Fast Multi-UAV Path Planning for Optimal Area Coverage in Aerial Sensing Applications

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Coverage Path Planning (CPP) is crucial for Unmanned Aerial Vehicle (UAV) missions.
• Efficient multi-UAV coordination for large-scale coverage remains a challenge.
• Existing methods often lack real-time optimization for dynamic environments.

Purpose of the Study:

• To develop and analyze fast coverage path planning solutions for multiple UAVs.
• To implement a software framework and algorithms for efficient UAV trajectory generation.
• To provide a practical tool for first responders like police and firefighters.

Main Methods:

• A back-and-forth path generation algorithm based on sensor footprint.
• Three path assignment methods: SIMPLE-BINPAT, BINPAT, and POWELL-BINPAT.
• Utilized heuristic algorithms, linear sum assignment, and minimization techniques for optimization.

Main Results:

• POWELL-BINPAT demonstrated superior performance in generating optimal UAV paths for minimum mission time.
• The proposed approach significantly reduced computation time for trajectory generation compared to existing literature.
• Simulations and real-world experiments validated the effectiveness of the POWELL-BINPAT method with RGB and thermal cameras.

Conclusions:

• The POWELL-BINPAT method offers an effective solution for fast and optimal multi-UAV coverage path planning.
• The developed software framework is practical for deployment by first responders.
• This research contributes to advancing efficient autonomous systems for critical applications.