RSS-2018 tutorial on dynamical systems based learning from demonstration banner image
  • We uploaded presentations for each lecture that were recorded together with instructions to run the exercises on your own.
  • Full set of Slides, Videos and Exercises have already been posted in the Documentation/Exercises page

Overview

This 3 hours long tutorial will introduce students to techniques used to program robots through human demonstration by using dynamical systems. We will start with an overview of existing techniques for teaching a desired behavior to robots. We will present different interfaces (haptic device, motion sensors, vision, speech, etc.) available to teach robots and discuss how they serve different purpose. The second part of the tutorial will introduce a set of techniques to modify the learned behaviors locally. We are, in particular, interested in three main scenarios; e.g. obstacles avoidance, non-contact/contact transition and defining via points. Students will be able to practice these techniques through computer-based simulations. The tutorial will end with a look-out on open research questions in the field. We provide a detailed description of the program under the DOCUMENTATION tab.

  • Instructions for participants

    The tutorial has several Matlab exercises that will highlight some of the concepts presented in the tutorial. These exercises should be done on your own laptop. The code for the exercises is available in a Github repository. Follow the link below and clone the repository onto your computer. Make sure that you have a stand-alone license for Matlab, so that you can run in offline during the tutorial.
  • Github Repository

    You can find more information under the Exercise tab.
  • Presentations

    The slides of this tutorial can be downloaded from the following link (it will be activated after the tutorial).

    Presentation Repository