Multi-Strategy Improved Red-Tailed Hawk Algorithm for Real-Environment Unmanned Aerial Vehicle Path Planning.

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Aerospace Engineering

Background:

• Unmanned Aerial Vehicle (UAV) technology is crucial for surveillance, search and rescue, and environmental monitoring.
• Reliable, safe, and economical path planning for UAVs in real-world environments presents significant challenges.

Purpose of the Study:

• To propose a novel multi-strategy improved red-tailed hawk (IRTH) algorithm for UAV path planning.
• To enhance the exploration and exploitation capabilities of UAV path planning algorithms.

Main Methods:

• Implemented stochastic reverse learning based on Bernoulli mapping for initial population enhancement.
• Utilized dynamic position update optimization with stochastic mean fusion to improve exploration.
• Introduced a trust domain-based optimization for frontier position updates to balance exploration and exploitation.

Main Results:

• The IRTH algorithm demonstrated competitive performance against 11 other algorithms on the IEEE CEC2017 test set.
• Statistical analysis confirmed significant differences, highlighting the algorithm's effectiveness.
• The IRTH algorithm achieved improved results in practical UAV path-planning scenarios.

Conclusions:

• The proposed IRTH algorithm is effective for UAV path planning in real-world environments.
• The multi-strategy enhancements improve exploration, exploitation, and overall path planning performance.
• The IRTH algorithm offers a viable solution for complex UAV navigation tasks.