Dev

Bearing.ai emerges from stealth to power recommendations for shipping boat captains


The company Bearing.ai emerged from stealth today to launch AI-powered software to provide the maritime shipping industry and tanker boat captains predictions to optimize trips shipping route navigation based on fuel efficiency, profit, or safety. Since the company was founded in 2019, Bearing.ai has raised $3 million from the AI Fund, a $175 million startup funding endeavor led by former Google Brain cofounder Andrew Ng, as well as Japanese shipping company Mitsui and Co.

Bearing.ai CEO Dylan Kiel told VentureBeat the startup was able to train its first models with historical data provided by investor Mitsui and Co. and 2,500 ships. As part of the deal, Bearing.ai announced deals to provide services to 300 K Line vessels as well as shipping companies MOL and ZeroNorth. The primary focus of what Bearing.ai does, Kiel said, is following fuel consumption because that’s the biggest single driver of operating costs for shipping companies. To do so, Bearing.ai takes in sensor data and considers factors like ship dimensions, location, and weather factors like wind speed and wave size when making predictions.

“Weather is one of the single biggest drivers of the variance that occurs with fuel consumption for a given voyage, I can have the same ship going on the same route, let’s say again, like, you know, Tokyo to San Diego, and carry the same cargo. And the consumption I have from voyage A to voyage B could be different by 30-40% based upon the weather,” Kiel said.

Bearing.ai claims its models are capable of predicting the fuel consumption of a container or hull ship with 98% accuracy, a feat made possible by use of sensors fuel and speed sensors collecting data on a minute-by-minute basis.

READ  XM Cyber raises $17 million to simulate and remediate cyberattacks

Predicted fuel consumption with early customer data with different types of shipping companies and types of types of ships with 97% accuracy. Container ships move a vast amount of global trade and saw a sharp decline in use in 2020 due to the COVID-19 pandemic, and, like other industries, faces pressure to automate. Kiel said Bearing.ai wants to help companies consider a range of costs to help them save money.

“It’s not just choosing the right route for one ship. If you choose that right route for that ship that impacts what the other ships need to do. And that impacts what you’re going to do with your contract and when you’re going to clean that ship and so on, so there’s a lot of decision points that ultimately are all interconnected if you’re trying to optimize the whole system,” he said. “And so that’s kind of what the mountain that we’re marching towards is that pretty much every decision you can make as a decision company whether it’s fuel to use the ship to use the route to take, how you position your fleet, all of that impacts your ultimate operational efficiency.”

Other examples of automation startups entering the maritime space include Sea Machines, which is working on autonomous shipping navigation, and Orca AI, which makes systems for avoiding ship collisions. Also of note is recent work by AI researchers to create amphibious robots capable of movement on sea and land.

Bearing.ai was founded in June 2019 and is based in Palo Alto, California. The company has 10 employees.

READ  Emtrain raises $10 million to prevent workplace harassment with data analytics

VentureBeat

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative technology and transact.

Our site delivers essential information on data technologies and strategies to guide you as you lead your organizations. We invite you to become a member of our community, to access:

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform
  • networking features, and more

Become a member



READ SOURCE

Leave a Reply

This website uses cookies. By continuing to use this site, you accept our use of cookies.