FURI | Spring 2026

Deadlock Resolution in Multi-Agent Systems Using Hierarchical Leader–Follower Control

Data icon, disabled. Four grey bars arranged like a vertical bar chart.

Robots in shared spaces can get stuck due to conflicting actions and obstacles. This research addresses this problem by developing a hierarchical control system that monitors group motion, helping robots detect when they are stuck, and adjust their behavior to continue making progress. When deadlock is detected, the system reorganizes the roles of individual robots to restore coordination. By allowing robots to adapt and continue communicating during these situations, the system can recover without relying on a central controller. This approach aims to improve the efficiency and reliability of autonomous systems used in applications such as robotics, drones, and self-driving vehicles.