Independent navigation in contested environments
Jamming and spoofing can take GNSS away. SenzFusion navigates on its own sensors: the IMU predicts motion, radar map matching corrects drift and a thermal scene check confirms the fix, while GNSS input is used to detect a contested environment. The host autopilot receives course corrections and keeps flight control.
- Sheet
- Navigation · Pipeline
- Layers
- L0 · L1 · L2
- Status
- Payload + SDK · demo scripted
- Revised
One estimate, two witnesses
The IMU predicts motion throughout the flight. Radar and thermal matches against stored references correct and cross-check the estimate; a position fix is accepted when both agree.
Predict motion
The IMU predicts position, velocity and orientation 1,000 times a second, including between fixes. Barometer and airspeed feed the same fusion core.
Radar altimeter
Ground heights measured along the track build a terrain profile beneath the aircraft. Imaging radar adds a 2D ground patch.
Radar map match
The radar profile is matched against the stored terrain map to correct accumulated navigation drift.
Thermal scene check
A thermal terrain picture is matched against the stored reference scene. The estimate is updated when radar and thermal agree.
Detects contested environments
Uses GNSS input to detect a contested environment. Satellite position is compared against the fused estimate; when the two disagree, jamming or spoofing is flagged while radar and thermal fixes carry the navigation.
FPGA processing core
Fixed-timing logic cleans readings, predicts motion and runs the radar and thermal matches; ARM cores update the estimate. Timing remains to be validated.
Accepted when both agree
The estimate is updated along-track and cross-track only when the radar map match and the thermal scene check agree.
Predictable timing. Motion prediction, the radar map match and the thermal scene check run in fixed-timing FPGA logic.
Proposed board architectureSensor reading to course correction in six steps
SenzFusion runs on an FPGA system-on-chip: fixed-timing logic for the sensor pipeline and ARM cores for the estimate update.
| Step | Input | What happens | Runs on |
|---|---|---|---|
| 1 · Time-stamp + clean | All sensors | A hardware clock time-stamps readings; weak readings are dropped | FPGA |
| 2 · Predict motion | IMU | Position, velocity and orientation predicted 1,000 times a second | FPGA |
| 3 · Ground profile | Radar altimeter | Ground heights along the track build the terrain profile | FPGA |
| 4 · Radar map match | Ground profile, imaging radar | Profile matched against the stored terrain map to correct drift | FPGA |
| 5 · Thermal scene check | Thermal camera | Terrain picture checked against the reference scene | FPGA |
| 6 · Update estimate | Radar + thermal agreement | Along-track and cross-track update; course correction to the autopilot over signed serial | ARM |
Barometer and airspeed also feed the core.
GNSS outage rehearsal
Watch the flight simulationThe ShoalOS Simulator flies an authored waypoint route through the Engadin valley. UAV camera, imaging IR, radar and navigation-sensor panels run alongside the 3D scene, with an event log of each phase and GNSS state.
- Phase 01GNSS available
Valley transit
Follow the authored waypoints along the lake valley with GNSS available.
- Phase 02GNSS outage rehearsed
Degraded environment
Rehearse the GNSS outage while the route continues.
- Phase 03Outage continues
Mountain passage
Cross mountain terrain along the planned route.
- Phase 04GNSS recovered
Observation orbit
GNSS recovered; orbit the observation area.
Scripted animation from an authored route; the UAV is enlarged for visibility. Sensor panels are simulated or illustrative, not flight results. Imagery © Esri & contributors · Terrain © Mapzen / source providers · OpenGlobus.
From flight plan through a GNSS outage
Six steps, from route planning on the ground to operator review.
- On the ground
- On the vehicle
- Across the squad
- With the operator
Start with a reviewed route
Select the destination and waypoints, calculate and review the route, then export the flight plan for the host autopilot.
Explore Nav Planner- On the ground
- On the vehicle
- Across the squad
- With the operator
Configure the payload
Load the terrain map, reference scenes and payload configuration, and expose navigation data to the host aircraft. RECONN.EARTH prepares the thermal reference scenes.
Explore the payload- On the ground
- On the vehicle
- Across the squad
- With the operator
Navigate independently
The IMU predicts motion; the radar map match corrects drift and the thermal scene check confirms the fix. GNSS is available and used as a check to detect a contested environment.
Explore the fusion pipeline- On the ground
- On the vehicle
- Across the squad
- With the operator
Keep navigating through the outage
Electronic warfare denies or spoofs GNSS, and the GNSS check flags the contested environment. Radar and thermal fixes continue, and a position fix is accepted when both agree.
Watch the flight simulation- On the ground
- On the vehicle
- Across the squad
- With the operator
Share confidence across the squad
Each aircraft shares its navigation confidence and payload health over the secured data link. If a sensor or drone fails, the squad can retask.
Explore SquadSense- On the ground
- On the vehicle
- Across the squad
- With the operator
Detect, recognize and track
Thermal imagery tracks the object while navigation continues. Video and track context return to the operator; the operator and host retain target decisions.
Explore detection and trackingObject tracking runs alongside navigation as a separate payload function. SquadSense and edge ATD/ATR are coming soon. The flight simulation is a scripted demonstration, not a flight result.
Integrate the navigation payload
Works alongside your existing autopilot.