Conference paper · 2025 · Open access

Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections

Zhihao Lin, Jianglin Lan, Christos Anagnostopoulos, Zhen Tian, David Flynn

IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 279–284 · Published 21 July 2025 · DOI 10.1109/icdcsw63273.2025.00053

Open PDFView at the publisherCite this paper

In brief

“Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections” is a 2025 conference paper by Zhihao Lin and 4 co-authors, published in IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW). OpenAlex counts 18 citations as of 22 November 2026. It is open access: the full text is free to read at Enlighten: Publications (University of Glasgow).

Citations
18
Most cited in
2025 (17)
Field-weighted impact
9.27
References
24
Authors
5

Abstract

Decision making at unsignalized intersections presents significant challenges for Autonomous Vehicles (AVs), particularly in mixed traffic scenarios where both AVs and Human-driven Vehicles (HDVs) must safely coordinate their movements. This paper proposes a safety-critical multi-agent Monte Carlo Tree Search (MCTS) that integrates deterministic and probabilistic predictions of HDVs behaviors to enable cooperative decision making of AVs in complex intersection scenarios. The paper has three main innovations: (i) a safety assessment mechanism that systematically handles AV-to-AV (V2V), AV-to-HDV (V2H), and Vehicle-to-Road (V2R) interactions using dynamic safety thresholds and spatiotemporal risk metrics, (ii) an adaptive HDV behavior prediction by combining the Intelligent Driver Model with probabilistic distributions, and (iii) a multiobjective reward function optimization approach that balances safety, efficiency, and cooperation. The results demonstrate the framework’s efficacy in challenging mixed traffic scenarios (50% AVs $\boldsymbol{+} \mathbf{5 0 \%}$ HDVs). Compared to benchmarks, our method reduces trajectory deviations up to $\mathbf{6 2. 4 3 \%}$ while maintaining significantly lower Post-Encroachment Time (PET) violations (2.8%).

Cite this paper

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

APA 7

Lin, Z., Lan, J., Anagnostopoulos, C., Tian, Z., & Flynn, D. (2025). Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections. IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 279–284. https://doi.org/10.1109/icdcsw63273.2025.00053

MLA 9

Lin, Zhihao, et al. “Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections.” IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 2025, pp. 279–284. https://doi.org/10.1109/icdcsw63273.2025.00053.

Chicago

Lin, Zhihao, Jianglin Lan, Christos Anagnostopoulos, Zhen Tian, and David Flynn. 2025. “Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections.” IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW): 279–284. https://doi.org/10.1109/icdcsw63273.2025.00053.

Harvard

Lin, Z. et al. (2025) ‘Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections’, IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), pp. 279–284. doi:10.1109/icdcsw63273.2025.00053.

IEEE

Z. Lin, J. Lan, C. Anagnostopoulos, Z. Tian, and D. Flynn, “Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections,” IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), pp. 279–284, 2025, doi: 10.1109/icdcsw63273.2025.00053.

BibTeX

@inproceedings{lin2025multi,
  title     = {{Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections}},
  author    = {Lin, Zhihao and Lan, Jianglin and Anagnostopoulos, Christos and Tian, Zhen and Flynn, David},
  booktitle = {IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW)},
  year      = {2025},
  pages     = {279--284},
  doi       = {10.1109/icdcsw63273.2025.00053},
  url       = {https://doi.org/10.1109/icdcsw63273.2025.00053}
}

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

Topic and keywords

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

  • unsignalized intersections
  • autonomous vehicles
  • mixed traffic
  • Intelligent Driver Model
  • safety assessment
  • vehicle-to-vehicle communication
  • cooperative decision-making
  • post-encroachment time

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?

Lin, Z., Lan, J., Anagnostopoulos, C., Tian, Z., & Flynn, D. (2025). Multi-Agent Monte Carlo Tree Search for Safe Decision making at Unsignalized Intersections. IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW), 279–284. https://doi.org/10.1109/icdcsw63273.2025.00053

How many times has this paper been cited?

18 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 Enlighten: Publications (University of Glasgow): sign in and open the PDF from this page.

Who wrote this paper?

Zhihao Lin, Jianglin Lan, Christos Anagnostopoulos, Zhen Tian, David Flynn.

What is the DOI of this paper?

10.1109/icdcsw63273.2025.00053, permanently at https://doi.org/10.1109/icdcsw63273.2025.00053. 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.