Adaptive Tutoring on a Virtual Reality Driving Simulator
S. Ropelato, F. Zünd, S. Magnenat, M. Menozzi, B. Sumner
1st Workshop on Artificial Intelligence Meets Virtual and Augmented Realities (AI-VR) in conjuction with SIGGRAPH Asia 2017
Paper Abstract
We propose a system for a Virtual Reality (VR) driving simulator including an Intelligent Tutoring System (ITS) to train the user's driving skills. The VR driving simulator comprises a detailed model of a city, Artificial Intelligence (AI) traffic, and a physical driving engine, interacting with the driver. In a physical mockup of a car cockpit, the driver operates the vehicle through the virtual environment by controlling a steering wheel, pedals, and a gear lever. Using a Head-Mounted Display (HMD), the driver observes the scene from within the car. The realism of the simulation is enhanced by a 6 Degrees of Freedom (DOF) motion platform, capable of simulating forces experienced when accelerating, braking, or turning the car. Based on a pre-defined list of driving-related activities, the ITS permanently assesses the quality of driving during the simulation and suggests an optimal path through the city to the driver in order to improve the driving skills. A user study revealed that most drivers experience presence in the virtual world and are proficient in operating the car.