An Efficient Fine-to-Coarse Wayfinding Strategy for Robot Navigation in Regionalized Environments

Area of Science:

• Robotics
• Artificial Intelligence
• Computational Geometry

Background:

• Robot navigation in large-scale environments presents significant computational challenges.
• Existing algorithms often struggle with efficiency and responsiveness in complex, regionalized spaces.
• Human spatial cognition offers insights into effective environmental representation and navigation.

Purpose of the Study:

• To propose an efficient wayfinding strategy for robot navigation in regionalized environments.
• To introduce a novel regionalized spatial knowledge (RSK) model for environment representation.
• To develop a region-based, fine-to-coarse A* (FTC-A*) search algorithm for enhanced route planning.

Main Methods:

• Designed a hierarchical RSK model mimicking human brain's environmental representation.
• Developed the FTC-A* algorithm for fine-to-coarse route planning.
• Implemented and validated the strategy through simulations and a physical experiment.

Main Results:

• The RSK model effectively represents regionalized environments using a nested hierarchical structure.
• The FTC-A* algorithm significantly reduces computational complexity for route search.
• Demonstrated enhanced efficiency and responsiveness in robot navigation, particularly in large-scale settings.

Conclusions:

• The proposed RSK model and FTC-A* algorithm provide a feasible and effective wayfinding strategy for robot navigation.
• This approach optimizes computational load and improves robot reaction times.
• The method shows promise for practical applications in complex and large-scale robotic systems.