CGA Simulation, a Liverpool-based SME that specialises in digital twins for Smart City applications, is set to carry out a 3-year Innovate UK-funded ‘Virtual Cities and Autonomous Learning’ project with South Korean artificial intelligence (AI) company Pintel Co. Ltd.
The £1 million international industrial research project has obtained funding from Innovate UK in partnership with the Korea Institute for Advancement of Technology (KIAT) in a bid to develop innovative future technologies with South Korea.
David Campbell-Molloy, Asia Partnership Manager at Innovate UK said, “We are delighted to support this highly innovative project. South Korea is a priority market for Innovate UK for co-innovation collaboration and it is great to see business partnerships such as this one being developed. We wish the project every success and look forward to seeing its benefits and outcomes in years to come.”
CGA’s focus is simulating transport systems based on real-world data from sensors and then making predictions, or synthesising data, for real-world adjustments to the technology that increasingly runs our cities. Virtual Cities and Autonomous Learning (ViCAL) will explore to what extent simulated environments can be used to train deep learning AI designed around capturing video and using that data to detect road traffic accidents.
ViCAL is a collaboration between UK consortium CGA Simulation and Future Coders and South Korean Machine Learning Technology company Pintel. This real-time traffic optimising system will be used in Seoul to combat congestion and improve accident detection performance. Smart Mobility Living Lab London will work with CGA, supplying an analogous UK location to test the technology developed for Seoul.
ViCAL integrates simulated data for training the deep learning models behind AI that analyses video and other sensor data from traffic control systems. Korean-based company, Pintel, has an existing product called Precise Video Analytics Experience (PreVAX), already in use in Korea. PreVAX is an intelligent traffic system that collects real-time data by applying an artificial intelligence-based algorithm to video from traffic control systems.
CGA’s work will provide the technology to help build a smart network of cameras that monitor traffic throughout journeys to measure elements like speed, journey time, and pollution to train smart cities. This will combat congestion, decrease accidents, and improve response time to issues that arise in road traffic networks. CGA’s existing work on digital twin systems such as ALEAD, a simulation platform, has been previously optimised for training Connected and Autonomous Vehicles (CAVs), planning installation of 5G infrastructure and transport infrastructure planning.
Max Zadow, CEO of Future Coders, added “CGA Simulation are doing some of the most innovative work in Digital Twins for Connected and Autonomous Mobility in the UK and we are excited about being part of a project that combines this with Pintel’s disruptive use of AI for Smart Cities in South Korea.”