Avatar

Rudolf Lioutikov

Tenure-Track Professor

Karlsruhe Insitute of Technology

Biography

Rudolf Lioutikov is a Tenure-Track Professor at the Karlsruhe Institute of Technology. He started the Intuitive Robots Lab in June 2021 after being accepted into the Emmy Noether Programme by the German Research Foundation (Deutsche Forschungsgemeinschaft). The group develops new robot learning methods that focus on human-robot interaction with non-experts.

Previously Rudolf was an Assistant Professor of Practice at the University of Texas at Austin. He developed and taught the Robot Learning Stream of the Freshmen Research Initiative. Simultaneously Rudolf was a Postdoctoral Fellow with the Personal Autonomous Robotics Lab, where he developed new methods for areas such as robot learning, reinforcement learning, imitation learning and human-robot collaboration.

Before he joined the UT Computer Science Department, Rudolf worked as a Ph.D. candidate at the Intelligent Autonomous Systems Lab in Darmstadt. In his dissertation he developed an imitation learning pipeline which learns a library of movement primitives and a comprehensible behavior representation from unlabeled data.

Rudolf was warded his Ph.D. with distinction by the Technische Univeristät Darmstadt in 2018 and his dissertation was considered a finalist for the Georges Giralt PhD Award by the European Robotics Federation.

Interests

  • Intuitive Robots
  • Machine Learning
  • Robotics
  • Robot Learning
  • Imitation Learning
  • Human-Robot Collaboration

Academic Career

  • Tenure-Track Professor

    Karlsruhe Insitute of Technology, since 12.2022

  • Research Group Leader

    Karlsruhe Insitute of Technology, 06.2021 - 11.2022

  • Assistant Professor of Practice

    University of Texas at Austin, 01.2019 - 05.2021

  • PhD in Machine Learning and Robotics

    Technische Universität Darmstadt, 10.2013 - 10.2018

Recent Publications

MaIL: Improving Imitation Learning with Selective State Space Models

This work introduces Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that offers a computationally …

Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models

A central challenge towards developing robots that can relate human language to their perception and actions is the scarcity of natural …

Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals

This work introduces the Multimodal Diffusion Transformer (MDT), a novel diffusion policy framework, that excels at learning versatile …

Contact

  • +49 721 608 47106
  • Adenauerring 4<br>76131 Karlsruhe
  • Buillding 50.21 (Access via Hölderlinstr. 2a), 3rd Floor