Environment-adaptive unmanned aerial vehicle flight energy consumption optimization system

Abstract

The invention relates to an environment-adaptive unmanned aerial vehicle flight energy consumption optimization system. The system comprises a navigation assembly line and an environment self-adaptive navigation strategy module which are connected with each other, the navigation assembly line is used for dynamically generating an environment map and path planning information according to the environment information, and is also used for controlling the flight action of the unmanned aerial vehicle according to the path planning information; the environment adaptive navigation strategy module is used for determining a first flight allowable speed, first mapping frequency adjustment information and first mapping resolution adjustment information according to unmanned aerial vehicle control information and an environment map. Compared with the prior art, the method has the advantages that the effective dynamic management of the calculation load is realized, the environmental adaptability is high, the robustness and efficiency of the overall navigation are improved, and the safety and the efficiency of the unmanned aerial vehicle in a complex and dynamic change environment are optimized and balanced.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) flight planning technology, and in particular to an environment-adaptive UAV flight energy consumption optimization system. Background Technology

[0002] With the widespread application of drones in logistics, surveillance, search and rescue, and other fields, their limited onboard energy has become a significant bottleneck restricting their performance and applicability. Therefore, optimizing drone navigation strategies to reduce energy consumption has become a key research focus. Drone navigation strategies typically encompass multiple interconnected tasks, including perception, planning, and control. Adjusting flight speed and path planning strategies can shorten mission execution time, thereby reducing energy consumption. Furthermore, the accuracy of perception strategies (such as map resolution and update frequency) directly affects the drone's computational load and power consumption; therefore, dynamically optimizing navigation strategies to adapt to changes in different environments helps to further reduce overall energy consumption.

[0003] Currently, the following strategies exist for optimizing drone energy consumption: (1) Navigation strategies based on fixed parameters (such as EGO-planner) tend to be conservative and static, emphasizing safety. However, they lack flexibility in complex dynamic environments. This leads to the need to maintain high-resolution and high-frequency perception strategies in open environments with sparse obstacles, resulting in excessive computational burden and failing to effectively reduce the computational energy consumption of UAVs.

[0004] (2) Strategy adjustment scheme based on manually designed flight rules, which determines the flight strategy by manually designing a cost function. This method is suitable for situations with low environmental complexity, but lacks versatility and is difficult to adapt to changing environments.

[0005] (3) The optimization of UAV flight energy consumption and strategy can be achieved through deep learning technology. However, deep learning and inference require additional computing resources from the UAV, which increases computing energy consumption. Furthermore, it cannot utilize the energy-saving space brought by low-precision perception strategies in open areas.

[0006] Overall, current technologies only optimize the single aspect of "speed strategy in navigation," neglecting the close connections between various tasks. Summary of the Invention

[0007] Therefore, it is necessary to provide an environmentally adaptive UAV flight energy consumption optimization system to address at least one of the aforementioned technical problems.

[0008] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: Firstly, an environment-adaptive unmanned aerial vehicle (UAV) flight energy consumption optimization system includes an interconnected navigation pipeline and an environment-adaptive navigation strategy module. The navigation pipeline includes functions for dynamically generating an environmental map and path planning information based on acquired environmental information; and for controlling the flight maneuvers of the UAV based on the path planning information; wherein the environmental map is a grid map. The environment adaptive navigation strategy module is used to determine a first permissible flight speed, a first mapping frequency adjustment information, and a first mapping resolution adjustment information based on the UAV control information and the environment map; wherein, the first permissible flight speed is used to constrain the flight speed of the UAV; the first mapping frequency adjustment information is used to adjust the generation rate of the environment map; and the first mapping resolution adjustment information is used to adjust the generation accuracy of the environment map.

[0009] Secondly, an electronic device includes: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements any of the processes performed by the system described in the first aspect.

[0010] Thirdly, a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, at least one program, code set, or instruction set being loaded and executed by a processor to perform any of the processes performed by the system as described in the first aspect.

[0011] Fourthly, a computer program product includes a computer program or computer-executable instructions, which, when executed by a processor, implement any of the processes performed by the system described in the first aspect.

