Automating the loop in traffic incident management on highway

Matteo Cercola, Nicola Gatti, Pedro Huertas Leyva, Benedetto Carambia, Simone Formentin
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:272-284, 2025.

Abstract

Effective traffic incident management is essential for ensuring safety, minimizing congestion, and reducing response times in emergency situations. Traditional highway incident management relies heavily on radio room operators, who must make rapid, informed decisions in high-stakes environments. This paper proposes an innovative solution to support and enhance these decisions by integrating Large Language Models (LLMs) into a decision-support system for traffic incident management. We introduce two approaches: (1) an LLM + Optimization hybrid that leverages both the flexibility of natural language interaction and the robustness of optimization techniques, and (2) a Full LLM approach that autonomously generates decisions using only LLM capabilities. We tested our solutions using historical event data from Autostrade per l’Italia. Experimental results indicate that while both approaches show promise, the LLM + Optimization solution demonstrates superior reliability, making it particularly suited to critical applications where consistency and accuracy are paramount. This research highlights the potential for LLMs to transform highway incident management by enabling accessible, data-driven decision-making support.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-cercola25a, title = {Automating the loop in traffic incident management on highway}, author = {Cercola, Matteo and Gatti, Nicola and Leyva, Pedro Huertas and Carambia, Benedetto and Formentin, Simone}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {272--284}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/cercola25a/cercola25a.pdf}, url = {https://proceedings.mlr.press/v283/cercola25a.html}, abstract = {Effective traffic incident management is essential for ensuring safety, minimizing congestion, and reducing response times in emergency situations. Traditional highway incident management relies heavily on radio room operators, who must make rapid, informed decisions in high-stakes environments. This paper proposes an innovative solution to support and enhance these decisions by integrating Large Language Models (LLMs) into a decision-support system for traffic incident management. We introduce two approaches: (1) an LLM + Optimization hybrid that leverages both the flexibility of natural language interaction and the robustness of optimization techniques, and (2) a Full LLM approach that autonomously generates decisions using only LLM capabilities. We tested our solutions using historical event data from Autostrade per l’Italia. Experimental results indicate that while both approaches show promise, the LLM + Optimization solution demonstrates superior reliability, making it particularly suited to critical applications where consistency and accuracy are paramount. This research highlights the potential for LLMs to transform highway incident management by enabling accessible, data-driven decision-making support.} }
Endnote
%0 Conference Paper %T Automating the loop in traffic incident management on highway %A Matteo Cercola %A Nicola Gatti %A Pedro Huertas Leyva %A Benedetto Carambia %A Simone Formentin %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-cercola25a %I PMLR %P 272--284 %U https://proceedings.mlr.press/v283/cercola25a.html %V 283 %X Effective traffic incident management is essential for ensuring safety, minimizing congestion, and reducing response times in emergency situations. Traditional highway incident management relies heavily on radio room operators, who must make rapid, informed decisions in high-stakes environments. This paper proposes an innovative solution to support and enhance these decisions by integrating Large Language Models (LLMs) into a decision-support system for traffic incident management. We introduce two approaches: (1) an LLM + Optimization hybrid that leverages both the flexibility of natural language interaction and the robustness of optimization techniques, and (2) a Full LLM approach that autonomously generates decisions using only LLM capabilities. We tested our solutions using historical event data from Autostrade per l’Italia. Experimental results indicate that while both approaches show promise, the LLM + Optimization solution demonstrates superior reliability, making it particularly suited to critical applications where consistency and accuracy are paramount. This research highlights the potential for LLMs to transform highway incident management by enabling accessible, data-driven decision-making support.
APA
Cercola, M., Gatti, N., Leyva, P.H., Carambia, B. & Formentin, S.. (2025). Automating the loop in traffic incident management on highway. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:272-284 Available from https://proceedings.mlr.press/v283/cercola25a.html.

Related Material