Date on Master's Thesis/Doctoral Dissertation

8-2021

Document Type

Doctoral Dissertation

Degree Name

Ph. D.

Department

Industrial Engineering

Degree Program

Industrial Engineering, PhD

Committee Chair

Gue, Kevin

Committee Co-Chair (if applicable)

Usher, John

Committee Member

Gentili, Monica

Committee Member

Yampolskiy, Roman

Author's Keywords

high-density parking; autonomous vehicles; heuristic search; facility layout; reinforcement learning

Abstract

In a common parking lot, much of the space is devoted to lanes. Lanes must not be blocked for one simple reason: a blocked car might need to leave before the car that blocks it. However, the advent of autonomous vehicles gives us an opportunity to overcome this constraint, and to achieve a higher storage capacity of cars. Taking advantage of self-parking and intelligent communication systems of autonomous vehicles, we propose puzzle-based parking, a high-density design for a parking lot. We introduce a novel method of vehicle parking, which leads to maximum parking density. We then propose a heuristic method to solve larger problems, and mathematically prove that the method produces near-optimal results. To improve layout designs reducing vehicular movements, we propose a use of a meta-heuristic algorithm integrated with a deep reinforcement learning method. Finally, to take advantage of these puzzle-based designs in large-scale, we propose a modular layout design. This design process consists of two steps: i) design of a high-density modular lot, which we call sub-lot, and ii) integration of these sub-lots into a large parking lot. We have conducted a set of experiments to determine which sub-lot size provide the best performance in terms of density and retrieval time.

Share

COinS