It’s the process of data collection that Doctor Dolittle likely didn’t divulge when he set about talking to the animals, but it’s the mission that scientists behind Project CETI (the Cetacean Translation Initiative) haven’t shied away from in their bid to better understand how sperm whales communicate.

This is, of course, the gargantuan effort of collecting ‘millions to billions’ of high-quality, highly contextualised vocalisations between sperm whales, to help shape our understanding of the ways in which this particular species speaks to one another.

But the sheer amount of data needed is only one part of the equation. The first hurdle scientists face is finding the whales to begin with, then it’s knowing when and where they’re going to surface next. If you’ve never tried – attaching listening devices and collecting visual information on sperm whales within their natural habitat is understandably difficult.

To make things easier, Project CETI – led by Stephanie Gil, Assistant Professor of Computer Science at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) – has proposed a new ‘reinforcement learning framework’ in which robotics and artificial intelligence meet sperm whales for the first time.

And this one will be using autonomous drones to find sperm whales and predict where they will surface.

It’s a new study that uses various sensing devices, including aerial drones with very high frequency sensing capabilities that will be used to emulate an ‘antenna ray in the air’ for estimating the direction of received ‘pings’ from CETI’s fleet of on-whale tags.

The research, published in Science Robotics, will demonstrate that it really is possible to predict when and where a whale may surface by using these various sensor data alongside predictive models of sperm whales’ dive behaviour. 

With this information, Project CETI can now design algorithms for the most efficient route for a drone to encounter a whale at the surface. It’s a development that opens up whole new possibilities for conservation efforts as well as new methods for helping ships avoid striking whales while at the surface.

The technology has been called the Autonomous Vehicles for Whale Tracking and Rendezvous by Remote Sensing (or AVATARS) which works to measure the angle from which ‘pings’ arrive back from the whale tags to inform the decision-making process of the autonomous drones. 

By calculating such measurements and cross-referencing with pre-existing whale motion models from previous studies, the AVATARS will be able to make decisions on when and where to interact with surfacing sperm whales, ‘minimising the number of missed rendezvous opportunities’ overall.

“I’m excited to contribute to this breakthrough for Project CETI. By leveraging autonomous systems and advanced sensor integration, we’re able to solve key challenges in tracking and studying whales in their natural habitats,” said Dr Stephanie Gil. “This is not only a technological advancement, but also a critical step in helping us understand the complex communications and behaviours of these creatures.”

The team has likened the application of the technology to popular rideshare apps, which use real-time sensing to note the dynamic paths and positions of drivers and potential riders, assigning a driver to rendezvous with the rider as efficiently and as timely as possible.  

Project CETI’s case is similar in the way the team is now ‘real-time’ tracking the whale with the goal of coordinating the drone’s rendezvous to meet the whale at the surface.

“This research is a major milestone for Project CETI’s mission. We can now significantly enhance our ability to gather high-quality and large-scale dataset on whale vocalisations and the associated behavioural context, putting us one step closer to better listening to and translating what sperm whales are saying,” said Dr David Gruber, Founder and Lead of Project CETI.

The project is the latest example of robotics and artificial intelligence being used to enrich the process of data collection while helping to speed up the research process within the “challenging” marine environment.

“The interdisciplinary work, that combines wireless sensing, artificial intelligence, and marine biology, is a prime example of how robotics can be part of the solution for further deciphering the social behaviour of sperm whales,” said Harvard University PhD candidate and first author of the paper, Ninad Jadhav.

Click here for more from the Oceanographic Newsroom.