Please use this identifier to cite or link to this item:
Authors: DU XINXIN
Keywords: autonomous vehicle, image processing, MPC
Issue Date: 5-Jul-2016
Citation: DU XINXIN (2016-07-05). TOWARDS SUSTAINABLE AUTONOMOUS VEHICLES. ScholarBank@NUS Repository.
Abstract: This thesis proposes a minimum viable vision-based autonomous vehicle (AV) platform, which is hybridized with remote human intervention to achieve a more sustainable AV solution with fine balance in cost, safety and efficiency. The minimum viable solution consists of a vision-based lane-level localization system, a path following control system based on nonlinear model predictive control (NMPC) scheme and a vision-based fully autonomous parking system. The localization system uses stereovision to detect and track the lane lines and estimates the vehicle position and orientation respected to the lines. This information is then passed to the NMPC scheme. It controls the vehicle velocity and steering simultaneously to follow the detected lane lines. The parking system uses a mono camera to detect the parking slots and a sliding mode controller is designed to control the vehicle to park into the slot. All these systems, working together, formulate the minimum viable AV solution.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
DuXX.pdf22.38 MBAdobe PDF



Page view(s)

checked on Nov 8, 2019


checked on Nov 8, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.