[0012] Compared with the prior art, the beneficial effects of the technical solution of the present invention are: This application discloses an environment-adaptive UAV flight energy consumption optimization system. It aims to reduce the UAV's flight and computational energy consumption by optimizing three key parameters: flight speed, mapping frequency (i.e., the rate of environmental map generation), and map resolution (i.e., the accuracy of environmental map generation). This minimizes the combined flight and computation time during UAV navigation, significantly improving the overall energy efficiency of UAV missions. Compared to existing technologies, this application achieves effective dynamic management of computational load through refined dynamic management of environmental perception and navigation parameters. It exhibits strong environmental adaptability, improves the robustness and efficiency of overall navigation, and ensures an optimal balance between safety and efficiency for UAVs in complex and dynamically changing environments. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the structure of the UAV flight energy consumption optimization system in some embodiments of this application.

[0014] Figure 2 This is another structural schematic diagram of the UAV flight energy consumption optimization system in some embodiments of this application.

[0015] Figure 3 This is a schematic diagram of the HIL simulation experiment process in some embodiments of this application. Detailed Implementation

[0016] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the description of embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of units is not necessarily limited to those units, but may include other units not explicitly listed or inherent to those processes, methods, products, or apparatuses. The term "determine" broadly covers a wide variety of actions, including acquiring, calculating, processing, deriving, investigating, searching (e.g., searching in a table, database, or other data structure), probing, and similar actions; it may also include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), and similar actions; it may also include generating, creating, establishing, and similar actions; and parsing, selecting, choosing, and similar actions, etc. Definitions of other terms will be given in the following description.

[0017] It should be noted that when one element is considered to be "connected" to another element, it can be directly connected to the other element or connected to the other element through an intermediary element. Furthermore, in the following embodiments, "connection" should be understood as "electrical connection," "communication connection," etc., if there is transmission of electrical signals or data between the connected objects.

[0018] It should be emphasized that the acquisition, transmission, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0019] In the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0020] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent. To better illustrate this embodiment, some parts in the accompanying drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions; It will be understood by those skilled in the art that certain well-known structures and their descriptions may be omitted in the accompanying drawings.

[0021] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] Traditional drone dispatching systems often face the problem of inappropriate frequency settings. For example, too low a frequency leads to a waste of computing resources, and the collected information cannot guarantee the smooth execution of the mission; while too high a frequency not only puts enormous pressure on the onboard computing module, but also excessively consumes the resources deployed on the drone, resulting in a decrease in endurance and mission capabilities. This inappropriate use of resources makes it difficult for drones to maintain efficient operation during long-duration flight missions.

[0023] In some embodiments of this application, an environment-adaptive unmanned aerial vehicle (UAV) travel energy consumption optimization system is provided, including an interconnected navigation pipeline and an environment-adaptive navigation strategy module (EANS), as shown in Figure 1; The navigation pipeline includes functions for dynamically generating an environmental map and path planning information based on acquired environmental information; and for controlling the flight maneuvers of the UAV (such as flight speed, aircraft attitude, etc.) based on the path planning information; wherein the environmental map is a grid map; The environment adaptive navigation strategy module is used to determine a first permissible flight speed, a first mapping frequency adjustment information, and a first mapping resolution adjustment information based on the UAV control information and the environment map; wherein, the first permissible flight speed is used to constrain the flight speed of the UAV; the first mapping frequency adjustment information is used to adjust the generation rate of the environment map; and the first mapping resolution adjustment information is used to adjust the generation accuracy of the environment map.

[0024] To address the shortcomings of existing navigation strategies (such as static conservative strategies and manually designed cost functions) in adapting to environmental changes and their low flexibility, the above embodiments aim to comprehensively optimize the navigation strategy by deeply analyzing the kinematic characteristics of UAVs and the time characteristics of the navigation pipeline, and fully considering the interaction between perception, planning, and control, thereby achieving energy saving. Specifically, the above embodiments disclose a UAV flight energy consumption optimization system that dynamically adjusts the UAV navigation strategy based on real-time environmental characteristics. The system uses a first permissible flight speed generated by the environment adaptive navigation strategy module based on the environmental characteristics reflected in the environmental map to guide the navigation pipeline to dynamically adjust the UAV's flight speed in different environments. The system also uses first mapping frequency adjustment information and first mapping resolution adjustment information generated by the environment adaptive navigation strategy module to dynamically guide the navigation pipeline in adjusting the generation rate (also referred to as "mapping frequency" and "mapping resolution" in relation to the environmental map). This allows the system to adapt to complex environments while adjusting response capabilities, reducing computation time and power consumption. This significantly improves the efficiency of UAV navigation tasks, significantly reduces overall energy consumption, and efficiently utilizes computing resources, while also demonstrating significant advantages in safety and versatility.

