ALOT-based low-altitude intelligent obstacle avoidance route planning system

Abstract

The invention relates to the technical field of aerospace, and discloses an ALOT-based low-altitude intelligent obstacle avoidance route planning system, which comprises a data collection module, a data calculation module, a feedback module, a feedback optimization module and an optimization management module, and is characterized in that the data collection module is responsible for collecting various environmental information required in the flight process of an unmanned aerial vehicle; the data calculation module performs calculation and analysis by using an algorithm based on the data collected by the data collection module to generate a preliminary dynamic route planning model, the feedback module performs real-time monitoring and feedback on a calculation result of the data calculation module and evaluates the flight state of the unmanned aerial vehicle, and the feedback optimization module adjusts a flight strategy according to a feedback result. According to the method, obstacle avoidance and route planning are optimized, optimization measures for adjusting the flight speed and changing the route are put forward in time, an optimization management module manages and implements the optimization measures, it is ensured that the unmanned aerial vehicle flies safely and efficiently according to the optimized route, meanwhile, the implementation effect of the optimization measures is monitored, and effective adjustment is conducted.

Description

Technical Field

[0001] The present invention relates to the field of aerospace technology, and specifically to a low-altitude intelligent obstacle avoidance route planning system based on ALOT. Background Art

[0002] During the flight of an unmanned aerial vehicle (UAV), one of the main challenges faced by the existing technology is the inability to predict and identify sudden obstacles in advance and effectively avoid these obstacles. In addition, based on the route planning, the UAV is also unable to further optimize its flight speed and acceleration to improve flight efficiency and safety.

[0003] The route planning speed of the UAV in a dynamic environment is slow, and its ability to respond to emergencies is insufficient. In terms of obstacle detection, although a variety of sensors and algorithms have been used to detect and avoid obstacles, such as cameras, lidar, etc., these methods still have limitations in dealing with high-dynamic obstacles and moving objects.

[0004] In addition, the optimization of the flight speed and acceleration of the UAV is also limited. The current path planning algorithms are mostly based on two-dimensional plane scenarios and are difficult to adapt to complex three-dimensional environments, resulting in the UAV being prone to stagnation or tracking failure during flight.

[0005] In response to these problems, researchers have proposed a variety of solutions, including using improved speed obstacle methods and deep reinforcement learning techniques to improve the real-time performance and accuracy of the UAV. However, these methods still need to be verified and improved in practical applications to ensure that the UAV can fly safely and efficiently in complex and changeable environments. Summary of the Invention

[0006] (1) Technical Problems to be Solved

[0007] In view of the deficiencies of the existing technology, the present invention provides a low-altitude intelligent obstacle avoidance route planning system based on ALOT, which has the advantages of being able to predict obstacles in advance and the UAV being able to optimize acceleration, and solves the problems that the existing technology cannot predict obstacles in advance and the UAV cannot optimize acceleration.

[0008] (2) Technical Solutions

[0009] To achieve the above object, the present invention provides the following technical solutions: A low-altitude intelligent obstacle avoidance route planning system based on ALOT, including a data collection module, a data calculation module, a feedback module, a feedback optimization module, and an optimization management module;

[0010] The data collection module is responsible for collecting various types of environmental information required during the flight of the UAV, providing basic data support for subsequent calculations, optimizations, and management;

[0011] The data calculation module is based on the data collected by the data collection module;

[0012] The feedback module monitors and feeds back the calculation results of the data calculation module in real time to evaluate the flight state of the drone and environmental changes;

[0013] The feedback optimization module adjusts the flight strategy according to the feedback results, optimizes obstacle avoidance and route planning, and timely proposes optimization measures for adjusting the flight speed and changing the route;

[0014] The optimization management module manages and implements the optimization measures to ensure that the drone flies safely and efficiently according to the optimized route. At the same time, it monitors the implementation effect of the optimization measures and makes effective adjustments.

[0015] Preferably, the data collection module includes an environmental perception unit, a meteorological monitoring unit, a GPS positioning unit, and a noise monitoring unit. The environmental perception unit uses lidar and millimeter-wave radar to scan the surrounding environment in real time to obtain environmental perception data, and the data includes the position change deviation angle, shape change deviation angle, and dynamic change deviation angle information of obstacles;

[0016] The meteorological monitoring unit monitors the weather conditions in real time through an integrated thermometer and anemometer and wind vane to obtain meteorological monitoring data, and the data includes the difference information between the actual wind force, wind direction, temperature, and humidity changes and the model prediction changes;

[0017] The GPS positioning unit obtains the GPS positioning data of the drone through a global satellite navigation system receiver, and the data includes the current position, speed, and heading information of the drone;

[0018] The noise monitoring unit obtains noise monitoring data through a sound level meter, a recording device, and a frequency analyzer sensor. The data includes the noise data generated during the flight of the drone and various noise conditions of the surrounding environment during the flight of the drone.

