Moving-Distance-Minimized PSO for Mobile Robot Swarm

Area of Science:

• Robotics
• Artificial Intelligence
• Optimization Algorithms

Background:

• Particle Swarm Optimization (PSO) and mobile robot swarms are distinct swarm intelligence techniques.
• The potential for integrating these techniques for real-world optimization problems remains largely unexplored.
• Mobile robot swarms offer a physical platform for exploring solution spaces in real-world scenarios.

Purpose of the Study:

• To propose a novel Moving-Distance-Minimized Particle Swarm Optimization (MPSO) algorithm tailored for mobile robot swarms.
• To minimize the total movement distance of robots during the optimization process, thereby reducing energy consumption and time.
• To enhance the efficiency and practicality of using robot swarms for real-world optimization tasks.

Main Methods:

• Developed an MPSO algorithm that leverages the positions of particles in the next generation to derive robot paths.
• Calculated robot paths to minimize the total distance traveled by the swarm.
• Implemented and tested the MPSO algorithm on a suite of 28 CEC2013 benchmark functions.

Main Results:

• The MPSO algorithm demonstrated a significant reduction in total robot moving distance, exceeding 66%.
• The makespan (total time to complete the optimization) was reduced by nearly 70% compared to standard PSO.
• The proposed method achieved comparable optimization results to standard PSO.

Conclusions:

• MPSO effectively minimizes robot movement distances, leading to substantial energy and time savings for mobile robot swarms.
• The integration of PSO with mobile robots, optimized for movement efficiency, provides a practical approach for real-world exploration and optimization.
• The MPSO algorithm offers a superior alternative to standard PSO for applications requiring efficient physical exploration and optimization.