Conference paper · 2021 · Open access

Quantification of Uncertainties in Deep Learning-based Environment Perception

Marco Braun, Moritz Luszek, Jan Siegemund, Kevin Kollek, Anton Kummert

IEEE International Conference on Omni-layer Intelligent Systems (COINS), 1–8 · Published 23 August 2021 · DOI 10.1109/coins51742.2021.9524106

Open PDFView at the publisherCite this paper

In brief

“Quantification of Uncertainties in Deep Learning-based Environment Perception” is a 2021 conference paper by Marco Braun and 4 co-authors, published in IEEE International Conference on Omni-layer Intelligent Systems (COINS). OpenAlex counts 5 citations as of 22 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
5
Most cited in
2025 (2)
Field-weighted impact
0.39
References
23
Authors
5

Abstract

In this work, we introduce a novel Deep Learning-based approach to perceive the environment of a vehicle based on radar scans while accounting for uncertainties in the model predictions. We segment the environment of the vehicle into equally sized grid cells, which we classify individually. Our algorithm is capable of differentiating uncertainties in the system output as being related to an inadequate model (epistemic uncertainty) or noisy data (aleatoric uncertainty). To this end, we utilize probability distributions on the weights that describe uncertainties in the model parameters and that can be learned in a supervised fashion using gradient descent. We show that the uncertainties in our model output correlate with the precision of the model predictions. Compared to previous concepts that estimate uncertainties by utilizing Monte Carlo Dropout layers, we show the superior performance of our approach to reliably perceive the environment of a vehicle.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Braun, M., Luszek, M., Siegemund, J., Kollek, K., & Kummert, A. (2021). Quantification of Uncertainties in Deep Learning-based Environment Perception. IEEE International Conference on Omni-layer Intelligent Systems (COINS), 1–8. https://doi.org/10.1109/coins51742.2021.9524106

MLA 9

Braun, Marco, et al. “Quantification of Uncertainties in Deep Learning-based Environment Perception.” IEEE International Conference on Omni-layer Intelligent Systems (COINS), 2021, pp. 1–8. https://doi.org/10.1109/coins51742.2021.9524106.

Chicago

Braun, Marco, Moritz Luszek, Jan Siegemund, Kevin Kollek, and Anton Kummert. 2021. “Quantification of Uncertainties in Deep Learning-based Environment Perception.” IEEE International Conference on Omni-layer Intelligent Systems (COINS): 1–8. https://doi.org/10.1109/coins51742.2021.9524106.

Harvard

Braun, M. et al. (2021) ‘Quantification of Uncertainties in Deep Learning-based Environment Perception’, IEEE International Conference on Omni-layer Intelligent Systems (COINS), pp. 1–8. doi:10.1109/coins51742.2021.9524106.

IEEE

M. Braun, M. Luszek, J. Siegemund, K. Kollek, and A. Kummert, “Quantification of Uncertainties in Deep Learning-based Environment Perception,” IEEE International Conference on Omni-layer Intelligent Systems (COINS), pp. 1–8, 2021, doi: 10.1109/coins51742.2021.9524106.

BibTeX

@inproceedings{braun2021quantification,
  title     = {{Quantification of Uncertainties in Deep Learning-based Environment Perception}},
  author    = {Braun, Marco and Luszek, Moritz and Siegemund, Jan and Kollek, Kevin and Kummert, Anton},
  booktitle = {IEEE International Conference on Omni-layer Intelligent Systems (COINS)},
  year      = {2021},
  pages     = {1--8},
  doi       = {10.1109/coins51742.2021.9524106},
  url       = {https://doi.org/10.1109/coins51742.2021.9524106}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202211
202411
202522
202611

Its field-weighted citation impact is 0.39: it has been cited 0.39 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety

  • uncertainty quantification
  • epistemic uncertainty
  • aleatoric uncertainty
  • vehicle perception
  • autonomous driving

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Braun, M., Luszek, M., Siegemund, J., Kollek, K., & Kummert, A. (2021). Quantification of Uncertainties in Deep Learning-based Environment Perception. IEEE International Conference on Omni-layer Intelligent Systems (COINS), 1–8. https://doi.org/10.1109/coins51742.2021.9524106

How many times has this paper been cited?

5 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Marco Braun, Moritz Luszek, Jan Siegemund, Kevin Kollek, Anton Kummert.

What is the DOI of this paper?

10.1109/coins51742.2021.9524106, permanently at https://doi.org/10.1109/coins51742.2021.9524106. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.