[0019] Preferably, the dynamic obstacle avoidance unit calculates the collision risk index Qc according to the environmental perception data, the optimal path unit calculates the total deviation value Kr of the flight path according to the environmental perception data, meteorological monitoring data, GPS positioning data, and noise monitoring data, and the adaptive speed unit calculates the deviation Us between the model and the actual flight speed according to the environmental perception data and meteorological monitoring data.

[0020] Preferably, the environmental perception unit numbers the position change deviation angle, shape change deviation angle, and dynamic change deviation angle information of the obstacle according to the characteristics of the environmental perception data. The position change deviation angle, shape change deviation angle, and dynamic change deviation angle of the obstacle are numbered as Y1, Y2, and Y3 respectively.

[0021] Preferably, the meteorological monitoring unit numbers the information on the differences between the actual changes in wind force, wind direction, temperature, and humidity and the model-predicted changes according to the characteristics of the meteorological monitoring data. The differences between the actual changes in wind force, wind direction, temperature, and humidity and the model-predicted changes are numbered as ΔV, ΔF, ΔT, and ΔW, respectively.

[0022] Preferably, the GPS positioning unit numbers the current position, speed, and heading of the UAV according to the characteristics of the UAV's GPS positioning data. The current position, speed, and heading of the UAV are numbered as d, j, and g, respectively.

[0023] Preferably, the noise monitoring unit numbers the information on various noise conditions in the surrounding environment during the flight of the UAV according to the characteristics of the noise monitoring data. The information on various noise conditions in the surrounding environment during the flight of the UAV is numbered as Z1, Z2, Z3, … Z m 。

[0024] Preferably, the dynamic obstacle avoidance unit calculates the collision risk index Qc based on the environmental perception data. The calculation formula is:

[0025] Qc = a1 * Y1 + a2 * Y2 + a3 * Y3

[0026] In the formula, Qc represents the collision risk index, Y1, Y2, and Y3 respectively represent the deviation angles of the position change, shape change, and dynamic change of the obstacle, and a1, a2, and a3 respectively represent the weights corresponding to the deviation angles of the position change, shape change, and dynamic change of the obstacle in the collision risk, respectively reflecting the influence degree of the obstacle position change on the collision risk, the influence degree of the obstacle shape change on the collision risk, and the influence degree of the obstacle dynamic change on the collision risk.

[0027] Preferably, the optimal path unit calculates the total deviation value Kr of the flight path based on the environmental perception data, meteorological monitoring data, GPS positioning data, and noise monitoring data. The calculation formula is:

[0028]

[0029] In the formula, Kr represents the total deviation value of the flight path, Y1, Y2, and Y3 respectively represent the deviation angles of the position change, shape change, and dynamic change of the obstacle, h maxrepresents the preset maximum deviation angle of the model, d represents the current position of the drone, ΔV, ΔF, ΔT, and ΔW respectively represent the differences between the actual changes in wind force, wind direction, temperature, and humidity and the model predictions, b1, b2, b3, and b4 respectively represent the weights corresponding to the changes in wind force, wind direction, temperature, and humidity in the total deviation value of the flight path, that is, the influence of the changes in wind force, wind direction, temperature, and humidity under meteorological factors on the flight path, Z1, Z2, Z3, … Z m represents various noise condition information of the surrounding environment during the flight of the drone, Z i represents the i-th noise condition information of the surrounding environment, α i represents the weight corresponding to the i-th noise condition information of the surrounding environment.

[0030] Preferably, the adaptive speed unit calculates the deviation Us between the model and the actual flight speed based on the environmental perception data and meteorological monitoring data, and its calculation formula is:

[0031]

[0032] In the formula, Us represents the deviation between the model and the actual flight speed, j and g respectively represent the speed and heading of the drone, ΔV, ΔF, ΔT, and ΔW respectively represent the differences between the actual changes in wind force, wind direction, temperature, and humidity and the model predictions, c1, c2, c3, and c4 respectively represent the weights corresponding to the changes in wind force, wind direction, temperature, and humidity in the deviation between the model and the actual flight speed, that is, the influence of the changes in wind force, wind direction, temperature, and humidity under meteorological factors on the flight speed of the drone, and k represents the maximum speed threshold under meteorological factors.

