An effective robot selection and recharge scheduling approach for improving robotic networks performance

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Mobile robots are increasingly used for remote communication and human-robot interaction.
• Challenges in mobile robot control include power consumption, network delays, and task-specific robot selection.
• Existing systems face difficulties in managing robot fleets efficiently.

Purpose of the Study:

• To enhance the efficacy of mobile robotic networks through a novel methodology.
• To optimize robot selection and charging processes for improved performance.
• To reduce the burden on individual robots by utilizing remote server and fog computing resources.

Main Methods:

• A strategy to eliminate unsuitable robots before selecting the optimal one for a task.
• A fuzzy algorithm-based procedure for scheduling robot recharging to prevent conflicts.
• Leveraging fog servers for faster data transfer and localized processing to improve real-time interaction.

Main Results:

• The proposed methodology achieved a 2.4% improvement in average accuracy.
• An average enhancement of 2.2% in power usage was observed compared to recent methods.
• The system effectively manages robot recharging, preserving battery life and physical resources.

Conclusions:

• The novel methodology significantly enhances mobile robotic network efficiency.
• The integration of fuzzy logic and fog computing offers a robust solution for robot management.
• The approach demonstrates improved performance in accuracy and power consumption for remote robot operations.