A Decision Support Framework for Collision Avoidance of Unmanned Maritime Vehicles - Intelligent Computing for Sustainable Energy and Environment - page 549

A Decision Support Framework for Collision Avoidance
of Unmanned Maritime Vehicles
Mamun Abu-Tair and Wasif Naeem ∗
The Energy and Intelligent Control Cluster
School of Electronics, Electrical Engineering and Computer Science, Queen's University
Belfast, Belfast, UK.
{m.abu-tair,w.naeem}@ qub.ac.uk
Abstract. Recently there has been considerable interest in the development of
Unmanned Surface Vehicles (USVs) due to the increasing demand in a number
of maritime applications. One of the main challenges for unmanned (and even
manned) vessels is detecting and avoiding the (static and dynamic) obstacles
that may appear during a mission. This paper presents a practical solution for
obstacle detection and avoidance mainly for USVs. More importantly, an
integrated decision support framework is proposed which provides risk
assessment as an integrated feature to the path planner. The hardware platform
consists of a high definition video camera and a laser range sensor mounted on
a pan and tilt device to detect obstacles in the vicinity of the ship. The
performance of the proposed system is extensively investigated in a number of
virtual maritime environment scenarios. The results reveal that the proposed
system is able to detect multiple dynamic obstacles. Additionally, the proposed
system provides a real-time visual interface (similar to radar screen) for the
captain which includes recommended actions to avoid the obstacles in
accordance with marine rules of the road.
1 Introduction
Unmanned surface vehicles (USVs) are routinely being deployed in applications such
as remote sensing, surveillance, coast patrolling and providing navigation and
communication support to unmanned underwater vehicles (UUVs). In many
instances, they are remotely operated to perform a specific mission in open or
confined waters. The intelligence of these vehicles primarily resides in the navigation,
guidance and control (NGC) systems design. Ideally, the vehicle needs to operate
without any human intervention. This means that the vessel's on-board control system
must be self-reliant and able to maintain and supervise each on-board component.
Having said that, even with the most advanced NGC design the craft cannot be fully
autonomous without the presence of an obstacle detection and avoidance (ODA)
system [3]. Studies have shown that, in manned vessels, more than 60% of casualties