pkolios – Panayiotis Kolios, PhD

Cooperative Aerial Robots Inspection Challenge

Received the first place at the

CDC 2023 Cooperative Aerial Robots Inspection Challenge!

We received the First Prize in the competition “Cooperative Aerial Robots Inspection Challenge”, that took place during the flagship 62^nd IEEE Conference on Decision and Control (CDC 2023), on 13-15 December 2023, in Singapore.

The “Cooperative Aerial Robots Inspection Challenge” (CARIC), utilizing open-source tools, aimed to accelerate the development of efficient and versatile multi-UAV systems for heterogeneous inspection tasks. The challenge’s scope encompassed the inspection of infrastructure in three diverse scenarios, employing a fleet of heterogeneous UAVs. At its core, the primary objective of an inspection mission is to capture images on the surface of various structures at the highest possible quality, and CARIC provided a standardized metric for evaluating different cooperative inspection schemes.

The team, consisting of Angelos Zacharia, Research Engineer I, Andreas Anastasiou, PhD Candidate, Dr. Savvas Papaioannou, Research Associate, Research Assist. Prof. Panayiotis Kolios, as well as Professors Christos Panayiotou and Marios Polycarpou, proposed an innovative cooperative strategy that effectively coordinates the operation of multiple robots to address the infrastructure inspection problem. Specifically, the team developed a distributed coordination multi-tasking algorithms that has outperformed the competition in 3D, reconstructing the search area in a robust manner (for obstacle avoidance) and thereafter inspecting the 3D structures (in both outdoor and indoor settings), to extract important features as fast as possible, by controlling both the drone trajectory and its camera gimbal settings in a joined fashion.

The developed solution secured the top ranking among 19 international teams. The evaluation of submitted solutions was carried out by the organizing committee, consisting of five experts in the field, with assessments grounded in inspection quality, infrastructure coverage, and execution time.

The award ceremony took place on the 14^th of December 2023, during the CDC Banquet Dinner, in the presence of more than 2000 conference participants.

Machine Learning for Emergency Management

Natural and human-made disasters, and other emergency events pose serious threats to society, critical infrastructures, the environment and the economy. Such adverse events may happen at any time and can have cascading effects across multiple sectors. Recent technological advancements have made it possible to collect huge amounts of data regarding natural and technological disasters, and the generated spatio-temporal data can be invaluable in gaining situational awareness and in helping emergency personnel (first responders, strategic and tactical decision makers) make the right decisions, both before and after a disaster happens. However, a key challenge is that data is generated in very large volumes and in a rapid manner thus making it difficult for relevant emergency personnel to be able to make sense of it and utilize it effectively, especially in time-critical and time-varying situations. Therefore, it is crucial to develop intelligent systems that can identify patterns, automate response, and predict situations in real-time, which can aid humans in emergency situations by improving disaster prevention, preparedness, response and recovery. Machine learning can be used to analyze the large volumes of heterogeneous spatio-temporal data in critical time-bound situations, in turn providing high-level actionable information that emergency personnel can process effectively. Ideally this can lead to systems that can support decision-making in the field, however key challenges both in the development as well as deployment of machine learning algorithms, such as sensing the right data at the right time, availability of sensors and data, real-time response, limited computational resources, and building trust with end-users, still exist. While most of the research effort has been focused on the development of application-specific machine learning algorithms, there has been some effort to summarize the work and present it in a concise way so as to highlight gaps and future research opportunities. This article provides a comprehensive survey of machine learning for all phases of emergency management (i.e., mitigation, preparedness, response, recovery), by highlighting key characteristics and challenges, as well as how machine learning algorithms can be applied across the different phases and operations. Based on the current state-of-the-art the article identifies promising future research directions for developing emergency management systems that utilize machine learning components.

Click here to access the paper.

Exchange of Experts Training Program on the use of AI Tools for Disaster Management

Successfully organized the 3rd Exchange of Experts training program on the development and use of Artificial Intelligence (AI) algorithms for disaster management. The training program was supported by the European Union’s Civil Protection Mechanism and took place on 2-4 November 2022, at the University of Cyprus premises.

Amongst the participants were 10 experts from seven European countries (Italy, Croatia, Moldova, Montenegro, Romania, Slovakia, and Finland) as well as 17 national first responders from the Cyprus Civil Defence, Fire Service, Cyprus Police, and the Department of Forestry.

The three-day training program consisted of two parts:

A training session aimed at explaining the topic and demonstrating AI technological solutions, focusing on emergency management needs. Presentations included topics on drone technologies, AI algorithms, vision technologies for UAVs, and mission planning software tools.
A field-exercise that demonstrated the use of AI tools as a way to enhance the situational awareness and decision-support capabilities of first responders during the response phase. The exercise was organized in collaboration with the Cyprus Civil Defence and took place at the Famagusta District area. The field-exercise scenario considered a search-and-rescue mission and tested the capabilities of multiple national and international teams in coordinating and sharing information during the emergency.

The Exchange of Experts training program provided participants with valuable knowledge, experience, and skills regarding the use of AI tools in several emergency situations. Furthermore, it gave the opportunity for networking and exchanging of views between participants.

This training is the outcome of the expertise developed at KIOS CoE through the EU DG ECHO funded preparedness and prevention projects PREDICATE, SWIFTERS, AIDERS, buffer capacity project LEAPFROG and knowledge network project ARTION.

AIDERS – truly a game changer!

DG ECHO AIDERS project: Artificial intelligence to support decision-making.

In Cyprus, Artificial Intelligence is being used to help first responders to make rapid and better-informed decisions even if they are not at the location of the emergency! The team of the ‘Real-time Artificial Intelligence for DEcision support via RPAS data analyticS’ – or the ‘AIDERS project’ identified a common problem for first responders: information collected by drones is limited to snapshots of the situation on the ground. If decision-makers have only a narrow picture of the emergency, situational awareness and subsequent decision-making becomes even more difficult. The AIDERS project, led by the Kios Center of Excellence of the University of Cyprus aims to better support decision-making in emergencies. They developed an online machine that uses algorithms to process and analyse the data collected from drones. Through this operation, the team creates real-time situational maps of the incident. The information is collected through sensors like visual or thermal cameras on board of the drones. This innovation allows decision-makers to have a clear understanding of situation in the field. As a result, they can make better-informed decisions… truly a game changer!

Knowledge Network Newsletter content can be accessed at: KN Newsletter Issue 5

ETEK Engineering Award

KIOS CoE received an Honorable Mention from Technical Chamber of Cyprus (ETEK), as part of the “ETEK Engineering Award”. The Award, which is announced every three years, recognizes engineering achievements that have an impact in the society of Cyprus, as well as internationally. This year, 23 engineering projects were submitted.

According to the award committee, an honourable mention was given to Drs. Panayiotis Kolios and Demetris Eliades, for coordinating the project “COVID-19 Emergency Response Management Platform”, the web platform which manages all the national data related to the COVID-19 cases. The Platform was developed by KIOS for the Ministry of Health, in collaboration with the Deputy Ministry of Research, Innovation and Digital Policy. The award committee recognized that this project utilized the know-how and experience of the KIOS researchers excellently, to create a trustworthy tool for managing the pandemic, with an added value for the society of Cyprus. The Award was delivered to KIOS by the Minister of Transport, Communication and Works, Mr Yiannis Karousos.