Practical Course: Visual Navigation for Flying Robots (6h SWS)
In this course, you will develop and implement algorithms for the visual navigation of multicopters. This includes e.g. simultaneous localization and mapping with monocular or stereo cameras, (semi-)dense 3D reconstruction, obstacle perception and avoidance, and autonomous path planning and execution.
We will work on tasks as considered in Stage I of the EuRoC Challenge 3 for autonomous multicopters: http://www.euroc-project.eu/fileadmin/Files/Call4Challengers/EuRoC_Call4Challengers_Annex3.pdf
Further information on EuRoC, a European robotics challenge, can be found here: http://www.euroc-project.eu/
The project work will be conducted in teams of up to 3 participants. During the project work, you will be provided with PC equipment. To facilitate a direct supervision of your project work, you should make use of the lab time from 9 am to 5 pm during the project work phase.
Please direct ALL questions regarding this course at firstname.lastname@example.org
- Jörg Stückler
Date and Location
Start: Mo, September 8, 2014, 9 am c.t.
The course will take place in our lab 02.05.014. The general time is September 8 – October 10, with the following preliminary timeline:
- introductory lectures (attendance mandatory): September 8 – 9
- 4 weeks project phase (attendance mandatory): September 10 – October 3
- final presentation: between October 6 – 10
- general lab time: 9am - 5pm
Course registration closed.
Please write an e-mail to email@example.com if you are interested to participate!
Requirements: Good knowledge of C/C++ is recommended. Prior knowledge of topics in robotics and computer vision are a plus.
Number of participants: up to 12
- Lecture: Multiple View Geometry
- LSD-SLAM: Large-Scale Direct Monocular SLAM (J. Engel, T. Schöps, D. Cremers), In European Conference on Computer Vision (ECCV), 2014
- Collision Avoidance for Quadrotors with a Monocular Camera (H. Alvarez, L.M. Paz, J. Sturm, D. Cremers), In Proc. of The 12th International Symposium on Experimental Robotics (ISER), 2014