Planning trajectory for UAVs using the self-organizing migrating algorithm.

Area of Science:

• Robotics and Autonomous Systems
• Artificial Intelligence
• Aerospace Engineering

Background:

• Unmanned Aerial Vehicles (UAVs) face significant challenges in safe trajectory planning within dynamic and complex environments.
• Key issues include real-time obstacle avoidance, adaptation to environmental changes, and multi-UAV collision prevention.

Purpose of the Study:

• To develop a novel trajectory planning approach for UAVs that integrates obstacle avoidance and target acquisition.
• To enhance the safety, efficiency, and adaptability of autonomous UAV operations in challenging scenarios.

Main Methods:

• A new cost function was designed to balance minimizing distance to target and maximizing distance from obstacles.
• The Self-Organizing Migrating Algorithm (SOMA), a swarm intelligence technique, was employed to optimize the cost function.
• The method enables real-time path generation, dynamic adaptation, and scalability for multi-UAV systems without centralized control.

Main Results:

• Simulations demonstrated successful target acquisition and collision avoidance for UAVs in complex environments with multiple agents.
• The proposed method proved effective in dynamic scenarios, showcasing adaptability to unpredictable changes.
• Scalability was confirmed, with the system handling a swarm of ten UAVs effectively.

Conclusions:

• The developed trajectory planning approach offers a reliable and robust solution for autonomous UAV operations.
• This work advances the field by providing a scalable and adaptable method for UAVs operating in challenging, dynamic environments.
• The integration of a novel cost function with swarm intelligence effectively addresses critical aspects of UAV navigation and safety.