Journal article · 2026 · Open access

Calibrating Perception Uncertainty for Autonomous Driving

Markus Kängsepp, Meelis Kull

International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 34(05), 621–645 · Published 23 June 2026 · DOI 10.1142/s0218488526500212

Open full textCite this paper

In brief

“Calibrating Perception Uncertainty for Autonomous Driving” is a 2026 journal article by Markus Kängsepp and Meelis Kull, published in International Journal of Uncertainty Fuzziness and Knowledge-Based Systems. OpenAlex counts 4 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at International Journal of Uncertainty Fuzziness and Knowledge-Based Systems.

Citations
4
Most cited in
2023 (2)
References
38
Authors
2

Abstract

Autonomous driving systems must be capable of making quick decisions based on the perceived environment and specific driving conditions. Perception models in these systems perform well in detecting objects under favorable conditions but their performance deteriorates in poor visibility or with partly occluded objects. To reduce risks from undetected objects, autonomous vehicles must incorporate all relevant uncertainties into their decision-making processes. Grid-based perception outputs, such as occupancy grids, and object-based outputs, like lists of detected objects, must be accompanied by well-calibrated uncertainty estimates. These uncertainties are essential for ensuring the model’s reliability and safety. In this paper, we identify limitations in the current state-of-the-art and propose a more comprehensive set of uncertainty estimates that should be reported. In addition to commonly estimated forms of uncertainty about the presence, location, shape, and trajectory of detected objects, we propose to quantify the uncertainty about undetected objects within a region. Access to this set of uncertainties enables planners to perform region occupancy queries, which provide the probability that a certain region, such as the area around a chosen trajectory, is free of obstacles. We propose a novel approach for generating these probabilistic outputs from bird’s-eye-view (BEV) probabilistic semantic segmentation. Our experiments demonstrate that the initial probabilistic outputs from segmentation are not calibrated, and we present methods to achieve well-calibrated uncertainty estimates. Finally, we conduct an experiment on a downstream task, underscoring the importance of calibrated uncertainties for planning and highlighting the advantages of including additional uncertainty types.

Cite this paper

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

APA 7

Kängsepp, M., & Kull, M. (2026). Calibrating Perception Uncertainty for Autonomous Driving. International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 34(05), 621–645. https://doi.org/10.1142/s0218488526500212

MLA 9

Kängsepp, Markus, and Meelis Kull. “Calibrating Perception Uncertainty for Autonomous Driving.” International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, vol. 34, no. 05, 2026, pp. 621–645. https://doi.org/10.1142/s0218488526500212.

Chicago

Kängsepp, Markus and Meelis Kull. 2026. “Calibrating Perception Uncertainty for Autonomous Driving.” International Journal of Uncertainty Fuzziness and Knowledge-Based Systems 34 (05): 621–645. https://doi.org/10.1142/s0218488526500212.

Harvard

Kängsepp, M. and Kull, M. (2026) ‘Calibrating Perception Uncertainty for Autonomous Driving’, International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 34(05), pp. 621–645. doi:10.1142/s0218488526500212.

IEEE

M. Kängsepp and M. Kull, “Calibrating Perception Uncertainty for Autonomous Driving,” International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, vol. 34, no. 05, pp. 621–645, 2026, doi: 10.1142/s0218488526500212.

BibTeX

@article{kangsepp2026calibrating,
  title     = {{Calibrating Perception Uncertainty for Autonomous Driving}},
  author    = {Kängsepp, Markus and Kull, Meelis},
  journal   = {International Journal of Uncertainty Fuzziness and Knowledge-Based Systems},
  year      = {2026},
  volume    = {34},
  number    = {05},
  pages     = {621--645},
  doi       = {10.1142/s0218488526500212},
  url       = {https://doi.org/10.1142/s0218488526500212}
}

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

Citations by year

YearCitationsShare of the best year
202322
202411
202511

Topic and keywords

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

  • uncertainty calibration
  • autonomous driving
  • perceptual uncertainty
  • bird's-eye view
  • occupancy grid
  • object detection
  • planning under uncertainty
  • occlusion

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?

Kängsepp, M., & Kull, M. (2026). Calibrating Perception Uncertainty for Autonomous Driving. International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 34(05), 621–645. https://doi.org/10.1142/s0218488526500212

How many times has this paper been cited?

4 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 International Journal of Uncertainty Fuzziness and Knowledge-Based Systems: sign in and open the full text from this page.

Who wrote this paper?

Markus Kängsepp, Meelis Kull.

What is the DOI of this paper?

10.1142/s0218488526500212, permanently at https://doi.org/10.1142/s0218488526500212. 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.