ICAR 2015 Workshop on Robot Learning

Bottom-up and top-down development of robot skills

Istanbul, Turkey, July 31st, 2015

• Objectives
• Program
• Invited Speakers
• ICAR 2015

Our 10 distinguished speakers, who work in different aspects of robot learning, such as developmental robotics, visuomotor learning, symbol and language acquisition, and multi-modal learning, will present their research, along with an overview of the current state-of-the-art in the respective fields

We are confident that with such a distinguished and diverse group of experts, this workshop can disseminate the current state of the art and plant the initial seeds for a research community to investigate and develop interaction mechanisms among different levels of learning approaches.

The list of the keynote speakers is as follows: (in alphabetical order)

	Minoru Asada has been a Professor of the department of Adaptive Machine Systems at the Graduate School of Engineering, Osaka University, Japan. The focus of his talk will be on cognitive development in robots Bio He received Ph.D. in control engineering from Osaka University in 1982. Since 1997, he has been a Professor of the department of Adaptive Machine Systems at the Graduate School of Engineering, Osaka University. He was the president of the International RoboCup Federation (2002-2008) and was the Research Director of "ASADA Synergistic Intelligence Project" of ERATO (2005-2012). In 2012, the Japan Society for Promotion of Science (JSPS) named him to serve as the Research Leader for the Specially Promoted Research Project (Tokusui) on Constructive Developmental Science Based on Understanding the Process From Neuro-Dynamics to Social Interaction. Since 2013, he has been the director of the division of cognitive neuroscience robotics, the Institute for Academic Initiatives (IAI), Osaka University.
	Tamim Asfour, is a full Professor the Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT), Germany , and chair of Humanoid Robotics Systems, High Performance Humanoid Technologies Lab. The title of his talk is Affordance-based Grasping, Balancing and Walking. Bio His major current research interest is 24/7 high performance humanoid robotics. His major research topics include humanoid mechano-informatics, grasping and dexterous manipulation, goal-directed imitation learning, active vision and active touch, modeling and analysis of human motion, software and hardware architectures and system integration. Abstract Exploiting interaction with the environment is a promising and powerful way to enhance humanoid robots' capabilities and robustness while executing locomotion and manipulation tasks. In this talk we first present an approach for autonomous interactive segmentation of unknown objects in a complex scene through physical interaction and strategies for reactive grasping using visual and haptic information. Following the idea of duality between object grasping and humanoid balancing, we show how co-joint object-action representations, Object-Action Complexes, are used and extended for associating whole-body actions of a humanoid robot with affordances of objects and environmental elements in the scene. We show how affordance hypotheses are generated through visual exploration and verified using haptic feedback as well as reachability and stability measures of the robot. Results on grasping unknown objects as well as generation of whole-body action for balancing and footstep planning will be discussed.
	Angelo Cangelosi is a Professor of Artificial Intelligence and Cognition and the Director of the Centre for Robotics and Neural Systems at Plymouth University, UK. The title of his talk will be Developmental Robotics for Embodied Language Learning. Bio Cangelosi studied psychology and cognitive science at the Universities of Rome La Sapienza and at the University of Genoa, and has been visiting scholar at the University of California San Diego and the University of Southampton. Cangelosi's main research expertise is on language grounding and embodiment in humanoid robots, developmental robotics, human-robot interaction, and on the application of neuromorphic systems for robot learning. He currently is the coordinator of the UK EPSRC project "BABEL: Bio-inspired Architecture for Brain Embodied Language" (2012-2016), and previously coordinated the Marie Curie ITN "RobotDoC: Robotics for Development of Cognition" (2009-2014) and the FP7 Integrating Project "ITALK” (2008-12). He also is Principal investigator for the ongoing projects “THRIVE” (US Air Force Office of Science and Research, 2014-1018), the FP7 projects POETICON++ and ROBOT-ERA, and the Marie Curie projects SECURE, ORATOR and DECORO. Overall, he has secured over £10m of research grants as coordinator/PI. Cangelosi has produced more than 200 scientific publications, and has chaired numerous workshops and conferences including the IEEE ICDL-EpiRob 2011 and 2013 Conferences (Frankfurt 2011, Osaka 2013). In 2012-13 he was Chair of the IEEE Technical Committee on Autonomous Mental Development. In January 2015 he became Editor-in-Chief of the IEEE Transactions on Autonomous Development, and also is Editor (with K. Dautenhahn) of the journal Interaction Studies. His latest book “Developmental Robotics: From Babies to Robots” (MIT Press; co-authored with Matt Schlesinger) has just been released, as of January 2015. Abstract Growing theoretical and experimental research