Forest fire fighting robot path planning method and system based on ground-air cooperation

Abstract

The invention discloses a forest fire fighting robot path planning method and system based on ground-air cooperation, and the method comprises the steps: carrying out the air scanning of a disaster area through employing an unmanned plane to carry a laser radar and infrared and visible light cameras, and obtaining the space information and fire intensity of a fire point in real time; the unmanned aerial vehicle is in communication connection with the wind power fire extinguishing robot, shares the three-dimensional point cloud model and performs environment proofreading and positioning; an improved A * algorithm is used for path planning, and a path planning mathematical model with the minimum disaster degree as the target is constructed; through fusion of a global satellite navigation system and an inertial navigation system, the working path of the wind power fire extinguishing robot is dynamically updated and planned; after a target fire point is reached, the wind power fire extinguishing robot identifies a fire source, calculates a safe fire extinguishing distance by using a flame detection model result, and dynamically adjusts an air duct angle according to a flame state to perform fire extinguishing operation. Through cooperative work between the unmanned aerial vehicle and the fire extinguishing robot, the efficiency and the intelligent degree of fire extinguishing operation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of forest fire fighting robots, and relates to a path planning method for forest fire fighting robots, in particular to a path planning method and system for forest fire fighting robots based on ground-air cooperation. Background Art

[0002] Forest fires are one of the major disasters that seriously threaten the ecological environment and the safety of human life and property. Traditional fire fighting methods mainly rely on manual fire fighting or ground mechanical equipment. However, in large-scale and complex terrain fire environments, these methods have many disadvantages such as slow response speed, low fire fighting efficiency, and limited coverage. With the rapid development of unmanned aerial vehicle (UAV) technology and robot technology, intelligent fire fighting systems based on ground-air cooperation have gradually become a research hotspot.

[0003] In the prior art, many research and technical solutions have attempted to use the cooperation between UAVs and robots for fire fighting. For example, some UAVs are equipped with sensors such as lidar and infrared cameras to detect information such as the location of fire points, the spread of fire, and the forest terrain; some fire fighting robots use sensors to obtain environmental data and plan paths to perform fire fighting tasks. However, these technologies still have some limitations. Especially in aspects such as path planning, fire point identification, prediction of fire spread, and dynamic adjustment of fire fighting strategies, true intelligent cooperation has not been achieved.

[0004] Although the prior art provides new ideas for fire fighting, there are still several technical bottlenecks. For example, existing path planning methods often ignore the dynamic changes of fire points and the speed of fire spread, resulting in non-optimal planned paths and inability to respond in real time to the changes brought about by fire spread. Although various sensors and algorithms are used for fire point identification and fire fighting operations in the prior art, they mostly rely on static judgments and do not fully consider the dynamic changes of flames and the flexibility of fire fighting strategies, which limits the improvement of fire fighting efficiency. The cooperation between robots and UAVs in most of the prior art is not perfect, lacking effective information sharing and cooperation mechanisms, resulting in the inability to efficiently complete fire fighting tasks in complex environments. Therefore, there is an urgent need for a new technical solution that can plan the optimal path in real time in a dynamically changing fire environment, accurately locate the fire source, and intelligently adjust fire fighting strategies to improve fire fighting efficiency and success rate. Summary of the Invention

[0005] The purpose of the present invention is to provide a path planning method and system for forest fire fighting robots based on ground-air cooperation, which improves the efficiency and intelligence level of fire fighting operations through the cooperation between UAVs and fire fighting robots.

