Plenary Talks

The organizing team is pleased to announce the DARS 2016 keynote speakers.

Nikolaus Correll (University of Colorado Boulder)

Material-integrated Intelligence for Robot Autonomy

Abstract:
Advances in miniature electronics, distributed algorithms and manufacturing technology have enabled a new generation of smart composites that tightly integrate sensing, actuation, computation and communication. Such “robotic materials” are inspired by multi-functional natural structures such as the skin of the cuttlefish that can change its color and patterning, bird wings that can change their shape, or the human skin that provides tactile sensing at high dynamic range. I will describe a series of recent results that best illustrate the benefits of material integrated computation: high-bandwidth sensing for texture recognition and localization in artificial skins, distributed optimization for controlling shape change, distributed classification for recognizing gestures drawn onto a modular facade, and feedback control of soft robotic actuators. I will then describe current challenges in robotic grasping and manipulation, and demonstrate how robotic materials can provide critical sensing and control during a series of manipulation tasks with applications to warehouse automation, manufacturing and lab automation.

Biography:
Nikolaus Correll is an Assistant Professor in Computer Science at the University of Colorado at Boulder with courtesy appointments in Aerospace, Electrical and Materials Engineering. Nikolaus obtained a degree in Electrical Engineering from ETH Zurich in 2003 with visits at Lund Tekniska Hogskola, Sweden, and Caltech, and earned a PhD in Computer Science from EPFL in Lausanne, Switzerland in 2007 working with Alcherio Martinoli. He did a post-doc at MIT CSAIL from 2007-2009.
Nikolaus is the recipient of a 2012 NSF CAREER award and a 2012 NASA Early Career Faculty Fellowship.

×
Nikolaus Correll (University of Colorado Boulder)

Nikolaus Correll (University of Colorado Boulder)

Material-integrated Intelligence for Robot Autonomy

Vijay Kumar (University of Pennsylvania)

Coordination, Cooperation, and Collaboration in Multi-Robot Systems

Abstract:
The central challenge in multi-robot systems lies in the synthesis of collective behaviors which enable group performance that exceeds the ability of individuals. We explore three different paradigms for collective behaviors. At a fundamental level, coordination is beneficial when individuals are confronted with a task that they can complete but can do so more efficiently as a group. Cooperation refers to the ability of robots to accomplish tasks they could not have completed on their own. Collaboration is useful for groups with different types of robots with diverse capabilities and tasks which cannot be completed with a single type of robot. This talk will discuss biological inspiration for these paradigms, mathematical frameworks, and resilience in collective behaviors with applications to ground and aerial robots.

Biography:
VIJAY KUMAR is the Nemirovsky Family Dean of Penn Engineering with appointments in the Departments of Mechanical Engineering and Applied MechanicsComputer and Information Science, and Electrical and Systems Engineering at the University of Pennsylvania.

Dr. Kumar received his Bachelor of Technology degree from the Indian Institute of Technology, Kanpur and his Ph.D. from The Ohio State University in 1987. He has been on the Faculty in the Department of Mechanical Engineering and Applied Mechanics with a secondary appointment in the Department of Computer and Information Science at the University of Pennsylvania since 1987.

Dr. Kumar served as the Deputy Dean for Research in the School of Engineering and Applied Science from 2000-2004. He directed the GRASP Laboratory, a multidisciplinary robotics and perception laboratory, from 1998-2004. He was the Chairman of the Department of Mechanical Engineering and Applied Mechanics from 2005-2008. He served as the Deputy Dean for Education in the  School of Engineering and Applied Science from 2008-2012. He then served as the assistant director of robotics and cyber physical systems at the White House Office of Science and Technology Policy (2012 – 2013).

Dr. Kumar is a Fellow of the American Society of Mechanical Engineers (2003), a Fellow of the Institution of Electrical and Electronic Engineers (2005) and a member of the National Academy of Engineering (2013).

Dr. Kumar’s research interests are in robotics, specifically multi-robot systems, and micro aerial vehicles. He has served on the editorial boards of the IEEE Transactions on Robotics and Automation, IEEE Transactions on Automation Science and Engineering, ASME Journal of Mechanical Design, the ASME Journal of Mechanisms and Robotics and the Springer Tract in Advanced Robotics (STAR).

He is the recipient of the 1991 National Science Foundation Presidential Young Investigator award, the 1996 Lindback Award for Distinguished Teaching (University of Pennsylvania), the 1997 Freudenstein Award for significant accomplishments in mechanisms and robotics, the 2012 ASME Mechanisms and Robotics Award, the 2012 IEEE Robotics and Automation Society Distinguished Service Award , a 2012 World Technology Network Award, and a 2014 Engelberger Robotics Award. He has won best paper awards at DARS 2002, ICRA 2004, ICRA 2011, RSS 2011, and RSS 2013, and has advised doctoral students who have won Best Student Paper Awards at ICRA 2008, RSS 2009, and DARS 2010.

