LACORO 2023 Speakers

LECTURERS

  •
    Tamim Asfour

    Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany

    Tamim Asfour is full Professor of Humanoid Robotics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology (KIT). His research focuses on the engineering of high per...

    Tamim Asfour is full Professor of Humanoid Robotics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology (KIT). His research focuses on the engineering of high performance 24/7 humanoid robotics as well as on the mechano-informatics of humanoids as the synergetic integration of informatics, artificial intelligence and mechatronics into humanoid robot systems, which are able to predict, act and interact in the real world. In his research, he is reaching out and connecting to neighboring areas in large-scale national and European interdisciplinary projects in the area of robotics in combination with machine learning and computer vision. Tamim is the developer of the ARMAR humanoid robot family. He is scientific spokesperson of the KIT Center “Information · Systems · Technologies (KCIST)”, president of the Executive Board of the German Robotics Society (DGR), the Founding Editor-in-Chief of the IEEE-RAS Humanoids Conference Editorial Board, deputy Editor-in-Chief and Editor of the Robotics and Automation Letters.

    Talk Title: Engineering Humanoids with Motion Intelligence

    Abstract: Humanoid robotics plays a central role in robotics research as well as in understanding intelligence. Engineering humanoid robots that are able to learn from humans and sensorimotor experience, to predict the consequences of actions and exploit the interaction with the world to extend their cognitive horizon remains a research grand challenge. Currently, we are experiencing AI systems with superhuman performance in games, image and speech processing. However, the generation of robot behaviors with human-like motion intelligence and performance has yet to be achieved. In this talk, I will present recent progress towards engineering 24/7 humanoid robots that link perception and action to generate intelligent behavior. I will show the ARMAR humanoid robots performing complex grasping and manipulation tasks in kitchen and industrial environments, learning actions from human observation and experience as well as reasoning about object-action relations.

  •
    Javier Ruíz Del Solar San Martín

    Departamento de Ingeniería Eléctrica, Universidad de Chile

    Dr. Javier Ruiz del Solar is Professor of Electrical Engineering at the Universidad de Chile and Executive Director of the Advanced Mining Technology Center. He is interested on robots, autonomous sys...

    Dr. Javier Ruiz del Solar is Professor of Electrical Engineering at the Universidad de Chile and Executive Director of the Advanced Mining Technology Center. He is interested on robots, autonomous systems and learning. His research focuses on two areas, fundamental research in perception and learning, and applications of robotics technology in the real-world, mainly in mining. In the last years his has focused on the application of deep reinforcement learning to mobile robot applications.

    Talk Title: Deep Reinforcement Learning in Robotics

    Abstract: The basic concepts of classical Reinforced Learning (tabular) and its implementation through neural networks (Deep Reinforced Learning - DRL) will be addressed. Some popular DRL architectures will be reviewed, as well as their application in robotics.

  •
    Yukie Nagai

    The University of Tokyo, Japan

    Yukie Nagai is a Project Professor at the International Research Center for Neurointelligence, the University of Tokyo. She received her Ph.D. in Engineering from Osaka University in 2004 and then wor...

    Yukie Nagai is a Project Professor at the International Research Center for Neurointelligence, the University of Tokyo. She received her Ph.D. in Engineering from Osaka University in 2004 and then worked at the National Institute of Information and Communications Technology, Bielefeld University, and Osaka University. Since 2019, she leads Cognitive Developmental Robotics Lab at the University of Tokyo. Her research interests include cognitive developmental robotics, computational neuroscience, and assistive technologies for developmental disorders. She was elected to '30 women in robotics you need to know about' in 2019, 'World's 50 Most Renowned Women in Robotics' in 2020, and '35 Women in Robotics Engineering and Science' in 2022.

