| Summary: | 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.
|
|---|