Researchers are pushing the boundaries of marine biology by developing technology to unlock the language of sperm whales.
The ambitious goal of Project CETI (Cetacean Translation Initiative), as it is known, is to gather millions – or maybe even billions – of detailed sperm whale vocalisations to decode how these majestic creatures communicate, allowing experts to make more informed conservation decisions.
But collecting this data poses significant challenges, say the scientists – from locating the whales to predicting where they’ll next surface, making it hard to capture sound and visual cues.
So, how are they planning to do it? With flying robots, says Stephanie Gil, Assistant Professor of Computer Science at Harvard University.
In a new development published in Science Robotics, Gil and her team introduced an innovative framework using reinforcement learning and autonomous drones.
Known as AVATARS (Autonomous Vehicles for whAle Tracking And Rendezvous by remote Sensing), this framework combines sensing and autonomy to track and meet sperm whales with unprecedented accuracy.
Central to AVATARS are Project CETI’s aerial drones, equipped with high-frequency sensing capabilities.
By processing signals from whale tags, these drones can estimate the direction and timing of whale surfacing, guiding the drones to intercept the whales’ paths in real-time, says the paper.
This approach mirrors 'ride-share' algorithms, which coordinate drivers and passengers for efficient pick-ups. Project CETI's drones similarly rely on continuous data to track the whales, optimising each encounter as they surface.
Science Robotics editor Melisa Yashinsk explains that field tests were successfully performed, "initially using a speedboat to mimic whale motions and later using only acoustic measurements of three untagged whales."
Not only does AVATARS bolster the efficiency of collecting vocalisations, but it also holds potential for conservation — helping vessels avoid collisions with whales.
By refining drone algorithms and gathering diverse data inputs, Project CETI moves closer to decoding whale communication, advancing both science and species conservation, says Gil.
"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 behaviours of these creatures."
More wildlife stories from around the world
- Bizarre new toad with missing body parts discovered in Brazilian rainforest
- The largest dam-removal project in US history has finally been completed. Now something truly amazing is happening
- Massive leeches are being grown in the middle of London. Here's why
- A prehistoric bone found 20 years ago in a Columbian desert has been hiding a big secret