AI in Transportation

The rapid advancements in artificial intelligence (AI) have revolutionized the transportation industry, with AI technologies harnessed to improve safety, efficiency and sustainability in transport systems worldwide. AI in Transportation at A*STAR aims to optimise land, sea and air transport related to traffic management, operations, infrastructure utilization, predictive maintenance and sustainability.

Digitalization and the implementation of increasingly complex sensor technologies in our traffic and vehicle systems have resulted in large datasets and real-time data streams for enhancing the monitoring and management of traffic, shipping and operations. Together with public agency, industry and university partners, research teams at A*STAR are building advanced AI capabilities based on domain specific insights, and developing solutions to target highly challenging and impactful problems related to transportation. With the ability to process vast amounts of data, learn from patterns, and make real-time responses, our transport-based AI is propelling local and international transportation into a new era of innovation and connectivity, promising a future mobility that is smarter, safer, and more sustainable.


Key Researchers

Dr Jaya Shankar, Institute for Infocomm Research (I2R)
Dr Qin Zheng, Institute of High Performance Computing (IHPC)
Dr Savitha Ramasamy, Institute for Infocomm Research (I2R)
Dr Fu Xiuju, Institute of High Performance Computing (IHPC)

Key Projects

CRUISE - Cooperative Unified Smart Traffic System

CRUISE is a collaborative project between A*STAR’s Institute for Infocomm Research (I2R) and Land Transport Authority (LTA) which aims to develop and deploy a locally owned, AI-based solution that would leverage on the feature rich vehicle-to-everything (V2X) data. Unlike existing traffic control systems, CRUISE uses a data-driven approach to optimize traffic flow based on real time demand and incorporates many intelligent features that contribute to energy savings and sustainability, such as automatic incident detection and management, fast and accurate traffic prediction coupled with route guidance, and priority movements for public transport, high pedestrian volumes or high vehicle demands. Besides LTA, CRUISE also includes multiple industry partners (More information).

Maritime AI

The Centre for Maritime Digitalisation (C4MD), led by A*STAR’s Institute for High Performance Computing (IHPC), aims to develop advanced digital solutions for smart shipping, port systems and decarbonisation. The new centre aims to increase sustainability, safety and efficiency in Singapore’s maritime ecosystem, by translating research capabilities in computational modelling, simulation and artificial intelligence (AI) into deployable maritime solutions.

The centre at A*STAR will partner Institutes of Higher Learning (IHLs), industry partners and public sector agencies on collaborative research in areas like modelling electrification of harbour crafts, developing sustainable technologies, conducting risk assessments using Computational Fluid Dynamics (CFD), detecting near-collision events of ships, and improving efficiency using predictive maintenance, emissions monitoring, and supply chain intelligence.

C4MD is supported through a S$4.78 million of funding awarded by the Singapore Maritime Institute (SMI) to IHPC to lead the Maritime AI Research Programme – as announced on MPA’s website. More information can be found here.

Air traffic management

This project is done in collaboration with Civil Aviation Authority of Singapore (CAAS) and aims to develop the next generation air traffic management systems for Singapore. The research team will develop a set of optimization tools to enable future schemes such as trajectory-based operations that will improve gate-to-gate efficiency and improve airport capacity.

The project goals are related to addressing current operational gaps and exploration of R&D areas that would help boost air traffic operation and management. The team is currently collaborating with CAAS and industry partners to study and develop AI related tools related to airspace and runway capacity estimation, trajectory optimisation, understanding the impact of convective weather on flight routes, automatic transcription of air-ground voice communications, and development of aerodrome twin for optimization of aircraft surface movement and airside operations.

AI for Airline Operations

Under a joint lab between Singapore Airlines (SIA), SIA Engineering Company (SIAEC) and A*STAR, the research team aims to develop advanced AI solutions that improve engineering productivity, customer experience and cost-effectiveness of airline operations through predictive analytics and optimisation. Powered by data harnessed from state-of-the-art deep learning techniques, the innovative predictive analytics technology reduces the risks of flight delays by detecting recurring defects and predicting component failures in aircrafts. It also enhances SIA’s customer experience with personalised shopping recommendations generated from customer behaviour analytics, and detects anomalies in their loyalty programme transactions through fraud analytics.

In addition, text analysis applied to manuals and guidelines for information extraction and building comprehensive knowledge bases allows for better Q&A systems and responses to customers’ queries. Additionally, A*STAR’s optimisation technology helps SIA and SIAEC improve their operational efficiency. This is made possible through the optimisation of maintenance interval, workflow sequence, manpower and resource allocation.

The joint lab is also covered on this Asian Aviation online article.


The project uses IHPC’s AI technology for behaviour understanding from videos to assess trainees’ soft competencies (e.g., situational awareness, teamwork, effective communication) at the Centre of Excellence for Maritime Safety (CEMS) at Singapore Polytechnic. A system was developed to automatically extract features from videos to make assessments more objective, quicker, and address issues of expertise retention among instructors in simulator training.