[0025] In some preferred embodiments, the environment adaptive navigation strategy module includes a speed adapter, a frequency adapter, and a resolution adapter, as shown in Figure 2; wherein, The Velocity Adapter is used to determine the first permissible flight speed based on the UAV control information, the environmental map, and the path planning information. The frequency adapter is used to determine the first mapped frequency adjustment information based on the UAV control information and the environmental map; The resolution adapter is used to determine the first mapping resolution adjustment information based on the path planning information and the UAV control information.

[0026] It should be noted that the adapters mentioned above combine the kinematic characteristics of the drone with the real-time environmental conditions, and dynamically adjust navigation parameters to ultimately reduce overall energy consumption.

[0027] Those skilled in the art will understand that adjusting the generation rate of the environmental map can reduce unnecessary computational resource consumption by affecting the map update frequency. Furthermore, adjusting the generation rate of the environmental map can also further affect the perception frequency and planning frequency during UAV navigation. Perception frequency refers to the number of times the UAV perceives and processes information about the environment per unit time. A high frequency allows for rapid response to changes in the surrounding environment, which is especially important during obstacle avoidance. However, an excessively high perception frequency obviously increases processing burden and energy consumption. Planning frequency refers to the frequency at which the UAV updates its flight path or action plan. It directly affects the system's adaptability and flexibility. A higher planning frequency can improve task execution efficiency but may also lead to excessive consumption of computational resources. Clearly, the frequency adapter used in the above embodiments can achieve a reasonable balance between perception frequency and planning frequency, thereby optimizing overall energy consumption during flight.

[0028] It should be emphasized that the environment-adaptive navigation strategy proposed in the above embodiments is highly modular and scalable. It is not limited to a specific navigation algorithm or controller and can be widely applied to any probabilistic map-based navigation system. It can be directly integrated into existing UAV systems without additional large-scale modifications or special hardware configurations, which greatly reduces implementation costs.

[0029] In some alternative embodiments, the drone control information includes the drone's current flight speed; Determining the first permissible flight speed based on the UAV control information, the environmental map, and the path planning information includes: Based on the environmental map, determine the first distance information between the current position of the drone and the obstacle; Based on the path planning information, second distance information and second angle information between the planned trajectory of the UAV and the nearest obstacle are determined; wherein, the second distance information reflects the distance between the UAV and the nearest obstacle at each position on the planned trajectory; Based on the first distance information, the second distance information, and the second angle information, the effective sensing distance is determined using a risk weighting function. The maximum permissible flight speed of the UAV is determined based on the effective sensing distance, and is taken as the first permissible flight speed.

[0030] It should be noted that the effective sensing distance d is defined as the distance required for the UAV sensor to capture obstacles. This distance is limited by the maximum detection range of the sensor and the environment. In complex environments, there may be situations where the effective sensing distance is less than the maximum detection range of the sensor and the environment. The effective sensing distance is a key parameter that determines the maximum permissible flight speed.

[0031] It should be emphasized that the effective sensing distance is determined by comprehensively considering the distance information (i.e., the second distance information) and angle information (i.e., the second angle information) between the planned trajectory and the nearest obstacle, the first distance information (which implicitly includes the maximum distance information that the UAV sensor can perceive), and the current flight speed.

[0032] In some specific implementations, the expression for the effective sensing distance is as follows:

[0033] In the formula, Indicates the effective perceived distance. This indicates the distance to the farthest obstacle perceived by the drone, carried in the first distance information. Indicates the weighting factor; The gradient coefficient is determined based on the second distance information. This represents the risk weighting function, which is determined by vector calculation based on the current flight speed (vector), second distance information, and second angle information.

