CONIX Publication

Poster: An Ultra-Low Power AI-enabled Sensor Tag for Marine Animal Tracking

Authors: Swapnil Sayan Saha, Caden Davis, Mani Srivastava

Abstract:

We present LocoMote, a compact, ultra-low-power, environmentally resilient and modular sensor tag configuration for GPS-free localization and behavior logging of marine animals. LocoMote integrates inertial measurement units, barometers, GPS, real-time clocks, ambient sensors, long-term storage, communication and energy harvesting systems, all within a 32 X 32 X 10 mm^3 tag. We showcase the resource utilization, power consumption and performance of various parts of the sensor tag, including the AI-driven localization stack, the communication stack, the energy harvesting stack, and the resource management stack, and compare our tag against competing proposals.

Release Date: 10/12/2022
Uploaded File: View