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

TL;DR

This paper introduces a learning-based stochastic MPC approach for cooperative adaptive cruise control that effectively detects and reacts to interfering vehicles, improving safety and traffic flow in critical scenarios.

Contribution

It presents a novel neural network-based cut-in detection and trajectory prediction scheme integrated into a probabilistic SMPC for robust CACC performance.

Findings

Enhanced reaction to interfering vehicles in simulations

Improved collision avoidance capabilities

Effective integration of NN-based prediction with SMPC

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 cut-in 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).