on action and language processing and on number learning and space representation clearly demonstrates the role of embodiment in cognition and language processing. In psychology and neuroscience this evidence constitutes the basis of embodied cognition, also known as grounded cognition (Pezzulo et al. 2012). In robotics, these studies have important implications for the design of linguistic capabilities in cognitive agents and robots for human-robot communication, and have led to the new interdisciplinary approach of Developmental Robotics (Cangelosi & Schlesinger 2015). During the talk we will present examples of developmental robotics models and experimental results from iCub experiments on the embodiment biases in early word acquisition studies, on word order cues for lexical development and number and space interaction effects. The presentation will also discuss the implications for the "symbol grounding problem" (Cangelosi, 2012) and how embodied robots can help addressing the issue of embodied cognition and the grounding of symbol manipulation use on sensorimotor intelligence. References: (1) Cangelosi A. (2012). Solutions and open challenges for the symbol grounding problem. International Journal of Signs and Semiotic Systems, 1(1), 49-54 (with commentaries) (2) Cangelosi A, Schlesinger M (2015). Developmental Robotics: From Babies to Robots. Cambridge, MA: MIT Press. (3) Pezzulo G., Barsalou L.W., Cangelosi A., Fischer M.H., McRae K, Spivey M.J. (2011). The mechanics of embodiment: a dialog on embodiment and computational modelling. Frontiers in Psychology, 2(5), 1-21
	Lorenzo Jamone is an associate researcher in humanoid robotics at Vis Lab, at Instituto Superior Tecnico, Portugal The focus of his talk will be on learning affordances Bio Lorenzo Jamone received his MS in Computer Engineering from the University of Genova in 2006 (with honors), and his PhD in Humanoid Technologies from the University of Genova and the IIT in 2010. He was Associate Researcher at the Takanishi Laboratory in Waseda University from 2010 to 2012, and since January 2013 he is an Associate Researcher at VisLab (Instituto Superior Tecnico, Lisbon, Portugal). His research interests include cognitive humanoid robots, motor learning and control, force and tactile sensing. Abstract Inspired by the extraordinary ability of young infants to learn how to grasp and manipulate objects, many works in robotics have proposed developmental approaches to allow robots to learn the effects of their own motor actions on objects, i.e., the objects affordances. While holding an object, infants also promote its contact with other objects, resulting in object-object interactions that may generate effects not possible otherwise. Depending on the characteristics of both the held object (intermediate) and the acted object (primary), systematic outcomes may occur, leading to the emergence of a primitive concept of tool. This will later on enable more and more complex planning skills, eventually allowing for problem solving. I will discuss our attempts toward modeling this kind of knowledge acquisition and exploitation in the humanoid robot iCub. The robot first learns a probabilistic causal model of object affordances through the interactive exploration of the environment, and then uses such model to make predictions, take decisions and plan sequences of actions to achieve given goals. The learned affordances are used to ground the planning rules, so to adapt them to the actual motor and perceptual capabilities of the robot, and to the properties of the objects around; this is made possible by the use of probabilistic techniques both for modeling affordances and for computing the plans.
	Takayuki Nagai is a Professor in Intelligent Systems Lab., The University of Electro-Communications, Japan. The title of his talk is Toward robots that learn concepts and words through experience Bio Takayuki Nagai received his BE, ME, and DE degrees from the Department of Electrical Engineering, Keio University, in 1993, 1995, and 1997, respectively. Since 1998, he has been with the University of Electro-Communications where he is currently a professor of the Graduate School of Informatics and Engineering. From 2002 to 2003, he was a visiting scholar at the Department of Electrical Computer Engineering, University of California, San Diego. Since 2011, he has also been a visiting researcher at Tamagawa University Brain Science Institute. Abstract To interact naturally with humans, robots need to understand human words and take actions based on the meaning behind those words. Moreover, it is desirable for robots to express their intentions through language in communication with humans. To achieve this many works have been done on the symbol grounding problem in the field of intelligent robotics. In this talk a statistical modeling of concepts and language, which makes possible for robots to learn concepts, words and grammar in a bottom-up manner, is introduced. The key ideas behind the framework are spatiotemporal segmentation and multimodal categorization.
