A Herd-Foraging-Based Approach to Adaptive Coverage Path Planning in Dual Environments.

Area of Science:

• Robotics
• Artificial Intelligence
• Swarm Intelligence

Background:

• Coverage Path Planning (CPP) is crucial for robotic tasks like environmental monitoring and terrain surveying.
• Existing methods like predator-prey CPP (PPCPP) are limited to bounded environments and cannot handle unbounded or dual-environment scenarios.
• Robots often need to operate in both bounded (e.g., buildings) and unbounded (e.g., open fields) areas, necessitating adaptable CPP strategies.

Purpose of the Study:

• To propose an online adaptive CPP approach for swarm robots capable of handling both bounded and unbounded environments.
• To develop a method that does not require prior knowledge of the environment.
• To enhance the versatility of swarm robots for complex, real-world tasks.

Main Methods:

• An novel approach inspired by herd-foraging behavior of animals is proposed, termed dual-environmental herd-foraging-based CPP (DH-CPP).
• The DH-CPP algorithm enables online adaptation to environmental conditions.
• Performance was evaluated in simulated dual environments with various obstacle configurations.

Main Results:

• DH-CPP demonstrated high effectiveness in handling dual environments.
• The approach successfully managed both stationary and dynamic obstacles of different shapes and quantities.
• Comparative analysis showed DH-CPP outperforming three state-of-the-art CPP methods.

Conclusions:

• The proposed DH-CPP approach provides a robust solution for swarm robots operating in complex, dual-environment settings.
• The herd-foraging inspiration allows for adaptive and efficient coverage planning.
• This method significantly advances the capabilities of swarm robotics for tasks requiring navigation in both known and unknown terrains.