Predicting the Risk of Vehicle–Cyclist Crashes in Urban Intersections Using Bayesian Networks

Kranthi Kumar Talluri, Anders L Madsen, Galia Weidl, Christer Ahlström, Johan Olstam
Proceedings of the 13th International Conference on Probabilistic Graphical Models, PMLR 343:850-863, 2026.

Abstract

The i4Driving European Union project aims to establish a credible and realistic human road safety baseline for virtual assessment of Connected, Cooperative, and Automated Mobility (CCAM) systems. As part of these efforts, multiple driving simulator experiments have been conducted to collect data to verify the developed human driver models. This paper focuses on the analysis of data from two urban road experiments in the same scenario involving a vehicle and a bicycle. The paper describes the development of a knowledge-driven Bayesian network (BN) to predict the risk of a right-turn maneuver involving a bicycle traveling straight through a four-way urban traffic intersection. The paper also reports on the results of an experimental analysis on data from the two urban road experiments, each involving several hundred driving sequences with a population of different human drivers. The predictive accuracy of the knowledge-driven model is high with a significant prediction horizon. That is, in most cases, the model can predict a high-risk scenario with high certainty in time to warn the driver, allowing a potential collision to be avoided.

Cite this Paper

BibTeX
@InProceedings{pmlr-v343-talluri26a, title = {Predicting the Risk of Vehicle–Cyclist Crashes in Urban Intersections Using {Bayesian} Networks}, author = {Talluri, Kranthi Kumar and Madsen, Anders L and Weidl, Galia and Ahlstr{\"o}m, Christer and Olstam, Johan}, booktitle = {Proceedings of the 13th International Conference on Probabilistic Graphical Models}, pages = {850--863}, year = {2026}, editor = {Camps-Valls, Gustau and Leonelli, Manuele and Varando, Gherardo}, volume = {343}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v343/main/assets/talluri26a/talluri26a.pdf}, url = {https://proceedings.mlr.press/v343/talluri26a.html}, abstract = {The i4Driving European Union project aims to establish a credible and realistic human road safety baseline for virtual assessment of Connected, Cooperative, and Automated Mobility (CCAM) systems. As part of these efforts, multiple driving simulator experiments have been conducted to collect data to verify the developed human driver models. This paper focuses on the analysis of data from two urban road experiments in the same scenario involving a vehicle and a bicycle. The paper describes the development of a knowledge-driven Bayesian network (BN) to predict the risk of a right-turn maneuver involving a bicycle traveling straight through a four-way urban traffic intersection. The paper also reports on the results of an experimental analysis on data from the two urban road experiments, each involving several hundred driving sequences with a population of different human drivers. The predictive accuracy of the knowledge-driven model is high with a significant prediction horizon. That is, in most cases, the model can predict a high-risk scenario with high certainty in time to warn the driver, allowing a potential collision to be avoided.} }
Endnote
%0 Conference Paper %T Predicting the Risk of Vehicle–Cyclist Crashes in Urban Intersections Using Bayesian Networks %A Kranthi Kumar Talluri %A Anders L Madsen %A Galia Weidl %A Christer Ahlström %A Johan Olstam %B Proceedings of the 13th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2026 %E Gustau Camps-Valls %E Manuele Leonelli %E Gherardo Varando %F pmlr-v343-talluri26a %I PMLR %P 850--863 %U https://proceedings.mlr.press/v343/talluri26a.html %V 343 %X The i4Driving European Union project aims to establish a credible and realistic human road safety baseline for virtual assessment of Connected, Cooperative, and Automated Mobility (CCAM) systems. As part of these efforts, multiple driving simulator experiments have been conducted to collect data to verify the developed human driver models. This paper focuses on the analysis of data from two urban road experiments in the same scenario involving a vehicle and a bicycle. The paper describes the development of a knowledge-driven Bayesian network (BN) to predict the risk of a right-turn maneuver involving a bicycle traveling straight through a four-way urban traffic intersection. The paper also reports on the results of an experimental analysis on data from the two urban road experiments, each involving several hundred driving sequences with a population of different human drivers. The predictive accuracy of the knowledge-driven model is high with a significant prediction horizon. That is, in most cases, the model can predict a high-risk scenario with high certainty in time to warn the driver, allowing a potential collision to be avoided.
APA
Talluri, K.K., Madsen, A.L., Weidl, G., Ahlström, C. & Olstam, J.. (2026). Predicting the Risk of Vehicle–Cyclist Crashes in Urban Intersections Using Bayesian Networks. Proceedings of the 13th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 343:850-863 Available from https://proceedings.mlr.press/v343/talluri26a.html.

Related Material