LocoMote: AI-Driven Sensor Tags for Fine-Grained Undersea Localization and Sensing

Long-term and fine-grained maritime localization and sensing are challenging due to sporadic connectivity, constrained power budget, limited footprint, and hostile environment. In this article, we present the design considerations and implementation of LocoMote, a rugged ultralow-footprint undersea sensor tag with on-device AI-driven localization, online communication, and energy-harvesting capabilities. LocoMote uses on-chip (< 30 kB) neural networks to track underwater objects within 3 m with
$\sim $
6 min of Global Positioning System (GPS) outage from 9-degrees of freedom (DoF) inertial sensor readings. The tag streams data at 2–5 kb/s (
$< 10^{-{3}}$
bit error rate) using piezoacoustic ultrasonics, achieving an underwater communication range of more than 50 m while allowing up to 55 nodes to concurrently stream via randomized time-division multiple access. To recharge the battery during sleep, the tag uses an aluminum-air salt water energy-harvesting system, generating up to 5 mW of power. LocoMote is ultralightweight (< 50 g) and tiny (
${32}\,\times \,{32}\times10$
mm3), consumes low power (
$\sim $
330 mW peak), and comes with a suite of high-resolution sensors. We highlight the hardware and software design decisions, implementation lessons, and the real-world performance of our tag versus existing oceanic sensing technologies.