Personal profile

Gianluca Baldassarre

The information published in this page are entirely managed by GIANLUCA BALDASSARRE who is completely responsible for it.

*** Position *** Senior Researcher, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche, Rome, Italy

*** Keywords *** Artificial Intelligence; Machine Learning; Classic and deep neural networks; Computational embodied neuroscience; Developmental robotics; Extrinsic motivations and emotions; Habitual and goal-directed behaviour; Hierarchical organisation of action; Open-ended learning; Intrinsic motivations; Neural networks.

*** Positions: *** 1996: Degree in Economics 1996-1997: Autonomous study in cognitive psychology and neuroscience 1997: Master in Cognitive Psychlogy and Neural Network Models 1998-2001: PhD in Computer Science, University of Essex, UK 2001-2005: Postdoc, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche (ISTC-CNR), Rome, Italy 2006-now: Researcher at ISTC-CNR 2006-now: Founder and principal investigator of the Research Group ''Laboratory of computational Embodied Neuroscience'', LOCEN-ISTC-CNR, now formed by 9 researchers 2006-2009: Principal investigator for ISTC-CNR of EU Integrated Project ''ICEA - Integrating Cognition, Emotion and Autonomy'' 2009-2013: Coordinator of EU Integrated Project IM-CLeVeR - Intrinsically Motivated Cumulative Learning Versatile Robots 1998-now: about 100 hundred peer-review publications in artificial life, cognitive science, autonomous robotics, and recently in psychology, neuroscience, developmental robotics

Other publication name:

Baldassarre

Other publication name:

Baldassarre, G.

Other publication name:

Baldassarre G

Interest areas:

*** General research goals *** The research group coordinated by Gianluca Baldassarre carries out research with two interdependent goals: 1) Developing architectures to control humanoid robots able to undergo open-ended learning based on self-generated goals and intrinsic motivations (curiosity). 2) Investigating how the brain generates behaviour by interacting with the body and with the environment, based on computational system-level models.

*** Specific research topics *** 1. Intrinsic motivations (robots: novelty/prediction/competence-based IMs; brain: superior colliculus and hippocampus) 2. Extrinsic motivations (the accomplishment of the user's goals; brain: based on the brain amygdala, hypothalamus, and nucleus accumbens) 3. The hierarchical organisation of motor behaviour (robots: hierarchical reinforcement learning; brain: based on basal ganglia, prefrontal, and motor cortex). 4. Learning (robots: supervised/unsupervised/reinforcement learning; Brain: Hebbian learning, STDP)

*** Research method used *** The research group coordinated by Gianluca Baldassarre uses two research methods that strongly synergise: 1) To study autonomous open-ended learning, the group builds architectures to control autonomous humanoid robots, with a particular focus on camera-arm-hand object manipulation tasks; the controllers are mainly developed in simulation to allow long periods of autonomous learning, and then when possible tested in real robots. The robot's architectures built are based on classic (shallow) and deep neural networks; these are trained with algorithms involving goal/based and model-based reinforcement learning, and supervised and unsupervised learning algorithms. 2) The computational models built to understand how the brain can produce adaptive behaviour are based on 'Computational Embodied Neuroscience'. This modelling approach, developed by the group, is based on these principles: (a) Importance given to natural evolution to understand behaviour in terms of its adaptive function; (b) view of behaviour as a phenomenon emergent from the brain-body-environment interaction, and the aim to understand the functioning of organisms 'as a whole' (overall, the used approach is a 'top-down approach', starting from behaviour and functions and then moving to the underlying brain mechanisms); (c) Using assumptions grounded on anatomy and physiology of the brain to build the architecture and functioning of models; (d) testing and comparing models for their capacity of reproducing and explaining several specific experimental data on behaviour and the brain physiology not incorporated in the model as assumptions, and for their capacity of producing predictions testable in empirical experiments.


