Conference paper · 2019 · Open access

Safe Reinforcement Learning With Model Uncertainty Estimates

Björn Lütjens, Michael Everett, Jonathan P. How

Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, 8662–8668 · Published 1 May 2019 · DOI 10.1109/icra.2019.8793611

Open PDFView at the publisherCite this paper

In brief

“Safe Reinforcement Learning With Model Uncertainty Estimates” is a 2019 conference paper by Björn Lütjens and 2 co-authors, published in Proceedings - IEEE International Conference on Robotics and Automation/Proceedings. OpenAlex counts 251 citations as of 22 November 2026, which puts it in the top 2% of works published in 2019 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
251
Most cited in
2024 (52)
Field-weighted impact
6.85
References
49
Authors
3

Abstract

Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly intractable to compute. This paper uses MC-Dropout and Bootstrapping to give computationally tractable and parallelizable uncertainty estimates. The methods are embedded in a Safe Reinforcement Learning framework to form uncertainty-aware navigation around pedestrians. The result is a collision avoidance policy that knows what it does not know and cautiously avoids pedestrians that exhibit unseen behavior. The policy is demonstrated in simulation to be more robust to novel observations and take safer actions than an uncertainty-unaware baseline.

Cite this paper

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

APA 7

Lütjens, B., Everett, M., & How, J. P. (2019). Safe Reinforcement Learning With Model Uncertainty Estimates. Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, 8662–8668. https://doi.org/10.1109/icra.2019.8793611

MLA 9

Lütjens, Björn, et al. “Safe Reinforcement Learning With Model Uncertainty Estimates.” Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, 2019, pp. 8662–8668. https://doi.org/10.1109/icra.2019.8793611.

Chicago

Lütjens, Björn, Michael Everett, and Jonathan P. How. 2019. “Safe Reinforcement Learning With Model Uncertainty Estimates.” Proceedings - IEEE International Conference on Robotics and Automation/Proceedings: 8662–8668. https://doi.org/10.1109/icra.2019.8793611.

Harvard

Lütjens, B., Everett, M. and How, J. P. (2019) ‘Safe Reinforcement Learning With Model Uncertainty Estimates’, Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, pp. 8662–8668. doi:10.1109/icra.2019.8793611.

IEEE

B. Lütjens, M. Everett, and J. P. How, “Safe Reinforcement Learning With Model Uncertainty Estimates,” Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, pp. 8662–8668, 2019, doi: 10.1109/icra.2019.8793611.

BibTeX

@inproceedings{lutjens2019safe,
  title     = {{Safe Reinforcement Learning With Model Uncertainty Estimates}},
  author    = {Lütjens, Björn and Everett, Michael and How, Jonathan P.},
  booktitle = {Proceedings - IEEE International Conference on Robotics and Automation/Proceedings},
  year      = {2019},
  pages     = {8662--8668},
  doi       = {10.1109/icra.2019.8793611},
  url       = {https://doi.org/10.1109/icra.2019.8793611}
}

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

Citations by year

YearCitationsShare of the best year
201966
20202323
20213535
20223232
20233939
20245252
20254040
20262424

Its field-weighted citation impact is 6.85: it has been cited 6.85 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 › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics

  • safe reinforcement learning
  • model uncertainty estimation
  • Monte Carlo dropout
  • bootstrapping
  • distribution shift
  • unseen data
  • collision avoidance
  • pedestrian navigation

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Lütjens, B., Everett, M., & How, J. P. (2019). Safe Reinforcement Learning With Model Uncertainty Estimates. Proceedings - IEEE International Conference on Robotics and Automation/Proceedings, 8662–8668. https://doi.org/10.1109/icra.2019.8793611

How many times has this paper been cited?

251 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?

Björn Lütjens, Michael Everett, Jonathan P. How.

What is the DOI of this paper?

10.1109/icra.2019.8793611, permanently at https://doi.org/10.1109/icra.2019.8793611. 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.