Skip to main navigationSkip to main content
The University of Southampton
Southampton Marine and Maritime Institute

An Automatic COLREGs-Compliant Obstacle Detection and Avoidance System for Unmanned Surface Vehicles Seminar

Time:
12:00
Date:
28 March 2013
Venue:
Southampton University, Highfield Campus, Building 28, Room 2001. Refreshments will be available.

For more information regarding this seminar, please telephone Dr. Yeping Xiong on +44 (0)23 80596619 or email Y.Xiong@soton.ac.uk .

Event details

With the increasing demand on deploying Unmanned surface vehicles (USVs) in maritime applications such as remote sensing, surveillance, coast patrolling and providing navigation and communication support to unmanned underwater vehicles (UUVs), the provisioning of obstacle detection and avoidance system has become a critical issue of the future USVs. Therefore a reliable obstacle detection and avoidance (ODA) system for USVs is necessarily needed to improve their autonomy, efficiency and safety. A practical ODA solution is thus presented 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 detection system employs a high definition video camera and a laser sensor mounted on a pan and tilt platform to provide the navigation, guidance and control (NGC) system of a USV with a visual reference of the surrounding area. The obstacle detection subsystem employs a modified form of the well-known background subtraction technique to extract the information regarding any obstacles in the vicinity.
The proposed online path planning method is a Rule-based Repairing A* (R-RA*) algorithm, an online version of the standard A* algorithm which generates and repairs new sub-paths quickly and efficiently. The unique rule-based feature permits the implementation of collision regulations (COLREGs) or marine ‘rules of the road’ for every encounter. The applicable COLREGs rule such as head-on, overtaking etc. is determined by the decision-maker which is based on the relative closest point of approach angle. The R-RA* method yields smooth paths through post-processing using -Splines and Dubins, which customises paths to accommodate the unique dynamics of a given USV, thus producing a sequence of waypoints for the autopilot. The system successfully handles static obstacles and moving vessels, and has also been extended to deal with multiple dynamic vessels.

Speaker information

Dr. Wasif Naeem, Queens University Belfast - School of Electronics, Electrical Engineering and Computer Science.. Dr Wasif Naeem obtained his bachelor’s degree in Electrical Engineering from NED University of Engineering and Technology, Pakistan in 1998. He obtained his PhD in Mechanical and Marine Engineering from the University of Plymouth, UK. He joined the Energy, Power and Intelligent Control Research cluster (EPIC) within the School of Electronics, Electrical Engineering and Computer Science at Queen’s University Belfast in 2007. He is the author of approximately 50 peer-reviewed journal and conference papers and two IET book chapters. Two journal papers in the area of marine navigation and control were awarded the Michael Richey medal and the Denny Medal in 2008 and 2010, by the Royal Institute of Navigation (RIN) and Institution of Marine Engineering, Science and Technology (IMarEST) respectively.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×