[0033] Compared with the prior art, the present invention provides a low-altitude intelligent obstacle avoidance route planning system based on ALOT, which has the following beneficial effects:

[0034] 1. The present invention calculates the collision risk index Qc through the dynamic obstacle avoidance unit, and the feedback module can generate corresponding obstacle avoidance strategies according to the specific range of the collision risk index. The strategies include adjusting the flight path, speed, and height parameters of the drone to ensure that the drone can fly safely in a complex environment. When the collision risk index Qc indicates a high risk, the feedback optimization module will trigger a change in the flight route to avoid potential obstacles, or adjust the obstacle avoidance measures of the flight speed and height to reduce the possibility of collision. When the collision risk index Qc is low, the drone can maintain the current flight state or perform smoother obstacle avoidance actions. This dynamic obstacle avoidance strategy based on real-time data enables the system to have the ability to predict obstacles in advance, thereby improving the flight efficiency of the drone while ensuring flight safety.

[0035] 2. Through the dynamic obstacle avoidance unit calculation model and the actual flight speed deviation Us, the present invention enables the system to optimize the acceleration of the UAV. This calculation process uses the weighted average method to comprehensively consider the impacts of various meteorological factors on the UAV's flight speed, and calculates the deviation Us between the model and the actual flight speed. This deviation helps to increase the system's control over the UAV's speed, enabling the UAV's acceleration to be adjusted in real time to adapt to the current flight environment and conditions, indicating that the UAV can quickly respond to sudden changes in wind speed, wind direction, as well as changes in temperature and humidity, thereby maintaining stable flight performance. Its optimized acceleration helps to improve the UAV's flight efficiency. On the premise of ensuring safety, the UAV can fly at a more economical speed, reducing energy consumption, thereby extending the flight time or increasing the payload capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic structural diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] Please refer to Figure 1 , the low-altitude intelligent obstacle avoidance route planning system based on ALOT includes a data collection module, a data calculation module, a feedback module, a feedback optimization module, and an optimization management module;

[0039] The data collection module is responsible for collecting various environmental information required during the UAV's flight, providing basic data support for subsequent calculations, optimizations, and management;

[0040] Based on the data collected by the data collection module, the data calculation module uses algorithms for calculation and analysis to generate a preliminary dynamic route planning model and a dynamic obstacle avoidance strategy. The data calculation module includes a dynamic obstacle avoidance unit, an optimal path unit, and an adaptive speed unit;

[0041] The feedback module monitors and feeds back the calculation results of the data calculation module in real time to evaluate the UAV's flight state and environmental changes;

[0042] According to the feedback results, the feedback optimization module adjusts the flight strategy, optimizes obstacle avoidance and route planning, and timely proposes optimization measures for adjusting the flight speed and changing the route;

[0043] The optimization management module manages and implements optimization measures to ensure that the UAV flies safely and efficiently according to the optimized flight path. At the same time, it monitors the implementation effect of the optimization measures and makes effective adjustments.

[0044] The data collection module includes an environmental perception unit, a meteorological monitoring unit, a GPS positioning unit, and a noise monitoring unit. The environmental perception unit scans the surrounding environment in real time through a lidar (LiDAR) and a millimeter-wave radar to obtain environmental perception data, which includes the deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle;

[0045] The meteorological monitoring unit monitors the weather conditions in real time by integrating a thermometer and a wind speed and direction sensor to obtain meteorological monitoring data, which includes the difference between the actual wind force, wind direction, temperature, and humidity changes and the model prediction changes (to evaluate the impact on flight);

[0046] The GPS positioning unit obtains the GPS positioning data of the UAV through a global navigation satellite system (GNSS) receiver, which includes the current position, speed, and heading information of the UAV (to ensure the accuracy of the flight path planning);

[0047] The noise monitoring unit obtains noise monitoring data through a sound level meter, a recording device, and a frequency analyzer sensor, which includes the noise data generated during the flight of the UAV and various noise conditions of the surrounding environment during the flight of the UAV (to provide important reference information for flight path planning and flight safety).

