optimization of unmanned aerial vehicles (UAVs) based on load distribution, characterized in that, The method includes: Collect cargo information corresponding to the current task of the UAV to be optimized, and construct the payload distribution data of the UAV to be optimized based on the cargo information; The three-axis center of gravity position of the UAV to be optimized is calculated based on the load distribution data, and a flight stability evaluation index of the UAV to be optimized is constructed based on the center of gravity position; wherein, the flight stability evaluation index is used to quantitatively evaluate the stability of the UAV during flight through stability parameters. Based on the flight stability assessment indicators, determine whether path reconstruction of the UAV to be optimized is triggered; If so, the optimal flight path of the UAV to be optimized is determined based on a pre-set joint path optimization objective function and a heuristic strategy; wherein, the pre-set joint path optimization objective function is constructed based on the mission requirement information and flight environment information of the UAV to be optimized, and the heuristic strategy is used to adjust the flight path of the UAV to be optimized to obtain the optimal flight path.
2. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 1, characterized in that, Before determining the optimal flight path of the UAV to be optimized based on a pre-set joint path optimization objective function and heuristic strategy, the method further includes: Obtain the coordinate positions of each existing path point in the existing path planning of the UAV to be optimized; wherein each existing coordinate point corresponds to a time step of equal length; Based on the coordinate positions corresponding to each existing path point and the number of time steps corresponding to each existing coordinate point, the estimated energy consumption and flight time corresponding to the existing path planning are obtained. The estimated energy consumption, the flight time, and the flight stability evaluation index are fused together to obtain the preset joint path optimization objective function corresponding to the UAV to be optimized. Based on the coordinates of each existing path point, the starting position of the UAV to be optimized is determined. Based on the starting position and the time steps corresponding to each of the existing coordinate points, the constraints of the preset joint path optimization objective function are determined; wherein, the constraints include: start and end point constraints, maximum speed limit, and maximum acceleration limit.
3. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 2, characterized in that, The step of fusing the estimated energy consumption, the flight time, and the flight stability evaluation index to obtain the pre-set joint path optimization objective function corresponding to the UAV to be optimized specifically includes: Based on a pre-set weight adjustment coefficient, the estimated energy consumption and flight time corresponding to the existing path planning are fused with the flight stability evaluation index to construct a pre-set joint path optimization objective function for the UAV to be optimized: ； in, , This is an energy consumption conversion factor used to square the displacement of adjacent path points. Converted to the corresponding energy consumption, To estimate energy consumption, For the first point in the existing path The coordinates of the path points. For the first point in the existing path The coordinates of the path points. Total flight time The total number of time steps. The time step length; This is the preset weight adjustment coefficient.
4. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 2, characterized in that, Based on a pre-defined joint path optimization objective function and heuristic strategy, the optimal flight path of the UAV to be optimized is determined, specifically including: Based on the position coordinates of the current path point of the UAV to be optimized, the existing path planning is divided to obtain the head path and the tail path, and the position coordinates of the current path point are used as the update starting point for path reconstruction. Based on the heuristic strategy, the path points between the update start point and the end point are searched to obtain the initial path sequence; Based on the initial path sequence, a flight state space vector of the UAV to be optimized is constructed. By combining the flight state vector with the preset action space of the UAV to be optimized, the coordinate positions of the path points in the initial path sequence are fine-tuned to obtain the path sequence to be optimized. Based on the flight stability evaluation index corresponding to each path point in the path sequence to be optimized, a disturbance-sensitive sub-path segment is constructed. The disturbance-sensitive sub-path segments are reconstructed to obtain the optimal flight path of the UAV to be optimized.
5. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 4, characterized in that, Reconstructing the disturbance-sensitive sub-path segments to obtain the optimal flight path of the UAV to be optimized specifically includes: Multiple local disturbance candidate paths are obtained for the disturbance-sensitive sub-path segment, and the cost value corresponding to each local disturbance candidate path is determined based on a preset joint path optimization objective function; Based on the cost value corresponding to each of the local disturbance candidate paths, the disturbance-sensitive sub-path segment with the minimum cost is determined as the target path; If the flight stability evaluation index corresponding to each path point in the target path is determined to be less than the preset index threshold, then the target path is retained to replace the tail path, thereby obtaining the optimal flight path of the UAV to be optimized.
6. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 1, characterized in that, The three-axis center of gravity position of the UAV to be optimized is calculated based on the load distribution data, and a flight stability evaluation index for the UAV to be optimized is constructed based on the center of gravity position, specifically including: The load distribution data is processed according to a preset mass-weighted averaging strategy to obtain the three-axis center of gravity position of the UAV to be optimized. Based on the difference between the preset static design center of gravity position of the UAV to be optimized and the three-axis center of gravity position, the center of gravity offset of the UAV to be optimized is determined. The flight stability evaluation index of the UAV to be optimized is constructed by using the center of gravity offset and a preset allowable offset threshold; wherein, the flight stability evaluation index is: , To preset the allowed offset threshold, This is a stability penalty coefficient. This represents the offset of the center of gravity.
7. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 6, characterized in that, Based on the flight stability assessment indicators, determine whether path reconstruction of the UAV to be optimized is triggered, specifically including: Based on the maximum center of gravity offset of the UAV to be optimized, the threshold value corresponding to the flight stability evaluation index is determined; wherein, the threshold value is: , This represents the maximum center of gravity offset. If the flight stability assessment index is determined to be less than or equal to the index threshold, then path reconstruction of the UAV to be optimized will not be triggered. If the flight stability assessment index is determined to be greater than the index threshold, then path reconstruction of the UAV to be optimized is triggered.
8. The method for dynamic path optimization of unmanned aerial vehicles based on load distribution according to claim 1, characterized in that, Collect cargo information corresponding to the current task of the UAV to be optimized, and construct payload distribution data of the UAV to be optimized based on the cargo information, specifically including: The UAV collects and optimizes cargo information corresponding to its current mission based on a pre-set payload sensing device; wherein, the cargo information includes: cargo weight, cargo dimensions, and cargo three-dimensional position coordinates; The cargo information is sorted based on matrix columns to construct the payload distribution data of the UAV to be optimized; wherein each matrix column corresponds to cargo information of the same type.
9. A device for dynamic path optimization of unmanned aerial vehicles based on load distribution, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1-8.
10. A non-volatile storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are capable of performing the method described in any one of claims 1-8.