	Yukie Nagai is a Specially Appointed Associate Professor at Graduate School of Engineering, Osaka University, Japan . The title of her talk is Predictive Learning of Sensorimotor Information as a Key for Cognitive Development. Bio She received her Ph.D. in Engineering from Osaka University in 2004 and worked as a postdoc researcher at National Institute of Information and Communications Technology in Kyoto from 2004 to 2006. She then worked at Bielefeld University, Germany for three and a half years until she started her current position at Osaka University in October 2009. Her research interests include the developmental mechanism of human social cognition such as self-other cognition, imitation, joint attention, and cooperation. She has been investigating how human infants acquire such abilities through interaction with their caregivers by means of constructive approaches. More information at: http://cnr.ams.eng.osaka-u.ac.jp/~yukie Abstract Human infants acquire various cognitive abilities such as self-other cognition, imitation, and cooperation in the first few years of life. Although developmental studies have revealed behavioral changes in infants, underlying mechanisms for the development are not fully understood yet. We hypothesize that predictive learning of sensorimotor information plays a key role in infant development. Predictive learning is defined as a process to minimize the prediction error between an actual sensory feedback and a predicted one. For example, minimizing the prediction error enables infants to discriminate the self from others because the self's body is controllable and thus recognized as a perfectly predictable entity. Social behaviors such as imitation and cooperation also emerge through predictive learning. A failure in others’ action, for example, induces a larger prediction error and thus triggers the execution of infants’ action to reduce the error, which results in a cooperative behavior. My talk will present our robotics studies investigating how predictive learning reproduces infant cognitive development. Furthermore, a potential of our hypothesis to explain the mechanism of autism spectrum disorders (ASD) will be explained. Our research supports a recent hypothesis that ASD is characterized by a difficulty in learning of sensorimotor prediction rather than in social interaction.
	Luka Peternel is a PhD. student in the Department of Automation, Biocybernetics and Robotics at Jozef Stefan Institute in Ljubljana. The title of this talk is Human-in-the-loop approach for teaching robots to dynamically interact with environment and humans. Bio Main research topics of Luka Peternel are human-in-the-loop robot teaching and exoskeleton control. He works with Dr. Jan Babic who is a Senior Researcher at "Jozef Stefan" Institute, Slovenia and an Assistant Professor at Faculty of Electrical Engineering, University of Ljubljana, Slovenia. Dr. Babic received my Ph.D. from Faculty of Electrical Engineering, University in Ljubljana examining the role of biarticular muscles in human locomotion. During the years 2006/2007 he was a visiting researcher at ATR Computational Neuroscience Laboratories in Japan. In November 2014, he was a visiting professor at The Institute for Intelligent Systems and Robotics, University of Pierre and Marie Curie in France. His current research is particularly concerned with the understanding how human brain controls movement of the body. He is using these neurophysical models to design biologically plausible solutions for a broad spectrum of robotic systems such as industrial robots, humanoids, exoskeletons and rehabilitation devices. Abstract We present a novel human-in-the-loop approach for teaching robots how to perform dexterous tasks involving physical interaction with unstructured and unpredictable environment. By including human into the robot control loop, the human learns to perform a given task using the robot. The newly acquired human skill is then captured and added to the robot control system. This enables the robot to perform the task autonomously. To demonstrate the applicability of the approach, I will present several experiments including reactive postural control of a humanoid robot, human-robot cooperation in dynamic manipulation tasks, and control of exoskeleton robots. Using our approach, we can collect a large amount of sensorimotor skills for specific robotic tasks. To achieve full robot autonomy, a cognitive-level algorithm is needed for the robot to decide which skill to use in the given situation. In addition, such algorithm could enable the robot to merge different sensorimotor skills and potentially create new skill. We hope that the discussion and idea-sharing at this workshop will lead to possible solutions of this issue.
	Amit Kumar Pandey is a Chief Scientist (R&D) at Aldebaran Robotics, Paris, France. The title of his talk is Development of Socially Intelligent Robots and the need of Learning: an industrial perspective and use cases. Bio Earlier for 6 years he worked as doctoral and postdoctoral researcher in Robotics and AI at LAAS-CNRS (French National Center for Scientific Research), Toulouse, France. His Ph.D. thesis in Robotics (title: Towards Socially Intelligent Robots in Human Centered Environment, 2012) is the second prize winner (tie) of the prestigious Georges Giralt Award for the best Ph.D. Thesis in Robotics in Europe, 2013, awarded by European Robotics Research Network euRobotics). His current research interest includes Socially Intelligent Robots, Human Robot Interaction (HRI) and Robot’s Cognitive Architecture. On these aspects, he has been actively contributed in various national and European Union (EU) projects as well as involved in their design and proposal. Among other responsibilities, he