Detail of the student project

Topic:Visual navigation using artificial landmarks
Department:Katedra kybernetiky
Supervisor:Ing. Vojtěch Vonásek, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:The task of visual navigation is to derive robot paths based on a visual information (camera data) and using a known map of (visual) landmarks [1]. The task of this semestral work is to derive a simple navigation algorithm for a 2D mobile robot that uses only the visual information. Student should select a suitable map representation (see [2-4] for inspiration) for visual landmarks (e.g. a bar-code or other image features like SIFT, SURF, etc.) and implement a state-of-the-art method for robot navigation ([3] for inspiration). The project requires programming in c/c++/python. The result of a project is a functional code demonstrated by a video and technical report.

[1] S. Se, D. G. Lowe and J. J. Little, "Vision-based global localization and mapping for mobile robots," in IEEE Transactions on Robotics, vol. 21, no. 3, pp. 364-375, June 2005, doi: 10.1109/TRO.2004.839228.

[2] Mirowski, P., Grimes, M. K., Malinowski, M., Hermann, K. M., Anderson, K., Teplyashin, D., ... & Hadsell, R. (2018). Learning to navigate in cities without a map. arXiv preprint arXiv:1804.00168.

[3] Chen, K., de Vicente, J. P., Sepulveda, G., Xia, F., Soto, A., Vázquez, M., & Savarese, S. (2019). A behavioral approach to visual navigation with graph localization networks. arXiv preprint arXiv:1903.00445.

[4] Qing Li, Jiasong Zhu, Tao Liu, Jon Garibaldi, Qingquan Li, and Guoping Qiu. 2017. Visual landmark sequence-based indoor localization. In Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery (GeoAI '17). Association for Computing Machinery, New York, NY, USA, 14–23.
Responsible person: Petr Pošík