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

Jakob Nazarenus, Simon Reichhuber, Manuel Amersdorfer, Lukas Elsner, Reinhard Koch, Sven Tomforde, Hossam Abbas

2024

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.

Paper Citation

in Harvard Style

Nazarenus J., Reichhuber S., Amersdorfer M., Elsner L., Koch R., Tomforde S. and Abbas H. (2024). Learning Occlusions in Robotic Systems: How to Prevent Robots from Hiding Themselves. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 482-492. DOI: 10.5220/0012431000003636

in Bibtex Style

@conference{icaart24,
author={Jakob Nazarenus and Simon Reichhuber and Manuel Amersdorfer and Lukas Elsner and Reinhard Koch and Sven Tomforde and Hossam Abbas},
title={Learning Occlusions in Robotic Systems: How to Prevent Robots from Hiding Themselves},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2024},
pages={482-492},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012431000003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Learning Occlusions in Robotic Systems: How to Prevent Robots from Hiding Themselves
SN - 978-989-758-680-4
AU - Nazarenus J.
AU - Reichhuber S.
AU - Amersdorfer M.
AU - Elsner L.
AU - Koch R.
AU - Tomforde S.
AU - Abbas H.
PY - 2024
SP - 482
EP - 492
DO - 10.5220/0012431000003636
PB - SciTePress