Conference paper · 2019 · Open access

Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning

Julian Bernhard, Stefan Pollok, Alois Knoll

IEEE Intelligent Vehicles Symposium, 2148–2155 · Published 1 June 2019 · DOI 10.1109/ivs.2019.8813791

Open PDFView at the publisherCite this paper

In brief

“Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning” is a 2019 conference paper by Julian Bernhard and 2 co-authors, published in IEEE Intelligent Vehicles Symposium. OpenAlex counts 55 citations as of 22 November 2026, which puts it in the top 8% of works published in 2019 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
55
Most cited in
2024 (15)
Field-weighted impact
3.20
References
33
Authors
3

Abstract

For highly automated driving above SAE level 3, behavior generation algorithms must reliably consider the inherent uncertainties of the traffic environment, e.g. arising from the variety of human driving styles. Such uncertainties can generate ambiguous decisions, requiring the algorithm to appropriately balance low-probability hazardous events, e.g. collisions, and high-probability beneficial events, e.g. quickly crossing the intersection. State-of-the-art behavior generation algorithms lack a distributional treatment of decision outcome. This impedes a proper risk evaluation in ambiguous situations, often encouraging either unsafe or conservative behavior. Thus, we propose a two-step approach for risk-sensitive behavior generation combining offline distribution learning with online risk assessment. Specifically, we first learn an optimal policy in an uncertain environment with Deep Distributional Reinforcement Learning. During execution, the optimal risk-sensitive action is selected by applying established risk criteria, such as the Conditional Value at Risk, to the learned state-action return distributions. In intersection crossing scenarios, we evaluate different risk criteria and demonstrate that our approach increases safety, while maintaining an active driving style. Our approach shall encourage further studies about the benefits of risk-sensitive approaches for self-driving vehicles.

Cite this paper

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

APA 7

Bernhard, J., Pollok, S., & Knoll, A. (2019). Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning. IEEE Intelligent Vehicles Symposium, 2148–2155. https://doi.org/10.1109/ivs.2019.8813791

MLA 9

Bernhard, Julian, et al. “Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning.” IEEE Intelligent Vehicles Symposium, 2019, pp. 2148–2155. https://doi.org/10.1109/ivs.2019.8813791.

Chicago

Bernhard, Julian, Stefan Pollok, and Alois Knoll. 2019. “Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning.” IEEE Intelligent Vehicles Symposium: 2148–2155. https://doi.org/10.1109/ivs.2019.8813791.

Harvard

Bernhard, J., Pollok, S. and Knoll, A. (2019) ‘Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning’, IEEE Intelligent Vehicles Symposium, pp. 2148–2155. doi:10.1109/ivs.2019.8813791.

IEEE

J. Bernhard, S. Pollok, and A. Knoll, “Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning,” IEEE Intelligent Vehicles Symposium, pp. 2148–2155, 2019, doi: 10.1109/ivs.2019.8813791.

BibTeX

@inproceedings{bernhard2019addressing,
  title     = {{Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning}},
  author    = {Bernhard, Julian and Pollok, Stefan and Knoll, Alois},
  booktitle = {IEEE Intelligent Vehicles Symposium},
  year      = {2019},
  pages     = {2148--2155},
  doi       = {10.1109/ivs.2019.8813791},
  url       = {https://doi.org/10.1109/ivs.2019.8813791}
}

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

Citations by year

YearCitationsShare of the best year
202022
202144
202299
20231111
20241515
202555
202699

Its field-weighted citation impact is 3.20: it has been cited 3.20 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

  • autonomous driving
  • behavior generation
  • risk-sensitive decision making
  • distributional reinforcement learning
  • conditional value at risk
  • risk assessment
  • intersection crossing
  • autonomous vehicles

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?

Bernhard, J., Pollok, S., & Knoll, A. (2019). Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning. IEEE Intelligent Vehicles Symposium, 2148–2155. https://doi.org/10.1109/ivs.2019.8813791

How many times has this paper been cited?

55 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?

Julian Bernhard, Stefan Pollok, Alois Knoll.

What is the DOI of this paper?

10.1109/ivs.2019.8813791, permanently at https://doi.org/10.1109/ivs.2019.8813791. 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.