We look at platooning applications that leverage two wireless technologies for the coordination of vehicle movements. The first technology is DSRC (dedicated short-range communications), based on IEEE 802.11p, which allows a distributed implementation of the platoon coordination. The second technology is 5G (and beyond). In the latter case, the platoon control algorithm is centralized in an edge computing facility close to the platoon (or in the cloud, if latency allows). Trying to maximize platoon performance and overcome the unpredictability of the radio channel, both radio access technologies are simultaneously active, and a deep neural network (DNN) is used to decide which of the two should be relied on for platoon control, at each point in time. The proposed platooning architecture is compared against previously proposed alternatives, investigating performance with detailed simulation tools. Results show significant advantages in terms of accuracy and safety in inter-vehicle distance for all vehicles within the platoon.
DNN-Controlled Multi-Technology Platooning / C. Quadri, M. Dileo, V. Mancuso, M.A. Marsan (IEEE VEHICULAR NETWORKING CONFERENCE). - In: 2025 IEEE Vehicular Networking Conference (VNC)[s.l] : IEEE, 2025 Jun. - ISBN 979-8-3315-2437-1. - pp. 1-8 (( Intervento presentato al 16. convegno 16th IEEE Vehicular Networking Conference, VNC 2025 tenutosi a Porto nel 2025 [10.1109/vnc64509.2025.11054110].
DNN-Controlled Multi-Technology Platooning
C. Quadri
Primo
;M. DileoSecondo
;
2025
Abstract
We look at platooning applications that leverage two wireless technologies for the coordination of vehicle movements. The first technology is DSRC (dedicated short-range communications), based on IEEE 802.11p, which allows a distributed implementation of the platoon coordination. The second technology is 5G (and beyond). In the latter case, the platoon control algorithm is centralized in an edge computing facility close to the platoon (or in the cloud, if latency allows). Trying to maximize platoon performance and overcome the unpredictability of the radio channel, both radio access technologies are simultaneously active, and a deep neural network (DNN) is used to decide which of the two should be relied on for platoon control, at each point in time. The proposed platooning architecture is compared against previously proposed alternatives, investigating performance with detailed simulation tools. Results show significant advantages in terms of accuracy and safety in inter-vehicle distance for all vehicles within the platoon.| File | Dimensione | Formato | |
|---|---|---|---|
|
VNC_2025_preprint.pdf
accesso riservato
Tipologia:
Pre-print (manoscritto inviato all'editore)
Licenza:
Nessuna licenza
Dimensione
797.46 kB
Formato
Adobe PDF
|
797.46 kB | 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.




