Karriere

Master Thesis/Internship: Parkour MPC

In order to strengthen our dedicated team in the Robotics Innovation Center (RIC) research department in Bremen we are looking for a  

Master Thesis/Internship Parkour MPC (full-time/part-time, 3 – 9 months) 

The Robotics Innovation Center research department, headed by Prof. Dr. Dr. h.c. Kirchner, develop robot systems that are used for complex tasks on land, under water, in the air, and in space. The recently established underactuated lab at DFKI-RIC is looking for outstanding students to join us in pushing the boundaries of highly dynamic and agile robots. Past internships and master thesis students have presented their work at the Summer of Underactuation events in 2022 and 2023.

Topic: 

Whole body control [1] has become the de-facto method of choice for the instantaneous control of highly redundant robotic systems like humanoids [2]. On the other hand, whole body trajectory optimization has become a popular tool for discovering optimal trajectories for a variety of complex tasks we expect from humanoids. This thesis aims to explore parkour-like dynamic trajectories for a bipedal robotic platform currently under development at the Underactuated Robotics lab at DFKI RIC. The goal of the thesis would be to develop an online Model-Predictive Controller for performing dynamic parkour-like movements on the bipedal platform while avoiding/jumping over obstacles.


Our requirements:

Mathematical: Whole body control (WBC), Model Predictive Control, Trajectory Optimization, Rigid body kinematics and dynamics, Linear Algebra.

Programming: C/C++, Python, experience with WBC frameworks, Model based optimization frameworks (e.g. drake, crocoddyl), experience with developing controllers for real systems

Literature:

1. Dennis Mronga, Tobias Knobloch, José de Gea Fernández & Frank Kirchner (2020) A constraint-based approach for human–robot collision avoidance, Advanced Robotics, 34:5, 265-281, DOI: https://doi.org/10.1080/01691864.2020.1721322

2. Bergonzani, I., Popescu, M., Kumar, S. and Kirchner, F., 2023. Fast Dynamic Walking with RH5 Humanoid Robot. IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2023.

Please contact Dennis Mronga for further information and send your application via E-Mail to Dennis.Mronga@dfki.de.

Deutsches Forschungszentrum für Künstliche Intelligenz GmbH
Research Department
Robotics Innovation Center
Robert-Hooke-Str. 1
28359 Bremen, Germany
www.dfki.de/ric
Phone: +49 421 17845 6560
Dennis.Mronga@dfki.de

© DFKI GmbH
zuletzt geändert am 31.03.2023