Distributed multi-UAV cooperation for dynamic target tracking optimized by an SAQPSO algorithm.

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Aerospace Engineering

Background:

• Real-time tracking of dynamic targets is critical for multi-unmanned aerial vehicle (UAV) systems.
• Target trajectory uncertainty and suboptimal path optimization hinder effective tracking.
• Existing methods struggle with prediction accuracy and local optimization deviations.

Purpose of the Study:

• To enhance real-time target tracking capabilities for multi-UAV systems.
• To address challenges in dynamic target trajectory prediction and path optimization.
• To improve the accuracy and efficiency of multi-UAV coordinated tracking.

Main Methods:

• A multi-step Unscented Kalman Filter (MUKF) is proposed for accurate multi-step trajectory forecasting.
• A hybrid Simulated Annealing-Quantum Particle Swarm Optimization (SAQPSO) algorithm is developed for path optimization.
• The SAQPSO algorithm integrates Simulated Annealing's annealing mechanism with Quantum Particle Swarm Optimization's global searchability.

Main Results:

• The MUKF demonstrates improved trajectory prediction accuracy over single-step methods.
• The SAQPSO algorithm effectively enhances global searchability and reduces local optimization deviations.
• Simulations comparing eight algorithms validate the superior performance of the proposed methods.

Conclusions:

• The proposed MUKF and SAQPSO algorithms significantly improve real-time dynamic target tracking.
• The hybrid approach offers a robust solution for complex multi-UAV tracking scenarios.
• This research contributes to more reliable and efficient autonomous tracking systems.