We have exciting new projects, not only for SA and MA students, but also other team members looking for a fun and interesting project next to ETH obligations. If you are interested in a SA or MA please contact one of our PhDs to discuss project ideas. For other projects, check out the list of current projects below and contact one of our TAs for more information.
If you are interested in previous projects, go to our Project Report site, where you can download multiple reports of previous projects.
If you are from a different team and your team works with the B-Human code framework, make sure to check our YouTube channel for some tutorials on the framework by Filippo Martinoni.
Semester / Master Projects
- Pose detection by Image Translation [closed]
- Objects and field detection in Robocup [closed]
- Design of a Dynamic Omni-directional Kick Engine for NAO Bipedal Robots in RoboCup [closed]
If interested in a thesis please directly reach out to the supervisors mentioned in the proposals or send an email to firstname.lastname@example.org for general questions about projects.
This is a glance of the projects we have to deal with as members of the team. Every year new challenges arise and our job is to find solution to them exploiting our capabilities while implementing the newest technological advancements to made our robots work better and better.
- Automatic Calibration
The joints and the sensors of the robots need to be calibrated from time to time. At the moment, this process is still very manual, time-consuming and error prone. We want to implement a procedure through which the robot can autonomously calibrate itself by walking on the field.
- Improve Whistle Detection
At the beginning of the game or after a goal is scored, all robots listen for a whistle and start playing when they hear it. If they don’t hear it, they have to wait for 15 seconds before they can start playing. Unfortunately, our current whistle detection is not up to par. Sometimes we don’t hear the whistle at all and sometimes we hear false whistles, which also results in a penalty. We would like a new (and better) whistle module for the upcoming tournaments!
- New Kick Development
During the 5 vs. 5 matches of our NAO robots it often happens that our robots need to duel with an opponent for acquiring the ball. In these cases, a side kick can be beneficial to use if the ball is stuck between our robot and the opponent, e.g. when dribbling towards the opponent. Therefore, we would like to create a new side kick motion, which can be executed in these situations. The motion of the kick should first be developed in a motion simulator.
- Whole-Body Control for Kicking
We want to develop a robust algorithm to produce the kicking motion, able to deal with stability issues that could arise from any unwanted contact with the floor or other robots. Also, this approach could lead to an improvement in control over kicking direction.
- Semantic Segmentation
Instead of object detection, we want to try out a more holistic approach to scene understanding: semantic segmentation. The goal of this project is to develop a deep learning model for semantic segmentation that can run in real-time on the embedded CPU of the NAO V6.
- Synthetic Image Generation
In recent years, deep learning models for computer vision have become more ubiquitous in the SPL. However, collecting and annotating training datasets is a very time-consuming task. We want to leverage state-of-the-art photorealistic simulators to generate synthetic datasets.