Marine biologists come closer to understanding the the ins and outs of communicating with sperm whales. But to decode what cetaceans say, they must first find them and know where they will surface. This is not an easy task, as sperm whales can dive over 10,000 feet and stay well below the surface for up to 60 minutes. Their habitats themselves extend over thousands of kilometers.

Now, scientists from CETI project (Cetacean Translation Initiative) and Harvard University propose a new method to find sperm whales and predict where they will surface using autonomous robots and a rich combination of sensor data. The method is detailed in a study published on October 30 in the journal Scientific robotics.

(Related: Sperm whales may have their own “alphabet.”)

This method provides an opportunity for scientists to test new algorithms, detection data and artificial intelligence in a difficult environment. Launched for the first time in 2020, the CETI project aims to collect vocalizations to decipher how sperm whales communicate with each other. They used tags affixed to the whales to track them in real time and personalized drones to track their behaviors.

THE new study uses various detection devices, including aerial drones equipped with very high frequency Signal detection capability (VHF). These devices can use the phase of the signal and the movement of the drone to imitate an “array of antennas in the air”. This can help estimate which direction the pings of any of the tagged whales that CETI is tracking are moving.

According to the teamThis shows how to predict when and where a sperm whale may surface using sensor data to predict its diving behavior. Using this data, the CETI project can now create algorithms to determine the most efficient route for a drone to reach or encounter a whale on the ocean surface. In the future this could be applied to conservation methods including help ships avoid hitting whales as they surface.

They call this method the Autonomous Vehicle Framework for Whale Tracking and Remote Sensing (AVATARS). It uses two interrelated components: autonomy and sensing. Autonomy determines the positioning commands of autonomous robots deployed to increase the chances of visually spotting whales. The detection measures the angle of arrival of whale tags to better inform the decision-making process of where to deploy the robots. Data extracted from autonomous drones, surface tags, underwater sensors, and whale movement patterns from previous biological studies of sperm whales are all integrated into the AVATARS autonomous decision-making algorithmwhich then aims to minimize missed opportunities for encounters with sperm whales.

(Related: Sperm whale clans are distinguished by their accent.)

A similar and more well-known application of this type of time-critical appointment method is found in carpooling apps. They use real-time sensing to note changes in trajectory and position. connect drivers with potential passengers. When a passenger requests a ride, the app can assign a driver to meet them as quickly and efficiently as possible. According to the team, the CETI project’s new method works in a similar way, tracking whales in real time with the eventual goal of coordinating the drone’s rendezvous to meet the whale on the surface.

“I am delighted to contribute to this major breakthrough for the CETI project,” said Stephanie Gil, study co-author and Harvard University computer scientist. said in a statement. “By leveraging autonomous systems and advanced sensor integration, we are able to solve key challenges in tracking and studying whales in their natural habitats. This is not only a technological advancement, but also a crucial step in helping us understand the complex communications and behaviors of these creatures.