[0006] The purpose of the present invention is achieved through the following technical solutions:

[0007] A path planning method for a forest fire-fighting robot based on ground-air cooperation, comprising the following steps:

[0008] Step S1: The unmanned aerial vehicle (UAV) conducts an aerial range scan of the forest disaster area by carrying a lidar, generates a three-dimensional point cloud model of the UAV, and obtains the longitude and latitude of each fire point, the size of the fire point area, and the fire intensity information in real time through an infrared camera and a visible light camera;

[0009] Step S2: The wind-powered fire-fighting robot is communicatively connected to the UAV, obtains a three-dimensional space model of the surrounding environment through the lidar, compares it with the three-dimensional point cloud model of the UAV, and locates the information of the wind-powered fire-fighting robot;

[0010] Step S3: Calculate the route length and time information for the wind-powered fire-fighting robot to reach the fire point, and construct a path planning mathematical model with the minimum disaster degree as the goal based on the above information, the size of the fire point area, and the fire spread speed;

[0011] Step S4: Through the fusion of the global satellite navigation system and the inertial navigation system, obtain the speed, position, and attitude information of the wind-powered fire-fighting robot, and dynamically update and plan the operation path of the wind-powered fire-fighting robot according to the fire point information;

[0012] Step S5: After reaching the target fire point, identify the fire source through the camera carried by the wind-powered fire-fighting robot, calculate the safe fire-fighting distance using the result of the flame detection model, and dynamically adjust the angle of the air duct according to the flame state for fire-fighting operations.

[0013] A path planning system for a forest wind-powered fire-fighting robot based on ground-air cooperation to implement the above method, comprising a ground-air communication module, an identification and positioning module, a navigation and planning module, and a detection and fire-fighting module, wherein:

[0014] The ground-air communication module is used to realize wireless communication between the ground control station, the UAV, and the wind-powered fire-fighting robot, and ensure the real-time transmission of data and the reception of instructions;

[0015] The identification and positioning module is used to identify the surrounding environment in real time through the sensors carried by the wind-powered fire-fighting robot and determine the position of the wind-powered fire-fighting robot itself;

[0016] The navigation and planning module is used to calculate and optimize the optimal path for the fire-fighting robot to reach the target fire point according to the position of the wind-powered fire-fighting robot itself and the surrounding environment information provided by the identification and positioning module, combined with the position of the target fire point and the fire spread speed parameter, through the improved A* path planning algorithm, and dynamically adjust the path according to the dynamic changes of the fire point;

[0017] The detection and fire extinguishing module is used to identify the position, shape, and flame height state of the flame in real time through the camera carried by the wind fire extinguishing and the flame detection model, and dynamically adjust the air duct angle and wind force of the wind fire extinguishing robot according to the changes of the flame to perform the fire extinguishing operation.

[0018] Compared with the prior art, the present invention has the following advantages:

[0019] (1) Based on the theories of unmanned aerial vehicle and vehicle path planning, a path planning model is constructed with dynamic fire data, multi-factor weights of the robot, and the goal of minimizing the disaster level. It can dynamically evaluate and select the optimal path to minimize the damage of the fire to the forest to the greatest extent.

[0020] (2) By adopting the improved A* algorithm, through optimizing the cost function and adjusting the heuristic weight, the calculation efficiency and accuracy of the path planning are further improved, and the optimal path can be generated more quickly to ensure the timely execution of the fire extinguishing task.

[0021] (3) The wind fire extinguishing robot dynamically adjusts the air duct angle in different fire stages by real-time monitoring the change rate of the flame height to ensure the flexibility and effectiveness of the fire extinguishing operation, improve the fire extinguishing success rate, and effectively suppress the spread of the fire. Description of the Drawings

[0022] Figure 1 is a flowchart of the path planning method for the forest wind fire extinguishing robot based on ground-air cooperation;

[0023] Figure 2 is a schematic diagram of the air duct angle adjustment strategy of the wind fire extinguishing robot;

[0024] Figure 3 is a schematic diagram of the structure of the path planning system for the forest wind fire extinguishing robot based on ground-air cooperation. Detailed Embodiments

[0025] The technical solutions of the present invention will be further described below in conjunction with the drawings, but are not limited thereto. Any modification or equivalent replacement of the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention shall be covered by the protection scope of the present invention.