Contacts

Phone: 0644595231
Fax: 0644595243
Address: Gianluca Baldassarre, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche (ISTC-CNR), Via San Martino della Battaglia 44, I-00185 Roma, Italy

International Ids


H-indexes

Google Scholar H-Index: 37
Scopus H-Index: 27
ISI-WoS H-Index: 24

Experience

Senior Researcher
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale San Martino della Battaglia 44, 00158 Roma, Italy
Company web site: https://www.istc.cnr.it/
Time period: 11/2019 - today

Computational neuroscience, Developmental robotics models, AI and Machine learning, Neural-Network models on: open-ended learning and development, simple and hierarchical reinforcement learning, intrinsic and extrinsic motivations, eye-hand coordination in organisms and robots, bottom-up and top-down attention in organisms and robots, brain mechanisms underlying classic and operant conditioning, brain hierarchical organization underlying motor behaviour and embodied cognition, mental diseases.


Researcher
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale San Martino della Battaglia 44, 00158 Roma, Italy
Company web site: https://www.istc.cnr.it/
Time period: 02/2009 - 11/2019

Computational neuroscience, Developmental robotics models, AI and Machine learning, Neural-Network models on: open-ended learning and development, simple and hierarchical reinforcement learning, intrinsic and extrinsic motivations, eye-hand coordination in organisms and robots, bottom-up and top-down attention in organisms and robots, brain mechanisms underlying classic and operant conditioning, brain hierarchical organization underlying motor behaviour and embodied cognition, mental diseases.


Researcher (contract)
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale San Martino della Battaglia 44, 00158 Roma, Italy
Company web site: https://www.istc.cnr.it/
Time period: 03/2006 - 02/2009

Computational neuroscience and robotic models of: classic and operant conditioning, drives and emotions, spatial orientation, eye-hand coordination, bottom-up and top-down attention, prediction and planning. Research carried out within the European Project "ICEA".


Researcher (contract)
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale San Martino della Battaglia 44, 00158 Roma, Italy
Company web site: https://www.istc.cnr.it/
Time period: 03/2005 - 03/2006

Neural and robotic models of eye-hand coordination, bottom-up and top-down prediction and planning. Research carried out within the European Project "MindRACES".


Research Fellow
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale Marx 43, 00137, Roma, Italy
Time period: 03/2004 - 03/2005

Collective robotics, simulated robots, self-organization, neural networks, genetic algorithms. Research within European Project "ECAgents".


Research Fellow
Company: ISTC - Istituto di scienze e tecnologie della cognizione - Viale Marx 43, 00137, Roma, Italy
Time period: 11/2001 - 03/2004

Collective robotics, simulated robots, self-organization, neural networks, genetic algorithms. Research carried out within the European Project "Swarm-bots".



Activities

Scientific projects

Related working experience: Senior Researcher
Role: Coordinator
Participation time period: 11/2016 - 04/2021
Involved organizations: EUROPEAN UNION;

The project has three main objectives: (1) to advance our understanding of how children form goals and use them to guide the learning of the skills and achieve them; (2) develop innovative computational robotic architectures and algorithms that support (2a) the autonomous generation of objectives based on mechanisms such as intrinsic motivations and (2b) the use of such objectives to efficiently and autonomously build large repertoires of skills; (3) demonstrate the potential of the proposed systems with a series of increasingly difficult demonstrators in which robots autonomously develop complex skills and use them to solve challenges in real-life scenarios (open-ended learning). Results achieved: The project is advancing our understanding of the fundamental principles of autonomous learning in children and is helping to bring about a paradigm shift in the field of autonomous robotics by producing for the first time robots capable of autonomously accumulating complex skills and knowledge in a way that truly open-ended.

Type/funding: European Commission, 8th Framework Program (H2020): Future Emergent Technology (FET) Project. Total amount of financing: 3,481,875.00 EUR Financing amount ISTC-CNR: EUR 1,278,708.00 Contract no.: Grant Agreement n. 713010

Other project partners: 1. Beneficiary Organisation - Université del Paris - UP; Principal investigator: Kevin J. O'Regan. 2. Beneficiary Organisation - Stiftung Frankfurt Institute for Advanced Studies - FIAS; Principal investigator: Jochen Triesch. 3. Beneficiary Organisation - Technische Universitat Darmstadt - TUDa; Principal investigator: Jan Peters.



