Watch Now


Orca AI is helping ships navigate safely in congested waters

 Photo: Flickr/Transportation Safety Board of Canada
Photo: Flickr/Transportation Safety Board of Canada

The maritime industry has witnessed a steady rise in the number of near-port and in-port vessel collisions. The number of collisions has climbed from 2,000 vessels in 2011 to nearly 4,000 in 2017. Though a part of this could be attributed to the increase in the overall vessel count across the globe, every collision is one too many.

Israeli-based maritime startup Orca AI plans to bring greater safety to hard-to-navigate situations by using artificial intelligence and data analytics. “The total cost of these collisions today is around $20 billion, making it a very serious issue. And these collisions do not usually happen in the middle of the ocean but near the port,” said Yarden Gross, co-founder and CEO of Orca AI.

Crowded waterways near ports and docks are a definitive problem, with 90 percent of all collisions being reported in these areas. Gross explained that there are navigation issues that can overwhelm a vessel’s crew, however experienced and adept are.

“When you get close to a port, it is usually very congested from all sorts of vessels like container ships and small shipping vessels. The existing navigation tools like radar and GPS are not sufficient for such waterways,” said Gross. “In such a situation, the captain and crew start aligning the vessel based on their instinct. But then, bad weather conditions also need to be considered. For instance, when there is a lot of fog or haze and/or its night time, you have low visibility. Eventually, it doesn’t matter how much experience you have, you are prone to making mistakes, and that can be catastrophic.”

Orca AI’s system uses vision sensors built into the thermal cameras that are utilized extensively in the Navy. The cameras are modified for the startup’s specific use case, combining them with low-light, high-definition cameras that are fused to existing sensors like radar and GPS. This allows ships to see through every obstacle in even the harshest weather and avoid possible collisions near the port.

“Our system continuously learns about the maritime environment by collecting and analyzing data in order to eventually add autonomous capabilities. Today we are working on many pilot programs with companies, and the feedback thus far has been amazing,” said Gross.

Gross explained that the maritime industry is in dire need of technology infusion, because there has not been much progress in navigation tools since the early 2000s. Though autonomous operations have found some traction within the trucking industry, the technology remains confined to research labs in the shipping space.

“The navigation technology in commercial ships is outdated. In the last 10 years, we’ve seen an increase in the number of ships. The vessels have also become bigger, making them harder to navigate. The existing navigation tools give you lousy results,” said Gross. “For instance, the radar we have is only suitable for long distance navigation and not when a ship is close to the port with many vessels in close proximity. And if there is cloud cover and haze, the picture is nowhere close to being accurate.”

However, times are changing, with several companies and incumbent manufacturers like Rolls- Royce working to develop autonomous ship technology. That said, Orca AI does not find this to be a challenge but rather welcomes participation, as the autonomous shipping ecosystem needs several companies with different competencies to collaborate in bringing out a commercially viable system.

“At Orca AI, we are taking a piece of the autonomous technology puzzle and solving it. We want to make sure that ships can travel from point A to point B in the best and safest way possible. As more and more ships install our system, it will be possible to statistically understand the extent to which we reduce the collision numbers,” said Gross. “Right now, we are working closely with our customers to improve the system, the user interface and the overall capabilities of our software.”