Masters Thesis Defense for Andrew Hegman • 05/25/18 at 11:00 AM
May 8, 2018
Faculty and Students,
You are cordially invited to my thesis defense.
Title: A Real-time Predictive Vehicular Collision Avoidance System on an Embedded General-purpose GPU
When: Friday, May 25th at 11:00am
Where: Simrall Hall, Room 228 (Conference Room)
Candida te: Andrew Hegman
Degree: Masters, Electrical and Computer Engineering
Committee:
Dr. Jian Shi
(Major Professor )
Dr. James Fowler
(Committee Member)
Dr. Michael Mazzola
(Committee Member)
Abstract:
Collision avoidance is an essential capability for autonomous and assisted driving ground vehicles. In this work, we developed a novel model predictive control based intelligent collision avoidance algorithm for a multi-trailer industrial ground vehicle implemented using a General Purpose Graphical Processing Unit (GPGPU). The collision avoidance problem is formulated as a multi-objective optimal control problem and solved using a limited look-ahead control scheme in real-time. Compared with present-day collision
avoidance technology, the controller-in- the-loop- simulation and experimental results obtained in this work have demonstrated that the proposed algorithm, paired with massive parallel computational capacities provided by an NVIDIA Jetson TX2 development board, is capable of dynamically assisting drivers and maintaining the vehicle a safe distance from the detected obstacles on-the- fly. We have shown that the prototype of the proposed collision avoidance system is capable of responding to objects of varying size entering the field of view suddenly at varying angles of attack when the vehicle is operated at maximum speed.