Responsive image

Download the Call for Papers (A4 format)

Satellite Call For Contributions

Special Issue on Emerging Topics on Development and Learning
IEEE Transactions on Cognitive and Developmental Systems

This special issue will include state-of-the-art research on emerging topics on development and learning in natural and artificial systems. In addition to new submissions, papers presented at ICDL-EpiRob 2020 will be invited to submit extended versions to the special issue. All submissions, including those that are based on ICDL-EpiRob 2020 papers, will be reviewed as regular TCDS papers.

This special issue has a focus on development and learning from a multidisciplinary perspective gathering researchers from computer science, robotics, psychology, and developmental studies. We invite researchers to share knowledge and research on how humans and animals develop sensing, reasoning and actions, and how to exploit robots as research tools to test models of development and learning. We expect the submitted contributions emphasize the interaction with social and physical environments and how cognitive and developmental capabilities can be transferred to computing systems and robotics. This approach goes hand in hand with the goals of both understanding human and animal development and applying this knowledge to improve future intelligent technology, including for robots that will be in close interaction with humans.

Important Dates

Special Issue Submission Deadline Friday, 15th January 2021
Special Issue Notification Monday, 15th March 2021
Special Issue Revised Manuscripts Thursday, 10th June 2021
Special Issue Final Version Saturday, 10th July 2021
Submission page

REAL 2020 – Robot open-Ended Autonomous Learning competition

Open-ended learning, also named "life-long learning", "autonomous curriculum learning", and "no-task learning", aims to build learning machines and robots that are able to acquire skills and knowledge in an incremental fashion. The REAL competition addresses open-ended learning with a focus on "Robot open-Ended Autonomous Learning" (REAL)", that is, on systems that: (a) acquire sensorimotor competence that allows them to interact with objects and physical environments; (b) learn in a fully autonomous way, i.e. with no human intervention, on the basis of mechanisms such as curiosity, intrinsic motivations, task-free reinforcement learning, self-generated goals, and any other mechanism that might support autonomous learning. The competition will have a two-phase structure where during a first "intrinsic phase" the system will have a certain time to explore and learn in the environment freely, and then during an "extrinsic phase" the quality of the autonomously acquired knowledge will be measured with tasks unknown at design time. The objective of REAL is to:

  1. track the state-of-the-art in robot open-ended autonomous learning;
  2. foster research and the proposal of new solutions to the many problems posed by open-ended learning;
  3. favour the development of benchmarks in the field.

Participation in the competition, which leads to addressing key problems relevant to the ICDL community, is free, and everyone is welcome to participate!

  • Prizes Round 1: The members of the top 3 teams will receive free registrations for ICDL 2020.
  • Prizes Round 2: The top 3 teams will be invited to co-author a shared paper.

Important Dates of the Competition

Round 1 starts Thursday, 6th August 2020
Round 1 ends Thursday, 15th October 2020
Round 2 starts Sunday, 1st November 2020
Round 2 ends Sunday, 31st January 2021
Final evaluations Monday, 15th February 2021
Demo 1 – On the Right
Demo 2 – From the top
Demo 3 – On the left

You can find more background and the rules of the competition, download the software to develop your models in your computer, and take part in the competition here:

Competition page

Call For Contributions

Journal Track

The Journal Track is designed to provide a forum to discuss important results related to cognitive and developmental systems recently published as journal articles, but have not been previously presented as conference papers. Thus, the journal track offers an opportunity to present outstanding results that might otherwise not be submitted to a conference due to their length and complexity.

Important dates for journal track submissions:

Journal Track Submission Open Tuesday, 31st March 2020
Journal Track Submission Deadline Monday, 29th June 2020
Journal Track Notification Monday, 20th July 2020

For more information, visit the Submission Guidelines Page

Regular Papers

ICDL is a unique conference gathering researchers from computer science, robotics, psychology and developmental studies to share knowledge and research on how humans and animals develop sensing, reasoning and actions. This includes taking advantage of interaction with social and physical environments and how cognitive and developmental capabilities can be transferred to computing systems and robotics. This approach goes hand in hand with the goals of both understanding human and animal development and applying this knowledge to improve future intelligent technology, including for robots that will be in close interaction with humans.

