Research On Random Coverage Path Planning Of Unmanned Aerial Vehicles For Forest Fire Monitoring Efficiently

China has the advantage of wide land.However,their forest resources are scarce.Thousands of forest fires occur every year,which poses a great threat to China’s ecological diversity.Forest fire monitoring is important to stop the development of forest fires in the early stages of forest fire development.UAVs are widely used for autonomous forest fire monitoring due to their advantages of fast mobility,low cost,and simple operation.The occurrence time and location of forest fires insurance are random absolutely.Therefore,this paper conducts research on random full coverage path planning for efficient monitoring of forest fire insurance by UAV.Firstly,this paper replaces the resistors R and diodes in the traditional Chua circuit with memristor and linear elements,constructs a memristive Chua system,and analyzes its Lyapunov exponent and bifurcation diagram.Under the same parameters,the maximum Lyapunov exponent of the memristor-Chua system system is bigger than the Chua system,so it has stronger chaos characteristics.Then,the memristive infinite coexistence attractor Chua system is constructed.By analyzing the phase diagram,power spectrum,and initial value sensitivity characteristics of the multiple attraction subsystems.It can be obtained that an infinite number of coexistence attraction subsystems have better random characteristics.The memristor-Chua system and the infinite coexistence attractor memristor-Chua system lay the foundation for the research of random full coverage path planning for drones.Secondly,a random full-coverage path planner for UAVs is constructed using the memristor-Chua system and the infinite coexistence attractor memristor-Chua system to generate chaotic random coverage paths.Due to the complexity of the environment in the forest area and the numerous obstacles,the mirror mapping method is used to constrain the drone path within the monitoring unit,design the random full coverage path of the UAV,and the obtained drone track can achieve obstacle avoidance.Using the Mount Tai forest area as a monitoring area to simulate and analyze the coverage and uniformity of the drone track points,the results show that the random coverage path of the drone based on the infinite coexistence attractor memristor-Chua system can satisfy the drone The requirements of track point coverage and uniformity,compared with UAV reciprocating coverage path planning and random walk coverage path planning,the random full coverage path planning algorithm proposed in this paper is more efficient in monitoring forest fires.Thirdly,taking the Mount Tai forest area as an example,in view of the season when forest fires are not prone to occur,the forest area is man-made,and the terrain and vegetation characteristics of the mountain forest are used to draw a map of the fire danger level in the monitoring area.In the medium-risk area and the low-risk area,the use of chaotic systems is sensitive to the initial point,and the UAV track points are constrained to be higher in areas with high fire danger levels than in areas with low fire danger levels.Finally,in order to determine that the planned random full coverage path of the UAV can be applied,the tracking of the UAV track is controlled based on the differential flat theory.The planned UAV track is used as a flat output,and a chaotic path tracker is designed.Numerical simulation is used to verify the tracking effect of the differential flat controller.After a certain number of iterations,the unmanned track and the planned track coincide with each other.Each state variable in the ergonomic kinematics equation tends to zero.The results show that the differential flat controller can track the chaotic random full coverage path by the drone.In summary,this paper will memorize that the UAV random full coverage path planning period constructed by the Chua system can meet the needs of drone tracks in forest fire danger monitoring,and the effectiveness of the method is verified using simulation results.