    Talk Title: Predictive Brain in Humans and Robots

    Abstract: What neural mechanisms underlie cognitive development? Can we build human-like intelligence in robots? My research group has been investigating human cognitive development by a computational approach. We suggest that a neuroscience theory called predictive coding provides a unified account for cognitive development. My talk first shows how artificial neural networks based on predictive coding enable robots to acquire various cognitive functions. Social behaviors such as reading intention/emotion and altruistic behavior emerge through prediction error minimization. Our experiments further demonstrate influences of altered predictive processing on cognitive development. Aberrant precision of prediction and sensation produce neurodiverse behaviors as observed in developmental disorders. I will discuss potentials and new challenges in building predictive brains in robots.

  •
    Lorenzo Jamone

    School of Electronic Engineering and Computer Science (EECS) of the Queen Mary University of London (QMUL), UK

    Lorenzo Jamone is a Senior Lecturer in Robotics at the School of Engineering and Materials Science of the Queen Mary University of London (UK). He is part of ARQ (Advanced Robotics at Queen Mary) and ...

    Lorenzo Jamone is a Senior Lecturer in Robotics at the School of Engineering and Materials Science of the Queen Mary University of London (UK). He is part of ARQ (Advanced Robotics at Queen Mary) and he is the founder and director of the CRISP group: Cognitive Robotics and Intelligent Systems for the People. He received the MS degree (honours) in computer engineering from the University of Genoa, Genoa, Italy, in 2006, and the PhD degree in humanoid technologies from the University of Genoa (Italy), and the Italian Institute of Technology, in 2010. He was an Associate Researcher at the Takanishi Laboratory, Waseda University (Tokyo, Japan) from 2010 to 2012, and at the Computer and Robot Vision Laboratory, Instituto Superior Técnico (Lisbon, Portugal) from 2012 to 2016. He has been a Turing Fellow since 2018. He has over 100 publications with an H-index of 26. His current research interests include cognitive robotics, robot learning, robotic manipulation, force and tactile sensing.

    Talk Title: The Intelligence of the Hand

    Abstract: The robots of today are mainly employed in heavy manufacturing industries (e.g. automotive): these are big robotic manipulators which perform simple and repetitive tasks in very structured environments. The robots of the future will be different. They will have to perform more complex tasks in more complex unstructured environments, even in collaboration with humans. To do so, they will need to use their hands (almost) as smartly as humans do, which is a tremendous challenge! How will this be achieved? Explicit insights from biology and psychology, well established control and engineering principles, modern AI techniques, have to be combined and properly integrated. In the talk I will briefly summarize our research efforts in the area of Cognitive Robotics (with the twofold objective of taking inspiration from humans to realize better robotic systems, and at the same time understanding more about human intelligence), with a focus on the intelligence of the hand: object exploration, grasping and manipulation, leveraging tactile sensing, computer vision and robot learning.

  •
    Pablo Barros

    Senior Machine Learning Researcher at Sony, Brussels, Belgium

    Pablo Barros is a machine learning scientist working at Sony R & D Center in Brussels, focusing on physiological and social signal processing applied to mental health solutions. Pablo holds a Ph.D. de...

    Pablo Barros is a machine learning scientist working at Sony R & D Center in Brussels, focusing on physiological and social signal processing applied to mental health solutions. Pablo holds a Ph.D. degree in computer science from the University of Hamburg, in Germany, and over the last years, has worked on different projects involving social robotics and affective computing. In particular, his research focuses on social perception, in particular facial expression recognition, but also on modelling, based on artificial intelligence, the role of social agents while interacting with humans.

    Talk Title: Simply) the Best: Modeling Social Components when Designing Competitive Reinforcement Learning Agents

    Abstract: With the recent advancements in deep reinforcement learning, we can build impressive and effective agents in competitive scenarios. The typical pipeline to design, implement and evaluate these agents, however, does not take into consideration the social parts of competitive interactions. In this talk, we will cover some of the recent developments in socially aware competitive reinforcement learning, and their advantages in building agents that can interact better with humans.

  •
    Bruno Lara

    Faculty of Sciences, Universidad Autónoma del Estado de Morelos (UAEM), Mexico

    Llevó a cabo estudios de doctorado en el King's College de la Universidad de Londres en el área de mecatrónica. Esto fue seguido de un posdoc en el TheorieLabor en la Universidad Friedrich Schiller en...

