Unmanned aerial vehicle adaptive path planning system and method based on information fusion and cooperation

Abstract

The invention discloses an unmanned aerial vehicle adaptive path planning system and method based on information fusion and collaboration, and the system comprises an environment sensing module which is used for collecting the landform, obstacle and threat information of a mining area in real time, and constructing a three-dimensional digital elevation model; the global path planning module is used for generating an initial global path by adopting an improved Theta * algorithm, and optimizing a path turning point through a father node relink; the dynamic obstacle avoidance module is used for generating a local obstacle avoidance path by combining real-time obstacle information with a speed sampling range constrained by an unmanned aerial vehicle kinetic model based on an improved DWA algorithm; the autonomous decision module is used for dynamically adjusting the man-machine authority level based on fuzzy reasoning and switching a planning mode; the execution module is used for realizing trajectory tracking through motor rotating speed control and outputting a rotating speed change curve of each motor and unmanned aerial vehicle state parameters; and the data fusion module is used for synchronizing the remote sensing data and the path planning result to the cloud and supporting multi-machine collaboration and historical data backtracking.

Description

Technical Field

[0001] The present invention belongs to the interdisciplinary technical field of unmanned aerial vehicle (UAV) technology, intelligent path planning and mining engineering, and specifically relates to an adaptive UAV path planning system and method based on information fusion and collaboration. Background Art

[0002] 1. Application of drones in mining, etc.: Currently, drones are mainly used in the mining industry for open-pit mine reserve monitoring and tailings pond safety assessment. However, traditional methods rely on satellites or manual measurements, which have problems such as poor timeliness, high costs, and difficulty in covering dangerous areas (Wang Kun, Yang Peng, Lv Wensheng, et al. Application status and development trend of drone remote sensing in the mining field. Journal of Engineering Science, 2020, 42(9): 1085-1095). In addition, sensors and algorithms are not optimized for special environments such as high dust and strong electromagnetic interference in mining areas, resulting in low data accuracy.

[0003] 2. Path planning algorithms: Existing algorithms (such as A* and RRT) are mostly targeted at static environments. However, in reality, the environment is complex and changing (such as mine collapse, equipment movement, and collapsed buildings in disaster-stricken areas). These algorithms cannot respond to the environment in real time and avoid obstacles. (Lin Siwei, Xi Wanqiang, Li Qingyun, et al. Three-dimensional path planning for UAVs in complex environments. Electro-Optics and Control, 2023, 30(2):31-35)

[0004] 3. Autonomy control: The traditional OODA loop (observe-judgment-decision-execution) faces a "trust crisis" in complex threat environments. Human-machine permissions are fixed and the autonomy level cannot be dynamically adjusted. (Liu Chang, Xie Wenjun, Zhang Peng, et al. Logical architecture of real-time route planning for UAVs in complex threat environments. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(10):1948-1957)

[0005] 4. Real-time human-machine collaboration: Existing systems find it difficult to dynamically adjust the level of autonomy, or decision-making methods, in complex environments. When the environment is complex and difficult for human-machine communication or the operator's operational response is delayed, drones are required to make dynamic autonomous decisions.

[0006] 5. Environmental perception: Traditional remote sensing data has a low update frequency and cannot support real-time path correction.

[0007] The paper "A Logical Architecture for Real-Time Route Planning of UAVs in Complex Threat Environments" proposes a variable autonomous architecture, but fails to incorporate slope constraints, making it inadequate for the steep terrain of mining areas. The paper "Three-Dimensional Path Planning of UAVs in Complex Environments" integrates the A* and DWA algorithms, but its global path fails to optimize redundant nodes and lacks a dynamic permission allocation mechanism, resulting in insufficient path efficiency and flexibility in human-machine collaboration. Therefore, a comprehensive solution that integrates global planning, dynamic obstacle avoidance, autonomous decision-making, and real-time environmental awareness is urgently needed and can be applied to complex environments such as the mining industry. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this paper proposes an adaptive path planning system and method for unmanned aerial vehicles (UAVs) based on information fusion and collaboration. This system aims to integrate the global planning of the Theta* algorithm with improved dynamic obstacle avoidance (DWA) to generate a smooth path that conforms to the UAV's dynamics, enabling real-time obstacle avoidance and efficient path planning in complex environments such as mining areas. Based on a fuzzy inference mechanism, the system dynamically adjusts human-machine permissions, i.e., the UAV's autonomy level, to achieve multi-mode switching between "autonomous planning, human-machine collaboration, and manual intervention," balancing the efficiency and safety of human-machine collaboration. Sensor configuration and data processing procedures are optimized to improve the accuracy and reliability of mining monitoring. Environmental models are updated in real time using UAV remote sensing data to enhance adaptability to complex dynamic scenarios.

