Article (Scientific journals)
A Fully-Autonomous Aerial Robot for Search and Rescue Applications in Indoor Environments using Learning-Based Techniques
Sampedro, Carlos; Rodriguez-Ramos, Alejandro; BAVLE, Hriday et al.
2019In Journal of Intelligent and Robotic Systems, 95 (2), p. 601--627
Peer Reviewed verified by ORBi
 

Files


Full Text
root.pdf
Author preprint (3.56 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Autonomous robots; Deep learning; Image-based visual servoing; Reinforcement learning; Search and rescue; Supervised learning
Abstract :
[en] Search and Rescue (SAR) missions represent an important challenge in the robotics research field as they usually involve exceedingly variable-nature scenarios which require a high-level of autonomy and versatile decision-making capabilities. This challenge becomes even more relevant in the case of aerial robotic platforms owing to their limited payload and computational capabilities. In this paper, we present a fully-autonomous aerial robotic solution, for executing complex SAR missions in unstructured indoor environments. The proposed system is based on the combination of a complete hardware configuration and a flexible system architecture which allows the execution of high-level missions in a fully unsupervised manner (i.e. without human intervention). In order to obtain flexible and versatile behaviors from the proposed aerial robot, several learning-based capabilities have been integrated for target recognition and interaction. The target recognition capability includes a supervised learning classifier based on a computationally-efficient Convolutional Neural Network (CNN) model trained for target/background classification, while the capability to interact with the target for rescue operations introduces a novel Image-Based Visual Servoing (IBVS) algorithm which integrates a recent deep reinforcement learning method named Deep Deterministic Policy Gradients (DDPG). In order to train the aerial robot for performing IBVS tasks, a reinforcement learning framework has been developed, which integrates a deep reinforcement learning agent (e.g. DDPG) with a Gazebo-based simulator for aerial robotics. The proposed system has been validated in a wide range of simulation flights, using Gazebo and PX4 Software-In-The-Loop, and real flights in cluttered indoor environments, demonstrating the versatility of the proposed system in complex SAR missions.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Sampedro, Carlos
Rodriguez-Ramos, Alejandro
BAVLE, Hriday  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Automation
Carrio, Adrian
de la Puente, Paloma
Campoy, Pascual
External co-authors :
no
Language :
English
Title :
A Fully-Autonomous Aerial Robot for Search and Rescue Applications in Indoor Environments using Learning-Based Techniques
Publication date :
2019
Journal title :
Journal of Intelligent and Robotic Systems
ISSN :
1573-0409
Publisher :
Journal of Intelligent & Robotic Systems
Volume :
95
Issue :
2
Pages :
601--627
Peer reviewed :
Peer Reviewed verified by ORBi
Commentary :
1084601808981
Available on ORBilu :
since 19 May 2021

Statistics


Number of views
70 (4 by Unilu)
Number of downloads
277 (1 by Unilu)

Scopus citations®
 
113
Scopus citations®
without self-citations
111
OpenCitations
 
70
WoS citations
 
112

Bibliography


Similar publications



Contact ORBilu