Intelligent systems that perform complex tasks in everyday environments require the ability to perceive their environment and the objects with which they interact. Besides tactile or proprioceptive sensing, vision is an important sensing modality for such systems that provides rich sensory information. The Embodied Vision group (https://ev.is.mpg.de) at the Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen investigates novel approaches to vision-based perception and learning for intelligent systems that are closely coupled with control and planning. Ideally, perception and control should not be investigated in isolation but in a coherent way to support robustness, flexibility, adaptation and learning for the complete system.
In this research context, we are looking for talented students who are pursuing a Master of Science degree in computer science, electrical or control engineering, applied mathematics or physics and are eager to pursue their Master thesis on a research topic in our group. Possible topic areas could include, for example:
- Visual and visual-inertial simultaneous localization and mapping (incl. approaches using deep learning)
- Dynamic 3D scene understanding
- Deep reinforcement learning
- Perceptual learning of intuitive physics for object manipulation
- Vision-based autonomous navigation of mobile robots and multicopters
The thesis will allow the student to gain hands-on experience with computer vision methods and intelligent systems, as well as be exposed to ongoing research. The concrete topics are subject to discussion with interested candidates. Earliest start date is February 2019.
Embodied Vision Group
The project will be carried out at the Max Planck Institute for Intelligent Systems (MPI-IS) located in Tübingen within the Embodied Vision Group headed by Dr. Joerg Stueckler. The group investigates fundamentals of embodied intelligent agents such as robots that learn to perceive and act within their environment. Further information on the group can be found at https://ev.is.mpg.de
High motivation, excellent skills in computer science, a solid background in mathematics and computer vision, and hands-on experience in deep learning are prerequisites. Furthermore, good programming skills in C/C++, Python and TensorFlow are required. Previous research experience in computer vision, deep learning or robotics is a plus.
How to apply
Applications should be sent in a single pdf (max. 10MB) per email and include a CV, a short motivation letter (why are you interested in this research?), current transcripts of BSc/MSc studies, earliest date of availability, and optionally other documentation helpful to evaluate your background. Don't hesitate to contact us by email if you have questions.
Contact Details: Dr. Joerg Stueckler | firstname.lastname@example.org MPI for Intelligent Systems, Max-Planck-Ring 4, 72076 Tübingen, Germany. +49 (0) 7071-601 385 | http://is.mpg.de/person/jstueckler