Led by Stephanie Gil, Assistant Professor of Computer Science at Harvard's John A. Paulson School of Engineering and Applied Sciences, a team from Project CETI is tackling this challenge by employing a novel reinforcement learning framework utilizing autonomous drones. These drones work to locate whales and anticipate their surfacing patterns, thus improving data collection accuracy and efficiency. The research is published in Science Robotics.
The study introduces advanced sensing capabilities in CETI's aerial drones, incorporating very high frequency (VHF) signal sensors that simulate an airborne antenna array to detect signals from CETI's on-whale tags. Combined with models of sperm whale dive patterns, these systems enable drones to predict whale surfacing with enhanced accuracy, guiding them to optimal rendezvous points. Such innovations may also serve conservation efforts by helping to prevent vessel strikes with surfacing whales.
This Autonomous Vehicles for whAle Tracking And Rendezvous by remote Sensing (AVATARS) framework integrates autonomy and sensing in two core functions: determining drone positions to maximize visual encounters and measuring the Angle-of-Arrival (AOA) from whale tags to inform drone navigation. The AVATARS algorithm uses data from the drone's sensors, underwater acoustic AOA, and known whale movement models to reduce missed encounters with the whales.
The AVATARS framework is the first to combine VHF-based sensing and reinforcement learning in this application, operating similarly to rideshare systems that match drivers and passengers in real time. In Project CETI's scenario, the drone's positioning aligns to meet the whale at the surface, enhancing data collection consistency.
This innovation brings Project CETI closer to its goal of compiling an extensive collection of whale vocalizations, enriched by more accurate location and timing data. "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.
David Gruber, Project CETI's Founder and Lead, highlighted the milestone, stating, "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 vocalizations and the associated behavioral context, putting us one step closer to better listening to and translating what sperm whales are saying."
Ninad Jadhav, Harvard PhD candidate and the paper's lead author, reflected on the project's impact, saying, "This research was an amazing opportunity to test our systems and algorithms in a challenging marine environment. This 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 behavior of sperm whales."
"This project provides an excellent opportunity to test our algorithms in the field, where robotics and artificial intelligence can enrich data collection and expedite research for broader science in language processing and marine biology, ultimately protecting the health and habitat of sperm whales," added Sushmita Bhattacharya, a postdoctoral researcher in Gil's REACT Lab at SEAS.
Research Report:Reinforcement learning - based framework for whale rendezvous via autonomous sensing robots
Related Links
Project CETI
Follow the Whaling Debate
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
