A Learning-Based Stochastic MPC Design for Cooperative Adaptive Cruise Control to Handle Interfering Vehicles

Abstract

Vehicle to Vehicle (V2V) communication has a great potential to improve reaction accuracy of different driver assistance systems in critical driving situations. Cooperative Adaptive Cruise Control (CACC), which is an automated application, provides drivers with extra benefits such as traffic throughput maximization and collision avoidance. CACC systems must be designed in a way that are sufficiently robust against all special maneuvers such as cutting-into the CACC platoons by interfering vehicles or hard braking by leading cars. To address this problem, a Neural-Network (NN)-based cut-in detection and trajectory prediction scheme is proposed in the first part of this paper. Next, a probabilistic framework is developed in which the cut-in probability is calculated based on the output of the mentioned cutin prediction block. Finally, a specific Stochastic Model Predictive Controller (SMPC) is designed which incorporates this cut-in probability to enhance its reaction against the detected dangerous cut-in maneuver. The overall system is implemented and its performance is evaluated using realistic driving scenarios from Safety Pilot Model Deployment (SPMD).

A Driver Behavior Modeling Structure Based on Non-Parametric Bayesian Stochastic Hybrid Architecture

“…‫݊݅ݐܴ݁ܿ݁‬ ‫݁ݐܴܽ‬ ‫‪ሻ‬ݖܪ(‬ ൌ 1 ‫ݐݏܽܿ݁ݎܨ(‬ ‫݊ݖ݅ݎܪ‬ (‫ݏ‬ሻ + 0.1ሻ (5) Therefore, by sweeping the forecast horizon from 100ms to 3s (or equivalently from 1 to 30 samples ahead), the reception rate sweeps from 5 Hz to almost 0.32 Hz.…”

“…The minimum required robust communication range is mainly forced by the application layer. More specifically, cooperative safety applications, such as Forward Collision Warning/Avoidance (FCW/A) [2]- [4], Cooperative Adaptive Cruise Control (CACC) [5], Lane-Keep-Assistance (LKA) [6], etc., which are supposed to employ the achieved situational awareness to make proper safety and efficiency decisions, play the main role to determine this range. According to technical documents from National Highway Traffic Safety Administration (NHTSA), 300m distance is considered as the minimum required range for a generic V2V communication standard, such as DSRC [7].…”

V2X System Architecture Utilizing Hybrid Gaussian Process-based Model Structures

“…In 1999, the Federal Communication Commission (FCC) allocated 75 MHz of spectrum at the 5.9 GHz frequency for the emerging field of Intelligent Transportation Systems (ITS). Different vehicular communication solutions such as Dedicated Short-Range Communication (DSRC) [1], [2], [3] and Cellular Vehicle-to-Everything (C-V2X) [4], [5] have been introduced and developed afterwards, aiming at facilitating the establishment of critical cooperative safety applications, e.g., Forward Collision Warning/Avoidance (FCW/A) [6], Cooperative Adaptive Cruise Control (CACC) [7], [8], and Intersection Management.…”

Time and Energy-Optimal Lane Change Maneuvers for Cooperating Connected and Automated Vehicles⋆

“…The emergence of CAVs brings up the opportunity for cooperation among vehicles traveling in both left and right lanes in carrying out an automated lane-change maneuver [9], [12], [13]. Such cooperation presents several advantages relative to the two-level architecture mentioned above.…”