[0026] The present invention provides a path planning method for a forest fire fighting robot based on ground-air cooperation. The method uses an unmanned aerial vehicle (UAV) equipped with a lidar, an infrared camera, and a visible light camera to conduct an aerial scan of the disaster area, real-time obtain the spatial information and fire intensity of the fire points, and transmit the data to the control center; the UAV is communicatively connected to the wind-powered fire fighting robot, shares the three-dimensional point cloud model, and conducts environmental calibration and positioning; the improved A* algorithm is applied for path planning, and a path planning mathematical model with the minimum disaster degree as the goal is constructed according to the distance to the fire point, time, fire point area size, and fire spread speed; through the fusion of the global satellite navigation system and the inertial navigation system, the operation path of the wind-powered fire fighting robot is dynamically updated; after reaching the target fire point, the wind-powered fire fighting robot identifies the fire source, calculates the safe fire fighting distance using the result of the flame detection model, and dynamically adjusts the angle of the air duct according to the flame state for fire fighting operations. As Figure 1 shown, the specific steps are as follows:

[0027] Step S1: The UAV conducts an aerial range scan of the forest disaster area through the lidar carried, generates a three-dimensional point cloud model of the UAV, and real-time obtains the longitude and latitude of each fire point, the fire point area size, and the fire intensity information through the infrared camera and the visible light camera. The specific steps are as follows:

[0028] Step S11: The UAV is equipped with a high-precision lidar and conducts an aerial scan of the forest disaster area according to a predetermined flight path to generate three-dimensional point cloud data of the UAV;

[0029] Step S12: Use the infrared camera to detect the temperature anomaly area and calibrate the fire point position, and combine the visible light camera to confirm the fire point characteristics;

[0030] Step S13: Real-time transmit information such as the fire point position, fire point area, and fire intensity to the control center to provide input for subsequent fire fighting planning.

[0031] Step S2: The wind-powered fire fighting robot is communicatively connected to the UAV, obtains a three-dimensional space model of the surrounding environment through the lidar, compares it with the three-dimensional point cloud model of the UAV, and locates the robot information. The specific steps are as follows:

[0032] Step S21: The wind-powered fire fighting robot starts the lidar and scans the surrounding environment multiple times to obtain multiple groups of local three-dimensional point cloud data;

[0033] Step S22: Use rigid transformation to align the local three-dimensional point cloud data obtained from different scans to obtain a unified local three-dimensional point cloud set. Downsample the local three-dimensional point cloud set to reduce the density of the point cloud and remove isolated and abnormal noise points, and establish a coordinate system with the current position of the wind-powered fire fighting robot;

[0034] Step S23: The wind fire extinguishing robot pairs each point in the current local 3D point cloud with the nearest point in the UAV 3D point cloud data according to the pre-provided UAV global point cloud model and combines it with the initial positioning of the wind fire extinguishing robot itself, calculates the rotation and translation transformation based on the matching points, and aligns the local point cloud with the global point according to the point cloud features to locate the position of the wind fire extinguishing robot itself.

[0035] Step S3: Calculate the route length and time information for the wind fire extinguishing robot to reach the fire point, and construct a path planning mathematical model with the minimum disaster degree as the goal based on the above information, the size of the fire point area, and the fire spread speed. The shortest path from position i to fire point j can be obtained through this function, and the path distance is L ij , the specific steps are as follows:

[0036] Step S31: Apply the improved A* path planning algorithm to generate the optimal path to each fire point, where:

[0037] The cost function of the improved A* path planning algorithm is as follows:

