Date of Award
12-2017
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
School of Computing
Committee Member
Dr. Andrew Robb, Committee Chair
Committee Member
Dr. Sabarish V. Babu, Committee Co-Chair
Committee Member
Dr. James Martin
Committee Member
Dr. Pierluigi Pisu
Abstract
Validation of Autonomous Vehicle behavior algorithms requires thorough testing against a wide range of test scenarios. It is not financially and practically feasible to conduct these tests entirely in a real world setting. We discuss the design and implementation of a VR based simulation testbed that allows such testing to be conducted virtually, linking a computer-generated environment to the system running the autonomous vehicle's decision making algorithms and operating in real-time. We illustrate the system by further discussing the design and implementation of an application that builds upon the VR simulation testbed to visually evaluate the performance of an Advance Driver Assist System (ADAS), namely Cooperative Adaptive Cruise Control (CACC) controller against an actor using vehicular navigation data from real traffic within a virtual 3D environment of Clemson University's campus. With this application, our goal is to enable the user to achieve spatial awareness and immersion of physically being inside a test car within a realistic traffic scenario in a safe, inexpensive and repeatable manner in Virtual Reality. Finally, we evaluate the performance of our simulator application and conduct a user study to assess its usability.
Recommended Citation
Rastogi, Vibhor, "Virtual Reality Based Simulation Testbed for Evaluation of Autonomous Vehicle Behavior Algorithms" (2017). All Theses. 2773.
https://tigerprints.clemson.edu/all_theses/2773