Enhanced Nutcracker Optimization Algorithm with Hyperbolic Sine-Cosine Improvement for UAV Path Planning.

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Three-dimensional (3D) path planning is essential for safe and efficient Unmanned Aerial Vehicle (UAV) navigation in complex environments.
• Traditional algorithms struggle with intricate obstacle avoidance and rapid optimal path identification.

Purpose of the Study:

• To introduce an improved optimization algorithm for UAV path planning.
• To enhance the efficiency and accuracy of pathfinding in complex 3D spaces.

Main Methods:

• Integration of the hyperbolic sine-cosine (sinh cosh) optimizer into a Nutcracker Optimizer (NO) framework, creating the ISCHNOA algorithm.
• Incorporation of the sinh cosh exploitation process into the foraging strategy for better food source location.
• Design of a nonlinear function to accelerate algorithm convergence.
• Introduction of a sinh cosh optimizer with historical positions and dynamic factors to refine optimal position influence.

Main Results:

• ISCHNOA demonstrated superior performance across 14 classical benchmark functions, CEC2014, and CEC2020 test suites.
• The algorithm was successfully applied to UAV path planning models.
• ISCHNOA significantly outperformed existing algorithms in path planning efficiency and accuracy.

Conclusions:

• The proposed ISCHNOA algorithm offers a significant advancement in 3D path planning for UAVs.
• ISCHNOA effectively addresses the limitations of traditional methods in complex environments.
• The algorithm leads to reduced total path costs, enhancing UAV operational efficiency and safety.