CoChat
Sign Up
Cited by 140Autonomous Vehicle Technology and SafetyEthics and Social Impacts of AISafety Systems Engineering in Autonomy

An ethical trajectory planning algorithm for autonomous vehicles

Open access
Geisslinger, Maximilian, Poszler, Franziska, Lienkamp, Markus·2023·Nature Machine Intelligence
DOI 10.1038/s42256-022-00607-z

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract With the rise of AI and automation, moral decisions are being put into the hands of algorithms that were formerly the preserve of humans. In autonomous driving, a variety of such decisions with ethical impli-cations are made by algorithms for behavior and trajectory planning. Therefore, we present an ethical trajectory planning algorithm with a framework that aims at a fair distribution of risk among road users. Our implementation incorporates a combination of five essential ethical principles: minimization of the overall risk, priority for the worst-off, equal treatment of people, responsibility, and maximum acceptable risk. To the best of the authors’ knowledge, this is the first ethical algorithm for trajectory planning of autonomous vehicles in line with the 20 recommendations from the EU Commission expert group and with general applicability to various traffic situations. We showcase the ethical behavior of our algorithm in selected scenarios and provide an empirical analysis of the ethical principles in 2000 scenarios. The code used in this research is available as open-source software.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s42256-022-00607-z

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Prior ethical AV approaches often rely on pre-defined rankings, hand-tuned parameters, or fixed weighting schemes, which may not adapt well to heterogeneous, real-world traffic.

    “At the same time, they often rely on pre-defined rankings, hand-tuned parameters, or fixed weighting schemes, which may not adapt well to heterogeneous, real-world traffic.”

    From Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving (2026) · cites this paper as [11]

    The Discussion (page unavailable) says that a particular set of weighting factors may not apply universally because countries, cultures, and individuals may demand different ethical emphases. This supports the concern about fixed weights, but the paper does not establish that prior ethical AV approaches often use pre-defined rankings or hand-tuned parameters, or that those approaches fail in heterogeneous real-world traffic. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 21

