Development of binocular vision guided mobility for autonomous vehicle

• Main Author: Lai, Tingfeng
• Other Authors: Xie Ming
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering
• Online Access: https://hdl.handle.net/10356/173435
• Institution: Nanyang Technological University

Unmanned Surface Vessels (USVs) or Autonomous Surface Vehicles (ASVs) are revolutionizing maritime activities. These self-operating boats use sensors like GPS, LiDAR, and cameras to move and make decisions on water without needing people. They're useful for a range of tasks, from military patrols to oceanographic explorations. The Maritime RobotX Challenge is an important international competition held every two years at the university level. It's designed to promote the development of autonomous maritime robots. Students from around the world participate, creating new technologies and building global partnerships between universities and the industry. In this competition, a key goal is to create innovative USVs that can perform various tasks. Our research focuses on the development of a binocular vision system tailored for RobotX tasks - obstacle avoidance, path following, and autonomous docking. The project began with a new principle toward achieving a robust matching solution which leverages on the use and integration of top down image sampling strategy, hybrid feature extraction, and Restricted Coulomb Energy (RCE) neural network for cognition as well as recognition, finally utilizing stereo matching to derive three-dimensional coordinates. A preliminary version of the proposed solution has been implemented and tested with data from Maritime RobotX Challenge. Also, a Graphical User Interface (GUI) was designed to present and direct visualization platform for researchers and operators.