Languages

Production Understanding
Written Oral Written Oral Notes
English - Full professional proficiencyC1C1C1C1

November 1998 - October 2001: PhD at the University of Essex, Colchester, UK


Research activities classification (ERC)

ARTIFICIAL INTELLIGENCE, INTELLIGENT SYSTEMS, MULTI AGENT SYSTEMS
BEHAVIORAL NEUROSCIENCE (E.G. SLEEP, CONSCIOUSNESS, HANDEDNESS)
COGNITION (E.G. LEARNING, MEMORY, EMOTIONS, SPEECH)
COGNITIVE AND EXPERIMENTAL PSYCHOLOGY: PERCEPTION, ACTION, AND HIGHER COGNITIVE PROCESSES
COMPUTER SCIENCE AND INFORMATICS: INFORMATICS AND INFORMATION SYSTEMS, COMPUTER SCIENCE, SCIENTIFIC COMPUTING, INTELLIGENT SYSTEMS
EDUCATION: SYSTEMS AND INSTITUTIONS, TEACHING AND LEARNING
EPISTEMOLOGY, LOGIC, PHILOSOPHY OF SCIENCE
EVOLUTION OF MIND AND COGNITIVE FUNCTIONS, ANIMAL COMMUNICATION
HUMAN COMPUTER INTERACTION AND INTERFACE, VISUALIZATION AND NATURAL LANGUAGE PROCESSING
MACHINE LEARNING, STATISTICAL DATA PROCESSING AND APPLICATIONS USING SIGNAL PROCESSING (EG. SPEECH, IMAGE, VIDEO)
NEUROSCIENCES AND NEURAL DISORDERS: NEUROBIOLOGY, NEUROANATOMY, NEUROPHYSIOLOGY, NEUROCHEMISTRY, NEUROPHARMACOLOGY, NEUROIMAGING, SYSTEMS NEUROSCIENCE, NEUROLOGICAL DISORDERS, PSYCHIATRY
PHILOSOPHY, HISTORY OF PHILOSOPHY
PSYCHIATRIC DISORDERS (E.G. SCHIZOPHRENIA, AUTISM, TOURETTE'S SYNDROME, OBSESSIVECOMPULSIVE DISORDER, DEPRESSION, BIPOLAR DISORDER, ATTENTION DEFICIT HYPERACTIVITY DISORDER)
ROBOTICS
SYSTEMS AND COMMUNICATION ENGINEERING: ELECTRONIC, COMMUNICATION, OPTICALAND SYSTEMS ENGINEERING
SYSTEMS NEUROSCIENCE
THE HUMAN MIND AND ITS COMPLEXITY: COGNITION, PSYCHOLOGY, LINGUISTICS, PHILOSOPHY AND EDUCATION

Skills

AMYGDALA
ARTIFICIAL INTELIGENCE
AUTONOMOUS ROBOTICS
BASAL GANGLIA
CLASSIC NEURAL NETWORKS
CLASSICAL AND INSTRUMENTAL CONDITIONING
COGNITIVE SCIENCE ARCHITECTURES
COMPUTATIONAL EMBODIED NEUROSCIENCE
DEEP NEURAL NETWORKS
GOAL-DIRECTED AND HABITUAL BEHAVIOUR
HIPPOCAMPUS
LEAKY AND SPIKING NEURON MODELS
MACHINE LEARNING
MOTOR BEHAVIOUR
MOTOR CORTEX
PLANNING
PREFRONTAL CORTEX
REINFORCEMENT LEARNING
ROBOTIC OBJECT MANIPULATION
SERVICE ROBOTS
SIMULATION OF BRAIN AND BEHAVIOUR
SUPERVISED LEARNING
UNSUPERVISED LEARNING

Curriculum Vitae

CV Gianluca Baldassarre June 2020 - Primo Ricercatore (Senior Researcher) (eng)