  1. Lin, P. Why Ethics Matters for Autonomous Cars. in Autonomous Driving: Technical, Legal and Social Aspects 69-85 (2016). doi:10.1007/978-3-662-48847- 8. · DOI · Paper page
  2. Kriebitz, A., Max, R. & Lütge, C. The German Act on Autonomous Driving : Why Ethics Still Matters. Philos. Technol. 1-13 (2022) doi:10.1007/s13347- 022-00526-2. · DOI
  3. Thornton, S. M., Pan, S., Erlien, S. M. & Gerdes, J. C. Incorporating Ethical Considerations into Automated Vehicle Control. IEEE Trans. Intell. Transp. Syst. 18, 1429-1439 (2017).
  4. Wang, H., Huang, Y., Khajepour, A., Cao, D. & Lv, C. Ethical Decision-Making Platform in Autonomous Vehicles with Lexicographic Optimization Based Model Predictive Controller. IEEE Trans. Veh. Technol. 69, 8164-8175 (2020).
  5. Geisslinger, M., Poszler, F., Betz, J., Lütge, C. & Lienkamp, M. Autonomous Driving Ethics: from Trolley Problem to Ethics of Risk. Philos. Technol. (2021) doi:10.1007/s13347-021-00449-4. · DOI
  6. Bhargava, V. & Kim, T. W. Autonomous vehicles and moral uncertainty. Robot Ethics 2.0 From Auton. Cars to Artif. Intell. 5-19 (2017) doi:10.1093/oso/9780190652951.003.0001. · DOI
  7. Keeling, G., Evans, K., Thornton, S. M., Mecacci, G. & Santoni de Sio, F. Four Perspectives on What Matters for the Ethics of Automated Vehicles. 49-60 (2019) doi:10.1007/978-3-030-22933-7_6. · DOI
  8. Bonnefon, J. F., Shariff, A. & Rahwan, I. The trolley, the bull bar, and why engineers should care about the ethics of autonomous cars. Proc. IEEE 107, 502-504 (2019).
  9. Horizon 2020 Commission Expert Group. Ethics of Connected and Automated Vehicles: recommendations on road safety, privacy, fairness, explainability and responsibility. (Publication Office of the European Union: Luxembourg, 2020). doi:10.2777/035239. · DOI
  10. Nyberg, T., Pek, C., Dal Col, L., Noren, C. & Tumova, J. Risk-aware motion planning for autonomous vehicles with safety specifications. IEEE Intell. Veh. Symp. Proc. 2021-July, 1016-1023 (2021).
  11. Applin, S. Autonomous Vehicle Ethics: Stock or custom? IEEE Consum. Electron. Mag. 6, 108-110 (2017).
  12. Werling, M., Ziegler, J., Kammel, S. & Thrun, S. Optimal trajectory generation for dynamic street scenarios in a frenét frame. Proc. -IEEE Int. Conf. Robot. Autom. 987-993 (2010) doi:10.1109/ROBOT.2010.5509799. · DOI
  13. Hansson, S. O. The Ethics of Risk. (Palgrave Macmillan UK, 2013). doi:10.1057/9781137333650. · DOI
  14. Hansson, S. O., Belin, M. Å. & Lundgren, B. Self- Driving Vehicles-an Ethical Overview. Philos. Technol. 1383-1408 (2021) doi:10.1007/s13347-021- 00464-5. · DOI
  15. Trautman, P. & Krause, A. Unfreezing the robot: Navigation in dense, interacting crowds. IEEE/RSJ 2010 Int. Conf. Intell. Robot. Syst. IROS 2010 -Conf. Proc. 797-803 (2010) doi:10.1109/IROS.2010.5654369. · DOI
  16. Geisslinger, M., Karle, P., Betz, J. & Lienkamp, M. Watch-and-Learn-Net: Self-supervised Online Learning for Probabilistic Vehicle Trajectory Prediction. 869-875 (2022) doi:10.1109/smc52423.2021.9659079. · DOI
  17. Rawls, J. A Theory of Justice. (Harvard University Press, Cambridge, 1971).
  18. Shalev-Shwartz, S., Shammah, S. & Shashua, A. On a Formal Model of Safe and Scalable Self-driving Cars. arxiv.org/abs/1708.06374 1-37 (2017). · arXiv
  19. Althoff, M. Reachability Analysis and its Application to the Safety Assessment of Autonomous Cars. Fak. für Elektrotechnik und Informationstechnik 221 (2010) doi:10.1017/CBO9781107415324.004. · DOI · Paper page
  20. Althoff, M., Koschi, M. & Manzinger, S. CommonRoad: Composable benchmarks for motion planning on roads. IEEE Intell. Veh. Symp. Proc. 719- 726 (2017) doi:10.1109/IVS.2017.7995802. · DOI · Paper page
  21. De Freitas, J. et al. From driverless dilemmas to more practical commonsense tests for automated vehicles. Proc. Natl. Acad. Sci. U. S. A. 118, 1-9 (2021).

Cited by

Sorted by citations

Authors
Geisslinger, M., Poszler, F., & Lienkamp, M.
Affiliations
Technical University of Munich (DE)
Corresponding author
Geisslinger, Maximilian
ORCID
Venue
Nature Machine Intelligence
Publisher
Springer Science and Business Media LLC
Published
2023-02-02
Volume
5
Issue
2
Pages
137-144
ISSN
2522-5839 (ISSN-L)
DOI
10.1038/s42256-022-00607-z
OpenAlex
W4318982572
Cited by
140
References
3
Citations by year
2026: 42 · 2025: 44 · 2024: 39 · 2023: 15
FWCI
9.72
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion, public-domain)
  • Research Square (acceptedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • mediaTUM (Technical University of Munich) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
The authors received financial support from the Technical University of Munich — Institute for Ethics in Artificial Intelligence (IEAI).
Topics
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
Keywords
autonomous vehicles, algorithmic ethics, ethical principles, equal treatment, responsibility, maximum acceptable risk, risk minimization

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review