Three-dimensional dynamic collaborative path planning for multiple UCAVs using an improved NSGAII

This paper proposes an improved crowding distance based non-dominated sorting genetic algorithm II, called INSGAII, to solve the three-dimensional collaborative path planning problem for unmanned combat aerial vehicles (UCAVs) with dynamic threats. To enhance the efficiency of finding the optimal pa...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing 2025-04, Vol.28 (2), p.75, Article 75
Main Authors: Zhong, Keyu, Xiao, Fen, Gao, Xieping
Format: Article
Language:English
Subjects:
Aircraft
Algorithms
Collaboration
Combat aircraft
Computer Communication Networks
Computer Science
Crowding
Energy consumption
Flight
Genetic algorithms
Information management
Operating Systems
Optimization
Path planning
Planning
Processor Architectures
Real time
Set theory
Sorting algorithms
Traveling salesman problem
Unmanned aerial vehicles
Vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an improved crowding distance based non-dominated sorting genetic algorithm II, called INSGAII, to solve the three-dimensional collaborative path planning problem for unmanned combat aerial vehicles (UCAVs) with dynamic threats. To enhance the efficiency of finding the optimal path, the good point set theory is employed to generate a variety of initial paths during the initial phase of path planning. This approach increases the probability of the planner discovering the optimal path, especially in environments characterized by unpredictable changes. To prevent the planner from being trapped in local optima, a novel crowding distance metric is designed for accurately estimating the diversity of different paths. The metric prefers to preserve uncrowded paths that have similar flight costs but are distant from each other by computing in parallel the crowding distances in the path space and the objective space, thus avoiding falling into the local optima. To effectively manage cooperative flight constraints among multiple UCAVs, a UCAV cooperative mechanism based on multi-population framework is utilized to facilitate information exchange among them, thereby preventing collisions. Simulation results show that the paths planned by INSGAII can successfully evade real-time threats compared to state-of-the-art planners.
ISSN:1386-7857
1573-7543
DOI:10.1007/s10586-024-04690-2