    Llevó a cabo estudios de doctorado en el King's College de la Universidad de Londres en el área de mecatrónica. Esto fue seguido de un posdoc en el TheorieLabor en la Universidad Friedrich Schiller en Jena, Alemania en el área de robótica evolutiva. Este trabajo se concentró en la investigación e implementación de neurocontroladores para agentes artificiales autónomos a través de evolución artificial. Después el Dr. Lara hizo un posdoc en el Max Planck Institute for Psychology Research en la ciudad de Munich, Alemania. Aquí llevó a cabo investigación en el papel que juegan diferentes conceptos de las ciencias cognitivas en el control de comportamiento de agentes autónomos. Desde el 2005 el Dr. Lara es profesor investigador en el Centro de Investigación en Ciencias de la Universidad Autónoma del Estado de Morelos en donde hasta el 2015 coordinó el cuerpo académico 'Sistemas Inteligentes de Percepción'. Desde el 2009 esta a cargo del laboratorio de robótica cognitiva, un espacio multidisciplinario, en donde convergen investigaciones desde diferentes áreas del conocimiento, incluyendo a la robótica, psicología, filosofía y computación entre otras. Durante el 2011 y 2012 llevó acabo una estancia sabática en el laboratorio de robótica cognitiva de la Dra. Verena Hafner en la Universidad Humboldt en Berlín. Esta colaboración se ha mantenido durante los años y resulto en una segunda estancia en el 2019-2020. Así mismo, el laboratorio de Robótica Cognitiva cuenta con múltiples colaboraciones nacionales e internacionales dentro de las que destacan la colaboración con la Dra. Alejandra Ciria, de la Faculta de Psicología de la UNAM y el Dr. Guido Schillaci del Joint Research Centre, de la Comisión Europea.

    Talk Title: Cognitive Robotics and Prediction Error Dynamics. New Perspectives.

    Abstract: How do cognitive agents decide which is the relevant information to learn and how goals are selected to gain this knowledge? We argue that emotions arise when differences between expected and actual rates of progress toward a goal are experienced. Therefore, the tracking of prediction error dynamics has a tight relationship with emotions. Here, we suggest that the tracking of prediction error dynamics allows an artificial agent to be intrinsically motivated to seek new experiences but constrained to those that generate reducible prediction error. We will talk about a proposed model which seeks to encompass all these ideas for a cognitive agent.

  •
    María José Escobar

    Electronics Engineering Department, Universidad Técnica Federico Santa María, Chile

  •
    Eduardo Benitez Sandoval

    Creative Robotics Lab, University of New South Wales, Kensington, Australia

  •
    Josip Josifovski

    Research Assistant and PhD candidate at the Technical University of Munich

    Josip Josifovski is a PhD candidate at the Technical University of Munich and a research assistant at the Chair for Robotics, Artificial Intelligence and Real-Time systems since September 2019. He rec...

    Josip Josifovski is a PhD candidate at the Technical University of Munich and a research assistant at the Chair for Robotics, Artificial Intelligence and Real-Time systems since September 2019. He received his master’s degree in Intelligent Adaptive Systems from the University of Hamburg in 2018 and his bachelor’s degree in Informatics and Computer Engineering from the Ss. Cyril and Methodius University in Skopje. At his current position, he is working within the Artificial Intelligence for Digitizing Industry (AI4DI) research project, where he is developing simulations and learning algorithms for robot control with a focus on continual robot learning and sim2real transfer. His previous experience includes research work in cross-modal robot learning with the Knowledge Technology research group at University of Hamburg and several years of industry experience in software development and computer vision.

