In IEEE ICDL 2021, totally 5 workshops were accepted after carefully peer review, and were notified by the May 20th.
  Brief Introductions of accepted workshops are listed as below:

Workshop 1: Human aligned Reinforcement Learning for Autonomous Agents and Robots

Date: Aug. 27th
Duration: One day
  The focus of this workshop is to bring together researchers from the fields of robotics and RL to discuss and share state of-the-art methods, challenges and novel solutions pertaining to the issue of incorporating human-related aspects into RL agents and robots. This workshop will aim to solicit works discussing aspects for human-alignment, as well as theoretical and experimental frameworks for incorporating them, with a focus on realizing RL agents and robots that explicitly give due consideration to human factors. The main topics of interest in the proposed workshop are explainability, interactivity, safety, and ethics in social robotics and autonomous agents especially from a reinforcement learning perspective. In this regard, approaches with special interest for this workshop are (but not limited to):   • Explainability, interpretability, and transparency methods for feature-oriented and goal-driven RL.
  • Explainable robotic systems with RL approaches.
  • Assisted and interactive RL in human-robot and humanagent scenarios.
  • Human-in-the-loop RL and applications.
  • RL from demonstrations and imperfect demonstrations.
  • Robot and agent learning from multiple human sources.
  • Multi-robot systems with human collaboration.
  • Safe exploration during learning.
  • Ethical reasoning and moral uncertainty.
  • Fairness in RL and multi-agent systems.
  • Theory of mind based RL frameworks.
  • Use of human priors in RL.
Francisco Cruz, Deakin University, Geelong, Australia
Thommen George Karimpanal, Deakin University, Geelong, Australia
Miguel Solis, Universidad Andres Bello, Santiago, Chile
Pablo Barros, Italian Institute of Technology (IIT), Genova, Italy
Richard Dazeley, Deakin University, Geelong, Australia

For more details, please click: Website

Workshop 2: Feel-COG – the role of affect in the development of cognition

Date: Aug. 19th, 13:00 to 17:00 CEST
Duration: Half day
  People are social beings, naturally predisposed to interact in an adaptive and empathetic manner with others. From birth, human beings develop their cognitive, affective, and social skills from the exposure to and interaction with their social group - family, friends, peers. As we grow and learn, we become capable to register the cognitive and affective state of our peers, adjust our actions and speech to their perceived needs, and over a prolonged period of interaction also learn which behaviors are the most appropriate and well-suited for each one of them individually. This collection of abilities - of perception, interaction, affect, reasoning, memory, motivation for action, learning, interaction, etc. - is what defines us as cognitive agents. Modelling these abilities into a cognitive architecture - either as a way of understanding human cognition or as an attempt to endow an artificial agent with cognitive skills - has been approached by researchers from many fields (computer science, cognitive psychology, robotics, philosophy, neuroscience), and has resulted in an impressive number of architectures. However, while the vast majority of them share some common model of cognition and recognise as crucial the elements of perception, attention, action selection, learning, memory and reasoning, very few of them acknowledge the role social and affective interaction plays in the development of these skills.
  The goal of our workshop is to tackle precisely this issue. We wish to rekindle the conversation on the key importance of affect in the development of different cognitive abilities, both in natural cognitive agents (i.e. humans) and artificial ones (i.e. cognitive and social robots). We would like to address this issue from an interdisciplinary angle and we welcome researchers from a broad range of disciplines such as robotics, neurosciences, social sciences, psychology and computer science.
Ana Tanevska, Italian Institute of Technology (IIT), Genova, Italy
Lola Canamero, CY Cergy Paris Universite´, Cergy-Pontoise, France

For more details, please click: Website

Workshop 3: 2nd SMILES workshop – Sensorimotor Interaction, Language and Embodiment of Symbols