[0009] To achieve the above object, the present invention provides the following solutions:

[0010] An adaptive path planning system for unmanned aerial vehicles (UAVs) based on information fusion and collaboration, comprising: an environmental perception module, a global path planning module, a dynamic obstacle avoidance module, an autonomous decision-making module, an execution module, and a data fusion module;

[0011] The environmental perception module is used to collect real-time information about the mining area's terrain, obstacles, and threats, and to construct a three-dimensional digital elevation model;

[0012] The global path planning module is used to generate an initial global path based on the three-dimensional digital elevation model using an improved Theta* algorithm, and optimize path turning points by relinking parent nodes;

[0013] The dynamic obstacle avoidance module is used to generate a local obstacle avoidance path based on the improved DWA algorithm, the speed sampling range constrained by the UAV dynamics model, and the real-time obstacle information;

[0014] The autonomous decision-making module is used to dynamically adjust the human-machine authority level based on fuzzy reasoning and switch the planning mode;

[0015] The execution module is used to achieve trajectory tracking through motor speed control and output the speed change curve of each motor and the state parameters of the drone;

[0016] The data fusion module is used to synchronize remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

[0017] Preferably, the global path planning module uses an improved Theta* algorithm to generate an initial global path and optimizes path turning points by relinking parent nodes, including:

[0018] After the Theta* algorithm generates the initial path, it performs visibility checks on adjacent nodes. If there are no obstacles between the current node and the parent node of the parent node, the intermediate nodes are skipped directly to generate a smooth global path.

[0019] Preferably, the dynamic obstacle avoidance module generates a local obstacle avoidance path based on an improved DWA algorithm, constraining the speed sampling range with the UAV dynamics model, and combining real-time obstacle information, including:

[0020]

[0021] Slope_Penalty=k·tan(θ max -θ current )

[0022] Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowed climb angle of the drone, θcurrent is the current slope angle, k is the penalty coefficient, k r =1.45×10 -6 , k r is the lift line coefficient of the blade, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, and U1 is the control input of the system;

[0023] The evaluation function of the DWA algorithm includes a terrain slope penalty term, whose weight coefficient is dynamically adjusted according to the terrain characteristics of the mining area, including:

[0024] G=α·e+β·d+γ·v+δ·Slope_Penalty

[0025] e=180°-|θ target -θ current |

[0026] d = min (obstacle distance)

[0027]

[0028] Among them, e is the heading angle evaluation value, d is the obstacle avoidance distance evaluation value, v is the current speed evaluation value, v x , vy , v z are the three-axis speed components, α, β, γ, and δ are the corresponding weights, and Slope_Penalty is the slope penalty term to prevent the drone from becoming unstable in steep slopes.

[0029] Preferably, the autonomous decision-making module, the fuzzy reasoning rules include 45 If-Then rules, the input variables are the threat level CTS, the task urgency TI, and the operator status OS, and the output is the autonomy level ALUS.

[0030] The present invention also provides a method for adaptive path planning of a UAV based on information fusion and collaboration, which is implemented by applying the aforementioned adaptive path planning system of a UAV based on information fusion and collaboration. The method comprises the following steps:

[0031] Collect mining area terrain, obstacles and threat information in real time to build a 3D digital elevation model;

[0032] Based on the three-dimensional digital elevation model, an improved Theta* algorithm is used to generate an initial global path, and the path turning points are optimized by relinking the parent nodes;

[0033] Based on the improved DWA algorithm, the speed sampling range is constrained by the UAV dynamics model, and a local obstacle avoidance path is generated in combination with real-time obstacle information.

