I am developing a multi-robot fleet management system in a simulated warehouse environment using ROS2 (Humble) and Gazebo. The system is designed to study scalable coordination and task allocation across multiple autonomous mobile robots operating in a structured environment.
The architecture follows a distributed approach where each robot is implemented as an independent agent node responsible for navigation, execution, and state reporting. A centralized fleet manager node handles global task allocation and coordination. Communication is implemented using ROS2 topics, services, and action interfaces to enable asynchronous and real-time interaction between components.
Navigation is implemented using the Nav2 stack, integrating localization, global and local path planning, and obstacle avoidance. LiDAR-based perception is used for environmental awareness and safe navigation within the simulated warehouse.
The system supports dynamic task allocation, where robots receive pick-and-deliver tasks, compute feasible paths, and execute them while continuously publishing execution status. A typical workflow involves a robot navigating to a shelf location, performing a simulated pickup, and delivering the item to a designated drop-off point.
This project focuses on understanding distributed robotic system design, inter-node communication, and multi-robot coordination challenges such as scalability and synchronization. Future work includes implementing conflict resolution strategies, fleet-level optimization, and extending the system toward real-world deployment.