[0038] F n = G n +(H n +1) k ·H n

[0039] Among them, F n represents the estimated cost from the starting node to the current node n; G n is the actual cost from the starting node to the current node n, that is, the distance already traveled or the actual cost already paid from the starting node to the current node; H n is the heuristic estimated cost from the current node n to the target node, that is, the estimated distance from the current node to the target node; k is the weight coefficient of the heuristic function, used to adjust the influence degree of the heuristic estimated cost on the total cost; the improved A* path planning algorithm introduces the dynamic weighting function (H n +1) k , when the node is far from the target, the weight of the heuristic function can be increased, making the algorithm more dependent on H n , accelerating the search process and moving faster towards the target direction; when the node is close to the target, reduce the weight coefficient of H n , reducing the dependence on the heuristic function, preventing over-searching, and ensuring that the algorithm pays more attention to the actual path cost G n , increasing the probability of finding the optimal path;

[0040] The formula of the heuristic function H n is as follows:

[0041]

[0042] Among them, (x1, y1) is the coordinate of the current node n; (x2, y2) is the coordinate of the target node; this heuristic function H n is calculated based on the Euclidean distance, representing the straight-line distance from the current node to the target node, ensuring that the path planning can select the shortest path as much as possible;

[0043] Step S32: According to the length and time of the route for the wind fire extinguishing robot to reach the fire point, the area of the fire point, and the fire spread speed parameter, with the goal of minimizing the disaster level, construct the objective function of the wind fire extinguishing robot. This objective function, based on the length and time of the route for the wind fire extinguishing robot to reach the fire point, the area of the fire point, and the fire spread speed parameter, when there are multiple fire points, determines which fire point to extinguish first, plans the extinguishing order for multiple fire points, and realizes the minimum disaster level. Among them:

[0044] The formula of the objective function is as follows:

[0045] F min = min{F ij | i ∈ N1, j ∈ N2}

[0046] Among them, F ij is the cost value for the wind fire extinguishing robot to reach the fire point position j from the current position i, where i ∈ N1, N1 is the set of the current positions of the wind fire extinguishing robot, j ∈ N2, and N2 is the set of the target fire point positions;

[0047]

[0048] Among them, L ij is the path length for the wind fire extinguishing robot to go from position i to the fire point j; T ij is the time taken for the wind fire extinguishing robot to reach the fire point j from position i; A j is the area size of the fire point j; V j is the fire spread speed of the fire point j; ε1, ε2, ε3, ε4 are the weights of L ij , T ij , A j and V j ; λ and μ are the penalty term coefficients of the path time and the fire spread speed;

[0049] The formula for calculating the fire spread speed V j is as follows:

[0050]

[0051] Among them, A j (t1) is the area size of A j at time t1, and A j (t2) is the area size of A jThe area size.

[0052] Step S4: Through the fusion of the global satellite navigation system and the inertial navigation system, obtain the speed, position, and attitude information of the wind fire extinguishing robot, and dynamically update the planned operation path of the wind fire extinguishing robot according to the fire point information. The specific steps are as follows:

[0053] Step S41: Use the global satellite navigation system and the inertial navigation system for position, speed, and attitude fusion, and combine simultaneous localization and mapping technology to complete high-precision navigation;

[0054] Step S42: Recalculate and adjust the operation path according to the fire point data updated by the unmanned aerial vehicle in real time and the path deviation state of the wind fire extinguishing robot.

[0055] Step S5: After reaching the target fire point, identify the fire source through the camera carried by the wind fire extinguishing robot, calculate the safe fire extinguishing distance using the results of the flame detection model, and dynamically adjust the air duct angle according to the flame state for fire extinguishing operations. The specific steps are as follows:

[0056] Step S51: The wind fire extinguishing robot obtains the real-time video of the flame area through the carried camera, and uses the YOLO flame detection model to extract the flame area and the flame spatial position information, where:

[0057] The formula for calculating the flame spatial position (X, Y, Z) is as follows:

[0058]

[0059] Among them, X and Y are the horizontal and vertical offsets of the flame in the camera coordinate system; Z is the depth distance between the flame and the camera; f x and f y are the camera focal lengths; x c and y c are the pixel coordinates of the flame in the image; x i and y i are the image center coordinates; d is the depth value, that is, the actual distance of the flame;