[0034] Dynamically adjust human-machine authority levels based on fuzzy reasoning and switch planning modes;

[0035] The trajectory tracking is achieved through motor speed control, and the speed change curve of each motor and the state parameters of the UAV are output;

[0036] Synchronize remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

[0037] Preferably, an improved Theta* algorithm is used to generate an initial global path, and the path turning points are optimized by relinking the parent nodes, including:

[0038] After the Theta* algorithm generates the initial path, it performs visibility checks on adjacent nodes. If there are no obstacles between the current node and the parent node of the parent node, the intermediate nodes are skipped directly to generate a smooth global path.

[0039] Preferably, based on the improved DWA algorithm, the speed sampling range is constrained by the UAV dynamics model, and a local obstacle avoidance path is generated in combination with real-time obstacle information, including:

[0040]

[0041] Slope_Penalty=k·tan(θ max-θ current )

[0042] Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowed climb angle of the drone, θcurrent is the current slope angle, k is the penalty coefficient, k r =1.45×10 -6 , k r is the lift line coefficient of the blade, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, and U1 is the control input of the system;

[0043] The evaluation function of the DWA algorithm includes a terrain slope penalty term, whose weight coefficient is dynamically adjusted according to the terrain characteristics of the mining area, including:

[0044] G=αe+β·d+γ·v+δ·Slope_Penalty

[0045] e=180°-|θ target -θ current |

[0046] d = min (obstacle distance)

[0047]

[0048] Among them, e is the heading angle evaluation value, d is the obstacle avoidance distance evaluation value, v is the current speed evaluation value, v x , v y , v z are the three-axis speed components, α, β, γ, and δ are the corresponding weights, and Slope_Penalty is the slope penalty term to prevent the drone from becoming unstable in steep slopes.

[0049] Preferably, the fuzzy reasoning rules include 45 If-Then rules, the input variables are the threat level CTS, the task urgency TI, and the operator state OS, and the output is the autonomy level ALUS.

[0050] The present invention also provides an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program run by the processor, and when the computer program is run by the processor, it executes any one of the methods for adaptive path planning of unmanned aerial vehicles based on information fusion and collaboration.

[0051] The present invention also provides a storage medium having a computer program stored thereon, and the computer program, when running, executes any one of the methods for adaptive path planning of unmanned aerial vehicles based on information fusion and collaboration.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] This invention combines a three-dimensional drone path planning method with a dynamic autonomous decision-making method and applies it to complex environments such as the mining industry. This allows drones to avoid obstacles more efficiently and safely, even in complex and changing environments like the mining industry. The method also synchronizes the drone's decision-making process with real-time environmental changes, improving emergency response speed and enabling more effective path optimization. This invention integrates existing methods and applies them to complex and changing environments like the mining industry, while also taking into account dynamic principles. This improves velocity smoothness, avoids the risk of attitude loss, and enhances adaptability to different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A schematic diagram of an adaptive path planning system for unmanned aerial vehicles based on information fusion and collaboration provided by an embodiment of the present invention;

[0056] Figure 2 A schematic diagram of the obstacle avoidance process provided by an embodiment of the present invention;

[0057] Figure 3 A flowchart of a method for adaptive path planning of a UAV based on information fusion and collaboration provided by an embodiment of the present invention;

[0058] Figure 4 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention.

[0059] Description of the drawings: 101—EEG signal acquisition device, 102—biofeedback adjustment module, 103—Bluetooth communication module, 104—intelligent sleep aid device, 1010—processor; 1020—memory; 1030—input / output interface; 1040—communication interface; 1050—bus. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0062] The present invention mainly adaptively combines the optimized three-dimensional path planning of drones with dynamic autonomous decision-making and applies them to complex mining environments. The present invention belongs to the intersection of drone technology, intelligent path planning and mining engineering, and specifically relates to a drone system based on multi-algorithm fusion and dynamic autonomous adjustment, which is used for high-precision remote sensing data acquisition, safety monitoring and emergency rescue tasks in complex environments such as mining (such as open-pit mines, tailings ponds, steep slopes, collapsed houses in disaster-stricken areas, etc.).