    Talk Title: Simulation-based Robot Learning – Current State, Challenges and Opportunities

    Abstract: In the last few years, learning-based approaches surpassed hand-crafted solutions for tasks in computer vision and natural language processing, not only due to the advances in machine learning methods, but also because of the abundant amount of available training data for these domains. Training data is either not available or very time- and resource-consuming to create for robotic applications, which is why simulations play a key role in development of learning-based methods for robot control. The simulation environments enable fast and safe model training, however, due to their approximate nature they might leave out or inaccurately simulate important real-world phenomena, making model transfer to real robots challenging. In this talk we will address the current state of the art in using simulations as training ground for robot learning, the current approaches and challenges of transferring simulation-trained models to real robots and interesting new developments and research directions of the field.

TUTORS

  •
    Lorenzo Jamone

    School of Electronic Engineering and Computer Science (EECS) of the Queen Mary University of London (QMUL), UK

    Lorenzo Jamone is a Senior Lecturer in Robotics at the School of Engineering and Materials Science of the Queen Mary University of London (UK). He is part of ARQ (Advanced Robotics at Queen Mary) and ...

    Lorenzo Jamone is a Senior Lecturer in Robotics at the School of Engineering and Materials Science of the Queen Mary University of London (UK). He is part of ARQ (Advanced Robotics at Queen Mary) and he is the founder and director of the CRISP group: Cognitive Robotics and Intelligent Systems for the People. He received the MS degree (honours) in computer engineering from the University of Genoa, Genoa, Italy, in 2006, and the PhD degree in humanoid technologies from the University of Genoa (Italy), and the Italian Institute of Technology, in 2010. He was an Associate Researcher at the Takanishi Laboratory, Waseda University (Tokyo, Japan) from 2010 to 2012, and at the Computer and Robot Vision Laboratory, Instituto Superior Técnico (Lisbon, Portugal) from 2012 to 2016. He has been a Turing Fellow since 2018. He has over 100 publications with an H-index of 26. His current research interests include cognitive robotics, robot learning, robotic manipulation, force and tactile sensing.

    Talk Title: The Intelligence of the Hand

    Abstract: The robots of today are mainly employed in heavy manufacturing industries (e.g. automotive): these are big robotic manipulators which perform simple and repetitive tasks in very structured environments. The robots of the future will be different. They will have to perform more complex tasks in more complex unstructured environments, even in collaboration with humans. To do so, they will need to use their hands (almost) as smartly as humans do, which is a tremendous challenge! How will this be achieved? Explicit insights from biology and psychology, well established control and engineering principles, modern AI techniques, have to be combined and properly integrated. In the talk I will briefly summarize our research efforts in the area of Cognitive Robotics (with the twofold objective of taking inspiration from humans to realize better robotic systems, and at the same time understanding more about human intelligence), with a focus on the intelligence of the hand: object exploration, grasping and manipulation, leveraging tactile sensing, computer vision and robot learning.

  •
    Pablo Barros

    Senior Machine Learning Researcher at Sony, Brussels, Belgium

    Pablo Barros is a machine learning scientist working at Sony R & D Center in Brussels, focusing on physiological and social signal processing applied to mental health solutions. Pablo holds a Ph.D. de...

    Pablo Barros is a machine learning scientist working at Sony R & D Center in Brussels, focusing on physiological and social signal processing applied to mental health solutions. Pablo holds a Ph.D. degree in computer science from the University of Hamburg, in Germany, and over the last years, has worked on different projects involving social robotics and affective computing. In particular, his research focuses on social perception, in particular facial expression recognition, but also on modelling, based on artificial intelligence, the role of social agents while interacting with humans.

    Talk Title: Simply) the Best: Modeling Social Components when Designing Competitive Reinforcement Learning Agents

    Abstract: With the recent advancements in deep reinforcement learning, we can build impressive and effective agents in competitive scenarios. The typical pipeline to design, implement and evaluate these agents, however, does not take into consideration the social parts of competitive interactions. In this talk, we will cover some of the recent developments in socially aware competitive reinforcement learning, and their advantages in building agents that can interact better with humans.

  •
    Francisco Leiva

    Advanced Mining Technology Center (AMTC), Universidad de Chile.