Autonomous Intruder Detection Using a ROS-Based Multi-Robot System Equipped with 2D-LiDAR Sensors

TL;DR

This paper presents a ROS-based multi-robot security system utilizing 2D-LiDAR sensors for autonomous intruder detection, emphasizing reliability in sensor-dependent scenarios and centralized detection processing.

Contribution

It introduces a multi-robot system with centralized detection using LiDAR sensors, addressing limitations of single-sensor reliance in security applications.

Findings

Effective intruder detection in warehouse scenarios

Robust performance with single-range-sensor-per-robot setup

Centralized detection improves system reliability

Abstract

The application of autonomous mobile robots in robotic security platforms is becoming a promising field of innovation due to their adaptive capability of responding to potential disturbances perceived through a wide range of sensors. Researchers have proposed systems that either focus on utilizing a single mobile robot or a system of cooperative multiple robots. However, very few of the proposed works, particularly in the field of multi-robot systems, are completely dependent on LiDAR sensors for achieving various tasks. This is essential when other sensors on a robot fail to provide peak performance in particular conditions, such as a camera operating in the absence of light. This paper proposes a multi-robot system that is developed using ROS (Robot Operating System) for intruder detection in a single-range-sensor-per-robot scenario with centralized processing of detections from all robots by our central bot MIDNet (Multiple Intruder Detection Network). This work is aimed at providing an autonomous multi-robot security solution for a warehouse in the absence of human personnel.