[0063] Example 1

[0064] like Figure 1 As shown, an embodiment of the present invention provides a UAV adaptive path planning system based on information fusion and collaboration, including: an environment perception module, a global path planning module, a dynamic obstacle avoidance module, an autonomous decision-making module, an execution module, and a data fusion module;

[0065] Environmental perception module:

[0066] (1) Hardware configuration: multispectral camera (band 400-1000nm, used to identify geological features of mining areas), 16-line laser radar (detection distance 100m, accuracy ±3cm, real-time generation of 3D point cloud data) and RTK positioning system (accuracy ±2cm, used for centimeter-level positioning) and dust concentration sensor (range 0-1000μg / m 3 ) to collect information on mining terrain, obstacles and threats in real time.

[0067] (2) Data preprocessing process:

[0068] Multispectral data fusion: Kalman filtering is used to reduce the noise of multispectral images (process noise Q = 0.01, observation noise R = 0.1), and the thermal infrared anomaly area (temperature threshold set at ±5°C) is extracted to output a three-dimensional DEM model.

[0069] Global path planning module (improved Theta* algorithm): uses the improved Theta* algorithm to generate the initial global path and optimizes the path turning points by relinking the parent nodes. The specific implementation is as follows: after the Theta* algorithm generates the initial path, the visibility of the adjacent nodes is detected. If there is no obstacle between the current node and the parent node of the parent node, the intermediate nodes are directly skipped to generate a smoother global path and reduce redundant nodes.

[0070] Specifically: 1. Initialize the grid map: divide the mining environment into a 1m×1m×1m cube grid, with obstacles marked as 1 and free space as 0.

[0071] 2. Path node generation:

[0072] The Theta* algorithm is used to generate the initial path. That is, the nodes on the initial path are selected from the nodes with the smallest cost evaluation among the adjacent nodes. The specific formula is:

[0073] f(n)=g(n)+h(n)+λ·Slope_cost(n)

[0074] Where f(n) is the cost evaluation for the current n nodes, g(n) is the actual cost (Euclidean distance) from the starting point to the current node n, h(n) is the heuristic cost (Manhattan distance) from the current node n to the end point; λ is the penalty coefficient, which is adjusted according to the actual terrain conditions.

[0075] (x n ,y n ,z n ) are the components of the node on the three axes of the coordinate system. When the slope exceeds 25°, λ = 10 (penalty coefficient).

[0076] 3. Parent node relink optimization:

[0077] For the path node sequence P = {p1, p2, ..., p n}, check p point by point i With p i+2 Is it visible (ray detection method). If visible, delete p i+1 , directly connect p i With p i+2 , reduce redundant nodes. Finally, output the optimized global path key node sequence P optimized ={(x1,y1,z1), (x2,y2,z2),…}.

[0078] Dynamic obstacle avoidance module: Based on the improved DWA algorithm, the velocity sampling range is constrained by the UAV dynamics model (the quadrotor dynamics equation is as follows), and a local obstacle avoidance path is generated in combination with real-time obstacle information. This is to improve the evaluation function in the DWA algorithm by adding a penalty term (Slope_Penalty). Its calculation formula is as follows:

[0079]

[0080] Slope_Penalty=k·tan(θ max -θ current )

[0081] Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowable climb angle of the drone (25°), and θcurrent is the current

[0082] Front slope angle, k is the penalty coefficient (set to 0.5), k r =1.45×10 -6 , k r is the lift line coefficient of the blade, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, g is the acceleration of gravity, and U i (i=1.2.3.4) is the control input of the system;

[0083] When the slope exceeds the safety threshold, the penalty term increases significantly, forcing the algorithm to choose a flatter path.

[0084] Motor speed range: 7000r / min; sampling interval 0.5s.

