Three NCCR Robotics Seminars
Event details
| Date | 29.01.2016 |
| Hour | 13:15 › 15:30 |
| Speaker |
Three international experts from the world of Robotics Speakers: Prof. Oliver Brock, TUB Oliver Brock is the Alexander von Humboldt Professor of Robotics in the School of Electrical Engineering and Computer Science at the Technische Universität Berlin in Germany. He received his Diploma in Computer Science in 1993 from the Technische Universität Berlin and his Master's and Ph.D. in Computer Science from Stanford University in 1994 and 2000, respectively. He also held post-doctoral positions at Rice University and Stanford University. Starting in 2002, he was an Assistant Professor and Associate Professor in the Department of Computer Science at the University of Massachusetts Amherst, before to moving back to the Technische Universität Berlin in 2009. The research of Brock's lab, the Robotics and Biology Laboratory, focuses on autonomous mobile manipulation, interactive perception, grasping, manipulation, soft hands, interactive learning, motion generation, and the application of algorithms and concepts from robotics to computational problems in structural molecular biology. He is also the president of the Robotics: Science and Systems foundation. Prof. Tamim Asfourm, KIT Tamim Asfour is is full Professor at the Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT) where he holds the chair of Humanoid Robotics Systems and is head of the High Performance Humanoid Technologies Lab (H2T). His current research interest is high performance 24/7 humanoid robotics. Specifically, his research focuses on engineering humanoid robot systems integrating the mechano-informatics of such systems with the capabilities of predicting, acting and learning from human demonstration and sensorimotor experience. He is developer of the ARMAR humanoid robot family and is leader of the Humanoid Research Group at KIT (2003-now). He is Founding Editor-in-Chief of the IEEE-RAS Humanoids Conference Editorial Board, co-chair of the IEEE RAS Technical Committee on Humanoid Robots (2010-2014), Editor of the Robotics and Automation Letters, Associate Editor of Transactions on Robotics (2010-2014). He is president of the Executive Board of the German Association of Robotics (Deutsche Gesellschaft für Robotik, DGR) and member of the Board of Directors of euRobotics (2013-2015). Prof. José Santos-Victor, IST José Santos-Victor received the Ph.D. degree in electrical and computer engineering from Instituto Superior Técnico (IST), Lisbon, Portugal, in 1995. He is currently Full Professor at IST, Director of the Institute for Systems and Robotics (ISR-Lisboa) and head of the Computer and Robot Vision Laboratory (VisLab). He was the scientific responsible for IST in many European and national research projects in computer vision and robotics. He is particularly interested in cognitive robotics, in some cases inspired by biological systems, or as embodied tools to help understanding biological systems. From 2006 and January 2015 he was the IST VIce President for International Affairs. |
| Location | |
| Category | Conferences - Seminars |
NCCR Robotics cordially invites you to join us for three seminars hosted by the Learning Systems and Algorithms Laboratory (LASA).
13h15-14h00 - Oliver Brock, Technische Universität Berlin
Deep Learning - Stairway to (Robotic) Heaven?
Deep Learning is certainly a huge success. Some believe it might solve robotics (whatever that may mean). I would like to take a step back and analyze the different types of problems we face in robotics, speculate about the types of problems for which Deep Learning it most promising, and present some alternative and/or complementary ideas. Such alternatives include:
1) excessive sensing feedback for simple linearized local models,
2) using general priors to aid learning in non-deep settings, and
3) the use of contextual data to assist learning, also in non-deep settings.
And then I guess my not-very-surprising conclusion will be two-fold:
A) Pick the "right" tool for the job!
B) To "solve robotics" we'll need more than one tool!
14h00-14h45 - Tamim Asfourm, Karlsruhe Institute of Technology (KIT)
On the Duality of Grasping and Balancing
The talk will discuss the parallelism between grasping and whole-body balancing. Inspired by the idea that a stable whole-body configuration of a humanoid robot can be seen as a stable grasp on an object, we present taxonomy for whole-body poses, whole-body grasps, and its validation based on human motion capture data. Further, we show how co-joint object-action representations used for object grasping can be extended to associate whole-body actions with affordances of objects and environmental elements in the scene. We demonstrate how affordance hypotheses are generated through visual exploration and verified using haptic feedback.
14h45-15h30 - José Santos-Victor, Instituto Superior Tecnico (IST)
Affordances and motor primed attention for humanoid robot
In this talk I will briefly present a model of affordances that allow a robot to learn how to interact with objects in a meaningful way and how the model can be extended for grounding language and for learning how to use tools. Affordances depend on the physical characteristics of the of the specific agent. As a related topic i will also describe how motor information primes attention in primates and... robots.
13h15-14h00 - Oliver Brock, Technische Universität Berlin
Deep Learning - Stairway to (Robotic) Heaven?
Deep Learning is certainly a huge success. Some believe it might solve robotics (whatever that may mean). I would like to take a step back and analyze the different types of problems we face in robotics, speculate about the types of problems for which Deep Learning it most promising, and present some alternative and/or complementary ideas. Such alternatives include:
1) excessive sensing feedback for simple linearized local models,
2) using general priors to aid learning in non-deep settings, and
3) the use of contextual data to assist learning, also in non-deep settings.
And then I guess my not-very-surprising conclusion will be two-fold:
A) Pick the "right" tool for the job!
B) To "solve robotics" we'll need more than one tool!
14h00-14h45 - Tamim Asfourm, Karlsruhe Institute of Technology (KIT)
On the Duality of Grasping and Balancing
The talk will discuss the parallelism between grasping and whole-body balancing. Inspired by the idea that a stable whole-body configuration of a humanoid robot can be seen as a stable grasp on an object, we present taxonomy for whole-body poses, whole-body grasps, and its validation based on human motion capture data. Further, we show how co-joint object-action representations used for object grasping can be extended to associate whole-body actions with affordances of objects and environmental elements in the scene. We demonstrate how affordance hypotheses are generated through visual exploration and verified using haptic feedback.
14h45-15h30 - José Santos-Victor, Instituto Superior Tecnico (IST)
Affordances and motor primed attention for humanoid robot
In this talk I will briefly present a model of affordances that allow a robot to learn how to interact with objects in a meaningful way and how the model can be extended for grounding language and for learning how to use tools. Affordances depend on the physical characteristics of the of the specific agent. As a related topic i will also describe how motor information primes attention in primates and... robots.
Practical information
- Informed public
- Free
Organizer
- Aude Billard
Contact
- Lirot Mayra <[email protected]>