An aerial/ground robot team for autonomous firefighting in urban GNSS-denied scenarios

Abstract

This paper presents a framework for urban firefighting with a heterogeneous aerial/ground robot team. The system was developed to address Challenge 3 of the MBZIRC’20. The challenge required autonomously detecting, locating, and extinguishing fires on multiple interior floors and on exterior facade and ground surfaces. Our multi-robot system consists of a robot team of up to three Unmanned Aerial Vehicles (UAV) and one Unmanned Ground Vehicle (UGV). We describe the main hardware and software components for UAV and UGV platforms and present the system’s main algorithmic components: a 3D LIDAR-based Mapping and Localization module able to work in GPS-denied scenarios, a Global Planner and a fast local re-planning system for robot navigation, Infrared-Based Perception and robot actuation control for fire extinguishing, and Mission Executive and coordination module based on Behavior Trees. Finally we describe our results from the competition, where the system worked fully autonomously and scored in all the trials performed. The presented system ended in 7 th place (out of 20 teams) in Challenge 3 and 5 th place (out of 17 teams) in the Grand Challenge’s Challenge 3 portion.

UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT

“…In order to reach survivors quickly in unstable caves or partially collapsed burning buildings, first responders, such as emergency rescuers and firefighters, may potentially put their lives at risk. In firefighting tasks, fires can be either localized and reported to personnel by robots or the robots can even directly begin extinguishing flames if the presence of human firefighters is too risky (Spurny et al, 2021;Pritzl et al, 2021;Martinez-Rozas et al, 2022). In such scenarios, ceilings can suddenly collapse, toxic gas can appear in a mine, flames can extend to an escape corridor, or a cave cavity can flood with water.…”