A Novel Path Planning Strategy for a Cleaning Audit Robot Using Geometrical Features and Swarm Algorithms

Area of Science:

• Robotics
• Environmental Science
• Computer Science

Background:

• Robot-aided cleaning auditing requires efficient dirt sample collection for accurate cleanliness assessment.
• Traditional coverage planning is unsuitable for selective dirt sample gathering.
• A path planning approach focusing on high-likelihood dirt accumulation areas is more feasible.

Purpose of the Study:

• To develop a novel dirt sample gathering strategy for cleaning auditing robots.
• To combine geometric feature extraction with swarm algorithms for optimal path planning.
• To establish a foundational approach for robot-aided cleaning auditing.

Main Methods:

• Utilized geometrical feature extraction to identify potential dirt accumulation locations.
• Integrated swarm algorithms, specifically ant colony optimization, for path planning.
• Validated the approach through systematic experiment trials and real-world robot deployment.

Main Results:

• Geometrical feature extraction effectively identified dirt-accumulated locations.
• Ant colony optimization generated an efficient cleaning auditing path.
• The proposed method demonstrated reduced travel distance, exploration time, and energy usage.

Conclusions:

• The combined approach of geometric feature extraction and swarm algorithms provides an efficient and optimal path for cleaning auditing robots.
• This strategy is foundational for robot-aided cleaning auditing, addressing the challenge of selective dirt sample collection.
• The ant colony optimization algorithm is highly effective in minimizing operational costs for cleaning auditing robots.