AI-Based Multi-Object Relative State Estimation with Self-Calibration Capabilities

Authors:
Thomas Jantos, Christian Brommer, Eren Allak, Stephan Weiss, and Jan Steinbrener
Publisher:
2023 IEEE International Conference on Robotics and Automation (ICRA)
Year:

This paper highlights the importance of extracting meaningful information from sensory data in mobile robotics. It introduces a method that combines AI-based object pose estimation from images with inertial measurement unit (IMU) data. This fusion enables accurate multi-object relative state estimation in a 6-DoF context, demonstrated through real-world experiments. The approach’s self-calibrating capabilities ensure reliable and reproducible results.

Citation

Citation key:
Jantos2023

BibTeX

@inproceedings{Jantos2023,
  title = {AI-Based Multi-Object Relative State Estimation with Self-Calibration Capabilities},
  url = {http://dx.doi.org/10.1109/ICRA48891.2023.10161375},
  DOI = {10.1109/icra48891.2023.10161375},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  publisher = {IEEE},
  author = {Jantos, Thomas and Brommer, Christian and Allak, Eren and Weiss, Stephan and Steinbrener, Jan},
  year = {2023},
  month = May,
  pages = {2789–2795}
}