Autonomous indoor navigation based on visual location
Abstract
In this article, a control law for autonomous indoor navigation based on the visual detection of fiducial markers is developed. External pose estimation techniques such as GPS tracking or RGB-D sensors on ceilings are difficult to implement in closed environments where there may be view or signal obstruction, such as in warehouses, so local pose estimation with on-board sensors presents a better solution. The implementation of high-definition webcams is a cheaper option than the use of high-quality sensors
such as laser ones (i.e. Lidar). In the designed control law, an ArUco visual marker is considered in a robot field of vision, as a local inertial frame of reference. Based on the errors measured by odometry, it is possible to execute the regulation task towards this marker.
Downloads
References
Babinec, A., Juriˇsica, L., Hubinsk´y, P., y Duchoˇn, F. (2014). Visual localization of mobile robot using artificial markers. Procedia Engineering, 96:1–9.
De Luca, A., Oriolo, G., y Vendittelli, M. (2001). Control of Wheeled Mobile Robots: An Experimental Overview. Springer Berlin Heidelberg, Berlin, Heidelberg.
de Oliveira Junior, A., Piardi, L., Bertogna, E. G., y Leitao, P. (2021). Improving the mobile robots indoor localization system by combining slam with fiducial markers. 2021 Latin American Robotics Symposium (LARS), 2021
Brazilian Symposium on Robotics (SBR), and 2021 Workshop on Robotics in Education (WRE). Guo, J., Wu, P., y Wang, W. (2020). A precision pose measurement technique based on multi-cooperative logo. Journal of Physics: Conference Series, 1607(1):012047.
Gutiérrez, H., Morales-D´ıaz, A., y Nijmeijer, H. (2017). Synchronization control for a swarm of unicycle robots: analysis of different controller topologies: Synchronization control for a swarm of unicycle robots. Asian Journal
of Control, 19.
Khalil, H. K. (2015). Nonlinear control / Hassan K. Khalil. Pearson.
Odroid (2022). Odroid-c4.
OpenCV (2022). Detection of aruco markers.
Poroykov, A., Kalugin, P., Shitov, S., y Lapitskaya, I. (2020). Modeling aruco markers images for accuracy analysis of their 3d pose estimation. Proceedings of the 30th International Conference on Computer Graphics and
Machine Vision (GraphiCon 2020). Part 2.
Team, T. A. (2022). Uno r3: Arduino documentation.
Zhang, C., Tao, D., Wang, L., y Wu, Y. (2021). Robot visual servo control system based on deep detection network and spatial pose estimation. 2021 33rd
Chinese Control and Decision Conference (CCDC).
