2018/02/26 by Hadi Kazemi, Kazemi, Hadi, Hossein Nourkhiz Mahjoub +5
Engineering · #Autonomous Vehicle Technology and Safety #FOS: Electrical engineering #Systems and Control (eess.SY) #Traffic control and management #Vehicular Ad Hoc Networks (VANETs) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1802.09356
openalex publication_date 2018/02/26 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28
Vehicle to Vehicle (V2V) communication has a great potential to improve\nreaction accuracy of different driver assistance systems in critical driving\nsituations. Cooperative Adaptive Cruise Control (CACC), which is an automated\napplication, provides drivers with extra benefits such as traffic throughput\nmaximization and collision avoidance. CACC systems must be designed in a way\nthat are sufficiently robust against all special maneuvers such as cutting-into\nthe CACC platoons by interfering vehicles or hard braking by leading cars. To\naddress this problem, a Neural- Network (NN)-based cut-in detection and\ntrajectory prediction scheme is proposed in the first part of this paper. Next,\na probabilistic framework is developed in which the cut-in probability is\ncalculated based on the output of the mentioned cut-in prediction block.\nFinally, a specific Stochastic Model Predictive Controller (SMPC) is designed\nwhich incorporates this cut-in probability to enhance its reaction against the\ndetected dangerous cut-in maneuver. The overall system is implemented and its\nperformance is evaluated using realistic driving scenarios from Safety Pilot\nModel Deployment (SPMD).\n