Integrated GNSS/INU, vehicle dynamics, and microscopic traffic flow simulator for automotive safety

Abstract

This paper presents the development of a comprehensive integrated GNSS/INU simulator consisting of a microscopic traffic simulator based on VISSIM, a vehicle dynamics simulator based on CarSim, and a GNSS/INU simulator. The resulting GNSS/INU simulator provides an integrated design, test and evaluation platform for exploring new ideas, developing advanced concept designs and investigating the impact of existing and emerging Global Navigation Systems (GNSS) and Inertial Navigation Unit (INU) technologies on automotive safety at the vehicle and network levels. For the simulation of hazardous conditions VISSIM generates safety warning events based on surrogate safety indicators. The warning events are intercepted at the vehicle dynamics simulator CarSim which generates simulated `ground truth' trajectories based on VISSIM's generated control parameters. GNSS/INU errors are generated by a GNSS/INU simulator and added to the CarSim `ground truth' trajectories. The simulated GNSS/INU vehicle trajectories and the `ground truth' CarSim trajectories are processed through a “Driver-Vehicle Response” module for the estimation of individual vehicle crashes. These crashes are employed to train a Neural Network (NN) as a non-parametric network crash estimator. The trained NN and V2V/V2I simulators are employed to estimate the reduction of network crashes resulting from the use of GNSS/IMU sensors in the vehicles.