[0034] In some unrestricted examples, the risk weighting function is based on the current flight speed. The cosine value of the second angle information between the planned trajectory and the nearest obstacle and preset coefficient of variation To calculate.

[0035] As a non-limiting example, the maximum permissible flight speed The expression is as follows: ; In the formula, This represents the response time, which is the time required for the drone to detect an obstacle and initiate a response. It can be considered a constant on the same drone. This indicates the maximum acceleration of the drone.

[0036] In some alternative embodiments, the navigation pipeline dynamically adjusts the flight speed in response to the first permitted flight speed.

[0037] In some alternative embodiments, the UAV control information includes the time taken for the UAV's perception planning operation (i.e., the time required for the navigation pipeline to complete a single perception planning operation) and the UAV's current flight speed. The step of determining the first mapping frequency adjustment information based on the UAV control information and the environmental map includes: Based on the environmental map, determine the environmental complexity of the current flight environment; The first mapping frequency adjustment information is determined based on the current flight speed, the time taken for the perception planning operation, and the complexity of the environment.

[0038] In the above embodiments, by analyzing the time consumption characteristics of the navigation pipeline and dynamically adjusting the mapping frequency, the UAV can be ensured to respond to obstacles in real time while reducing the computational load.

[0039] It should be noted that the time required for the navigation pipeline to complete a single perception and planning operation includes the time required for the UAV to start capturing environmental information, confirm obstacles, and execute mapping algorithms to create an environmental map (referred to as perception calculation time), and the time required to plan a path based on the environmental map (referred to as planning time).

[0040] As a non-limiting example, when determining the first mapping frequency adjustment information, it can be determined based on the current flight speed, the perception calculation time in the perception planning operation time, and the environmental complexity, or it can be determined based on the current flight speed, the perception calculation time and planning time in the perception planning operation time, and the environmental complexity.

[0041] In some specific implementations, the first mapping frequency adjustment information is an interval value, with the lower threshold determined by the environmental complexity and the current flight speed, and the upper threshold determined by the perception calculation time.

[0042] It should be noted that Environmental Complexity Index (ECI) is an important parameter for measuring the density of obstacles in the operating environment of a drone. It can be defined by assessing the number, size, and distribution of obstacles near the drone's flight path, the drone's effective sensing distance, and their potential impact on the drone's flight safety. Those skilled in the art should understand that a higher ECI value indicates a more complex environment for the drone, and thus higher requirements for the drone's obstacle avoidance capabilities, path planning, and autonomous decision-making abilities.

[0043] It should be understood that when the environmental complexity reflects a low number of obstacles (i.e., low obstacle density, such as in an open scene), small obstacle size, large usable flight space between obstacles, and / or a large effective sensing distance in the UAV's operating environment, the first mapping frequency adjustment information is used to actively reduce the update frequency of the environmental map (i.e., the mapping frequency) to reduce computation time and power consumption. When the environmental complexity reflects a high number of obstacles (large obstacle size), small usable flight space between obstacles, and / or a small effective sensing distance in the UAV's operating environment, the first mapping frequency adjustment information is used to actively increase the update frequency of the environmental map to ensure flight safety. This dynamic adjustment mechanism overcomes the problems of insufficient flexibility and lack of coordination in map adjustment in existing technologies.

[0044] In some non-limiting examples, the complexity of the environment can be determined by the number of obstacles per unit space, or by a combination of the number of obstacles per unit space and the moving speed of the obstacles. This disclosure does not impose any limitations on this.

[0045] In some optional embodiments, the UAV control information may further include third distance information between the current position of the UAV and the target position; The step of determining the first mapping resolution adjustment information based on the path planning information and the UAV control information includes: Calculate the path suitability probability based on the third distance information and the path planning information; Determine whether the path suitability probability meets a preset threshold interval: If so, then generate first mapping resolution adjustment information to instruct the navigation pipeline not to adjust the generation accuracy of the environment map; If the path suitability probability is less than the lower boundary of the threshold interval, then first mapping resolution adjustment information is generated to instruct the navigation pipeline to improve the generation accuracy of the environment map; If the path suitability probability is greater than the upper boundary of the threshold interval, then a first mapping resolution adjustment information is generated based on a greedy algorithm to instruct the navigation pipeline to reduce the generation accuracy of the environment map, until the path suitability probability re-determined by the path planning information regenerated by the navigation pipeline in response to the first mapping resolution adjustment information satisfies the preset threshold interval.