[0085] Improve the evaluation function of the DWA algorithm, add the steep slope constraint of the mining area terrain and the obstacle risk weight, the formula is as follows:

[0086] G=α·e+β·d+γ·v+δ·Slope_Penaltye=180°-|θ target -θ current |

[0087] d = min (obstacle distance)

[0088]

[0089] Among them, e is the heading angle evaluation value, d is the obstacle avoidance distance evaluation value (safety distance threshold 5m), v is the current speed evaluation value (v x , v y , v z are the three-axis speed components respectively), α, β, γ, and δ are the corresponding weights, and Slope_Penalty is the slope penalty term to prevent the drone from becoming unstable in steep slopes.

[0090] Obstacle avoidance process:

[0091] The global path key nodes are used as sub-goals, and the local path is updated every 0.5 seconds. The spiral diffusion strategy is used to search for obstacles. With the current position of the drone as the center, the obstacles are detected layer by layer with a radius of r = 5m (each layer is 1m apart). If an obstacle is detected entering the safety buffer zone, the DWA is triggered to resample the speed window and generate a local obstacle avoidance path (as shown below). Figure 2), the specific method of DWA resampling speed is to first set the UAV position as the starting point, the speed, three-axis angle, and three-axis angular velocity are all 0, then set the first target node as the target point, and sample the motor speed range, and then according to the quadrotor dynamics model and the w before adjustment i (i=1,2,3,4) calculate the new U i (i=1,2,3,4) and three-axis acceleration, three-axis angular acceleration, and then calculate the UAV position, speed, angle, and angular acceleration based on the sampling time dt and acceleration, and substitute them into the evaluation function to obtain a. Then check whether the motor speed range has been traversed. If not, continue to sample the motor speed range and repeat the above steps. If the traversal is completed, take the maximum G value and obtain the corresponding UAV state quantity, and judge whether it has reached the target point. If not, continue to repeat the motor speed range sampling. If it has reached the target point, end.

[0092] Autonomous decision-making module (dynamic authority allocation):

[0093] Fuzzification of input variables:

[0094] Environmental Threat Level (CTS): It is divided into low (03), medium (25), and high (48) according to the obstacle density and movement speed, and the membership function is a trapezoidal distribution.

[0095] Task urgency (TI): divided into low (02), medium (14), and high (36).

[0096] Operator status (OS): categorized according to fatigue level (01, 0 is optimal) as low (0.03), medium (0.20), and high (0.51).

[0097] Fuzzy Inference Rule Base: 45 self-constructed rules (e.g., "If CTS is high, TI is high, and OS is poor, then the autonomy level is high"). Rule 1: If CTS = high, TI = high, and OS = low, then the autonomy level is high (fully autonomous mode). Rule 2: If CTS = medium, TI = low, and OS = high, then the autonomy level is low (human-computer interaction mode).

[0098] Defuzzification: Using the center of gravity method, the corresponding permission mode (fully manual, operator-assisted, operator-confirmed, fully autonomous) for each autonomy level (L, M, H) is output. If the autonomy level is H, the drone will automatically replan its global path; if the autonomy level is M, the operator must confirm the local path (if there is no response after 5 seconds, the drone will automatically switch to H mode).

[0099] Execution module: realizes trajectory tracking through motor speed control, outputs the speed change curve of each motor and the drone status parameters (position, speed, attitude angle).

[0100] Motor control logic:

[0101] According to the speed command output by DWA (v x , v y , v z ) Adjust the motor speed through the PID controller:

[0102]

[0103] Among them, w i (i=1,2,3,4) respectively correspond to the speeds of the four motors after adjustment. i (i=1.2.3.4) is the control input of the system.

[0104] The relationship between the quadrotor control input and the motor speed is as follows:

[0105]

[0106] l is the distance from the center of the blade to the center of mass of the quadrotor, k r is the blade lift line coefficient, k M is the blade torque coefficient,

[0107] w i (i=1, 2, 3, 4) respectively correspond to the rotational speeds of the four motors before adjustment.

