Environmental Complexity Based UAV Path Planning with Variable Step RRT

In response to the problem of three-dimensional path planning for unmanned aerial vehicles (UAVs) in complex environments, this paper proposes an environmental complexity based variable step Rapidly-exploring Random Tree (RRT) path planning algorithm. Firstly, a model of environmental complexity function is established in a three-dimensional environment to measure the complexity of UAV flight environments. Then, an evaluation function for path planning is established. Based on the environmental complexity function and the evaluation function, the optimal step size for the RRT algorithm is found with the genetic algorithm. With a large number of simulated random environmental variables and the corresponding optimal step size, the environmental complexity based RRT step size function is identified and established that represents the relationship between the optimal step size of the RRT algorithm and the complexity of the environment. Based on the sliding window and the environmental complexity based RRT step size function, the variable step RRT path planning for UAVs is constructed. This algorithm can dynamically select the optimal step size according to the local environment, improving the overall performance of UAV path planning algorithms.Finally, comparative experiments are conducted to verify that the proposed algorithm is superior to the traditional on