You are here: Home / Symposium

Submission deadline : May 1, 2023

Presentation

The 26th RoboCup International Symposium will be held on 10 July 2023, in conjunction with RoboCup23 (July 4 to 10, 2023) in Bordeaux, France.

Program
Poster - Regular track
Poster - Dev track

Focus on Cynthia Breazeal’s speech – Social Robots: Reflections and Predictions of Our Future Relationship with Personal Robots 

Abstract
In this keynote, I offer a perspective and reflections on the field of Social Robotics from its origins, its evolution and achievements, and its importance for the future. Since its inception in the late 1990s, Social Robotics introduced and advanced the socio-emotional and interpersonal dimensions of how people interact with autonomous robots.  Kismet, widely regarded as the first social robot, explored the dynamic interplay of computationally modeled socio-emotive-cognitive processes with real-time human social behavior to engage, communicate, and collaborate with people. Since then, the field of Social Robotics has grown into a vibrant global community that has continued to advance three key areas and their interplay 1) the computational science of endowing autonomous robots with greater social and emotional skills and intelligence, 2) the interaction design of social robots for a wide range of tasks and contexts where rapport is important and 3) the psychological science of understanding how people experience and interact with social robots in increasingly sophisticated ways over longer periods of time. About twenty years since its origins, we are witnessing social robots begin to enter consumer and industrial markets in manufacturing, healthcare, education, aging, entertainment, mobility, and more. And the field continues to inform and influence the design of a menagerie of other personified AI technologies across a wide range of uses. The future of social robotics promises to be exciting as advances in AI, robotics, and cloud computing platforms are enabling the community to deploy multitudes of social robots over longer periods of time to more deeply understand what it means for all kinds of people to live and collaborate with social robots as part of daily life – beyond short-term interaction to consider the future of the human-robot relationship. This promise also raises important issues, challenges, and opportunities for how to design personified AI technologies in an ethical and responsible way to promote social good.

Cynthia Breazeal is a Professor at the MIT Media Lab where she directs the Personal Robots Group. She also director of the MIT initiative on Responsible AI for Social Empowerment and Education (RAISE) and is MIT Dean of Digital Learning. She is recognized as a pioneer of social robotics and human-robot interaction, is a fellow of the AAAI, and has commercialized personal robots for the home. Her work balances technical innovation in AI, UX design, and understanding the psychology of engagement to design personified AI technologies that promote human flourishing and personal growth in areas such as education, emotional wellness, aging, and more.  She is an international award-winning innovator, designer, and entrepreneur. She did her graduate work at the MIT AI Lab and received her doctorate in 2000 in Electrical Engineering and Computer Science from MIT.

Focus DeepMind’s speech : Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning

Abstract: We will present our work applying Deep Reinforcement Learning to synthesize sophisticated and safe movement skills for the Robotis OP3 humanoid robot with 20 actuated joints to play a simplified one-versus-one soccer game. We trained individual skills in isolation and then composed those skills end-to-end in a self-play setting. The resulting policy exhibited robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and it transitioned between them in a smooth, stable, and efficient manner. The agents also developed a basic strategic understanding of the game, and learned, for instance, to anticipate ball movements and to block opponent shots. The full range of behaviors emerged from a small set of simple rewards. Our agents were trained in simulation and transferred to real robots zero-shot. We found that a combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training in simulation enabled good-quality transfer, despite significant unmodeled effects and variations across robot instances. Although the robots are inherently fragile, minor hardware modifications together with regularization of the behavior during training led the robots to learn safe and effective movements while still performing in a dynamic and agile way.

Bios:

Ben Moran: Ben Moran is a Research Engineer at Google DeepMind, working on embodied AI and robotic locomotion.  Prior to joining Deepmind, he worked in automated trading and financial applications of machine learning.
Guy Lever: Guy Lever is a Research Scientist at Google DeepMind, working on reinforcement learning, multi-agent systems and embodied intelligence. His recent focus has been applying deep learning and reinforcement learning to embodied systems and robotics.

Title – Socio-affective robots: ethical issues

Abstract: In this keynote, I offer studies and reflections on the ethical issues of socio-affective Robots. Conversational agents and social robots using autonomous learning systems and affective computing will change the game around ethics. We need to build long-term experimentation to survey Human-Machine Co-evolution and to build ethics by design chatbots and robots. In the chair HUMAAINE (L. Devillers, CNRS), we aim to study the
Human-Machine Affective interactions and relationships, in order to audit and measure the potential influence of intelligent and affective systems on humans, and finally to go towards a conception of “ethical systems”, by design or not and to propose evaluation measures. In this
purpose, the planned scientific work focuses on the detection of social emotions in human voice, and on the study of audio and spoken language “nudges”, intended to induce changes in the behavior of the human interlocutor. This work should be complemented by experimental studies (long- term, human vs. machine influence, etc.) to evaluate ethical aspects and confidence in machines, as well as by demystification of these technologies among the general public which naturally tends towards anthropomorphism. The importance of this subject also lies in the variety of its societal applications (from care to the elderly and vulnerable people, to the economy, and education). way.