[0108] Data fusion module: Synchronizes remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

[0109] In summary, the present invention 1. Multi-algorithm fusion: Theta* global planning is combined with DWA local obstacle avoidance and adaptively applied to mining scenarios, taking into account efficiency and dynamic constraints. At the same time, the slope penalty term is introduced in the DWA algorithm to reduce the average slope of the path. 2. Dynamic authority allocation: A dynamic autonomous level adjustment mechanism based on fuzzy reasoning realizes human-machine adaptive collaboration and shortens response time. 3. Real-time environment update: Dynamically corrects the path planning model through drone remote sensing data to improve adaptability to complex environments. 4. Mining scenario optimization: Emergency mechanism: In the event of a sudden landslide, the drone automatically switches to autonomous mode, and the drone generates an escape path within 2 seconds based on historical point cloud data (stored in the last 10 minutes). Sensor fusion: Combined with thermal infrared cameras to monitor tailings pond leakage, multispectral sensors to evaluate vegetation reclamation effects, and the data is denoised by Kalman filtering. Safety buffer: Generate a three-dimensional buffer zone (such as a radius of 5m) around obstacles to improve path safety.

[0110] Example 2

[0111] like Figure 3As shown, the present invention also provides a method for adaptive path planning of a UAV based on information fusion and collaboration, which is implemented by applying the aforementioned adaptive path planning system of a UAV based on information fusion and collaboration. The method includes the following steps:

[0112] Collect mining area terrain, obstacles and threat information in real time to build a 3D digital elevation model;

[0113] Based on the three-dimensional digital elevation model, an improved Theta* algorithm is used to generate an initial global path, and the path turning points are optimized by relinking the parent nodes;

[0114] Based on the improved DWA algorithm, the speed sampling range is constrained by the UAV dynamics model, and a local obstacle avoidance path is generated in combination with real-time obstacle information.

[0115] Dynamically adjust human-machine authority levels based on fuzzy reasoning and switch planning modes;

[0116] The trajectory tracking is achieved through motor speed control, and the speed change curve of each motor and the state parameters of the UAV are output;

[0117] Synchronize remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

[0118] In this embodiment, an improved Theta* algorithm is used to generate an initial global path, and the path turning points are optimized by relinking the parent nodes, including:

[0119] After the Theta* algorithm generates the initial path, it performs visibility checks on adjacent nodes. If there are no obstacles between the current node and the parent node of the parent node, the intermediate nodes are skipped directly to generate a smooth global path.

[0120] In this embodiment, based on the improved DWA algorithm, the velocity sampling range is constrained by the UAV dynamics model and combined with real-time obstacle information to generate a local obstacle avoidance path, including:

[0121]

[0122] Slope_Penalty=k·tan(θ max -θ current )

[0123] Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowed climb angle of the drone (25°), θcurrent is the current slope angle, and k is the penalty coefficient (set to 0.5). k r =1.45×10 -6, k r is the blade lift line coefficient, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, and U1 is the control input of the system. When the slope exceeds the safety threshold, the penalty term increases significantly, forcing the algorithm to choose a smoother path.

[0124] In this embodiment, the fuzzy inference rules include 45 If-Then rules, the input variables are the threat level CTS, the task urgency TI, and the operator status OS, and the output is the autonomy level ALUS.

[0125] Specific method flow:

[0126] 1. Initialization: Load the mining area DEM map, set the starting point, end point and task constraints.

[0127] 2. Global Planning: The Theta* algorithm generates a global path and outputs a sequence of key nodes. The generated sequence of key nodes on the initial path serves as the sub-goal input of the dynamic obstacle avoidance module.

[0128] 3. Real-time obstacle avoidance:

[0129] The improved DWA algorithm uses key nodes as sub-goals to dynamically adjust speed and heading. Obstacle search employs a spiral diffusion strategy, prioritizing nearby and same-layer obstacles. The local obstacle avoidance path is updated every 0.5 seconds. If an obstacle is detected entering the safety buffer zone (5m radius), the improved DWA algorithm is triggered to resample the speed window and generate a local path incorporating a slope penalty.

[0130] 4. Autonomous decision-making:

[0131] The system assesses the threat level (CTS), mission urgency (TI), and operator status (OS) every 10 seconds, updating the authorization level in real time through fuzzy reasoning. If authorization level is H, fully autonomous mode is enabled, and the global path planning module immediately triggers replanning based on the latest DEM data; if it drops to M, the operator is requested to confirm the path correction points.

