KIT | KIT-Bibliothek | Impressum | Datenschutz

Learning Occlusions in Robotic Systems: How to Prevent Robots from Hiding Themselves

Nazarenus, Jakob; Reichhuber, Simon; Amersdorfer, Manuel ORCID iD icon 1; Elsner, Lukas; Koch, Reinhard; Tomforde, Sven; Abbas, Hossam
1 Institut für Mechanische Verfahrenstechnik und Mechanik (MVM), Karlsruher Institut für Technologie (KIT)

Abstract:

In many applications, robotic systems are monitored via camera systems. This helps with monitoring automated production processes, anomaly detection, and the refinement of the estimated robot’s pose via optical tracking systems. While providing high precision and flexibility, the main limitation of such systems is their line-of-sight constraint. In this paper, we propose a lightweight solution for automatically learning this occluded space to provide continuously observable robot trajectories. This is achieved by an initial autonomous calibration procedure and subsequent training of a simple neural network. During operation, this network provides a prediction of the visibility status with a balanced accuracy of 90% as well as a gradient that leads the robot to a more well-observed area. The prediction and gradient computations run with sub-ms latency and allow for modular integration into existing dynamic trajectory-planning algorithms to ensure high visibility of the desired target.


Download
Originalveröffentlichung
DOI: 10.5220/0012431000003636
Zugehörige Institution(en) am KIT Institut für Mechanische Verfahrenstechnik und Mechanik (MVM)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2024
Sprache Englisch
Identifikator ISBN: 978-9-897586804
KITopen-ID: 1000169014
Erschienen in Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART 2024)
Veranstaltung 16th International Conference on Agents and Artificial Intelligence (ICAART 2024), Rom, Italien, 24.02.2024 – 26.02.2024
Auflage 2
Verlag SciTePress
Seiten 482-492
Schlagwörter Vision and Perception, Robot and Multi-Robot Systems, Simulation, Neural Networks, Classification, Autonomous Systems.
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page