Marine biologists are inching closer to understanding the details of sperm whale communication. But to decipher what cetaceans are saying, you first need to find them and know where they surface. This is no easy feat, as sperm whales can. Dive over 10,000 feet Stays underwater for up to 60 minutes. Their habitat itself spans thousands of miles.
Now, the scientists from here… Project CETI (Cetacean Translation Initiative) and Harvard University are proposing a new method to spot sperm whales and predict where they will surface using a rich combination of autonomous robots and sensor data. For this method, The study was published in the journal Oct. 30 science robotics.
[Related: Sperm whales may have their own ‘alphabet.’]
This method provides scientists with an opportunity to test new algorithms, sensing data, and artificial intelligence in difficult environments. Project CETI, first launched in 2020, works to collect vocalizations to decipher how sperm whales communicate with each other. They tracked the whales in real time using tags attached to them and customized drones to track the whales’ movements.
of new research using a variety of sensing devices, including aerial drones with very high frequency (VHF) signal sensing function. These devices can leverage signal phasing and the drone’s movement to mimic an “airborne antenna array.” This helps CETI estimate which direction a ping from one of the tagged whales it tracks is moving.
According to the teamwhich shows how sensor data can be used to predict when and where sperm whales surface and predict their diving behavior. Using that data, Project CETI can now create algorithms for the most efficient routes for drones to reach or encounter whales at sea. In the future, this could be applied to conservation methods, such as avoiding ships hitting whales as they surface.
they use this method Autonomous Vehicles for Whale Tracking and Rendezvous with Remote Sensing (AVATARS) Framework. It uses two interrelated components: autonomy and sensing. Autonomy determines the positioning commands of the autonomous robots deployed to increase the likelihood of visually detecting whales. Sensing measures the angle of arrival from the whale tag, providing pertinent information to the decision-making process of where to deploy the robot. Data from autonomous drones, flotation tags, underwater sensors, and whale movement models from previous biological studies of sperm whales all Incorporated into AVATARS autonomous decision-making algorithmAnd the aim is to minimize the loss of opportunities to meet sperm whales.
[Related: Sperm whale clans tell each other apart by their accents.]
A similar and more well-known application of this type of time-critical rendezvous method is ride-sharing apps. They use real-time sensing to record changing routes and locations, connecting drivers with potential riders. When a passenger requests a ride, the app can assign a driver to get to the passenger as quickly and efficiently as possible. The team says Project CETI’s new method works similarly, with the goal of tracking whales in real time and eventually coordinating a drone rendezvous to meet them at the surface.
“We are excited to contribute to this breakthrough in Project CETI,” said study co-author Stephanie Gill, a computer scientist at Harvard University. stated in a statement. “By leveraging autonomous systems and advanced sensor integration, we can solve important challenges in tracking and studying whales in their natural habitat. It is also an important step in understanding social communication and behavior.