[0048] The dynamic obstacle avoidance unit calculates the collision risk index Qc based on the environmental perception data, enabling it to have the advantage of predicting obstacles in advance. The optimal path unit calculates the total deviation value Kr of the flight path based on the environmental perception data, meteorological monitoring data, GPS positioning data, and noise monitoring data, obtaining the advantage that the UAV can optimize the flight path. The adaptive speed unit calculates the deviation Us between the model and the actual flight speed based on the environmental perception data and meteorological monitoring data, obtaining the advantage that the UAV can optimize the acceleration.

[0049] The environmental perception unit numbers the deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle according to the characteristics of the environmental perception data. The deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle are numbered as Y1, Y2, and Y3 respectively.

[0050] The meteorological monitoring unit numbers the difference between the actual wind force, wind direction, temperature, and humidity changes and the model prediction changes according to the characteristics of the meteorological monitoring data. The difference between the actual wind force, wind direction, temperature, and humidity changes and the model prediction changes are numbered as ΔV, ΔF, ΔT, and ΔW respectively.

[0051] The GPS positioning unit numbers the current position, speed, and heading of the UAV according to the GPS positioning data characteristics of the UAV. The current position, speed, and heading of the UAV are numbered as d, j, and g respectively.

[0052] The noise monitoring unit numbers the various noise condition information of the surrounding environment during the flight of the UAV according to the noise monitoring data characteristics. The various noise condition information of the surrounding environment during the flight of the UAV is numbered as Z1, Z2, Z3, … Z m 。

[0053] The dynamic obstacle avoidance unit calculates the collision risk index Qc based on the environmental perception data. The calculation formula is:

[0054] Qc = a1 * Y1 + a2 * Y2 + a3 * Y3

[0055] In the formula, Qc represents the collision risk index. Y1, Y2, and Y3 respectively represent the deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle. a1, a2, and a3 respectively represent the weights corresponding to the deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle in the collision risk, and respectively reflect the influence degree of the position change of the obstacle on the collision risk, the influence degree of the shape change of the obstacle on the collision risk, and the influence degree of the dynamic change of the obstacle on the collision risk;

[0056] The advantages are as follows: By calculating the collision risk index Qc through the dynamic obstacle avoidance unit, the feedback module can generate corresponding obstacle avoidance strategies according to the specific range of the collision risk index. The strategies include adjusting the flight path, speed, and altitude parameters of the UAV to ensure that the UAV can fly safely in a complex environment. When the collision risk index Qc indicates a high risk, the feedback optimization module will trigger a change in the flight route to avoid potential obstacles, or adjust the obstacle avoidance measures of the flight speed and altitude to reduce the possibility of collision. When the collision risk index Qc is low, the UAV can maintain the current flight state or perform a smoother obstacle avoidance action. This dynamic obstacle avoidance strategy based on real-time data enables the system to have the ability to predict obstacles in advance, thereby improving the flight efficiency of the UAV while ensuring flight safety.

[0057] The optimal path unit calculates the total deviation value Kr of the flight path according to the environmental perception data, meteorological monitoring data, GPS positioning data, and noise monitoring data. The calculation formula is:

[0058]

[0059] In the formula, Kr represents the total deviation value of the flight path. Y1, Y2, and Y3 respectively represent the deviation angle of the position change, the deviation angle of the shape change, and the deviation angle of the dynamic change of the obstacle. h maxLet \(\theta\) represent the preset maximum deviation angle of the model, \(d\) represent the current position of the drone, \(\Delta V\), \(\Delta F\), \(\Delta T\), and \(\Delta W\) respectively represent the differences between the actual changes in wind force, wind direction, temperature, and humidity and the predicted changes by the model, and \(b_1\), \(b_2\), \(b_3\), \(b_4\) respectively represent the weights corresponding to the changes in wind force, wind direction, temperature, and humidity in the total deviation value of the flight path, that is, the impacts of the changes in wind force, wind direction, temperature, and humidity under meteorological factors on the flight path, and \(Z_1\), \(Z_2\), \(Z_3,\cdots,Z\) m represents various noise condition information of the surrounding environment during the flight of the drone, \(Z\) i represents the \(i\)-th noise condition information of the surrounding environment, \(\alpha\) i represents the weight corresponding to the \(i\)-th noise condition information of the surrounding environment.

