Digital twin places workers and straddle carriers on a single map at BNCT

Oct 6, Seoul - CyberLogitec has deployed an AI-based collision prevention system at Busan New Container Terminal (“BNCT”), operator of Terminal 5 at Busan New Port, that detects workers without wearable tags and alerts straddle carrier drivers when a worker is close by in the same working lane.

The deployment comes as the industry focuses on vehicle–pedestrian safety. ICHCA International ranks pedestrians run over by vehicles, particularly by handling equipment, as a close second among the causes of cargo-handling fatalities, and in August 2026 PEMA, TT Club and ICHCA International jointly called for stronger collision-prevention measures across terminals.

At the core of the system is CyberLogitec’s digital twin-based real-time port monitoring platform, which places people and equipment on a single coordinate system. AI cameras on the STS cranes detect workers, and a patent-pending vision-to-geolocation technique, developed jointly by CyberLogitec and GlobeAI, converts each detection into real-world coordinates. These are combined with RTK positions from straddle carriers, so the distance between any worker and any machine can be calculated in real time. The system locates people without identifying them.

To avoid nuisance alarms, the system applies lane-aware logic, evaluating distance only when a carrier and a worker share the same working lane. Alerts are tiered at 15, 10 and 5 metres and shown to drivers as directional bars on the in-cab display. In field validation, equipment positioning was accurate to under 3 centimetres and worker localisation to under 20 centimetres.

“Under an STS crane, a colleague working safely in the next lane is often only a few metres away,” said Dr Junhee Cho, Digital Team Leader at CyberLogitec, who led development. “If alarms sound all shift for no reason, drivers switch the system off. The measure of a safety system is not how much it catches, but whether people keep trusting it.”

Worker detection uses GlobeAI’s deep-learning vision, trained on port imagery to perform in clutter, low light, fog and rain. Equipment positioning uses LG Uplus’s RTK network, which draws on more than 200 reference stations across Korea to overcome signal interference from steel container stacks. RTK receivers are fitted to around 70 mobile units, and 28 AI cameras are installed on 14 STS cranes.

In the control room, a 3D Virtual Terminal allows operators to monitor the site, replay past events to investigate near-misses and maintain an auditable alert history. The platform is integrated with the OPUS Terminal operating system and can be extended to terminal tractors and other mobile equipment.

“The hard part was locating a worker who carries no device, against the same reference as a machine moving with centimetre precision,” said Hans Moh, Senior Vice President and Head of CyberLogitec’s Port Solution Group. “How many boxes a terminal moves in a day matters less than whether everyone goes home safely.”

“Safety is never open to compromise and remains our highest priority,” said Chris Choi, CEO and Representative Director of BNCT. “Through our collaboration with CyberLogitec, we have further strengthened our prevention-focused approach to safety management. We will continue to proactively manage operational risks and provide a safer working environment for everyone working at the terminal.”

CyberLogitec plans to extend the solution to other ports in Korea and overseas.