Research on UAV Path Planning Based on Enhanced Artificial Lemming Algorithm

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Optimization Algorithms

Background:

• Unmanned aerial vehicle (UAV) path planning presents significant challenges in achieving both effectiveness and safety.
• Traditional optimization methods often struggle to identify optimal flight routes efficiently.
• Ensuring reliable navigation is critical for various UAV applications.

Purpose of the Study:

• To propose an enhanced artificial lemming optimization algorithm (ALAEN) for improved UAV path planning.
• To address the limitations of existing optimization methods in finding optimal UAV trajectories.
• To enhance the safety and efficiency of UAV navigation.

Main Methods:

• Introduction of stochastic differential mutation and Beta opposition-based learning into the artificial lemming algorithm (ALA).
• Comparative analysis of ALAEN against other algorithms using the CEC2017 benchmark test set.
• Empirical testing of ALAEN on two distinct map scenarios for real-world UAV trajectory planning simulation.

Main Results:

• ALAEN demonstrated superior optimization ability and convergence speed compared to the standard ALA and other algorithms.
• ALAEN achieved a significantly improved ranking (1.34) compared to ALA (5.45) on the CEC2017 test set.
• In simulations, ALAEN resulted in a lower average cost function (91.598) than ALA (92.999) on a small map.
• ALAEN produced the shortest trajectory routes and lowest trajectory cost functions among tested algorithms.

Conclusions:

• The enhanced artificial lemming optimization algorithm (ALAEN) effectively improves UAV path planning capabilities.
• ALAEN offers enhanced safety and efficiency in trajectory planning compared to the basic ALA.
• The proposed ALAEN algorithm represents a significant advancement for complex UAV navigation tasks.