is the coordinator of Socially Intelligent Robots and Societal Applications (SIRoSA) topic group of EU Robotics, and active contributor in the MultiAnnual Roadmap of euRobotics, aims to shape the future of robotics in Europe in collaboration with European Commission (EC) ( http://www.sparc-robotics.net/ ) Abstract With significant advancements in robotics, now the robots are beginning to coexist and work with us, to assist and accompany us, and to interact, play, learn and teach. Time has arrived, when social robots are getting deployed or available for practical purposes in homes, stores, and public places. E.g., P epper robot of Aldebaran SoftBank group is planned for mass production and already being used for social interaction at SoftBank stores in Japan, the Romeo2 project, focusing on development and evaluation of humanoid robot companion for everyday life, etc. However diverse the application might be, the common requirement is that such robots, beyond their short term engaging effect due to novelty, should actually be able to establish long term social relations with human and with individuals, by behaving in socially expected and accepted manners. For this, the S ocial Intelligence , being the underlying engine for reasoning, play crucial role. But the question is how to embody such capabilities and how to close the loop of interaction and learning? There are also crucial from commercial and industrial perspective of exploitation of social robots. The talk will emphasize on these aspects, highlight some of the R&D challenges and needs from industrial perspective along with some use cases.
	Justus Piater is a Professor in Computer Science, University of Innsbruck, Austria. The title of this talk is Stacked learning of affordances Bio After eight years as a professor at the University of Liege, Belgium, including one year as a visiting scientist at the Max Planck Institute for Biological Cybernetics in Tubingen, Germany, Prof. Piater moved to Innsbruck in 2010. There he founded the IIS group at the Institute of Computer Science, which currently counts 6 postdoctoral researchers and 8 doctoral students. He has written about 150 publications in international, peer-reviewed journals, conferences and workshops, and has been a principal investigator in 1 EU-FP6 and 6 EU-FP7 projects, of which 4 are currently active. Abstract General-purpose autonomous robots for deployment in unstructured domains such as service and households require a high level of understanding of their environment. For example, they need to understand how to handle objects, how to operate devices, the function of objects and their important parts, etc. How can such understanding be made available to robots? Hard-coding is not feasible, and conventional machine learning approaches will not work in such high-dimensional, continuous perception-action spaces and realistic amounts of training data. One way to get robots to learn higher-level concepts may be to focus on simple learning problems first, and then learn harder problems in ways that make use of simpler problems already-learned. For example, learning problems can be stacked by making the output of lower-level learners available as input to higher-level learning problems, effectively turning hard problems into easier problems by expressing them in terms of highly-predictive attributes. This talk discusses how this can be done, including further boosting learning efficiency by active learning, and automatic, unsupervised structuring of sets of learning problems and their interconnections.
	Sanem Sariel is an Assistant Professor in Computer Engineering, Istanbul Technical University, Turkey. The title of her talk is Robots learn they can not afford in every context Bio Sanem Sariel received the BS, MSc, and PhD degrees in Computer Engineering from Istanbul Technical University, in 1999, 2002 and 2007, respectively. During her PhD studies, she worked as a researcher at Georgia Institute of Technology, Atlanta, GA, USA from 2004-2006. She was co-advised by Tucker Balch (Georgia Tech) and Nadia Erdogan (ITU). Sanem's research interests include robot intelligence, robust cognitive systems and multirobot systems. She is the PI of an ongoing project (funded by TUBITAK, the Scientific and Technological Research Council of Turkey) on automated reasoning, planning and learning methods for autonomous mobile robots. Abstract Several studies present different methods for robots to learn to complete tasks more efficiently; and task completion is always the highest priority in these studies. However, especially in unstructured environments, there are cases where task completion is not possible, or certain precautions should be taken into account to ensure safety in task execution. We study how learning helps a robot determine general or specific limitations on task execution beyond its capabilities, and gain experience on these cases to make safe decisions on future tasks. In this talk, I will present our experiential learning framework for robots to build online experience and transfer knowledge among appropriate contexts. We use Inductive Logic Programming (ILP) to frame hypotheses represented in first-order logic that are useful for further reasoning and planning processes. We analyzed the performance of the learning method on our autonomous mobile robot and our robot arm both building their experience on action executions at runtime.