Bio : Laurence Devillers is a Full Professor of Artificial Intelligence (AI) at Sorbonne University and heads the research team on “Affective and social dimensions in Spoken interactions with (ro)bots: technological and ethical issues” at CNRS-LISN. Since 2020, she also leads the interdisciplinary Chair (including economists, linguists and computer scientists) on AI and digital nudge HUMAAINE: HUman-MAchine Affective INteraction & Ethics at CNRS. Her topics of research are Human-Machine co-evolution: from the modeling of emotions and human-robot dialogue to the ethical impacts for society and the risks and benefits of AI. She is a member of the National Comity Pilot on Ethics of Numeric (CNPEN). She is president of the Foundation Blaise Pascal on cultural mediation on Mathematics and Computer Science. She is responsible of the JTC21/CEN_CENELEC WG4 on Foundational and Societal Impact of AI that include AI-enhanced Nudging, Trustworthiness AI and “Green” AI. She wrote large-audience books : ‘Les robots émotionnels’ (Ed. L’Obs., 2020) and ´Des Robots et des Hommes: mythes, fantasmes et réalité’ (Ed. Plon, 2017).

List of topics

  • Robot Hardware and Software
    • mobile robotics
    • humanoid robotics
    • sensors and actuators
    • embedded and mobile devices
    • robot construction and new materials
    • robot system integration
    • robot software architectures
    • robot programming environments and languages
    • real-time and concurrent programming
    • robot simulators
    • sim2real learning
  • Perception and Action
    • 3D perception
    • distributed sensor integration
    • sensor noise filtering
    • real-time image processing and pattern recognition
    • motion and sensor models
    • sensory-motor control
    • robot kinematics and dynamics
    • high-dimensional motion control
  • Robot Cognition and Learning
    • world modelling and knowledge representation
    • learning from demonstration and imitation
    • localisation, navigation, and mapping
    • planning and reasoning
    • decision making under uncertainty
    • neural systems and deep learning
    • complex motor skill acquisition
    • reinforcement learning and optimisation
    • motion and sensor model learning
  • Human-Robot Interaction
    • robot social intelligence
    • fluency of interaction
    • speech synthesis and natural language generation
    • natural language recognition
    • explainable robot behaviours
    • emotion recognition and reaction
    • understanding human intent and behaviour
    • safety, security and dependability
    • enabling humans to predict robot behaviour
  • Multi-Robot Systems
    • team coordination methods
    • communication protocols
    • learning and adaptive systems
    • teamwork and heterogeneous agents
    • dynamic resource allocation
    • adjustable autonomy
  • Education and Edutainment
    • robotics and artificial intelligence education
    • educational robotics
    • robot kits and programming tools
    • robotic entertainment
  • Applications and Benchmarking
    • search and rescue robots
    • robot surveillance service and social robots
    • robots at home, at work and in public spaces
    • robots in the real world
    • performance metrics
    • human-robot interaction

Submission Guidelines

All papers will be peer-reviewed and evaluated by members of the senior program committee. The proceedings of the RoboCup International Symposium will be published and archived within the Lecture Notes in Artificial Intelligence (LNCS/LNAI) series by Springer-Verlag after the conference. Papers should be formatted following the LNAI author guidelines (https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines) and must be electronically submitted through the EasyChair electronic submission system (https://easychair.org/my/conference?conf=rcsymposium2023).

Submissions are limited to 12 pages including references.

Springer’s proceedings LaTeX templates are also available in Overleaf: https://de.overleaf.com/latex/templates/springer-lecture-notes-in-computer-science/kzwwpvhwnvfj

Invited Speakers

  • Laurence Devillers, Sorbonne University, France (confirmed)
  • Cynthia Breazeal, Massachusetts Institute of Technology, USA (confirmed)

Organizing committee

Venue

The conference will be held at 43 rue Pierre Noailles, Domaine du Haut Carré 33400 Talence.

Contact

Please feel free to ask for further information by emailing Alessandra Rossi – a.rossi@herts.ac.uk

En poursuivant votre navigation sur notre site, vous acceptez l’utilisation de cookies et/ou autres traceurs.
Ils sont utilisés pour vous proposer une expérience de navigation maximale et d’optimiser le fonctionnement de notre site. By continuing to browse our website, you accept the use of cookies and/or other tracking devices.
They are used in order to offer you a maximum browsing experience and to optimize the functioning of our website.

J'accepteI acceptPolitique relative aux cookiesCookie policy