[0132] 5. Data update: Use drone remote sensing to correct the DEM model in real time and trigger global path replanning.

[0133] In summary, the present invention has achieved the following progress:

[0134] 1. Multi-algorithm fusion: Improved Theta* global planning and improved DWA local obstacle avoidance are combined and adaptively applied to mining scenarios, taking into account both efficiency and dynamic constraints.

[0135] 2. Dynamic authority allocation: A dynamic autonomous level adjustment mechanism based on fuzzy reasoning enables adaptive human-machine collaboration.

[0136] 3. Real-time environmental updates: Dynamically modify the path planning model through drone remote sensing data to improve adaptability to complex environments.

[0137] 4. Multi-sensor data fusion and the design of a mining-specific safety buffer zone can make mining operations safer and more accurate.

[0138] Example 3

[0139] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, it implements the drone adaptive path planning method based on information fusion and collaboration described in any of the above embodiments.

[0140] Figure 4 10 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0141] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0142] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0143] The input / output interface 1030 is used to connect input / output modules to implement information input and output. The input / output modules can be configured as components within the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0144] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (e.g., USB (Universal Serial Bus), network cable, etc.) or a wireless method (e.g., mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0145] The bus 1050 comprises a path for transmitting information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0146] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0147] The system of the above embodiment is used to implement the corresponding UAV adaptive path planning method based on information fusion and collaboration in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0148] Example 4

[0149] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the drone adaptive path planning method based on information fusion and collaboration as described in any of the above embodiments.

[0150] The computer-readable media of this embodiment include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules 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 technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0151] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the UAV adaptive path planning method based on information fusion and collaboration as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0152] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples. Within the scope of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0153] In addition, to simplify the description and discussion, and in order not to obscure the embodiments of the present invention, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, devices may be shown in the form of block diagrams to avoid obscuring the embodiments of the present invention, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention will be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0154] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the embodiments discussed.

[0155] Therefore, the units of each example described in the embodiments of this application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0156] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. An adaptive path planning system for unmanned aerial vehicles based on information fusion and collaboration, characterized in that: include: Environmental perception module, global path planning module, dynamic obstacle avoidance module, autonomous decision-making module, execution module and data fusion module; The environmental perception module is used to collect real-time information about the mining area's terrain, obstacles, and threats, and to construct a three-dimensional digital elevation model; The global path planning module is used to generate an initial global path based on the three-dimensional digital elevation model using an improved Theta* algorithm, and optimize path turning points by relinking parent nodes; The dynamic obstacle avoidance module is used to generate a local obstacle avoidance path based on the improved DWA algorithm, the speed sampling range constrained by the UAV dynamics model, and the real-time obstacle information; The autonomous decision-making module is used to dynamically adjust the human-machine authority level based on fuzzy reasoning and switch the planning mode; The execution module is used to achieve trajectory tracking through motor speed control and output the speed change curve of each motor and the state parameters of the drone; The data fusion module is used to synchronize remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

2. The UAV adaptive path planning system based on information fusion and collaboration according to claim 1 is characterized in that: The global path planning module uses an improved Theta* algorithm to generate an initial global path and optimizes path turning points by relinking parent nodes, including: After the Theta* algorithm generates the initial path, it performs visibility checks on adjacent nodes. If there are no obstacles between the current node and the parent node of the parent node, the intermediate nodes are skipped directly to generate a smooth global path.

3. The UAV adaptive path planning system based on information fusion and collaboration according to claim 1 is characterized in that: The dynamic obstacle avoidance module, based on the improved DWA algorithm, constrains the speed sampling range using the UAV dynamics model and combines real-time obstacle information to generate a local obstacle avoidance path, including: Slope_Penalty=k·tan(θ max -θ current ) Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowed climb angle of the drone, θcurrent is the current slope angle, k is the penalty coefficient, k r =1.45×10 -6 , k r is the lift line coefficient of the blade, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, and U1 is the control input of the system; The evaluation function of the DWA algorithm includes a terrain slope penalty term, whose weight coefficient is dynamically adjusted according to the terrain characteristics of the mining area, including: G=α·e+β·d+γ·v+δ·Slope_Penalty e=180°-|θ target -θ current | d = min (obstacle distance) Among them, e is the heading angle evaluation value, d is the obstacle avoidance distance evaluation value, v is the current speed evaluation value, v x , v y , v z are the three-axis speed components, α, β, γ, and δ are the corresponding weights, and Slope_Penalty is the slope penalty term to prevent the drone from becoming unstable in steep slopes.

