You are here: Home Teaching SS 2025 Seminar: Learning for Robot …

Seminar: Learning for Robot Manipulation

Organizer:
Dr. Tim Welschehold

Co-Organizers:
Imen Mahdi, Akshay L Chandra

In the era of intelligent automation, the ability of robots to interact with their environment through precise and adaptive manipulation is crucial. This seminar explores the latest advancements in learning for robot manipulation, where machine learning, computer vision and motion generation converge to equip robots with human-like dexterity. In particular, we will analyze contributions to the field using techniques including reinforcement learning, imitation learning and diffusion-based policy learning for tackling various challenges in robotic manipulation.

Course Information

Details:
Course Number: 11LE13S-7354-M
Places: 10
Location: Georges-Köhler-Allee 80, Room Number 00.021
Course Program:
Introduction: 23/04/2025 @ 16:00
How to make a presentation: 27/06/2025 @ 10:00
Block Seminar: 29/07/2025
Evaluation Program:
  Seminar Presentation: 29/07/2025
  Summary Due Date: 05/08/2025 @ 23:59 CEST
Requirements:
  Basic knowledge of Deep Learning or Reinforcement Learning or Robotics
Remarks:
Topics will be assigned for the seminar via preference voting. If there are more interested students than places, places will be assigned based on priority suggestions of the HisInOne system. 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. 

Course Material

Additional Information

Enrollment Procedure

  • Enroll through HISinOne, the course number is 11LE13S-7354-M.
  • The registration period for the seminars are from 22/04/2025 to 28/04/2025.
  • Attend the introductory session on 23/04/2025.
  • Select three papers from the topic list below and complete this form by 28/04/2025.
  • Places will be assigned based on the priority suggestions of HISInOne and the student's motivation on 2/05/2025.

Evaluation Details

  • Students are expected to prepare a 20-minute long presentation and draft a summary.
  • The seminar will be held as a "Blockseminar" on TBA/2025
  • 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/08/202%. 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 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 (Summary / Presentation).

Topics

  1. Octo: An Open-Source Generalist Robot Policy
    Supervisor: Imen Mahdi
  2. OpenVLA: An Open-Source Vision-Language-Action Model
    Supervisor: Imen Mahdi
  3. π0 : A Vision-Language-Action Flow Model for General Robot Control
    Supervisor: Imen Mahdi
  4. Open X-Embodiment: Robotic Learning Datasets and RT-X Models
    Supervisor: Imen Mahdi
  5. Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
    Supervisor: Imen Mahdi
  6. PERCEIVER-ACTOR: A Multi-Task Transformer for Robotic Manipulation
    Supervisor: Imen Mahdi
  7. PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
    Supervisor: Imen Mahdi
  8. Inference-Time Policy Steering through Human Interactions
    Supervisor: Imen Mahdi
  9. Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
    Supervisor: Akshay L Chandra
  10. HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation
    Supervisor: Akshay L Chandra
  11. Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
    Supervisor: Akshay L Chandra
  12. Real-is-Sim: Bridging the Sim-to-Real Gap with a Dynamic Digital Twin for Real-World Robot Policy Evaluation
    Supervisor: Akshay L Chandra

Questions?

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