Butterfly magnetoreception based neighbour awareness strategy protocol for autonomous aerial vehicles

Area of Science:

• Robotics and Artificial Intelligence
• Aerospace Engineering
• Disaster Management Technologies

Background:

• Autonomous Aerial Vehicles (AAVs) are crucial for emergency response but struggle with navigation in complex, obstacle-rich environments.
• Existing methods face challenges with dynamic conditions, scalability, and efficient obstacle avoidance.

Purpose of the Study:

• To propose a novel Neighbour Awareness Strategy (NAS) protocol for enhanced AAV navigation in challenging environments.
• To improve safety, adaptability, and reactiveness in AAV operations during disaster management.

Main Methods:

• Integration of Butterfly Magnetoreception Mechanism (BMM) for enhanced navigational safety and reduced decision delays.
• Application of Machine Learning (ML) algorithms for optimal energy consumption and dynamic path selection.
• Utilizing key navigation parameters like orientation angle (θ), heading angle (α), and velocity vector (V) for precise control.

Main Results:

• NAS protocol demonstrated superior obstacle avoidance compared to existing methods like APA-DOA and REAT.
• Achieved faster reaction times and enhanced operational efficiency in simulations.
• Enabled AAVs to maintain optimal orientation and adapt heading to environmental changes.

Conclusions:

• The NAS protocol effectively addresses challenges in AAV navigation within high-density obstacle environments.
• NAS facilitates coordinated swarm movements and effective navigation in complex 3D spaces.
• This strategy enhances the reliability and efficiency of AAVs in emergency response and disaster management.