Recently, Project CETI (‘Cetacean Translation Initiative’), led by Stephanie Gil, Assistant Professor of Computer Science at Harvard John A. Paulson of Engineering and Applied Sciences (SEAS) proposed a new reinforcement learning framework using autonomous drones to find sperm whales and predict where they will surface.
The research, which is published in Science Robotics, addresses the considerable challenge of identifying where sperm whales will surface to capture the kind of data it needs in order to understand how they communicate, through vocalisations – which includes attaching listening devices and collecting visual information.
The proposal uses various sensing devices, such as Project CETI aerial drones with very high frequency signal sensing capability that leverages signal phase along with the drone’s motion to emulate an ‘antenna array in air’ for estimating directionality of received pings from CETI’s on-whale tags.
In doing so, the technology predicts where and when whales will surface, by using this various sensor data along with predictive models of sperm whales’ dive behaviour.
Harnessing this information means Project CETI can now design algorithms for the most efficient route for a drone to encounter a whale at the surface. It also opens up the conservation possibility of helping ships to avoid striking whales who do surface.
Presenting the Autonomous Vehicles for whAle Tracking And Rendezvous by remote Sensing, or AVATARS framework, the study develops two interrelated components of autonomy and sensing: autonomy determines the positioning commands of the autonomous robots and Sensing measures the Angle-of-arrival (AOA) from whale tags to inform the process.
Measurements from the autonomous drone to surfaced tags, acoustic AOA from existing underwater sensors and whale motion models from previous biological studies of sperm whales all provide necessary input to the AVATARS autonomous decision-making algorithm.
AVATARS is the first co-development of VHF sensing and reinforcement learning decision-making for maximising rendezvous of robots and whales at sea. A well-known example of time-critical rendezvous can be observed in rideshare apps, which utilises real-time sensing to track the positions of drivers and potential riders. When a rider requests a ride through the app, it can assign a driver to rendezvous with the rider as efficiently as possible.
Project CETI uses similar technology in real-time tracking the whale, with the aim to coordinate the drone’s rendezvous to meet the whale at the surface.
“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. This is not only a technological advancement, but also a critical step in helping us understand the complex communications and behaviors of these creatures,” said Gil.
“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 behavioral context, putting us one step closer to better listening to and translating what sperm whales are saying,” added David Gruber, Founder and Lead of Project CETI.
There’s plenty of other editorial on our sister site, Electronic Specifier! Or you can always join in the conversation by commenting below or visiting our LinkedIn page.
