Avatar

Dr. Antonio Andriella

Postdoctoral Researcher @

Artificial Intelligence Research Institute (IIIA)



Last update: November, 11th 2024

I’m a Postdoctoral Researcher at the Artificial Intelligence Research Institute (IIIA) working in the Value-Aware Artificial Intelligence (VALAWAI) project that aims at developing AI systems that are able to understand and act by a value system and explain their own behaviour or understand the behaviour of others in terms of a value system. I was a Research Scientist at Pal Robotics awarded with a Marie Skłodowska-Curie cofund fellowship in the H2020 project PRO-CARED (no.801342) which aimed at designing social robots with proactive personalised behaviour during long-lasting interactions (2022-2024). I received my PhD with a thesis entitled “Personalising robot assistance for cognitive training therapy” from the Institut de Robòtica i Informàtica Industrial (IRII) under the supervision of Dr. Guillem Alenyà and Prof. Carme Torras (2017-2022). My thesis was awarded the prestigious Georges Giralt award for the best European PhD thesis from euRobotics. Furthermore, I also won the AIHUB.CSIC prize for the best AI PhD Thesis from the AI Hub of the Spanish National Research Council (CSIC). I was an Early Stage Researcher in the Marie Skłodowska-Curie Innovative Training Network (ITN) project called SOCRATES, which focused on Quality of Interaction in Eldercare.
Prior to IRII, I worked at Cogisen as Artificial Intelligence lead. I was a visiting student at the University of Naples (2021) and University of Hamburg (2018-19). In 2022, I was a visiting Postdoctoral researcher at the University of Naples Federico II collaborating with Prof. Silvia Rossi.

My work focuses on creating proactive, personalised robots that can tailor their behaviour to each individual’s unique needs and preferences. Additionally, I investigate how robots can explain their decisions, helping users build clearer mental models of these systems. Ultimately, I aim to make robots more transparent and understandable, enabling users to interact confidently with technology that integrates seamlessly into their lives. I have organised workshops on topics realated to trust,ai, ethics and personalisation at HRI, RO-MAN and ICSR conferecences. I have served as guest editor of several special issues of journals such as International Journal of Social Robotics, Frontiers in Robotics and AI, Paladyn Journal of Behaviour and Interaction Studies and as associate editor at IROS, RO-MAN and ICSR.

Interests

  • Human-Centered Robotics
  • Socially Assistive Robotics
  • Short- and Long-term Personalisation
  • Robot Personalisation
  • Experimental Design
  • Proactive Behaviour
  • Explainable Robotics
  • User Mental Models

Education

  • PhD in Control, Robotics and Vision, 2022

    Institut de Robotica i Informatica Industrial, CSIC-UPC

  • MEng in Artificial Intelligence, 2009

    Sapienza, University of Rome

  • BSc in Computer Engineering, 2006

    Sapienza, University of Rome

Latest News

Jun 2024
-


Dic 2023
-
Our work Dataset and Evaluation of Automatic Speech Recognition for Multi-lingual Intent Recognition on Social Robots will be presented at the 2024 ACM/IEEE International Conference on Human-Robot Interaction

Experience

 
 
 
 
 

Researcher Scientist

Pal Robotics

Feb 2022 – Present Barcelona, ESP
Marie Curie fellow in the EU PRO-CARED project funded by the H2020 Program and Acció. The aim of the project is to develop social robots to help children and adults learn a second language, focusing primarily on people arriving from foreign countries. Language learning is the first obvious barrier to the integration of this population and their adaptation to different cultures. I focus on designing and developing mechanisms for personal robots to proactively interact with students providing them with adaptive and personalised assistance in an educational context.
 
 
 
 
 

Researcher and PhD Student

Institut de Robotica i Informatica Industrial

Mar 2017 – Feb 2022 Barcelona, ESP
Designed and developed a fully autonomous personalised-robot assisted cognitive training for patients affected by cognitive impairment. Tacked personalisation by designing robots that are both adaptable and adaptive. Adaptable in such a manner as to enable therapists to set them up and customise their high-level behaviour. Adaptive in such a manner that they can tailor their intervention to suit the individual’s unique needs as they evolve through time. Developed a novel framework called aCtive leARning agEnt aSsiStive bEhaviouR (CARESSER) which enables therapists to customise the robot’s assistive behaviour (adaptable) and allows the robot to learn in situ personalised patient-specific policies (adaptive) in a fully autonomous fashion. Evaluation of the robotic system in a healthcare centre with 22 patients affected my mild cognitive impairment and mild dementia.
 
 
 
 
 

Artificial Intelligence Lead

Cogisen

Jan 2012 – Oct 2016 Rome, IT
Worked on developing a set of machine learning algorithms aiming to go beyond the current limitations. The algorithms had been used for gaze tracking technology with RGB cameras as well as for image and video compression. The platform I worked on, allowed for the quick creation of models to capture and follow specific sparse changes of information in the frequency domain.
 
 
 
 
 

Artificial Intelligence Expert

Cogisen

Jan 2010 – Jan 2012 Rome, IT
Worked on the first gaze tracking solution for an F1 simulator at Ferrari. Furthermore, developed a silhouette detection pipeline for a kart simulator for a Ferrari Driver Academy pilot.
 
 
 
 
 

Artificial Intelligence Consultant

Cogisen

Jul 2009 – Jan 2010 Rome, IT
Analysed and evaluated the opportunity to introduce artificial intelligence into the automotive market.
 
 
 
 
 

MEng in Artificial Intelligence

La Sapienza, University of Rome

Jan 2007 – Mar 2009 Rome, IT
Studied the generation of rational behaviors through the planning of actions for teams of robots that follow different objectives. The thesis work consisted of three different activities: i) formalize the domain in Situation Calculus, ii) formulate an approach to find a solution that takes into account both the cooperative aspect of the team as well as the conflict situations, iii) validate the proposed approach in a rescue scenario.
 
 
 
 
 

BSc in Computer Engineering

La Sapienza, University of Rome

Sep 2003 – Dec 2006 Rome, IT
Analysis and evaluation of the object recognition algorithm, SIFT.

Contact

  • C/ Llorens i Artigas 4-6, Barcelona, CAT, 08028, Spain
  • First Floor, Office 13
  • DM Me
  • Skype Me