Low-cost Multi-agent Fleet for Acoustic Cooperative Localization Research
Nelson Durrant, Braden Meyers, Matthew McMurray, Clayton Smith, Brighton Anderson, Tristan Hodgins, Kalliyan Velasco, Joshua G. Mangelson
TL;DR
The paper introduces CoUGARs, a low-cost, configurable AUV platform designed to enable scalable multi-agent acoustic localization research. It details a 3D-printed CougUV hardware design powered by a Raspberry Pi 5 and a Teensy 4.1, integrated with a DVL/USBL payload, GPS, IMU, depth sensors, and a modular, containerized ROS 2 software stack tightly coupled to the HoloOcean simulator. The authors present state estimation via a GTSAM-based factor graph, a nested control system, and MOOS-IvP-based mission planning, all supporting multi-agent coordination through USBL-based underwater communications. Validation includes extensive simulation with ROS 2-HoloOcean and over twenty field trials in Utah lakes and reservoirs, showing successful end-to-end operation and data collection, while outlining future enhancements such as improved messaging compression, surface GNSS/WiFi capabilities, and expansion to a larger fleet.
Abstract
Real-world underwater testing for multi-agent autonomy presents substantial financial and engineering challenges. In this work, we introduce the Configurable Underwater Group of Autonomous Robots (CoUGARs) as a low-cost, configurable autonomous-underwater-vehicle (AUV) platform for multi-agent autonomy research. The base design costs less than $3,000 USD (as of May 2025) and is based on commercially-available and 3D-printed parts, enabling quick customization for various sensor payloads and configurations. Our current expanded model is equipped with a doppler velocity log (DVL) and ultra-short-baseline (USBL) acoustic array/transducer to support research on acoustic-based cooperative localization. State estimation, navigation, and acoustic communications software has been developed and deployed using a containerized software stack and is tightly integrated with the HoloOcean simulator. The system was tested both in simulation and via in-situ field trials in Utah lakes and reservoirs.