Important Dates for Regular Paper Submissions

Paper Submission Open Saturday, 15th February 2020
Paper Submission Deadline (Extended) Sunday, 15th March 2020
Sunday, 21st June 2020
Paper Author Notification (Extended) Friday, 15th May 2020
Friday, 31st July 2020
Final Paper Version Due Wednesday, 1st July 2020
Sunday, 30th August 2020

For more information, visit the Submission Guidelines Page

Two-page extended abstract submissions

To encourage discussion of late-breaking results or for work that is not sufficiently mature for a regular paper, we will accept two-page extended abstracts, including references. These submissions will NOT be included in the conference proceedings. Accepted abstracts will have a 1-minute “teaser” presentation as part of the main conference session and will be showcased in the poster sessions.

Important Dates for Two-page extended abstract submissions

Abstract Submission Open Friday, 1st May 2020
Abstract Submission Deadline (Extended) Friday, 31st July 2020
Sunday, 9th August 2020
Abstract Author Notification Friday, 26th June 2020
Sunday, 30th August 2020
Final Abstract Version Due Friday, 10th July 2020
Wednesday, 30th September 2020

For more information, visit the Submission Guidelines Page


We invite experts in different areas to organize a tutorial. The goal of tutorials is to provide insights into specific topics through hands-on training and interactive experiences or in-depth state of the art review.

Tutorial organizers have several responsibilities, including activities scheduling, publicizing and providing the content on time. ICDL will support the organization with rooms, audio-visual equipment and coffee breaks.

Important dates for tutorial submissions:

Tutorial Proposals Open Saturday, 15th February 2020
Tutorial Proposals Deadline (Extended) Thursday, 30th April 2020
Friday, 15th May 2020
Tutorial Proposals Notification Saturday, 30th May 2020

For more information, visit the Submission Guidelines Page


We invite experts in different areas to organize a workshop. The goal of the workshops is to provide an informal forum for researchers to discuss emerging research questions and challenges.

Workshop organizers have several responsibilities, including coordinating workshop participation and content, publicizing and providing the program on time and moderating the program throughout the workshop. ICDL will support the organization with rooms, audio-visual equipment, coffee breaks and poster boards.

Workshops will be held on Monday, 7th September 2020 Wednesday, 28th October 2020 . Workshops will extend to a half or full-day.

Important dates for workshop submissions:

Workshops Monday, 7th September 2020
Wednesday, 28th October 2020
Workshop Proposals Open Sunday, 15th December 2019
Workshop Proposals Deadline (Extended) Wednesday, 15th January 2020
Wednesday, 29th January 2020
Workshop Proposals Notification Saturday, 15th February 2020

For more information, visit the Submission Guidelines Page

Keynote Speakers

Karen Quigley
Karen Quigley

Department of Psychology, Northeastern University

Dr. Quigley's basic science work examines the psychophysiological correlates of affective experience including emotions and stress, the role of interoception in affective experience, and how the body and brain work together to construct our affective experience. She is an experimental psychologist and psychophysiologist with more than 25 years' experience conducting research with a wide range of measures and samples, including people who have experienced negative functional impacts after major life events. She is a former president of the Society for Psychophysiological Research, and a Fellow of both the Association for Psychological Science and the Academy of Behavioral Medicine Research. She was formerly an Associate Editor for Psychophysiology, where she is currently a Consulting Editor. She is also on the editorial board for the new journal, Affective Science. In early work, she co-authored a model for quantifying and assessing autonomic control of cardiovascular responses during stressors in animals and humans, including in early life, and validated noninvasive indices of autonomic control of the heart for use in children and adults. New work focuses on better understanding the wide variation across people and contexts in how physiological features can map to affective experiences. To enable this work, she developed a new physiologically-triggered experience sampling method. Other work focuses on the role of biological features (such as energy regulation) and contextual features (such as exposure to major stressful life events) in shaping affective experience. In her applied work, she uses health technology as a means to intervene and enable positive lifestyle change, with the goal of improving health outcomes such as sleep, physical activity, and pain.

Understanding Variation in Affective Experience using Physiology

Maja Mataric
Maja Mataric

Chan Soon-Shiong Distinguished Professor of Computer Science, Neuroscience, and Pediatrics, University of Southern California

Maja Mataric is Chan Soon-Shiong Professor of Computer Science, Neuroscience, and Pediatrics at USC, founding director of the Robotics and Autonomous Systems Center and Vice Dean for Research. Her PhD and MS are from MIT, and BS from Kansas University. She is Fellow of AAAS, IEEE, and AAAI, recipient of the Presidential Award for Excellence in Science, Mathematics & Engineering Mentoring, Anita Borg Institute Women of Vision for Innovation, NSF Career, MIT TR35 Innovation, and IEEE RAS Early Career Awards, is highly active in K-12 outreach (leading the USC Engineering K-12 STEM Center) and in mentoring of women and under-represented groups in engineering, and authored “The Robotics Primer” (MIT Press). A pioneer of the filed of socially assistive robotics, her research team is developing human-robot interaction methods for convalescence, rehabilitation, training, and education for children with autism spectrum disorders, stroke and traumatic brain injury survivors, and individuals with Alzheimer's Disease. She is also co-founder of Embodied, Inc.

