Composite Improved Algorithm Based on Jellyfish, Particle Swarm and Genetics for UAV Path Planning in Complex Urban...

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Aerospace Engineering

Background:

• Path planning is critical for unmanned aerial vehicles (UAVs) operating in complex urban environments.
• Existing algorithms often struggle with safety, path smoothness, and efficiency in multi-obstacle scenarios.
• Single algorithms may exhibit slow convergence and susceptibility to local optima.

Purpose of the Study:

• To develop an innovative composite algorithm for UAV path planning.
• To enhance path safety, smoothness, and shortest path acquisition in complex urban environments.
• To overcome limitations of individual optimization algorithms.

Main Methods:

• Integration of the jellyfish search algorithm and the particle swarm algorithm.
• Development of a composite improvement algorithm.
• Evaluation using 23 benchmark functions, a 3D city model simulation, and 100 repetitive experiments.

Main Results:

• The composite algorithm demonstrated superior performance compared to traditional methods.
• Achieved fast convergence, high accuracy, and robust global/local search capabilities.
• Significantly reduced UAV flight time and obstacle avoidance maneuvers.

Conclusions:

• The proposed algorithm provides effective path planning for UAVs in complex urban environments.
• It offers robust technical support for advancing UAV technologies.
• The method enhances UAV path optimization, stability, and operational efficiency.