Leveraging RL for Efficient Collection of Perception Messages in Vehicular Networks

Chaima Zoghlami (1, 2, 3) , Rahim Kacimi (2, 3) , Riadh Dhaou (1, 4)

1 IRIT-RMESS - Réseaux, Mobiles, Embarqués, Sans fil, Satellites
2 IRIT-T2RS - Temps Réel dans les Réseaux et Systèmes
3 UT3 - Université Toulouse III - Paul Sabatier
4 Toulouse INP - Institut National Polytechnique (Toulouse)

Cooperative messages play a vital role in vehicle-toeverything (V2X) applications by enhancing situational awareness, supporting collision avoidance and improving traffic efficiency. Additionally, they contribute to Vulnerable Road Users (VRU) safety by increasing environment perception. The purpose of this paper is to introduce a novel Q-Learning technique that can improve the selection of cooperative messages' type, size and frequency. The methodology is based on leveraging the diversity of existing messages in vehicular networks to determine the best message type with the appropriate size while adjusting its transmission frequency according to the environmental context in order to efficiently manage network resources. In addition to alleviating the network overload and decreasing the number of messages sent simultaneously, our method could result in significant energy savings when applied to VRUs when they are identified by Connected and or Autonomous Vehicles (CAV).

Mots clés: V2X communications; Reinforcement Learning; VRU's safety; MEC

Domaines: Informatique [cs]

Chaima Zoghlami, Rahim Kacimi, Riadh Dhaou. Leveraging RL for Efficient Collection of Perception Messages in Vehicular Networks. Global Information Infrastructure and Networking Symposium (GIIS 2024), Feb 2024, Dubai, United Arab Emirates. à paraître. ⟨hal-04408979⟩