What if an ESP32-S3 could hear a drone before you could see it? Agam Rossen's VolAnti is an open-source acoustic drone detector built around an ESP32-S3, four MEMS microphones, e-paper display and LoRa radio. It analyzes the harmonic signature of spinning propellers instead of looking for radio signals, making... it interesting for detecting fibre-optic FPV drones that can leave the radio spectrum silent. The concept could be useful for perimeter monitoring, wildlife & environmental monitoring, industrial site awareness, event security, search and rescue operations and early-warning sensor networks, especially where visual detection or conventional radio-based detection is difficult. The creator reports 104 m measured detection, 0.23 s alert latency in its fastest detector, and roughly 18–22 hours of battery life. What I really like is how much signal processing, embedded hardware and wireless communication has been packed into a small device. Would you build an acoustic sensor like this?show more

No expensive radar. No cloud. Just microphones, DSP and an ESP32-S3. It hears the propellers, not the radio, so it works against fibre-optic FPV aircraft that emit no signal at all. Repo:

If you gave it very sensitive microphones and a lot more power then linked it with others nodes via LoRa it could be deployed in a mesh system to detect and triangulate drones over a large area. That would be insanely useful, possibly a viable startup.

That's very good idea. Thank you for it.

Where is @PalmerLuckey collab! 😂

@PalmerLuckey 😄

H O L Y - S H I T. This is exactly what I am working on. Mine uses Pan Tilt to detect volume based on audio signiature - the only difference is I am using revived world war 2 technology to isolate the angle and elevation. Put this person in touch.

The PCB is what makes this project especially interesting. A compact board bringing together four MEMS microphones, ESP32-S3 processing, power management, e-paper and LoRa turns the idea into a practical edge device. Great example of how thoughtful PCB design can make embedded sensing far more capable.

Wow! Thanks for sharing this! I've been thinking about exactly this.

What makes yours different with this? Really good to know more folks are working on it.

I mean, I think it's obvious that battlefield ambient sounds are going to pose a major challenge in this case, where signal-to-noise ratio falls, and competing sources can have spectral structures which resemble parts of the drone signature. However, under other circumstances (for example air ports, rooftops close to critical infrastructure, protected sites, etc) this could be a great component if hooked up to an early warning system.

Yes, if applied well, it can unlock new potential for warning system.

Which types of drones it can detect?

Very cool maybe also adding a pan tilt heading with a laser microphone to further improve range ?

We need more civilian defense technologies like these. European government have their heads in their arses and we are not ready for the future threats.

I'm glad you added the link to his github, you streetshitting waste of biomass.