You are here: Home Teaching SS 2021 Proseminar: Robot Learning

Proseminar: Robot Learning

Deep learning has become a key enabler of real world autonomous systems. Due to the significant advancement in deep learning, these systems are able to learn various tasks end-to-end, including for perception, state estimation, and control, thereby making important progress in object manipulation, scene understanding, visual recognition, object tracking, and learning-based control, amongst others. In this seminar, we will study a selection of state-of-the-art works that propose deep learning techniques for tackling various challenges in autonomous systems. In particular, we will analyze contributions in architecture design, and techniques selection that also include computer vision, reinforcement learning, imitation learning, and self supervised learning.

autonomous-seminar

Course Information

Details:
Course Number: 11LE13S-7316-MB
Places: 12
Zoom Session Details:
Meeting ID: 649 5703 9523
Passcode: roblearn21
Course Program:
Introduction: 23/04/2021 @ 14:00
How to make a presentation: 25/06/2021 @ TBA
Evaluation Program:
  Abstract Due Date: 18/06/2021
  Seminar Presentation: 23/07/2021
  Summary Due Date: 30/07/2021
Requirements:
  Basic knowledge of Deep Learning or Reinforcement Learning
Remarks:
Due to the Corona crisis, the entire seminar will be held online.
Topics will be assigned for the seminar via a preference voting. If there are more interested students than places, places will be assigned based on priority suggestions of the HisInOne system and motivation (tested by asking for a short summary of the preferred paper). The date of registration is irrelevant. In particular, we want to avoid that students grab a topic and then leave the seminar. Please have a coarse look at all available papers to make an informed decision before you commit. 

Slides and Templates

Slides:
Lecture 1: Introduction
Lecture 2: How to make a good presentation
Templates:

Additional Information

Enrollment Procedure

  • Enroll through HISinOne, the course number is 11LE13S-7316-MB.
  • The registration period for the seminars are from 19/04/2021 to 28/04/2021.
  • Attend the introductory session on 23/04/2021 via Zoom (Session details have been provided above).
  • Select three papers out of the topics list (see below) and complete this form.
  • Places will be assigned based on priority suggestions of HISInOne and motivation of the student on 29/04/2021.

Evaluation Details

  • Students are expected to write an abstract, prepare a 20-minute long presentation and draft a summary.
  • The abstract should not exceed two pages and is due on TBA.
  • The seminar will be held as a virtual "Blockseminar" on TBA.
  • The slides of your presentation should be discussed with the supervisor two weeks before the Blockseminar.
  • The summary should not exceed seven pages (excluding bibliography and images) and is due on TBA. Significantly longer summaries will not be accepted.
  • Ensure you cite all work you use including images and illustrations. Where possible, try to use your own illustrations.
  • The final grade is based on the oral presentation, the written abstract, the summary, and participation in the blockseminar.

What should the Summary contain?

The summary should address the following questions:

  • What is the paper's main contribution and why is it important?
  • How does it relate to other techniques in the literature?
  • What are the strengths and weaknesses of the paper?
  • What would be some interesting follow-up work? Can you suggest any possible improvements in the proposed methods? Are there any further interesting applications that the authors might have overlooked?

Graded Component Submission

  • Save your document as a PDF and directly submit it to your topic supervisor via email.
  • The filename should be in the format "FirstName_LastName_X.pdf" where X is the evaluation component (Abstract / Summary / Presentation).

Topics

  1. PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
    Supervisor: Nikhil Gosala
  2. DroNet: Learning to Fly by Driving
    Supervisor: Nikhil Gosala
  3. Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification
    Supervisor: Juana Valeria Hurtado
  4. Context Encoders: Feature Learning by Inpainting
    Supervisor: Juana Valeria Hurtado
  5. R2D2: Repeatable and Reliable Detector and Descriptor
    Supervisor: Dr. Daniele Cattaneo
  6. SegMatch: Segment Based Place Recognition in 3D Point Clouds
    Supervisor: Dr. Daniele Cattaneo
  7. Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
    Supervisor: Eugenio Chisari
  8. A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
    Supervisor: Eugenio Chisari
  9. Playing Atari with Deep Reinforcement Learning
    Supervisor: Daniel Honerkamp
  10. Recurrent Models of Visual Attention
    Supervisor: Daniel Honerkamp
  11. Efficiency and Equity are Both Essential: A Generalized Traffic Signal Controller with Deep Reinforcement Learning
    Supervisor: Dr. Tim Welschehold
  12. Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
    Supervisor: Dr. Tim Welschehold

Questions?

If you have any questions, please direct them to Nikhil Gosala before the topic allotment, and to your supervisor after you have received your topic.