Socially Assistive Robotics Right Now: The Need for Personalized Embodied Systems for In-Home Support of Health, Wellness, Education, and Training

The nexus of advances in robotics, NLU, and machine learning has created opportunities for personalized robots for the ultimate robotics frontier, the home. The current pandemic has both caused and exposed unprecedented levels of health & wellness, education, and training needs worldwide, which must increasingly be addressed in the home. Socially assistive robotics has the potential to address those needs through personalized and affordable in-home support. This talk will discuss human-robot interaction methods for socially assistive robotics that utilize multi-modal interaction data and expressive and persuasive robot behavior to monitor, coach, and motivate users to engage in health, wellness, education and training activities. Methods and results will be presented that include modeling, learning, and personalizing user motivation, engagement, and coaching of healthy children and adults, stroke patients, Alzheimer's patients, and children with autism spectrum disorders, in short and long-term (month+) deployments in schools, therapy centers, and homes. Research and commercial implications and pathways will be discussed.

Adrián Palacios
Adrián Palacios

Universidad de Valparaíso and Centro Interdisciplinario de Neurociencia de Valparaiso (CINV)

Featured Speakers 20 years of Developmental Learning Conferences

Hideki Kozima
Hideki Kozima

Graduate School of Education, Tohoku University, Japan

Hideki Kozima is a professor at the Graduate School of Education, Tohoku University, since 2018. He received his Ph.D. in Computer Science and Information Mathematics from the University of Electro-Communications (Tokyo, Japan) in 1994. He worked as a research scientist at the National Institute of Information and Communications Technology (NICT; headquarter in Tokyo) from 1994 to 2008. In 2001, he and Dr. Jordan Zlatev (Lund University, Sweden) co-founded a research community under the title of “Epigenetic Robotics” and started a series of international conferences, which is known as “IEEE ICDL-EpiRob” today. In 2008, he moved to Miyagi University (Miyagi, Japan), serving as a professor and vice president. His current research interest includes cognitive developmental robotics, autism and developmental disorders, and information technologies for education and therapy.

Epigenesis of Social Intelligence: Twenty-year Research Since EpiRob 2001

ICDL-EpiRob has its roots in ICDL and EpiRob. For the latter, EpiRob, Jordan Zlatev (Lund University, Sweden) and myself (CRL/NICT, Japan) started in 2001 as a series of conferences on “Epigenetic Robotics”, which aimed at “modeling cognitive development in robotic systems”. For the last 20 years, EpiRob contributed to establishing a new research field and research community for modeling “embodiment and situatedness”, “development and learning”, “communication and socialization”, “language and semiosis” and so on.

In that large context, we pursued an engineering model of “social development”, especially “human communication in the preverbal stage”, and “autism” as the other side of a coin. I developed a child-like humanoid, “Infanoid”, which is capable of making eye-contact and joint attention with human caregivers. Joint attention is one of the most important keys to communicative development through social interaction with caregivers. Infanoid had been used in psychological experiments to investigate how humans, especially children, interpret its gaze and behavior. We found that even 4-year-olds read the “mind” of the robot. Then, we move forward to making a simpler robot for psychological experiments with younger children. The new robot, “Keepon”, has a simple appearance, but it is still capable of pre-verbal communication as that of Infanoid. We found that children of different ages, from 6 months old, understand and acted on Keepon differently according to their developmental stages.

We intensively used those robots, especially Keepon, for autism research. Autism is characterized by (1) deficits in communication in both verbal and non-verbal ways and (2) restricted imagination, such as repetitive and/or restricted behavior and interest. Understanding autism and understanding human communication are the two sides of a coin. Keepon engaged in a longitudinal observation at a daycare center for autistic children for over 10 years, where we learned that Keepon's simple appearance worked well in establishing meaningful interaction with the children. Based on the observation, we hypothesized that autistic children have difficulty in transforming high-dimensional perceptual information (for instance, visual/auditory image of others) into low-dimensional social meanings (for instance, attention/emotion of others). The actual mechanism of this information transformation is still unknown.

