Seminar Humanoid Robots (MA-INF 4213)

In this seminar, we cover state-of-the-art research papers from conferences and journals in the field of humanoid robotics and related fields. The available topics are presented in the Introductory Meeting and can be selected during the registration for the seminar on our website. In the Introductory Meeting, we will present the available topics, the registration process, the requirements, and answer your questions.

Participants of the seminar have to prepare a talk of 25 minutes which will be given on the Seminar Day at the end of the semester. After the talk, there will be a Q&A of about 5 minutes where you will be asked questions by the staff and other participants of the seminar. Bachelor students can choose to present their topic in German, master students must give their presentation in English.

The Seminar Day is a whole day event, typically from 8:30am to 3:30pm, which takes place towards the end of the semester. All participants are required to be present on the Seminar Day, to give their presentation, and also to listen to the talks of the other participants. Active participation during the Q&A sessions counts as a bonus towards your final score.

Participating students are also required to write a summary and discussion of their assigned topic. The summary and discussion should be written in LaTeX using the following template: seminar_template.tex The document should be 7 pages long not including images and references! Bachelor students can opt to write their summary in German.

Each participant will be paired up with a supervisor who monitors their progress and is available to help with questions or difficulties. Students can work freely during the semester to prepare their material. The written summary and the presentation slides must be submitted by the morning of the Seminar Day.

Contact:

• Prof. Dr. Maren Bennewitz
• Course organization and registration: Dr. Marcell Missura

Important dates:

Registration

The registration is closed.

Topics:

1. Footstep and Motion Planning in Semi-unstructured Environments Using Randomized Possibility Graphs.
   Michael X. Grey, Aaron D. Ames, and C. Karen Liu.
   IEEE International Conference on Robotics and Automation (ICRA), 2017.
   Supervisor: Maren Bennewitz
   [PDF]
2. Using Previous Experience for Humanoid Navigation Planning
   Y.-C. Lin and D. Berenson
   IEEE International Conference on Humanoid Robots (Humanoids), 2016.
   Supervisor: Maren Bennewitz
   [PDF]
3. Feedback Control for Cassie with Deep Reinforcement Learning
   Zhaoming Xie, Glen Berseth, Patrick Clary, Jonathan Hurst, Michiel van der Panne
   IROS 2018.
   Supervisor: Marcell Missura
   [PDF]
4. Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
   Michael Everett, Yu Fan Chen, Jonathan P. How
   IROS 2018.
   Supervisor: Marcell Missura
   [PDF]
5. The Elephant in the Room
   A. Rosenfeld, R. Zemel, J. K. Tsotsos
   ArXiv preprint, 2018.
   Supervisor: Lilli Bruckschen
   [PDF]
6. Smart Augmentation: Learning an Optimal Data Augmentation Strategy
   J. Lemley, S. Bazrafkan, P. Corcoran
   IEEE Access, 2017.
   Supervisor: Lilli Bruckschen
   [PDF]
7. Fast Kinodynamic Bipedal Locomotion Planning with Moving Obstacles
   J. Ahn, O. Campbell, D. Kim, L. Sentis
   IROS 2018.
   Supervisor: Philipp Karkowski
   [PDF]
8. Efficient Humanoid Motion Planning on Uneven Terrain Using Paired Forward-Inverse Dynamic Reachability Maps
   Y. Yang, W. Merkt, H. Ferrloho, V. Ivan, S. Vijayakumar
   IROS 2017.
   Supervisor: Philipp Karkowski
   [PDF]
9. Robot Companion: A Social-Force based Approach with Human Awareness-Navigation in Croweded Environments
   Gonzalo Ferrer, Anais Garrell and Alberto Sanfeliu
   IROS 2013.
   Supervisor: Peter Regier
   [PDF]
10. Map-based Deep Imitation Learning for Obstacle Avoidance
    Y. Liu, A. Xu, Z. Chen
    IROS 2018.
    Supervisor: Peter Regier
    [PDF]