Cookies help us deliver the best experience on our website. By using our website, you agree to our use of cookies Dismiss

Singapore research group to create vessel traffic predictive technologies

Singapore research group to create vessel traffic predictive technologies Zairon, CC4.0

Fujitsu, Singapore Management University (SMU), and A*STAR’s Institute of High Performance Computing (IHPC) have announced a collaboration agreement to develop new technologies for vessel traffic management at the Port of Singapore, with the support of the Maritime and Port Authority of Singapore (MPA).

{mprestriction ids="1,2"}The partners aim to leverage artificial intelligence (AI) and Big Data analytics to create predictive technologies to optimise the management of Singapore’s port and surrounding waters. The systems will also be validated using real-world data to improve the forecasting of congestion and identification of potential collisions and other risks before they occur at sea.

Research and development is being conducted under the guidance of Singapore’s Urban Computing and Engineering Centre of Excellence (UCE CoE), a public-private partnership consisting of the Agency for Science, Technology and Research (A*STAR), SMU, and Fujitsu, which was established in 2014.

The outcomes of this research and development phase will be combined with data gained through project trials and integrated into Fujitsu’s future maritime systems.

A range of technologies are being developed under the collaboration agreement between Fujitsu, IHPC and SMU to improve the management of maritime vessel traffic, including short-term and long-term prediction models.

The short-term trajectory prediction model predicts the trajectory of a vessel using machine learning and motion physics, while the long-term traffic model can forecast the traffic situation based on the traffic patterns of a large number of vessel types, derived from historical data.

A risk calculation model that can reliably quantify the near-miss risk of a pair of vessels, by integrating various risk models (an ‘ensemble risk model’), will also be developed, alongside a hotspot model that dynamically reveals changing risk hotspots through spatio-temporal data analysis.

Other focus areas include a spatial coordination model that re-routes vessels to avoid near-miss and collision incidents, and a temporal coordination model that coordinates the passage timing of vessels to reduce congestion. Both of these models will support real-time decision-making to mitigate predicted risks while minimising disruption for vessels.

The new technologies will eventually be integrated and test-bedded to assess their potential to enhance navigational safety, with MPA to provide data and information for further research and development and test-bedding of technologies developed by UCE CoE for application in Singapore waters.

“Multi-agent technology has been used extensively in coordinating the movements of unmanned aerial vehicles and unmanned ground vehicles,” said Professor Lau Hoong Chuin, SMU’s lab director and lead investigator of the UCE CoE.

“In this project with MPA, SMU is breaking new ground in research by proposing a next generation maritime traffic coordination technology that is akin to air traffic control, yet respecting major differences and constraints between air and sea navigation.”

“With the advent of autonomous ships, this technology can potentially disrupt vessel traffic management to reduce human errors and improve navigational safety.”{/mprestriction}

Related items

Joomla SEF URLs by Artio

Login/Register

Register or Login to view even more of our content. Basic registration is free.

Register now

Digital Ship magazine provides the latest information about maritime satellite communications technology, software systems, navigation technology, computer networks, data management and TMSA. It is published ten times a year.

 

Address:
Digital Ship Ltd
Digital Ship - Digital Energy Journal
39-41 North Road
London
N7 9DP
United Kingdom

Copyright © 2020 Digital Ship Ltd. All rights reserved           Cookie Policy         Privacy Policy