Connected and Automated Vehicles (CAVs) represent a crucial step forward in the evolution of Intelligent Transport Systems (ITS), supporting enhanced communication, coordination, and decision-making among vehicles, infrastructure, and road users. Vehicle-to-everything (V2X) communication enables information sharing between road users and could be employed in various intelligent transportation scenarios. In particular, maneuver coordination is a fundamental aspect of cooperative driving and remains a key challenge for autonomous vehicles, as it requires consistent shared understanding and synchronized decision-making among multiple agents. This paper introduces an AI-assisted lane change maneuver coordination solution that integrates a maneuver coordination algorithm and an AI model. The AI model is designed to identify and restrict coordinations triggered by the algorithm that are predicted to fail. We demonstrate that integrating AI into maneuver coordination algorithms increases the coordination success rate regardless of traffic conditions and the accuracy of the trajectory predictions exchanged during coordination.
AI-Assisted Maneuver Coordination for Connected and Automated Vehicles / Gasco, D., Sepulcre, M., Molina-Masegosa, R., Casetti, C., Gozalvez, J.. - ELETTRONICO. - (2026), pp. 1-7. (Vehicular Technology Conference (VTC) Nice (FRA) 9-12 June 2026) [10.1109/VTC2026-Spring68026.2026.11756839].
AI-Assisted Maneuver Coordination for Connected and Automated Vehicles
Gasco, Diego;Casetti, Claudio;
2026
Abstract
Connected and Automated Vehicles (CAVs) represent a crucial step forward in the evolution of Intelligent Transport Systems (ITS), supporting enhanced communication, coordination, and decision-making among vehicles, infrastructure, and road users. Vehicle-to-everything (V2X) communication enables information sharing between road users and could be employed in various intelligent transportation scenarios. In particular, maneuver coordination is a fundamental aspect of cooperative driving and remains a key challenge for autonomous vehicles, as it requires consistent shared understanding and synchronized decision-making among multiple agents. This paper introduces an AI-assisted lane change maneuver coordination solution that integrates a maneuver coordination algorithm and an AI model. The AI model is designed to identify and restrict coordinations triggered by the algorithm that are predicted to fail. We demonstrate that integrating AI into maneuver coordination algorithms increases the coordination success rate regardless of traffic conditions and the accuracy of the trajectory predictions exchanged during coordination.| File | Dimensione | Formato | |
|---|---|---|---|
|
ManeuverCoordination.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
1.62 MB
Formato
Adobe PDF
|
1.62 MB | Adobe PDF | Visualizza/Apri |
|
AI-Assisted_Maneuver_Coordination_for_Connected_and_Automated_Vehicles.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
2.35 MB
Formato
Adobe PDF
|
2.35 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/3008889
