UAV Path Planning Algorithm Based on Improved Harris Hawks Optimization.

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Aerospace Engineering

Background:

• Efficient path planning is crucial for Unmanned Aerial Vehicle (UAV) systems.
• Existing algorithms struggle with complex three-dimensional (3D) flight environments, yielding suboptimal results.
• The need for low-cost and fast search speed in UAV path planning is a significant challenge.

Purpose of the Study:

• To propose an improved Harris Hawks Optimization (HHO) algorithm for UAV path planning.
• To enhance the performance of UAV path planning in complex 3D environments.
• To address limitations of current algorithms in terms of planning effectiveness and efficiency.

Main Methods:

• Developed a 3D mission space model and a flight path cost function.
• Improved the Harris Hawks Optimization (HHO) algorithm by incorporating Cauchy mutation and adaptive weights for enhanced exploration.
• Integrated the Sine-cosine Algorithm (SCA) to mitigate local extremum issues and ensure convergence to optimal solutions.

Main Results:

• The proposed improved HHO algorithm demonstrated high optimization accuracy.
• The algorithm exhibited superior convergence speed compared to existing methods.
• Simulation results confirmed the robustness of the algorithm in generating optimized UAV flight paths.

Conclusions:

• The improved HHO algorithm effectively addresses the challenges of UAV path planning in 3D environments.
• The integration of Cauchy mutation, adaptive weights, and SCA enhances search capabilities and solution optimality.
• The developed algorithm offers a promising solution for generating efficient and optimized flight paths for UAVs.