[0046] It should be noted that in the above embodiments, the map resolution is gradually reduced by a greedy algorithm, and the path suitability probability is recalculated using the low resolution. This ensures that the computational burden is reduced without affecting the safety of path planning, and avoids the safety risks caused by overly aggressive flight strategies.

[0047] In some specific implementations, the map resolution is determined by the size of the cube elements in the map. When the path suitability probability is greater than the upper boundary of the threshold interval, the map is constructed using cube elements with larger side lengths; if the path suitability probability is less than the lower boundary of the threshold interval, the map is constructed using cube elements with smaller side lengths, and the path is replanned to control the mapping resolution and ensure the safety and effectiveness of the UAV and the path.

[0048] Furthermore, the expression for the path suitability probability is as follows:

[0049] In the formula, Indicates the length of the planned trajectory. This indicates the third distance information between the drone's current position and the target position; Indicates the optimal trajectory length; Indicates an adjustable constant; This represents the path suitability probability of the planned path at time T=b; It can measure how a fixed-length error affects the trajectory probability at different distances.

[0050] In some specific implementation processes, the optimal trajectory length is determined based on the third distance information, which can be the Euclidean distance between the current position of the UAV and the target position.

[0051] It should be noted that, compared to existing static or conservative strategies, the speed adapter settings in the aforementioned embodiments can flexibly adapt to different environmental scenarios, proactively increasing speed in open areas and promptly reducing speed in complex areas to avoid unnecessary deceleration or pauses. By accurately integrating the UAV speed with the shortest distance between the planned trajectory and obstacles to calculate risk weights (i.e., risk weight function), the safe distance is calculated using risk weights to determine the maximum flight speed and make rapid adjustments, effectively avoiding the energy waste and safety hazards caused by overly conservative or aggressive methods in traditional approaches. Addressing the problem of excessive computational resource consumption caused by existing fixed-frequency mapping methods, the frequency adapter settings in the aforementioned embodiments can reduce the mapping frequency in low-risk areas and improve perception accuracy in high-risk areas, achieving effective dynamic management of computational load. This avoids navigation performance fluctuations caused by excessively high or low mapping frequencies, improving the overall robustness and efficiency of navigation. Compared to traditional fixed-resolution schemes, the resolution adapter settings in the aforementioned embodiments effectively prevent the waste of computational resources, especially ensuring path safety and reliability even after reducing resolution in open environments. It overcomes the environmental adaptability issues caused by fixed thresholds and static resolution adjustments in existing technologies (such as ASAP or Roborun), further improving the computational efficiency and energy-saving effect of navigation. In some preferred embodiments, the navigation pipeline includes: The perception module is used to capture the environmental information and dynamically generate the environmental map reflecting the environmental information based on the generation rate and the generation accuracy. The route planning module is used to respond to the dynamically generated environment map and trigger the generation of route planning information. The control module is used to control the flight maneuvers of the UAV based on the path planning information and the first permitted flight speed.

[0052] The above embodiments significantly reduce energy consumption by establishing the task coupling relationship of the navigation pipeline and analyzing the kinematic characteristics and environmental features of the UAV.

[0053] In some specific implementations, the speed adapter transmits the first mapping frequency adjustment information determined by the frequency adapter and the first mapping resolution adjustment information determined by the resolution adapter to the sensing module.

[0054] In some specific implementations, the frequency adapter transmits the first permitted flight speed to the path planning module, which in turn transmits it to the control module.

[0055] Furthermore, the path planning module includes a global planning unit and a path optimization unit. The global planning unit is used to generate a global path plan based on the environment map, and the path optimization unit is used to perform local path optimization on the global path plan to generate the path planning information.

[0056] Those skilled in the art should understand that the basic navigation tasks of the UAV can be achieved based on the aforementioned perception module, path planning module, and control module.