1996: BA and MSc in Economics (Thesis: "Simulation of oligopolistic competing agents") 1996-1997: MSc in Cognitive Psychology and Neural Network Modelling (Thesis: "A model of eye-arm coordination") 1997-1998: Research Assistant, Institute of Cognitive Sciences and Technologies, Italian National Research Council (ISTC-CNR), Rome, Italy (Research: "A model of attention", "A model of cultural evolution") 1998-2001: PhD in Computer Science , University of Essex, UK (Thesis: "Planning with neural-networks and reinforcement learning") 2001-2005: Postdoc at ISTC-CNR (Research: "Swarm robotics, neural networks, evolutionary algorithms") 2006-now: Researcher at ISTC-CNR (Topics: "Autonomous robots, AI, machine learning, classic and deep neural networks: open-ended learning, goal self-generation and intrinsic motivations, hierarchical reinforcement learning, supervised and unsupervised learning, camera-arm-gripper object manipulation. Brain and behaviour: leaky and spiking neuron networks, evolution, development, goal-directed and habitual behaviour, motor behaviour, planning, consciousness; amygdala, hippocampus, basal ganglia, prefrontal and motor cortex.") 2006-now: Founder and Principal Investigator of the Research Group ''Laboratory of computational Embodied Neuroscience'' (LOCEN-ISTC-CNR) 2006-2009: Principal investigator for ISTC-CNR of EU Integrated Project ''ICEA - Integrating Cognition, Emotion and Autonomy'' 2009-2013: Coordinator of EU Integrated Project "IM-CLeVeR - Intrinsically Motivated Cumulative Learning Versatile Robots" 2016-2021: Coordinator of EU Project "GOAL-Robots - Goal-based Open-ended Autonomous Learning Robots" 2020-2021: Coordinator of EU EIC Project "PLUS-ME - Transitional Wearable Companions for the therapy with children with Autism Spectrum Disorders" 2020-2022: Coordinator of EU EIC Project "IM-TWIN - from Intrinsic Motivations to Transitional Wearable INtelligent companions for autism spectrum disorder " 1998-now: More than 100 international publications in developmental robotics and computational system-level models of brain and behaviour


Research products

Gianluca BALDASSARRE Daniele CALIGIORE Adriano CAPIRCHIO Maria Luisa DI MUZIO Massimo GIULIANO Pierandrea MIRINO

Costituzione Spin off di Ricerca AI2Life srl

(2020)
Sperati, Valerio; Ozcan, Beste; Romano, Laura; Moretta, Tania; Scaffaro, Simone; Faedda, Noemi; Turturo, Giada; Fioriello, Francesca; Pelosi, Simone; Giovannone, Federica; Sogos, Carla; Guidetti, Vincenzo; Baldassarre, Gianluca

Acceptability of the Transitional Wearable Companion "+me" in Children With Autism Spectrum Disorder: A Comparative Pilot Study

(2020) in Frontiers in Psychology
Mattera A, Pagani M, Baldassarre G

A computational model integrating multiple phenomena on cued fear conditioning, extinction, and reinstatement

(2020) in Frontiers in systems neuroscience
Kristsana Seepanomwan; Daniele Caligiore; Kevin J. O'Regan; Gianluca Baldassarre

Intrinsic Motivations and Planning to Explain Tool-Use Development: A Study with a Simulated Robot Model

(2020) in IEEE Transactions on Cognitive and Developmental Systems
Caligiore D.; Silvetti M.; D'Amelio M.; Puglisi-Allegra S.; Baldassarre G.; Anbarjafari G.

Computational Modeling of Catecholamines Dysfunction in Alzheimer's Disease at Pre-Plaque Stage

(2020) in Journal of Alzheimer's disease
Angelo Oddi and Riccardo Rasconi and Vieri Giuliano Santucci and Gabriele Sartor and Emilio Cartoni and Francesco Mannella and Gianluca Baldassarre

Integrating Open-Ended Learning in the Sense-Plan-Act Robot Control Paradigm

(2020) ECAI 2020 - 24th European Conference on Artificial Intelligence, Santiago de Compostela, Spain, 29/08/2020, 8/9/2020
Oddi A.; Rasconi R.; Santucci V.G.; Sartor G.; Cartoni E.; Mannella F.; Baldassarre G.

An intrinsically motivated planning architecture for curiosity-driven robots

(2020) Proceedings of the 6th Italian Workshop on Artificial Intelligence and Robotics (AIRO 2019), 22/11/2019
Santucci, Vieri Giuliano; Oudeyer, Pierre-Yves; Barto, Andrew; Baldassarre, Gianluca

Intrinsically Motivated Open-Ended Learning in Autonomous Robots

(2020) in Frontiers in neurorobotics
Vieri Giuliano Santucci, Davide Montella, Bruno Castro da Silva and Gianluca Baldassarre

Autonomous learning of multiple,context-dependent tasks

(2020)
Visualizza ulteriori prodotti