An Improved Equilibrium Optimizer with Application in Unmanned Aerial Vehicle Path Planning.

Area of Science:

• Robotics and Control Systems
• Optimization Algorithms
• Aerospace Engineering

Background:

• Unmanned Aerial Vehicle (UAV) path planning is a complex multi-constraint optimization challenge.
• Existing methods often struggle with balancing multiple objectives and constraints effectively.

Purpose of the Study:

• To develop an efficient algorithm for UAV path planning that addresses fuel consumption, altitude, and threat costs.
• To transform a constrained optimization problem into an unconstrained one using penalty functions.

Main Methods:

• A Multiple Population Hybrid Equilibrium Optimizer (MHEO) was proposed, dividing populations into subpopulations for distinct strategies.
• Incorporated Gaussian distribution estimation, equilibrium pool adjustment, Lévy flight, and inferior solution shift strategies.
• Utilized a fitness function including fuel consumption, altitude, and threat costs, with constraints on flight distance, altitude, and turn/climb angles.

Main Results:

• MHEO demonstrated superior convergence speed and accuracy compared to other algorithms on the CEC2017 test suite.
• Simulation experiments confirmed MHEO's ability to consistently plan feasible and efficient UAV flight paths that satisfy all constraints.

Conclusions:

• The proposed MHEO algorithm is a superior and feasible solution for complex UAV path planning problems.
• The developed path planning model effectively integrates multiple constraints and cost factors.