4. The UAV adaptive path planning system based on information fusion and collaboration according to claim 1 is characterized in that: The autonomous decision-making module, the fuzzy reasoning rules include 45 If-Then rules, the input variables are threat level CTS, task urgency TI, operator status OS, and the output is the autonomy level ALUS.

5. A method for adaptive path planning of unmanned aerial vehicles based on information fusion and collaboration, characterized in that: The method is implemented by using the information fusion and collaboration-based UAV adaptive path planning system according to any one of claims 1 to 4, and the method comprises the following steps: Collect mining area terrain, obstacles and threat information in real time to build a 3D digital elevation model; Based on the three-dimensional digital elevation model, an improved Theta* algorithm is used to generate an initial global path, and the path turning points are optimized by relinking the parent nodes; Based on the improved DWA algorithm, the speed sampling range is constrained by the UAV dynamics model, and a local obstacle avoidance path is generated in combination with real-time obstacle information. Dynamically adjust human-machine authority levels based on fuzzy reasoning and switch planning modes; The trajectory tracking is achieved through motor speed control, and the speed change curve of each motor and the state parameters of the UAV are output; Synchronize remote sensing data and path planning results to the cloud, supporting multi-machine collaboration and historical data backtracking.

6. The method for adaptive path planning of unmanned aerial vehicle based on information fusion and collaboration according to claim 5, characterized in that: An improved Theta* algorithm is used to generate an initial global path and optimize path turning points by relinking parent nodes, including: After the Theta* algorithm generates the initial path, it performs visibility checks on adjacent nodes. If there are no obstacles between the current node and the parent node of the parent node, the intermediate nodes are skipped directly to generate a smooth global path.

7. The method for adaptive path planning of unmanned aerial vehicle based on information fusion and collaboration according to claim 5, characterized in that: Based on the improved DWA algorithm, the velocity sampling range is constrained by the UAV dynamics model and combined with real-time obstacle information to generate a local obstacle avoidance path, including: Slope_Penalty=k·tan(θ max -θ current ) Among them, x, y, and z are the components of the three axes of the world coordinate system; θ represents the pitch angle, φ represents the roll angle, represents the yaw angle, θmax is the maximum allowed climb angle of the drone, θcurrent is the current slope angle, k is the penalty coefficient, k r =1.45×10 -6 , k r is the lift line coefficient of the blade, w1, w2, w3, and w4 correspond to the speeds of the four motors before adjustment, m is the mass of the quadrotor, and U1 is the control input of the system; The evaluation function of the DWA algorithm includes a terrain slope penalty term, whose weight coefficient is dynamically adjusted according to the terrain characteristics of the mining area, including: G=α·e+β·d+γ·v+δ·Slope_Penalty e=180°-|θ target -θ current | d = min (obstacle distance) Among them, e is the heading angle evaluation value, d is the obstacle avoidance distance evaluation value, v is the current speed evaluation value, v x , v y , v z are the three-axis speed components, α, β, γ, and δ are the corresponding weights, and Slope_Penalty is the slope penalty term to prevent the drone from becoming unstable in steep slopes.

8. The method for adaptive path planning of unmanned aerial vehicle based on information fusion and collaboration according to claim 5, characterized in that: The fuzzy inference rules include 45 If-Then rules, with the input variables being the threat level CTS, the mission urgency TI, and the operator status OS, and the output being the autonomy level ALUS.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the computer program executes the adaptive path planning method for unmanned aerial vehicle based on information fusion and collaboration as described in any one of claims 1 to 4.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the method for adaptive path planning of a UAV based on information fusion and collaboration as described in any one of claims 1 to 4.

Images