To understand the social transformer, which we called “mentalizing filter”, we are currently looking into brains. Based on the recent findings of the higher density in mini-columnar structure in autistic brains, we assumed the following points. (1) The density of the cortical structure determines “cognitive granularity”, especially in perceptual and linguistic categories. (2) The cognitive granularity is related to the abstraction level in mentalizing others' behavior, at which we explain others' behavior in terms of intentions or states of mind. And, (3) such finer cognitive granularity will produce the diversity of ASD's behavioral symptoms, including social communication disorders and the restricted interest and behavior. We are currently working on theorizing and experimenting (in medical and computational ways) this grand hypothesis.

Kozima, H., & Yano, H. (2001). A Robot That Learns to Communicate with Human Caregivers. International Workshop on Epigenetic Robotics (EpiRob), 1st.

Gianluca Baldassarre
Gianluca Baldassarre

Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche (ISTC-CNR), Italy

Gianluca Baldassarre received the B.A. and M.A. degrees in economics and the M.Sc. degree in cognitive psychology and neural networks from the University of Rome “La Sapienza,” Rome, Italy, in 1998 and 1999, respectively, and the Ph.D. degree in computer science with the University of Essex, Colchester, U.K., in 2003, with a focus on planning with neural networks. He was a Post-Doctoral Fellow with the Italian Institute of Cognitive Sciences and Technologies, National Research Council, Rome, researching on swarm robotics, where he has been a Researcher, since 2006, and coordinates the Research Group that he founded called the Laboratory of Computational Embodied Neuroscience. From 2006 to 2009, he was a Team Leader of the EU Project “ICEA—Integrating Cognition Emotion and Autonomy” and the Coordinator of the European Integrated Project “IM-CLeVeR— Intrinsically-Motivated Cumulative-Learning Versatile Robots,” from 2009 to 2013, and is currently Team Leader of the EU Project “GOAL-Robots – Goal-based Open-ended Autonomous Learning Robots”. He has over 100 international peer-review publications. His cur- rent research interests include cumulative learning of multiple sensorimotor skills driven by extrinsic and intrinsic motivations. He studies these topics with two interdisciplinary approaches: with computational models constrained by data on brain and behavior, aiming to understand the latter ones and with machine-learning/robotic approaches, aiming to produce technologically useful robots.

What Are Intrinsic Motivations? A Biological and Robotics Perspective

Intrinsic motivations (IMs) have for long been studied by psychologists, and lately by cognitive science and computer modelling that is greatly contributing to give operational definitions and taxonomies of them. The identification of IMs is challenging as they involve several functions and mechanisms that interplay in complex ways within brain and robot architectures. Following the talk I gave at ICDL2011, I contribute here to disentangling these aspects from a biology perspective and add also a second perspective from the robotics perspective. First, by contrasting them to extrinsic motivations (EMs), I give a general definition of IMs as fundamental drives that can guide the autonomous acquisition of knowledge and skills. Then I focus on what I call epistemic IMs, and proceed to distinguish between novelty-based, prediction-based and competence-based IMs. I then present few examples of how EMs and such IMs can be implemented in the brain. I then proceed to consider IMs from the perspective of robots. To this purpose, I introduce the EU funded project GOAL-Robots, focussed on IMs for the acquisition of skills, that is stressing how IMs are very important to lead to the autonomous acquisition of goals that in turn support the acquisition of skills. I then illustrate this more in detail with two examples of robotics models able to fully autonomously acquire goals and skills. Overall, the presentation highlights the importance that IMs have as drives for the non-materialistic development of humans and for supporting open-ended learning in robots.

Baldassarre, G. (2011). What Are Intrinsic Motivations? A Biological Perspective. IEEE International Conference on Development and Learning (ICDL), 2, 1–8.

Andrew G. Barto
Andrew G. Barto

University of Michigan, Ann Arbor, Michigan, USA

Tentative Video Conference

Barto, A. G., Singh, S., & Chentanez, N. (2004). Intrinsically Motivated Learning of Hierarchical Collections of Skills. International Conference on Developmental Learning (ICDL), 112–119.


Department of Engineering, Aarhus University

Universidad Técnica Federico Santa María

Advanced Mining Technology Center

Centro de Innovación y Robótica

Deakin University

Universidad Andrés Bello



IEEE Computational Intelligence Society


The Clover: Ingeniería 2030


Universidad Técnica Federico Santa María

Advanced Center of Electrical and Electronic Engineering


Advanced Mining Technology Center