Real-time Remote Tracking and Autonomous Planning for Whale Rendezvous using Robots

TL;DR

This paper presents a real-time autonomous system for tracking and rendezvous with sperm whales at sea, integrating model-based reinforcement learning, sensor data, and empirical whale models to navigate and communicate effectively.

Contribution

It introduces a novel autonomous system combining reinforcement learning and empirical models for real-time whale tracking and rendezvous at sea.

Findings

Successful real-world rendezvous with sperm whales in Dominica

Effective real-time acoustic tracking amidst multiple whales

System demonstrated robust performance in land experiments and simulations

Abstract

We introduce a system for real-time sperm whale rendezvous at sea using an autonomous uncrewed aerial vehicle. Our system employs model-based reinforcement learning that combines in situ sensor data with an empirical whale dive model to guide navigation decisions. Key challenges include (i) real-time acoustic tracking in the presence of multiple whales, (ii) distributed communication and decision-making for robot deployments, and (iii) on-board signal processing and long-range detection from fish-trackers. We evaluate our system by conducting rendezvous with sperm whales at sea in Dominica, performing hardware experiments on land, and running simulations using whale trajectories interpolated from marine biologists' surface observations.