[0060] Step S52: Based on the pixel coordinates and depth information obtained in Step S51, construct Figure 2 the air duct angle adjustment strategy shown. The wind fire extinguishing robot adjusts the angle and wind force of the fire extinguishing air duct according to different stages of the flame; when the flame height does not increase significantly or the flame begins to decrease, the air duct angle is parallel to the horizontal direction and remains close to 0°, the air duct is aimed at the top of the flame for suppression, strong wind is sprayed upward and the air duct is swung to disperse the heat; when the height of the flame continues to decrease or the fire intensity weakens, the air duct will gradually move to the bottom of the flame for fire extinguishing, the air duct angle will gradually increase from 0°, the maximum angle limit is 45°, and finally it points to the bottom of the flame for cutting to quickly extinguish the fire source;

[0061] The air duct angle adjustment strategy is as follows:

[0062]

[0063] Among them, θ ft represents the angle between the air duct and the horizontal direction at time t; Δh fire represents the change rate of the flame height, that is, the change amount of the flame height per unit time; h fire represents the flame height at time t; d1 is the horizontal distance between the air duct and the flame; α is the sensitivity coefficient, which is used to adjust the sensitivity of the air duct angle to respond to the change of the flame height.

[0064] The present invention also provides a path planning system for a forest wind fire extinguishing robot based on ground-air cooperation, as Figure 3 shown. The system includes a ground-air communication module, an identification and positioning module, a navigation and planning module, and a detection and extinguishing module, where:

[0065] The ground-air communication module is used to realize wireless communication between the ground control station, the unmanned aerial vehicle, and the wind fire extinguishing robot, and ensure real-time data transmission and instruction reception;

[0066] The identification and positioning module is used to identify the surrounding environment in real time through the sensors carried by the wind fire extinguishing robot and determine the position of the wind fire extinguishing robot itself;

[0067] The identification and positioning module includes a lidar unit and an inertial measurement unit. The lidar unit is used to scan the surrounding environment to generate three-dimensional point cloud data, and the inertial measurement unit is used to provide the attitude and motion state information of the wind fire extinguishing robot, and realize the precise positioning of the position of the wind fire extinguishing robot and the surrounding environment through a data fusion algorithm;

[0068] The navigation and planning module is used to calculate and optimize the optimal path for the wind fire extinguishing to reach the target fire point according to the position of the wind fire extinguishing itself and the surrounding environment information provided by the identification and positioning module, combined with the position of the target fire point and the fire spread speed parameter, through an improved A* path planning algorithm, and adjust the path in real time according to the dynamic change of the fire point;

[0069] The detection and extinguishing module is used to identify the position, shape, and flame height state of the flame in real time through the camera and the flame detection model carried by the wind fire extinguishing, and dynamically adjust the air duct angle and wind force of the wind fire extinguishing according to the change of the flame, and perform the fire extinguishing operation.

Claims

1. A path planning method for a forest fire-fighting robot based on ground-air cooperation, characterized in that The method includes the following steps: Step S1: The UAV conducts an aerial range scan of the forest disaster area by carrying a lidar, generates a 3D point cloud model of the UAV, and obtains the longitude and latitude, fire point area size, and fire intensity information of each fire point in real time through an infrared camera and a visible light camera; Step S2: The wind-powered fire extinguishing robot is communicatively connected to the UAV, obtains a 3D space model of the surrounding environment through the lidar, compares it with the UAV's 3D point cloud model, and locates the information of the wind-powered fire extinguishing robot; Step S3: Calculate the route length and time information for the wind-powered fire extinguishing robot to reach the fire point, and construct a path planning mathematical model with the minimum disaster level as the goal based on the above information, the fire point area size, and the fire spread speed; Step S4: Through the fusion of the global satellite navigation system and the inertial navigation system, obtain the speed, position, and attitude information of the wind-powered fire extinguishing robot, and dynamically update and plan the operation path of the wind-powered fire extinguishing robot according to the fire point information; Step S5: After reaching the target fire point, identify the fire source through the camera carried by the wind-powered fire extinguishing robot, calculate the safe fire extinguishing distance using the results of the flame detection model, and dynamically adjust the air duct angle according to the flame state for fire extinguishing operations.