[0057] In some specific implementation processes, environmental information is scanned in real time by lidar and / or cameras deployed on the drone body, and an environmental map is constructed in the form of an occupancy grid using a mapping module.

[0058] In some specific implementations of this application, HIL simulation experiments were also conducted on the aforementioned system, as shown in Figure 3.

[0059] (1) System composition: Simulation platform: PC host (AMD Ryzen5 3600 CPU + NVIDIA GTX 1660 GPU).

[0060] Embedded platform: Nvidia Jetson TX2 onboard computing unit.

[0061] Software environment: ROS + Gazebo, navigation pipeline, EANS adaptive module.

[0062] (2) Workflow: 1) Initialization: Execute the working script, start the ROS node, load the virtual environment scene, and initialize the navigation pipeline and environment adaptation module.

[0063] 2) Start the drone: Prepare and start the drone through the control interface. 3) Set target: Set the drone's flight positioning target and start navigation.

[0064] 4) EANS parameter calculation and positioning: After the perception module updates the map, it passes the data to EANS for parameter calculation. The maximum speed adapter calculates the safe flight speed and passes it to the mapping frequency adapter. After calculating the optimal frequency, the mapping resolution adapter dynamically adjusts the resolution.

[0065] 5) Feedback parameters and path planning: After EANS transmits the data to the navigation pipeline, it plans and executes the path and controls the UAV's flight and movement. 6) Iterative cycle: Repeat the above process until the target location is reached.

[0066] HIL experimental results show that, compared to the static navigation strategy used as a baseline, the system based on the aforementioned embodiments reduces the task completion time to approximately one-third of the original time, significantly reduces the average CPU utilization and overall energy consumption compared to the baseline method, improves speed optimization by approximately 3.2 times, and significantly reduces flight time compared to the baseline method. Overall, it reduces computational and flight energy consumption, shortens task time, and maintains safe obstacle avoidance capabilities.

[0067] In some other specific implementations of this application, real-world scenario experiments were also conducted on the aforementioned system.

[0068] (1) System composition: Platform: Quadrotor drone, dimensions 55 cm × 55 cm × 35 cm; Embedded computing unit: Nvidia Jetson TX2; Sensors: Forward-looking depth cameras or LiDAR, used for real-time environmental perception; Navigation pipeline; Environment Adaptive Module (EANS).

[0069] (2) Workflow: 1) Pre-flight check: Verify the drone's power, battery level, and sensor status, and set the maximum flight speed limit. 2) Initialization and target setting: Similar to the HIL simulation experiment, calculations, positioning, and target setting are performed after initialization. 3) Dynamic navigation: In dense obstacle areas, EANS uses system control to improve obstacle avoidance accuracy, while in open areas, it reduces computational load. Specifically, referring to the HIL simulation experiment, it performs a loop of perception → parameter calculation → planning → control until the task is completed.

[0070] In real-world experiments, in a typical forest area, CPU utilization decreased by 18.9%, memory utilization decreased by 11.4%, and task time decreased from 45 seconds to 17.5 seconds, a 2.6-fold reduction compared to existing solutions, achieving energy savings. In narrow passages, CPU utilization decreased by 15.6%, and memory utilization decreased by 2.0%. After passing through the narrow passage with high-precision perception, the UAV automatically switches to low-precision in open areas to accelerate flight, ensuring safety while improving efficiency. Furthermore, the system exhibits consistent energy-saving and speed-up effects with simulation experiments in both completely different scenarios, verifying its versatility and robustness.

[0071] The results of real-world experiments fully demonstrate that, compared with existing strategies, the system described in this application can greatly improve the efficiency of UAVs in actual missions and effectively expand the application scope and usage time of UAVs under energy-constrained conditions.

[0072] Based on the comprehensive experimental results, the dynamic adjustment strategy proposed in the aforementioned embodiments significantly reduces unnecessary high-precision sensing and computation tasks compared to existing technologies (such as fixed resolution or static threshold strategies). Furthermore, experimental data shows that in high-density obstacle areas, the system safety and reliability described in the aforementioned embodiments are comparable to or better than existing technologies (such as the EGO-planner strategy), avoiding the safety risks associated with overly aggressive flight strategies. Moreover, the dynamic adjustment of mapping frequency and resolution can more effectively manage risks and prevent accidental collisions. The system demonstrates stable performance in various scenarios (including simulated and real complex scenarios), exhibiting strong robustness and versatility, and is easily scalable.

