Automotive · Strong theory
Passenger Down — Fall & Medical Event Detection in Transit
Knows when a passenger falls on the bus — and if they get up.
The physics is solid; our own validation is scheduled.
How it works
A fall is a fast downward motion with a sharp burst in the signal, followed by stillness at floor level. Ordinary braking sway looks different — slower, and the whole cabin moves together. The system tells them apart, alerts the driver, and logs whether the person got back up.
In the physics: A fall is a high-velocity vertical bulk-motion transient with a characteristic broadband Doppler burst followed by an abrupt transition to a floor-level static or breathing-only channel state; braking-induced sway has a distinct, horizontally-coherent lower-velocity signature.
See it work
This is real pipeline output for Automotive, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
OPERAnet and CSI-Bench fall tasks for the detector; own pilot: instrumented bus with staged falls (stunt protocol) during real braking maneuvers to measure false-alarm rate against normal lurching.
Who it is for
Automatic fall evidence and real-time 'passenger down' alerts, camera-free — sold to transit insurers and bus fleet risk managers drowning in slip-and-fall claims.
runtime Runs today in LatentField 2.0 as fall_detect
The matching solution
Complete first-room estimateCabin Presence Node1 nodes · ~$40 parts · 45 min Request kit, subscribe, or set up →Compatible DIY hardware options
45 min · intermediate