KCIST Kolloquium -
Planning in the Age of Learning - for Robotic Task and Motion Planning

  • Tagungsort:

    Online (Zoom) und im InformatiKOM I, Geb. 50.19, Atrium, Adenauerring 12, 76131 Karlsruhe

  • Datum:04. April 2024, 14:00 Uhr
  • Referent:

    Marc Toussaint is professor for Intelligent Systems at TU Berlin and was previously professor for ML and Robotics at University 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.

  • 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 problemformulation 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 I will discuss own work on TAMP, covering both, planning (i.e., optimization & sampling) and learning methods, and try to clarify these characteristics we want to see. I will also spend some time discussing whether "getting things to work" is our only goal, and the "call for more data" the solution.