2. The path planning method of the forest fire-fighting robot based on ground-air cooperation according to claim 1, wherein The specific steps of step S1 are as follows: Step S11: The UAV carries a high-precision lidar and conducts an aerial scan of the forest disaster area according to a predetermined flight path to generate 3D point cloud data of the UAV; Step S12: Use the infrared camera to detect the temperature anomaly area and calibrate the fire point position, and combine the visible light camera to confirm the fire point characteristics; Step S13: Transmit the fire point position, fire point area, and fire intensity information to the control center in real time to provide input for subsequent fire extinguishing planning.

3. The path planning method of the forest fire-fighting robot based on ground-air collaboration according to claim 1, wherein The specific steps of step S2 are as follows: Step S21: The wind-powered fire extinguishing robot starts the lidar, scans the surrounding environment multiple times, and obtains multiple groups of local 3D point cloud data; Step S22: Use rigid transformation to align the local 3D point cloud data obtained from different scans to obtain a unified local 3D point cloud set. Downsample this local 3D point cloud set to reduce the density of the point cloud and remove isolated and abnormal noise points, and establish a coordinate system with the current position of the wind-powered fire extinguishing robot; Step S23: The wind-powered fire extinguishing robot, according to the pre-provided global point cloud model of the UAV and in combination with its own preliminary positioning, pairs each point in the current local 3D point cloud set with the nearest point in the UAV's 3D point cloud data, calculates the rotation and translation transformation according to the matching points, and aligns the local point cloud with the global point in combination with the point cloud characteristics to locate the position of the wind-powered fire extinguishing robot itself.

4. The method for path planning of a forest fire-fighting robot based on ground-air cooperation according to claim 1, wherein The specific steps are as follows: Step S31: Apply the improved A* path planning algorithm to generate the optimal path to each fire point, where: The cost function of the improved A* path planning algorithm is as follows: F n = G n +(H n + 1) k · H n Among them, F n represents the estimated cost from the starting node to the current node n; G n is the actual cost from the starting node to the current node n, that is, the traveled distance or the actual cost paid from the starting node to the current node; H n is the heuristic estimated cost from the current node n to the target node, that is, the estimated distance from the current node to the target node; k is the heuristic function weight coefficient, which is used to adjust the influence degree of the heuristic estimated cost on the total cost; Step S32: According to the route length and time for the wind-powered fire extinguishing robot to reach the fire point, the fire point area, and the fire spread speed parameters, construct an objective function for the wind-powered fire extinguishing robot with the minimum disaster level as the goal, where: The objective function formula is as follows: F min = min{F ij | i ∈ N1, j ∈ N2} Among them, F ij is the cost value for the wind fire extinguishing robot to reach the fire point position j from the current position i, where i ∈ N1, N1 is the set of the current positions of the wind fire extinguishing robot, and j ∈ N2, N2 is the set of target fire point positions.

5. The path planning method of the forest fire-fighting robot based on ground-air cooperation according to claim 4, wherein The heuristic function H n has the following formula: Where, (x1,y1) is the coordinate of the current node n; (x2,y2) is the coordinate of the target node; The said F ij has the following formula: Among them, L ij is the path length of the wind fire extinguishing robot from position i to fire point j; T ij is the time taken by the wind fire extinguishing robot to reach fire point j from position i; A j is the area size of fire point j; V j is the fire spreading speed of fire point j; ε1, ε2, ε3, ε4 are the weights of L ij , T ij , A j and V j ; λ and μ are the penalty term coefficients of path time and fire spreading speed.

