- Michael Beetz (Universität Bremen)
- Georg Bartels (Universität Bremen)
- Marc Toussaint (Universität Stuttgart)
- Alin Albu-Schäffer (DLR)
- Oussama Khatib (Stanford University)
- Cognition-enabled Robot Manipulation
- Learning and Adaptive Systems
- Manipulation Planning
- Mobile Manipulation
- Motion Control
- Perception for Grasping and Manipulation
- Submission: August 5, 2018
- Acceptance: August 24, 2018
- Camera-ready: September 7, 2018
- Workshop day: October 1, 2018
The research field of mobile manipulation is at an exciting stage. Researchers have endowed robots with sophisticated motion capabilities. Those capabilities are the prerequisites for robots to perform real-world actions like cooking meals, assembling products, helping dress people, or doing laundry. However, there are still many open research questions. For instance, the robot control systems providing those motion capabilities typically have to be parameterized with action and context-specific mathematical models. Unfortunately, it is still an open question how to autonomously translate a given manipulation problem and a perceived geometric scene into a meaningful mathematical model for motion generation. As a result, endowing a robot with a new manipulation skill or transferring a skill to a new context requires human creative input. To overcome this bottleneck in the development of mobile manipulation applications, robots need 'manipulation intelligence.'
Manipulation intelligence refers to the ability to understand the interplay of motions and effects. To clarify this description, let us consider the instructive example of a robot that shall flip a pancake with a spatula. A robot with manipulation intelligence knows that pancakes can break or fold during the flipping. This knowledge allows the creation of an automated feedback loop: Before performing an intended motion, the robot can predict probable effects on the pancake. If those are problematic, e.g. because one particular pancake appears to be unusually thin, the robot can modify the motion– without the need for human intervention. During and after flipping, the robot can monitor what happens to the pancake and trigger motion adaptation, if unwanted effects like folding occur or the robot failed to flip the pancake.
Research on this new generation of robot control systems has already started. As a result, the development of robotic applications will be faster and easier, enabling projects of much grander scale and ambition than the robotics community can tackle today. The resulting robots will possess better abilities to learn new actions and perform known actions in new contexts.
This workshop aims to bring together researchers that are fascinated and driven by the question of how to build this next generation of robot control systems. Specifically, we invite researchers working on robot control, machine learning, task and motion planning, and knowledge-based robotics who try to combine these technologies. The main objectives of this workshop are to formulate key research questions, identify potential synergies, and outline a road map for young researchers towards robots that exhibit manipulation intelligence.
Call for Papers
We invite authors to submit papers that they will present as spotlight talks (2-3min per paper), as well as during the interactive poster session (60min). The manuscripts shall use the standard IEEE IROS two-column format (2-4 pages). Manuscripts will be selected based on their originality, technical quality, clarity, and relevance to the topics of the workshop. Papers hosted on arXiv may be submitted, too.
We especially encourage women and young researchers to submit papers.
Please submit your manuscripts via e-mail to iros18-manip-intel<AT>cs<DOT>uni-bremen<DOT>de
- 09:00: Welcome
- 09:10: Invited talk by Michael Beetz
- 09:40: Lightning talks of posters
- 10:10: Coffee break
- 10:30: Interactive poster session
- 11:30: Invited talk by Oussama Khatib
- 12:00: Lunch break
- 13:30: Invited talk by Alin Albu-Schäffer
- 14:00: Invited talk by Jeannette Bohg
- 14:30: Invited talk by Dieter Fox
- 15:00: Coffee break
- 15:30: Invited talk by Marc Toussaint
- 16:00: Panel discussion
- 17:00: End of workshop