[0073] In some embodiments of this application, a computer-readable storage medium is also provided, which stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor, causing the processor to perform some or all of the steps performed by the system provided in the foregoing embodiments of this application.

[0074] It is understood that the storage medium can be transient or non-transient. Exemplarily, the storage medium includes, but is not limited to, 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.

[0075] By way of example, the processor may be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0076] By way of example, the read-only memory includes, but is not limited to, MASK ROM, PROM, EPROM, EEPROM, Flash, etc.

[0077] By way of example, the random access memory includes, but is not limited to, DRAM, SRAM, SDRAM, DDR SDRAM, etc.

[0078] In some examples, a computer program product is provided, which can be implemented by hardware, software, or a combination thereof. As a non-limiting example, the computer program product can be embodied in the storage medium, or it can be embodied in a software product, such as an SDK (Software Development Kit).

[0079] As a non-limiting example, a computer program product is provided, comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer program or computer-executable instructions from the computer-readable storage medium, and executes the computer-executable instructions, causing the electronic device to perform some or all of the steps performed by the system described in the foregoing embodiments of this application.

[0080] In some examples, a computer program is provided, including computer-readable code, which, when executed in a computer device, causes a processor in the computer device to perform some or all of the steps for implementing the system.

[0081] This embodiment also proposes an electronic device, including a memory and a processor. The memory stores at least one instruction, at least one program, code set, or instruction set. When the processor executes the at least one instruction, at least one program, code set, or instruction set, it implements some or all of the steps performed by the system as described in the foregoing embodiments.

[0082] In some examples, a hardware entity of the electronic device is provided, including: a processor, a memory, and a communication interface; wherein the processor typically controls the overall operation of the electronic device; the communication interface is used to enable the electronic device to communicate with other terminals or servers via a network; the memory is configured to store instructions and applications executable by the processor, and may also cache data to be processed or already processed (including but not limited to image data, audio data, voice communication data, and video communication data) to be processed by the processor and various modules in the electronic device, and may be implemented using flash memory (FLASH), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or random access memory (RAM).

[0083] A processor may include one or more processing elements. Therefore, a processor may include one or more integrated circuits (ICs) configured to perform the functions of the processor. Furthermore, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, and other circuitry) configured to perform the functions of the processor.

[0084] Furthermore, data can be transferred between the processor, communication interface, and memory via a bus, which can include any number of interconnected buses and bridges, connecting various circuits of one or more processors and memories together.

[0085] The same or similar labels correspond to the same or similar parts; The terms used to describe positional relationships in the accompanying drawings are for illustrative purposes only and should not be construed as limiting this application. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0086] In different specific implementations, the methods or systems described in this application can be implemented in software, hardware, or a combination thereof. Furthermore, the order of the method steps can be changed, and various elements can be added, reordered, combined, omitted, or modified.

[0087] Obviously, the above embodiments of this application are merely examples for clearly illustrating this application, and are not intended to limit the implementation of this application, nor are they intended to limit this application. For those skilled in the art, other variations or modifications can be made based on the above description. The separate structural / functional modules or units can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. The structure and function of the separate components can be implemented as a combined structure or component. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of the claims of this application.

Claims

1. An environment-adaptive unmanned aerial vehicle (UAV) flight energy consumption optimization system, characterized in that, This includes interconnected navigation pipelines and environment-adaptive navigation strategy modules; The navigation pipeline includes functions for dynamically generating an environmental map and path planning information based on acquired environmental information; and for controlling the flight maneuvers of the UAV based on the path planning information; wherein the environmental map is a grid map. The environment adaptive navigation strategy module is used to determine a first permissible flight speed, a first mapping frequency adjustment information, and a first mapping resolution adjustment information based on the UAV control information and the environment map; wherein, the first permissible flight speed is used to constrain the flight speed of the UAV; the first mapping frequency adjustment information is used to adjust the generation rate of the environment map; and the first mapping resolution adjustment information is used to adjust the generation accuracy of the environment map.