6. The method for path planning of a forest fire-fighting robot based on ground-air cooperation according to claim 5, wherein The fire spreading speed V j has the following calculation formula: Among them, A j (t1) is the area of A at time t1 j , and A j (t2) is the area of A at time t2 j .

7. The path planning method of the forest fire fighting robot based on ground-air cooperation according to claim 1, wherein The specific steps of step S4 are as follows: Step S41: Use the global satellite navigation system and inertial navigation system for position, speed, and attitude fusion, and combine simultaneous localization and mapping technology to complete high-precision navigation; Step S42: Recalculate and adjust the operation path according to the real-time updated fire point data of the UAV and the path deviation status of the wind-powered fire extinguishing robot.

8. The method for path planning of a forest fire-fighting robot based on ground-air cooperation according to claim 1, wherein The specific steps of step S5 are as follows: Step S51: The wind-powered fire extinguishing robot obtains real-time video of the flame area by carrying a camera, and uses the YOLO flame detection model to extract the flame area and flame spatial position information; Step S52: Based on the pixel coordinates and depth information obtained in step S51, construct a wind tunnel angle adjustment strategy. The wind-powered fire extinguishing robot adjusts the angle and wind force of the fire extinguishing wind tunnel according to different stages of the flame; when the flame height does not increase significantly or the flame begins to decrease, the wind tunnel angle is parallel to the horizontal direction and remains close to 0°, the wind tunnel is aimed at the top of the flame for suppression, strong wind is sprayed upward and the wind tunnel is swung to disperse the heat; when the height of the flame continues to decrease or the fire intensity weakens, the wind tunnel will gradually move to the bottom of the flame for fire extinguishing, the wind tunnel angle will gradually increase from 0°, the maximum angle limit is 45°, and finally it points to the bottom of the flame for cutting to quickly extinguish the fire source.

9. The path planning method of the forest fire-fighting robot based on ground-air cooperation according to claim 8, wherein The calculation formula for the flame spatial position (X, Y, Z) is as follows: Among them, X and Y are the horizontal and vertical offsets of the flame in the camera coordinate system; Z is the depth distance between the flame and the camera; f x and f y are the camera focal lengths; x c and y c are the pixel coordinates of the flame in the image; x i and y i are the image center coordinates; d is the depth value, that is, the actual distance of the flame; The wind tunnel angle adjustment strategy is as follows: Among them, θ ft represents the angle between the air duct and the horizontal direction at time t; Δh fire represents the change rate of the flame height, that is, the change amount of the flame height per unit time; h fire represents the flame height at time t; d1 is the horizontal distance between the air duct and the flame; α is the sensitivity coefficient, which is used to adjust the sensitivity of the air duct angle to respond to the change of the flame height.

10. A path planning system for a forest wind fire extinguishing robot based on ground-air cooperation for implementing the method according to any one of claims 1-9, characterized in that The system includes a ground-air communication module, an identification and positioning module, a navigation and planning module, and a detection and fire extinguishing module, where: The ground-air communication module is used to realize wireless communication between the ground control station and the UAV and the wind-powered fire extinguishing robot, and ensure the real-time transmission of data and the reception of instructions; The identification and positioning module is used to identify the surrounding environment in real time through the sensors carried by the wind-powered fire extinguishing robot and determine the position of the wind-powered fire extinguishing robot itself; The navigation and planning module is used to calculate and optimize the optimal path for the fire extinguishing robot to reach the target fire point according to the position of the wind-powered fire itself and the surrounding environment information provided by the identification and positioning module, combined with the target fire point position and the fire spread speed parameter, and adjust the path in real time according to the dynamic changes of the fire point; The detection and fire extinguishing module is used to identify the position, shape, and flame height status of the flame in real time through the camera and flame detection model carried by the wind-powered fire extinguishing, and dynamically adjust the angle and wind force of the wind tunnel of the wind-powered fire extinguishing robot according to the changes of the flame to perform fire extinguishing operations.

Images