Insights & Ideas
from Experts in the Field
Next Lecture:
Marc Toussaint - Planning in the Age of Learning
Monday, April 8th, 5pm
Arcisstr. 21, 80333 Munich, Room 2750 (3rd floor)
Abstract
When a system (say, transformer model) is trained to output full plans conditional to a situation – would one call this planning?
Task and Motion Planning (TAMP) became a standard problem formulation within robotics to describe the complex behavior we strive for. However, despite the word Planning in TAMP, it doesn’t mean that one has to use planning methods in the traditional sense – it rather characterizes the behavior we want to see. In this talk, Marc Toussaint will discuss his own work on TAMP, covering both, planning (i.e., optimization & sampling) and learning methods, and try to clarify these characteristics. He will also spend some time discussing whether “getting things to work” is the only goal, and the “call for more data” the solution.
Bio
Marc Toussaint is professor for Intelligent Systems at TU Berlin and was previously professor for Machine Learning and Robotics at University of Stuttgart, Max Planck Fellow at the MPI for Intelligent Systems, visiting scholar at MIT, and some months head of the Core ML Robotics team at Amazon. In his view, a key in AI is the interplay of learning and reasoning. His research therefore combines planning, optimization, inference, and machine learning to tackle fundamental problems in robotics and physical reasoning. As board member of CoRL and R:SS, he is actively supporting the international community in the intersection of robotics, AI and ML.
Join Us!
On a monthly basis, we invite top-level AI researchers to give us a glimpse into their work and the future of AI. Join us for our next lecture!
Our lectures consist of a short presentation followed by a Q&A to enable a lively discussion with our speakers. Each lecture lasts about one hour and will be streamed live on our YouTube channel. Recordings will be available afterwards.