Research Assistant
Dipl.-Ing. Marko Pavlić
Machine Vision and Perception Group (MVP)
Work address 1
Machine Vision and Perception Group (MVP)
Parkring 13
85748
Garching b. München
Contact
Room: 2.02.23
Floor: 2
Building: 8101 Parkring 11-13 Garching b. München
Research Interests
- Human Action Analysis
- Learning from Demonstration (LfD)
- Kalman Filter Design
- Robotics
Education
Marko Pavlić is a research assistant in the Machine Vision and Perception Group under Prof. Dr.-Ing. Darius Burschka. He received his master's degree in Eletrical Engineering from the Technical University of Graz, Austria, in 2019. Before joining the Machine Vision and Perception Group as a doctoral candidate in 2021, he worked as a Systems Engineer designing software for localisation of railway vehicles.
In his new role, he is part of the KI.Fabrik project that will enable to manufacture various mechatronic products by means of fully modular, reconfigurable, highly automated and integrated AI technologies.
Current Projects
Here are current topics listed which I am working on. Please do not hesitate to contact me if you are interested in any of the following topics!!!
I am also open to new topics if you have any in mind and want to work with me.
Designing the factory of the future for AI-supported production technologies
In the KI.Fabrik project we are responsible for the development of sensitive robots and new AI algorithms.
Learning from Demonstration
The goal is to teach a robot new tasks by simply demonstrating the task to him. We use a RGB-D camera to track human motion and use this input to model the task. The robot can recognize and repeat the learned motions, scaled in time and amplitude. You are welcome to help improving the framework by trying different models. Even though Deep Learning is not my preferred approach, I am not averse to mentoring someone who wants to try this approach for the problem.
Human Action Analysis
The idea is to use the model description of the "Learning from Demonstration" topic to analyse the human motion.
Kalman Filter Design for Tracking of Human Motion
We use a RGB-D camera to track human motion. This data is usually very noise and the task is to design a Kalman Filter for improving the human motion tracker.
Object Detection and Pose Estimation
The task is to use RGB-D camera input to recognize and estimate the 6D pose of objects. Objects will be factory related, e.g. gear box parts.