Chasing Ghosts: A Simulation-to-Real Olfactory Navigation Stack with Optional Vision Augmentation
Kordel K. France, Ovidiu Daescu, Latifur Khan, Rohith Peddi · 2026
Read Chasing Ghosts: A Simulation-to-Real Olfactory Navigation Stack with Optional Vision Augmentation by Kordel K. France, Ovidiu Daescu, Latifur Khan, Rohith Peddi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13166020.txt.
Description
A drone that can smell its way to a gas leak would be handy, but turbulent air, faint signals, and tiny payloads make the job hard. Kordel France and co-authors present a complete open-source system that does it with a minimal sensor set. Custom scent hardware rides on a quadrotor, and a navigation policy learned in simulation flies the real craft.
The drone heads straight for the source without building a gas map and without outside positioning. A camera can join in as an optional helper that speeds the search under some conditions. Indoor flight tests with an ethanol source showed steady source-finding in realistic airflow. The team releases the firmware, simulation code, dataset, and circuit board designs, aiming to give other groups a reproducible base for smell-guided flight.
Catalog record
| CREATOR | Kordel K. France, Ovidiu Daescu, Latifur Khan, Rohith Peddi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |