Learning to control an elephant trunk robot
Event details
| Date | 13.10.2014 |
| Hour | 14:00 |
| Speaker | Prof. Jochen Steil, University of Bielefeld, Germany |
| Location | |
| Category | Conferences - Seminars |
The New Scientist: "I am in Jochen Steil's lab, grasping a segmented, whiplashing tentacle that resists and tries to push me away.
"It feels strangely alive, as though I am trying to throttle a giant alien maggot. In fact, I am training a bionic elephant's trunk to do real-world jobs like picking apples or replacing light bulbs – something non-experts haven't been able to do until now." - Paul Marks, 13.03.2014
This talk presents the scientific work behind this experience with the futuristic bionic handling assistant (BHA) soft robot, which indeed was modelled after an elephant's trunk by its producer FESTO. The BHA is a large-scale pneumatically operated, flexible, soft and compliant continuum robot, which is inherently safe to interact with.
However, the BHA comes without an automatic control system and its soft material and complex dynamics prevents simple modeling, simulation, identification or standard control. We show how to use advanced learning methods to establish a proper mixture of adaptive controllers, approximations, and autonomous exploration for this challenging platform. Bound together by means of a coherent software architecture, this enables the BHA to perform actual grasping tasks, kinesthetic teaching, and accelarated online-learning in physical interaction, which creates the experience described above.
Bio: Prof. Jochen Steil is the Managing Director of the Research Institute for Cognition and Robotics (CoR-Lab) and apl. Professor for Neuroinformatics at the Faculty of Technology, University of Bielefeld. He received his diploma in Mathematics and doctorate in "Input-Output stability of Recurrent Neural Networks" from the Bielefeld University and later worked as a principal scientist at the Honda Research Institute Europe and as Managing Director of DFG Cluster for Cognitive Interaction Technology (CITEC). He has been part of EU projects ECHORD and CODEFOR and served as project coordinator for the AMARSI project. He is a recipient of the ZiF research group fellowship. His current research interests include cognitive and humanoid robotics, developmental and autonomous motor learning, visual online learning, modeling of visual attention, learning and stability in recurrent networks, nonlinear dynamics.
"It feels strangely alive, as though I am trying to throttle a giant alien maggot. In fact, I am training a bionic elephant's trunk to do real-world jobs like picking apples or replacing light bulbs – something non-experts haven't been able to do until now." - Paul Marks, 13.03.2014
This talk presents the scientific work behind this experience with the futuristic bionic handling assistant (BHA) soft robot, which indeed was modelled after an elephant's trunk by its producer FESTO. The BHA is a large-scale pneumatically operated, flexible, soft and compliant continuum robot, which is inherently safe to interact with.
However, the BHA comes without an automatic control system and its soft material and complex dynamics prevents simple modeling, simulation, identification or standard control. We show how to use advanced learning methods to establish a proper mixture of adaptive controllers, approximations, and autonomous exploration for this challenging platform. Bound together by means of a coherent software architecture, this enables the BHA to perform actual grasping tasks, kinesthetic teaching, and accelarated online-learning in physical interaction, which creates the experience described above.
Bio: Prof. Jochen Steil is the Managing Director of the Research Institute for Cognition and Robotics (CoR-Lab) and apl. Professor for Neuroinformatics at the Faculty of Technology, University of Bielefeld. He received his diploma in Mathematics and doctorate in "Input-Output stability of Recurrent Neural Networks" from the Bielefeld University and later worked as a principal scientist at the Honda Research Institute Europe and as Managing Director of DFG Cluster for Cognitive Interaction Technology (CITEC). He has been part of EU projects ECHORD and CODEFOR and served as project coordinator for the AMARSI project. He is a recipient of the ZiF research group fellowship. His current research interests include cognitive and humanoid robotics, developmental and autonomous motor learning, visual online learning, modeling of visual attention, learning and stability in recurrent networks, nonlinear dynamics.
Practical information
- General public
- Free
Organizer
- Mayra LIROT
Contact
- Mayra LIROT