# Managing a Fleet of Autonomous Mobile Robots (AMR) using Cloud Robotics Platform

## TL;DR

This paper compares three approaches to managing a fleet of autonomous mobile robots in factory or warehouse settings, highlighting the advantages and limitations of each, especially focusing on cloud robotics versus traditional ROS frameworks.

## Contribution

It introduces and evaluates a cloud robotics platform for fleet management, contrasting it with ROS-based architectures through simulations and real-world experiments.

## Key findings

- Rapyuta cloud platform offers comparable performance to ROS-based systems.
- Identifies critical limitations of the current Rapyuta platform.
- Provides practical insights for implementing cloud robotics in industrial environments.

## Abstract

In this paper, we provide details of implementing a system for managing a fleet of autonomous mobile robots (AMR) operating in a factory or a warehouse premise. While the robots are themselves autonomous in its motion and obstacle avoidance capability, the target destination for each robot is provided by a global planner. The global planner and the ground vehicles (robots) constitute a multi agent system (MAS) which communicate with each other over a wireless network. Three different approaches are explored for implementation. The first two approaches make use of the distributed computing based Networked Robotics architecture and communication framework of Robot Operating System (ROS) itself while the third approach uses Rapyuta Cloud Robotics framework for this implementation. The comparative performance of these approaches are analyzed through simulation as well as real world experiment with actual robots. These analyses provide an in-depth understanding of the inner working of the Cloud Robotics Platform in contrast to the usual ROS framework. The insight gained through this exercise will be valuable for students as well as practicing engineers interested in implementing similar systems else where. In the process, we also identify few critical limitations of the current Rapyuta platform and provide suggestions to overcome them.