Cooperative Path Planning of Multiple UAVs by using Max–Min Ant Colony Optimization along with Cauchy Mutant Operator

Abstract

In a dynamic environment with wind forces and tornadoes, eliminating fluctuations and noise is critical to get the optimal results. Avoiding collision and simultaneous arrival of multiple unmanned aerial vehicles (multi-UAVs) is also a great problem. This paper addresses the cooperative path planning of multi-UAVs with in a dynamic environment. To deal with the aforementioned issues, we combine the maximum–minimum ant colony optimization (MMACO) and Cauchy Mutant (CM) operators to make a bio-inspired optimization algorithm. Our proposed algorithm eliminates the limitations of classical ant colony optimization (ACO) and MMACO, which has the issues of the slow convergence speed and a chance of falling into local optimum. This paper chooses the CM operator to enhance the MMACO algorithm by comparing and examining the varying tendency of fitness function of the local optimum position and the global optimum position when taking care of multi-UAVs path planning problems. It also makes sure that the algorithm picks the shortest route possible while avoiding collision. Additionally, the proposed method is more effective and efficient when compared to the classic MMACO. Finally, the simulation experiment results are performed under the dynamic environment containing wind forces and tornadoes.

Critical analysis: bat algorithm-based investigation and application on several domains

“…Wang et al (2012), Ali et al (2020a) have proposed a new bat algorithm with a mutation to solve the route planning problems of unmanned warship aerial vehicles (Ali et al , 2020b). The standard bat algorithm has been used for solving the UCAV path planning problem before they applied a modification to the original BA to switch between bats in generating new solutions step.…”

Semantic Optimization of Feature-Based SLAM

“…For the problem of establishing a dictionary of k words with N feature points in the image, each word can be regarded as a set of local feature points. In the following studies, on the basis of k-means, the hierarchical clustering method and k-means++ [23,24] were proposed to improve k-means. Considering the efficiency of search, the K fork tree is used to express the dictionary on the basis of k-means.…”

A new K-means grey wolf algorithm for engineering problems

“…Balancing between exploration and exploitation is one of the issues that are related to GWO (Luo et al, 2019;Mittal et al, 2016). Despite having the efficient capability, GWO has poor performance in the search space because sometimes it sticks in local optima (Jadhav and Gomathi, 2018;Ali et al, 2020aAli et al, , 2020b). Slow convergence rates and low accuracy are problems that can be enhanced by researchers (Wu et al, 2020;Wang and Li, 2019).…”

“…Slow convergence rates and low accuracy are problems that can be enhanced by researchers (Wu et al, 2020;Wang and Li, 2019). Therefore, different methods are used by researchers to improve the capacity of optimization algorithms and solve optimization problems (Ali et al, 2020a(Ali et al, , 2020bChakraborty, 2017;Rashid et al, 2019;Kohli and Arora, 2018). For example, a modified GWO was proposed to tune the parameters of the recurrent neural network (Panwar et al, 2018).…”