Speed Control for Leader-Follower Robot Formation Using Fuzzy System and Supervised Machine Learning.

Area of Science:

• Robotics
• Artificial Intelligence
• Control Systems

Background:

• Mobile robots require sophisticated control for autonomous navigation, facing challenges like non-holonomic constraints and sensor uncertainty.
• Efficient speed control is crucial for autonomous robots to achieve collision-free navigation and maintain formations.

Purpose of the Study:

• To propose an intelligent technique for speed control of wheeled mobile robots.
• To enable flexible leader-follower formation control using a combination of fuzzy logic and supervised machine learning (SML).

Main Methods:

• A fuzzy controller determines the follower robot's desired distance from the leader using ultrasonic sensor data.
• A supervised machine learning (SML) algorithm estimates the follower robot's speed based on the calculated distance.
• Simulations were conducted to validate the proposed control technique.

Main Results:

• The proposed technique effectively adjusts the follower robot's speed.
• Flexible leader-follower formations were maintained with varying safe distances.
• The system demonstrated robust performance in simulations.

Conclusions:

• The integration of fuzzy logic and SML provides an effective solution for mobile robot speed control.
• This approach facilitates adaptable and safe autonomous navigation in formation scenarios.
• The technique enhances the autonomy of wheeled mobile robots.