SearcharxivSearch

arXiv subjects

Marco Franceschini

Publications and source records attributed to Marco Franceschini.

2 recordsLinked to original sources

Heterogeneous CACC Coexistence: Simulation, Analysis, and Modeling

The design of Cooperative Adaptive Cruise Control (CACC) algorithms for vehicle platooning has been extensively investigated, leading to a wide range of approaches with different requirements and performance. Most existing studies evaluate these algorithms under the assumption of homogeneous platoons, i.e., when all platoon members adopt the same CACC. However, market competition is likely to result in vehicles from different manufacturers implementing distinct CACCs. This raises fundamental questions about whether heterogeneous vehicles can safely cooperate within a platoon and what performance can be achieved. To date, these questions have received little attention, as heterogeneous platoons are difficult to model and analyze. In this work, we introduce the concept of mixed platoons, i.e., platoons made of vehicles running heterogeneous CACCs, and we study their performance through simulation-based experiments. We consider mixtures of three well-established CACCs from the literature. In the first part of the paper, we study a single mixed platoon in isolation to understand the microscopic effects on safety: we evaluate the performance of various CACC-mixtures across speed change and emergency braking scenarios. In the second part, we examine a high-density ring-road scenario to assess macroscopic impacts on safety, comfort, and traffic throughput, especially comparing throughput results with those obtained from vehicles controlled by a standard Adaptive Cruise Control (ACC) or by human drivers. Our findings highlight that some combinations of CACCs can operate robustly and safely, while others exhibit critical limitations in safety, comfort, or efficiency. These results emphasize the need for careful system design and the development of theoretical frameworks for modeling heterogeneous platoons.

eess.SY

A neural-network based anomaly detection system and a safety protocol to protect vehicular network

This thesis addresses the use of Cooperative Intelligent Transport Systems (CITS) to improve road safety and efficiency by enabling vehicle-to-vehicle communication, highlighting the importance of secure and accurate data exchange. To ensure safety, the thesis proposes a Machine Learning-based Misbehavior Detection System (MDS) using Long Short-Term Memory (LSTM) networks to detect and mitigate incorrect or misleading messages within vehicular networks. Trained offline on the VeReMi dataset, the detection model is tested in real-time within a platooning scenario, demonstrating that it can prevent nearly all accidents caused by misbehavior by triggering a defense protocol that dissolves the platoon if anomalies are detected. The results show that while the system can accurately detect general misbehavior, it struggles to label specific types due to varying traffic conditions, implying the difficulty of creating a universally adaptive protocol. However, the thesis suggests that with more data and further refinement, this MDS could be implemented in real-world CITS, enhancing driving safety by mitigating risks from misbehavior in cooperative driving networks.

cs.LG