2. The environmentally adaptive UAV flight energy consumption optimization system according to claim 1, characterized in that, The environment adaptive navigation strategy module includes a speed adapter, a frequency adapter, and a resolution adapter; wherein... The speed adapter is used to determine the first permissible flight speed based on the UAV control information, the environmental map, and the path planning information; The frequency adapter is used to determine the first mapping frequency adjustment information based on the UAV control information and the environmental map; The resolution adapter is used to determine the first mapping resolution adjustment information based on the path planning information and the UAV control information.

3. The environmentally adaptive UAV flight energy consumption optimization system according to claim 2, characterized in that, The drone control information includes the drone's current flight speed; Determining the first permissible flight speed based on the UAV control information, the environmental map, and the path planning information includes: Based on the environmental map, determine the first distance information between the current position of the drone and the obstacle; Based on the path planning information, second distance information and second angle information between the planned trajectory of the UAV and the nearest obstacle are determined; wherein, the second distance information reflects the distance between the UAV and the nearest obstacle at each position on the planned trajectory; The effective sensing distance is determined based on the first distance information, the second distance information, the second angle information, and the current flight speed, combined with a risk weighting function. The maximum permissible flight speed of the UAV is determined based on the effective sensing distance, and is taken as the first permissible flight speed.

4. The environmentally adaptive UAV flight energy consumption optimization system according to claim 2, characterized in that, The UAV control information includes the time taken for the UAV's perception and planning operations and its current flight speed; The step of determining the first mapping frequency adjustment information based on the UAV control information and the environmental map includes: Based on the environmental map, determine the environmental complexity of the current flight environment; The first mapping frequency adjustment information is determined based on the current flight speed, the time taken for the perception planning operation, and the complexity of the environment.

5. The environmentally adaptive UAV flight energy consumption optimization system according to claim 2, characterized in that, The drone control information also includes third distance information between the drone's current position and the target position; The step of determining the first mapping resolution adjustment information based on the path planning information and the UAV control information includes: Calculate the path suitability probability based on the third distance information and the path planning information; Determine whether the path suitability probability meets a preset threshold interval: If so, then generate first mapping resolution adjustment information to instruct the navigation pipeline not to adjust the generation accuracy of the environment map; If the path suitability probability is less than the lower boundary of the threshold interval, then first mapping resolution adjustment information is generated to instruct the navigation pipeline to improve the generation accuracy of the environment map; If the path suitability probability is greater than the upper boundary of the threshold interval, then a first mapping resolution adjustment information is generated based on a greedy algorithm to instruct the navigation pipeline to reduce the generation accuracy of the environment map, until the path suitability probability re-determined by the path planning information regenerated by the navigation pipeline in response to the first mapping resolution adjustment information satisfies the preset threshold interval.

6. The environmentally adaptive UAV flight energy consumption optimization system according to claim 5, characterized in that, The expression for the path suitability probability is as follows: In the formula, Indicates the length of the planned trajectory. This indicates the third distance information between the drone's current position and the target position; Indicates the optimal trajectory length; Indicates an adjustable constant; Indicates in The probability that the planned path is suitable at any given time.

7. An environment-adaptive unmanned aerial vehicle (UAV) flight energy consumption optimization system according to any one of claims 1-6, characterized in that, The navigation pipeline includes: A perception module is used to capture the environmental information and dynamically generate an environmental map reflecting the environmental information based on the generation rate and the generation accuracy. The path planning module is used to respond to the dynamically generated environment map and trigger the generation of path planning information; The control module is used to control the flight maneuvers of the UAV based on the path planning information and the first permitted flight speed.

8. An electronic device, characterized in that, include: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, performs any process performed by the system according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, which is loaded and executed by a processor to implement any process performed by the system as described in any one of claims 1-7.

10. A computer program product comprising a computer program or computer-executable instructions, characterized in that, When the computer program or computer-executable instructions are executed by the processor, they implement any of the processes performed by the system according to any one of claims 1-7.

Images