# Battery-free wildlife monitoring with Riotee *2025-04-01 — idea* Monitoring wildlife in the field today relies heavily on [battery-powered devices](https://anil.recoil.org/papers/2024-terracorder), like GPS collars or acoustic recorders. However, such devices are often deployed in remote environments, where battery replacement and data retrieval can be labour-intensive and time-consuming. Moving away from battery-powered field devices could radically reduce the environmental footprint and labour cost of wildlife monitoring. The rise of batteryless energy-harvesting platforms could enable ultra-low-power, long-term, maintenance-free deployments. However, existing battery-less devices are severely constrained, often unable to perform meaningful on-device computation such as ML inference or high-frequency audio capture. This project explores the development of next-generation, battery-less wildlife monitoring platforms using [Riotee](https://www.crowdsupply.com/nessie-circuits/riotee), an open-source platform purpose-built for [intermittent computing](https://www.sciencedirect.com/science/article/pii/S1383762120301430). Riotee integrates energy harvesting with a powerful Cortex-M4 MCU and full SDK for managing state-saving, redundancy, and graceful resume from power failures. The project could involve work on one or more of the following areas: - SDK tooling: developing a user-friendly C/Rust SDK that integrates audio recording, ML-based data processing, scheduling, and wireless communication into a unified and easily configurable framework for non-technical users in conservation and ecology. - GPS tracking: building a hardware/software solution using Riotee for wildlife tracking, harvesting energy from both motion and solar. - Acoustic monitoring: exploring the feasibility of bioacoustic monitoring on Riotee, quantifying the trade-off between scalability/lifetime and ecological data yield. - On-device ML: adapting or training lightweight ML models to fit within Riotee’s memory and energy budgets, and intermittent compute runtime. This project would suit a student interested in low-power hardware and/or applied ML. Prior experience with C and embedded programming would be helpful, but the desire to get your hands dirty with low-level debugging is essential\! Status: Completed Level: Any Year: 2025 Project: Remote Sensing of Nature Supervisors: Josh Millar, Anil Madhavapeddy Students: Dominico Parish ## Related - [EEG internships for the summer of 2025](https://anil.recoil.org/notes/eeg-interns-2025) (note, 2025-06-28) - [Terracorder: Sense Long and Prosper](https://anil.recoil.org/papers/2024-terracorder) (paper, 2024-08-01) --- Canonical: https://anil.recoil.org/ideas/battery-free-riotee Type: idea License: CC BY 4.0 Tags: conservation, biodiversity, sensing, embedded, urop