More information about Kumar’s research can be found in his TED talks.

×
Vijay Kumar (University of Pennsylvania)

Vijay Kumar (University of Pennsylvania)

Coordination, Cooperation, and Collaboration in Multi-Robot Systems

James A R Marshall (The University of Sheffield)

Go to the bee and be wise: swarm engineering inspired by house-hunting honeybees

Abstract:
Distributed autonomous systems are likely to become increasingly important for robotics and other applications, due to their potential for resilience, scalability and flexibility. However, designing group-level behaviours that are implemented by simple individual-level rules operating with local information is an inherently hard problem, and guaranteeing properties of that behaviour is even harder. For example, search techniques and formal methods applied to swarms both rapidly fall foul of the curse of dimensionality as number of agents increases. However natural selection has successfully designed such systems repeatedly, and tools from the natural sciences have rigorously described the behaviour of very large systems of interacting components. In this talk I will recount how observations of house-hunting honeybees led to the design of a new class of distributed decision-making algorithm, and its deployment on hundreds of small and simple robots. Rather than simply imitating nature, however, the algorithm’s principled development requires the integration of concepts and techniques from areas as diverse as behavioural ecology and statistical physics.

Biography:
James Marshall is Professor of Theoretical and Computational Biology at the University of Sheffield, where he is head of the Complex Systems Modelling Group in the Department of Computer Science, an affiliate member of the Evolution and Behaviour Research Group in the Department of Animal and Plant Sciences, and a member of Sheffield Robotics. After obtaining a Bachelors degree in Computer Science James combined doctoral studies into the evolution of cooperation with a career developing AI technology for computer games at Sony. He went on to postdoctoral positions at Imperial College London and the University of Bristol, then academic positions at Bristol and Sheffield. James’ interests are predominantly in animal behaviour, its evolution, and the interplay of these topics with engineering. He is the author of ‘Social Evolution and Inclusive Fitness: An Introduction’ (Princeton, 2015). His research into collective robotics is currently funded by the European Research Council, and his work on flying robots by a Programme Grant from the Engineering and Physical Sciences Research Council.

×
James A R Marshall (The University of Sheffield)

James A R Marshall (The University of Sheffield)

Go to the bee and be wise: swarm engineering inspired by house-hunting honeybees

Katia Sycara (Carnegie Mellon University)

Robust Human Control of Multi-Robot Swarms

Abstract:
As robotic platforms become cheaper and more reliable, multi-robot deployment becomes possible and desirable. Since complete robot autonomy for these deployments is not yet possible, the presence of a human operator is necessary. Multiple human studies have shown that cognitive limitations prevent effective human control of multi-robot systems of tens of robots. Another difficulty is that many different types of human interactions may be necessary to maintain and control multi-robot systems. Additionally, the coordination scheme of multiple robots can vary which has consequences on the operator's difficulty of control. We have developed a characterization of human-robot tasks, and appropriate human robot interaction modes, based on the task's cognitive complexity of control. This scheme helps explicate the forms of control likely to be needed and the demands they pose on human operators. This talk will present two lines of research following from this characterization. The first evaluates the potential for using scheduling techniques to improve the performance of systems in which operators must attend to multiple independently operating robots. The second presents challenges and results pertaining to human control of autonomously cooperating robotic swarms.

Biography:
Katia Sycara is a Professor in the Robotics Institute, School of Computer Science at Carnegie Mellon University and the Director of the Laboratory for Advanced Robotics and Semantic Web Technologies. She holds a B.S in Applied Mathematics from Brown University, M.S. in Electrical Engineering from the University of Wisconsin and PhD in Computer Science from Georgia Institute of Technology. She holds an Honorary Doctorate from the University of the Aegean. She is a Fellow of the IEEE, Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), the recipient of the ACM/SIGART Agents Research Award and the recipient of the Research Award of the Group Decision and Negotiation section of the Institute of Operations Research and the Management Sciences (INFORMS). She has received multiple best paper awards and multimillion research grants. She has served as General Chair and Program Chair of multiple conferences, has given numerous invited talks, authored more than 600 technical papers dealing with multi-agent and multi-robot systems, human robot interaction, complex systems, negotiation, game theory, and data mining. She is a founding member of the International Foundation of Agents and Multiagent Systems (IFAAMAS), and a founding member of the Semantic Web Science Association. She is a founding Editor-inChief of the journal “Autonomous Agents and Multiagent Systems” and is currently serving on the editorial board of 5 additional journals.

×
Katia Sycara (Carnegie Mellon University)

Katia Sycara (Carnegie Mellon University)

Robust Human Control of Multi-Robot Swarms
Visit Us On FacebookVisit Us On Google PlusVisit Us On Twitter