Path Planning for UAV with Constrained conditions Based on Ant Colony Algorithm

Abstract

Abstract. In order to improve UAV's operational efficiency and survival probability, the optimal path of an UAV should be designed before the UAV performs a mission. This paper applies UAV's constrained conditions to the search strategies of ant colony and use a new evaluation method of path's cost. The algorithm's state transformation rules and pheromone updating rules are improved. These make its convergence speed and global searching ability enhanced remarkably. The simulation results show that this method can get a flight path which can avoid threats effectively in a short time and is a more efficient path planning method

Quantum and Condor-Based Brainstorming Optimization Algorithm for NOx Prediction

“…(1) 𝜀 = 𝑙𝑜𝑔𝑠𝑖𝑔((0.5 * 𝑚𝑎𝑥_𝑖𝑡𝑒𝑟𝑛𝑎𝑡𝑖𝑜𝑛 − 𝑐𝑢𝑟𝑟𝑒𝑛𝑡_𝑖𝑡𝑒𝑟𝑎𝑡𝑖𝑜𝑛)/𝑘) * 𝑟𝑎𝑛𝑑(1, 𝐷) (2) where D stands for the dimension of data, which in Matlab corresponds to the logistic regression's sigmoid function as well as the function for generating random integers with a positive distribution.…”

“…(5) We measure the probability of operating results for |0>,|1> respectively|α𝑘| 2 ，|𝛽𝑘| 2 =1-|α𝑘| 2 . We create a random number, compare it to |α𝑘| 2 random generation 0 and 1, which produce binary code; shift the binary number to produce a decimal number; and then, receive the population initialization.…”

“…Particle swarm optimization (PSO) is currently a well-known swarm-intelligent optimization algorithm [1]. Optimization of ant colonies (ACO) [2]. Humans are the world's greatest social organism, and their peculiar thinking can be utilized as a novel swarm intelligence optimization algorithm.…”