[0060] The advantages are as follows: The total deviation value \(K_r\) of the flight path is calculated by the optimal path unit. The feedback module can evaluate the deviation between the current flight path and the ideal flight path. The feedback optimization module can adjust the flight path to avoid obstacles, adjust the speed to adapt to changes in meteorological conditions, and adjust the altitude to reduce energy consumption or avoid noise-sensitive areas according to the total deviation value \(K_r\) of the flight path. In this way, the flight efficiency of the drone is improved because it can take the most direct route to the destination while reducing unnecessary energy consumption. At the same time, the optimized flight path can also ensure flight safety because the calculation formula takes into account real-time environmental and meteorological data, enabling the drone to timely avoid potential risks caused by environmental and meteorological factors.

[0061] The dynamic obstacle avoidance unit calculates the collision risk index \(Q_c\) based on the environmental perception data, and the adaptive speed unit calculates the deviation \(U_s\) between the model and the actual flight speed based on the environmental perception data and meteorological monitoring data. Its calculation formula is:

[0062]

[0063] In the formula, \(U_s\) represents the deviation between the model and the actual flight speed, \(j\) and \(g\) respectively represent the speed and heading of the drone, \(\Delta V\), \(\Delta F\), \(\Delta t\), \(\Delta W\) respectively represent the differences between the actual changes in wind force, wind direction, temperature, and humidity and the predicted changes by the model, and \(c_1\), \(c_2\), \(c_3\), \(c_4\) respectively represent the weights corresponding to the changes in wind force, wind direction, temperature, and humidity in the deviation between the model and the actual flight speed, that is, the impacts of the changes in wind force, wind direction, temperature, and humidity under meteorological factors on the flight speed of the drone, and \(k\) represents the maximum speed threshold under meteorological factors.

[0064] The advantages are as follows: By calculating the deviation Us between the dynamic obstacle avoidance unit calculation model and the actual flight speed, the system can optimize the acceleration of the UAV. This calculation process uses the weighted average method to comprehensively consider the influence of various meteorological factors on the UAV flight speed, and calculates the deviation Us between the model and the actual flight speed (the deviation between the model predicted speed and the actual flight speed). This deviation helps to increase the system's control over the UAV speed, enabling the UAV's acceleration to be adjusted in real time to adapt to the current flight environment and conditions, indicating that the UAV can quickly respond to sudden changes in wind speed and direction, as well as changes in temperature and humidity, so as to maintain stable flight performance. Its optimized acceleration helps to improve the flight efficiency of the UAV. On the premise of ensuring safety, the UAV can fly at a more economical speed, reduce energy consumption, thereby extending the flight time or increasing the payload capacity.

[0065] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent low-altitude obstacle avoidance route planning system based on ALOT, characterized in that, It includes a data collection module, a data calculation module, a feedback module, a feedback optimization module and an optimization management module; The data collection module is responsible for collecting various environmental information required during the flight of the drone; The data calculation module uses an algorithm to calculate and analyze the data collected by the data collection module to generate a preliminary dynamic route planning model and a dynamic obstacle avoidance strategy. The data calculation module includes a dynamic obstacle avoidance unit, an optimal path unit and an adaptive speed unit; The feedback module monitors and feeds back the calculation results of the data calculation module in real time, and evaluates the flight status and environmental changes of the UAV; The feedback optimization module adjusts the flight strategy according to the feedback results, optimizes obstacle avoidance and route planning, and proposes optimization measures for adjusting the flight speed and changing the route in a timely manner; The optimization management module manages and implements the optimization measures to ensure that the UAV flies safely and efficiently according to the optimized route, while monitoring the implementation effect of the optimization measures and making effective adjustments.

2. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, wherein: The environment perception unit scans the surrounding environment in real time through laser radar and millimeter wave radar to obtain environment perception data, which includes the position change deviation angle, shape change deviation angle and dynamic change deviation angle information of the obstacle; The meteorological monitoring unit monitors the weather conditions in real time by integrating a thermometer and a hygrometer and an anemometer and wind speed and direction to obtain meteorological monitoring data, which includes information on the difference between the actual wind force, wind direction, temperature and humidity changes and the model predicted changes; The GPS positioning unit obtains the GPS positioning data of the drone through a global satellite navigation system receiver, and the data includes the current position, speed and heading information of the drone; The noise monitoring unit obtains noise monitoring data through a sound level meter, a recording device and a frequency analyzer sensor. The data includes noise data generated during the flight of the drone and various noise condition information of the surrounding environment during the flight of the drone.

3. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, characterized in that: The data collection module includes an environmental perception unit, a meteorological monitoring unit, a GPS positioning unit and a noise monitoring unit. The dynamic obstacle avoidance unit calculates a collision risk index Qc based on environmental perception data. The optimal path unit calculates a total deviation value Kr of the route path based on environmental perception data, meteorological monitoring data, GPS positioning data and noise monitoring data. The adaptive speed unit calculates a deviation Us between the model and the actual flight speed based on environmental perception data and meteorological monitoring data.

4. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, wherein: The environmental perception unit numbers the position change deviation angle, shape change deviation angle and dynamic change deviation angle information of the obstacle according to the environmental perception data characteristics, and the position change deviation angle, shape change deviation angle and dynamic change deviation angle of the obstacle are numbered Y1, Y2 and Y3 respectively.

5. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, characterized in that: The meteorological monitoring unit numbers the difference information between the actual wind force, wind direction, temperature and humidity and the model predicted change according to the characteristics of the meteorological monitoring data. The actual wind force, wind direction, temperature and humidity changes and the model predicted change differences are numbered ΔV, ΔF, ΔT, and ΔW respectively.

6. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, characterized in that: The GPS positioning unit numbers the current position, speed and heading of the UAV according to the GPS positioning data characteristics of the UAV, and the current position, speed and heading of the UAV are numbered as d, j, and g respectively.

7. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 1, characterized in that: The noise monitoring unit numbers various noise condition information of the surrounding environment during the flight of the drone according to the characteristics of the noise monitoring data, and the numbers of various noise condition information of the surrounding environment during the flight of the drone are z1, Z2, Z3, … Z m .

8. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 4, characterized in that: The dynamic obstacle avoidance unit calculates the collision risk index Qc according to the environmental perception data, and its calculation formula is: Qc = a1 * Y1 + a2 * Y2 + a3 * Y3 In the formula, Qc represents the collision risk index, Y1, Y2, and Y3 respectively represent the position change deviation angle, shape change deviation angle, and dynamic change deviation angle of the obstacle, and a1, a2, and a3 respectively represent the weights corresponding to the position change deviation angle, shape change deviation angle, and dynamic change deviation angle of the obstacle in the collision risk, respectively reflecting the influence degree of the obstacle position change on the collision risk, the influence degree of the obstacle shape change on the collision risk, and the influence degree of the obstacle dynamic change on the collision risk.

9. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 7, characterized in that: The optimal path unit calculates the total deviation value Kr of the flight path according to the environmental perception data, meteorological monitoring data, GPS positioning data and noise monitoring data, and its calculation formula is: In the formula, Kr represents the total deviation value of the flight path, Y1, Y2, and Y3 respectively represent the deviation angles of the position change, shape change, and dynamic change of the obstacle, and h max represents the preset maximum deviation angle of the model, d represents the current position of the UAV, ΔV, ΔF, ΔT, and ΔW respectively represent the differences between the actual changes in wind force, wind direction, temperature, and humidity and the model-predicted changes, and b1, b2, b3, and b4 respectively represent the weights corresponding to the changes in wind force, wind direction, temperature, and humidity in the total deviation value of the flight path, that is, the influence of the changes in wind force, wind direction, temperature, and humidity under meteorological factors on the flight path, Z1, Z2, Z3, … Z m represents the information on various noise conditions in the surrounding environment during the flight of the UAV, Z i represents the information on the i-th noise condition in the surrounding environment, α i represents the weight corresponding to the information on the i-th noise condition in the surrounding environment.

10. The low-altitude intelligent obstacle avoidance route planning system based on ALOT according to claim 7, wherein: The adaptive speed unit calculates the deviation Us between the model and the actual flight speed according to the environmental perception data and meteorological monitoring data, and its calculation formula is: In the formula, Us represents the deviation between the model and the actual flight speed, j and g respectively represent the speed and heading of the UAV, ΔV, ΔF, ΔT, and ΔW respectively represent the differences between the actual wind force, wind direction, temperature and humidity changes and the model prediction changes, and c1, c2, c3, and c4 respectively represent the weights corresponding to the actual wind force, wind direction, temperature and humidity changes in the deviation between the model and the actual flight speed, that is, the influence of the changes in wind force, wind direction, temperature and humidity under meteorological factors on the flight speed of the UAV, and k represents the maximum speed threshold under meteorological factors.

Images