Ionic’s tankers and bulkers navigate some of the world’s most congested and restricted waterways—from the South China Sea to the English Channel—where heavy traffic, non-AIS fishing vessels, and low visibility demand constant vigilance. Traditional navigation tools struggled to maintain the situational awareness needed to balance safety, COLREG compliance, and fuel efficiency under tight schedules. By deploying an AI-assisted visual cross-check on the bridge and giving shore teams real-time analytics, Ionic strengthened hazard detection, reduced close encounters by 22% in the North Sea, and increased minimum passing distances by 20%. The system also delivered a 3% fleet-wide fuel saving, scaled across 19 vessels and over 160,000 nautical miles, proving that smarter awareness drives safer, steadier, and more efficient voyages.
Case Study Source: Orca AI
Problem Statement
Ionic’s vessels operate in some of the world’s busiest and most restricted sea lanes, often with low visibility and many non‑AIS targets. Traditional navigation tools alone were no longer enough to keep risk consistently low while maintaining steady tracks and fuel efficiency.
Goal
Strengthen situational awareness on the bridge and give shore teams clear visibility of real‑world navigational behaviour to spot developing risks sooner, support COLREG‑compliant decisions, and run safer, steadier, and more efficient voyages across tanker and bulker fleets.
Challenges
High traffic density and numerous non‑AIS fishing vessels in areas such as the South China Sea and the Sea of Marmara increased collision risk.
Restricted waterways and traffic separation schemes (e.g., the English Channel and Panama Canal), combined with fog, rain, and night operations, made hazard detection harder and demanded precise COLREG adherence.
Tight schedules for tankers and bulkers meant even small course deviations could hurt fuel efficiency and voyage performance.
Actions
Implemented an AI‑assisted visual cross‑check on the bridge to detect AIS and non‑AIS targets, maintain awareness in low visibility and heavy traffic, track encounter development, and validate decisions when electronic data was limited.
Equipped shore teams with a visibility and analytics platform to monitor live bridge video, receive critical alerts, review close‑encounter events even without incidents, and compare navigational behaviour across routes and regions.
Positioned the system as a complement to radar, ECDIS, and human lookouts; officers were encouraged to explore it without obligation, enabling organic integration into normal bridge routines.
Used thermal camera views at night and in open waters to make small craft—especially fishing vessels—easier to identify.
Key Results
Impact
Earlier hazard recognition and steadier tracks reduced reactive manoeuvres, lifting safety margins across tanker and bulker fleets.
More predictable voyage execution and improved efficiency supported schedule adherence and cost control, including a documented 3% fuel saving.
Bridge teams experienced lower cognitive strain in demanding watches, while shoreside visibility enabled fleet‑wide learning and continuous improvement.
The Challenge
Ionic’s tankers and bulkers navigate some of the most congested shipping routes on the planet. Crowded lanes, fishing boats without AIS transponders, and narrow passages like the English Channel and Panama Canal create a perfect storm of hazard. Add fog, rain, and darkness, and the risk of collision climbs quickly. Traditional radar and chart systems couldn’t always fill the gaps, and even minor detours to avoid trouble hit fuel budgets and schedules hard.
The company needed a smarter way to see what was really happening around their vessels—and to help shore teams understand how crews respond under pressure.
What They Did
Ionic installed an AI-powered visual monitoring system on the bridge. It works alongside existing radar and ECDIS displays, flagging both tracked and untracked vessels in real time. Officers can cross-check what they see through the window with what the cameras detect, especially useful when electronic data is patchy or absent.
Thermal cameras improved night-time detection of small craft—fishing vessels in particular—that might otherwise vanish into the darkness. The system doesn’t replace the human watch; it supports it. Crews were free to explore the tool at their own pace, which encouraged genuine buy-in rather than reluctant compliance.
Onshore, the operations team gained live video feeds and automated alerts. They could review near-miss events even when nothing went wrong, compare how different ships handled similar situations, and identify patterns across routes. That shift from reactive incident reports to proactive learning proved surprisingly powerful.
The Results
Close calls dropped by 22% in the North Sea, one of the busiest testing grounds. Ships began passing other vessels with 20% more clearance, a measurable increase in safety margin. Smoother navigation translated into 3% less fuel burned across the fleet—a meaningful saving at scale.
The rollout covered 19 vessels, which logged more than 160,000 nautical miles and captured over 2,000 navigational events for analysis. That dataset now feeds continuous improvement efforts fleet-wide.
Why It Worked
Early hazard detection meant fewer last-minute course changes. Crews held steadier tracks, which kept fuel consumption down and eased the mental load during long watches. Officers report feeling more confident in low-visibility conditions, knowing the AI acts as an extra set of eyes.
For shore teams, the ability to watch bridge operations in real time—and review them afterwards—unlocked a new level of insight. They can spot training needs, celebrate good decisions, and share lessons learned without waiting for something to go wrong.
The system succeeded because it complemented existing skills and tools rather than attempting to replace them. Crews adopted it organically, and the measurable gains in safety and efficiency speak for themselves.
Case Study Source: Orca AI
These industry AI case studies featured on our site are based on publicly available sources and are presented for informational and educational purposes only; we do not claim ownership of these case studies or affiliation with the companies mentioned, and attribution is provided where applicable.