Multi-UAV Collaborative Target Search Method in Unknown Dynamic Environment.

Area of Science:

• Robotics
• Artificial Intelligence
• Operations Research

Background:

• Search inefficiency in multi-UAV swarms is caused by repeated area searches and dynamic target movement.
• Uncertain environments complicate coordinated search operations for unmanned aerial vehicles (UAVs).

Purpose of the Study:

• To enhance the search efficiency of multiple UAV swarms in dynamic and uncertain environments.
• To address challenges of repeated searches and target mobility in cooperative search missions.

Main Methods:

• Developed a distributed adaptive real-time planning search (DAPSO) technique for UAV swarms.
• Implemented localized communication for collaborative exploration and dynamic situational awareness updates.
• Utilized local particle swarm optimization for adaptive mission planning and trajectory adjustment.
• Proposed a distance-based collision avoidance strategy for safe multi-UAV operations.

Main Results:

• The DAPSO method significantly improved search coverage compared to other strategies.
• DAPSO demonstrated higher target detection rates in dynamic and uncertain scenarios.
• Experimental findings validated the effectiveness of the proposed adaptive search technique.

Conclusions:

• The DAPSO technique offers a robust solution for improving multi-UAV swarm search efficiency.
• Adaptive planning and collaborative exploration are key to overcoming search inefficiencies in dynamic environments.
• The proposed method ensures safe and effective cooperative search operations.