Date: Aug. 31st
Duration: One days
  On the one hand, models of sensorimotor interaction are embodied in the environment and in the interaction with other agents. On the other hand, recent Deep Learning development of Natural Language Processing (NLP) models allow to capture increasing language complexity (e.g. compositional representations, word embedding, long term dependencies). However, those NLP models are disembodied in the sense that they are learned from static datasets of text or speech. How can we bridge the gap from low-level sensorimotor interaction to high-level compositional symbolic communication? The SMILES workshop will address this issue through an interdisciplinary approach involving researchers from (but not limited to):
  • Sensori-motor learning.
  • Emergent communication in multi-agent systems.
  • Chunking of perceptuo-motor gestures (gestures in a general sense: motor, vocal, ...).
  • Sensori-motor learning, Symbol grounding and symbol emergence.
  • Compositional representations for communication and action sequence.
  • Hierarchical representations of temporal information.
  • Language processing and acquisition in brains and machines.
  • Models of animal communication.
  • Understanding composition and temporal processing in neural network models.
  • Enaction, active perception, perception-action loop.
Xavier Hinaut, Inria, Bordeaux, France
Clément Moulin-Frier, Inria and Ensta ParisTech, Bordeaux, France
Silvia Pagliarini, Inria, Bordeaux, France
Michael Spranger, Sony AI and Sony CSL, Tokyo, Japan
Tadahiro Taniguchi, Ritsumeikan University, Kyoto, Japan
Anne S. Warlaumont, University of California, Los Angeles, America
Junpei Zhong, Nottingham Trent University, Nottingham, United Kingdom

For more details, please click: Website

Workshop 4: Spatio-temporal Aspects of Embodied Predictive Processing

Date: Aug. 22th, 13:30-18:00 CST
Duration: Half day
  Understanding human intelligence and building strong AI systems is a key challenge of our generation. A particularly puzzling aspect is that the human brain seems to cope very well with spatio-temporal variability and fluctuations in sensory perception and uncertainty in the feedback of actions. In turn, the information processing in the brain seems to be embodied and tightly coupled across modalities. For explaining these characteristics, there are strong accounts that the brain is constantly predicting sensory input and feedback while minimizing free energy in the prediction, and hierarchically abstracting the perception as well as hierarchically composing action. Furthermore, it is also hypothesized that hyperpriors and hypopriors, which may be derived from meta priors, induce a failure of hierarchical inference in the brain, accounting for atypical perception and action of psychiatric disorders. The big open mystery is: how is the brain developing this on a mechanistic level and thus how can this get learned within an AI system? Thus, to lift this mystery , we further need to bring together research from computational neuroscience, cognitive psychology, and artificial intelligence.
  With this workshop, we particularly want to wrap up different recent hypotheses, models, and experiments, as well as discuss in-depth how to shape future imaging, behavioural, and developmental robotics studies. As a guiding theme, we aim to approach the following central questions:
  • How does the brain learn spatio-temporal stochasticity in perception and action?
  • What is the role of meta priors in learning spatio-temporal adaptive prediction?
  • How can developmental robotics help us to study spatio-mporal stochasticity as an analogy to infant learning?
  We examine these questions with the insight from invited key speakers from complementary fields as well as original contributions in breakout sessions in order to conclude the next step in a panel discussion.
Stefan Heinrich, The University of Tokyo, Tokyo, Japan
Shingo Murata, Keio University, Tokyo, Japan
Yukie Nagai, The University of Tokyo, Tokyo, Japan
Yuichi Yamashita, National Center of Neurology and Psychiatry, Tokyo, Japan

For more details, please click:Website

Workshop 5: Grand Challenges of Next-Generation Cognitive and Developmental Robotics

Date: Aug. 30th or 21st 3:00 pm - 6:20 pm(JST) (6am -9:20 am UTC, 11pm-2:20am PDT)
Duration: Half day
  The IEEE CIS Cognitive Developmental Systems (CDS) Technical Committee Task Force on Robotics and the IEEE RAS Cognitive Robotics (CoRo) Technical Committee have collaborated to organize this workshop. On December 21, 2020, the organizers held a collaborative online round table titled “What is the role of next generation of cognitive robotics?” to explore the next generation of cognitive robotics studies. The round table discussion aimed to bridge the gaps between cutting-edge researchers’ challenges in cognitive and developmental robotics. Based on the discussion, the organizers and speakers are collaboratively writing a survey paper, which will be on arXiv very soon (before the call for papers of this workshop). Owing to the round table’s overwhelming success, we are eager to expand the activity to the CDS and CoRo communities. We will have an open discussion about the future development of studies in the CDS and CoRo communities, i.e., core participants of ICDL-Epirob.
  In this workshop, we will discuss “grand challenges” to clarify and share current achievements and future challenges in cognitive and developmental robotics. The workshop will be held virtually because of COVID-19. However, we believe that having this virtual workshop will allow us to welcome more scholars and students from around the world, thereby expanding the community of cognitive and developmental robotics.
Tadahiro Taniguchi, Ritsumeikan University, Chair of Robotics TF
Shingo Shimoda, Riken, Chiar of Cognitive Robotics TC
Takyuki Nagai, Osaka University
Chie Hieida, Nara Institute of Science and Technology

For more details, please click: Website