Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring

TL;DR

This paper introduces a decentralized, vision-based multi-quadrotor system for scalable wildlife monitoring, enabling robust identification and tracking in natural habitats with minimal sensors and without centralized control.

Contribution

It presents novel decentralized coordination and tracking algorithms tailored for unstructured environments, advancing autonomous wildlife monitoring capabilities.

Findings

Successful real-world deployment in diverse conditions

Reliable identification and tracking of large species

Scalable and low-bandwidth system design

Abstract

Wildlife field operations demand efficient parallel deployment methods to identify and interact with specific individuals, enabling simultaneous collective behavioral analysis, and health and safety interventions. Previous robotics solutions approach the problem from the herd perspective, or are manually operated and limited in scale. We propose a decentralized vision-based multi-quadrotor system for wildlife monitoring that is scalable, low-bandwidth, and sensor-minimal (single onboard RGB camera). Our approach enables robust identification and tracking of large species in their natural habitat. We develop novel vision-based coordination and tracking algorithms designed for dynamic, unstructured environments without reliance on centralized communication or control. We validate our system through real-world experiments, demonstrating reliable deployment in diverse field conditions.