Multiple elite strategy enhanced RIME algorithm for 3D UAV path planning.

Area of Science:

• Artificial Intelligence
• Robotics
• Optimization Algorithms

Background:

• Unmanned Aerial Vehicles (UAVs) are increasingly utilized across diverse applications.
• Efficient and reliable 3D path planning is critical for UAV operational effectiveness.
• Existing algorithms often face challenges with exploration, exploitation, and local optima.

Purpose of the Study:

• To develop an advanced optimization algorithm for 3D UAV path planning.
• To improve exploration and exploitation capabilities for finding global optima.
• To enhance the diversity and stability of the path planning process.

Main Methods:

• Proposed an elite RIME algorithm incorporating an elite reverse learning population selection strategy.
• Implemented a stochastic factor-controlled elite pool exploration strategy.
• Introduced a hard frost puncture exploitation strategy utilizing sine-cosine functions.

Main Results:

• The elite RIME algorithm (ELRIME) demonstrated competitive results against 13 other algorithms on 52 test functions across CEC2017, CEC2020, and CEC2022 benchmark sets.
• ELRIME achieved significant performance improvements in 3D UAV path planning across varied terrain.
• Specifically, ELRIME doubled performance in the 7-peak model and showed enhanced stability and reduced cost in 9-peak and 12-peak models compared to the RIME algorithm.

Conclusions:

• The proposed ELRIME algorithm offers a robust and efficient solution for 3D UAV path planning.
• The novel strategies enhance global search capabilities and mitigate local optima entrapment.
• ELRIME provides a stable and high-performing approach for complex UAV mission planning.