Datasheet

PhantomNAV™

SYNTHETIC GPS FOR CONTESTED AUTONOMY

PRODUCT SLICK v1.0 | Domain-Agnostic Module | SWAP-C Optimized | Made in U.S.A.

A high-tech naval vessel speeds through choppy waters at night, illuminated by glowing digital dots.

PhantomNAV is our patent-pending Machine Learning State Estimator (MLSE) for Contested Autonomy in GPS-denied environments. A sim-to-real machine-learning pipeline trains domain-specific inertial navigation models in high-fidelity simulation, then deploys lightweight inference packages to commodity edge compute. Models broadcast position corrections to the autopilot over MAVLink or other protocol. Single platform across air and maritime today, with subsea, ground, and orbit on the roadmap. Vendor-agnostic. No GNSS reliance at runtime.

Core Capabilities

Sim-to-Real

VICTUS PhantomNOISE bridges simulation and hardware noise profiles. Models trained in sim transfer cleanly to live platforms.

Multi-Domain

Single platform spans air and marine. Pluggable architecture extends to subsea and ground (roadmap).

Edge-Deployed

ONNX inference on commodity ARM compute. Real-time at 10–50+ Hz with sub-100 ms latency.

Autopilot-Native

MAVLink position-correction broadcast. ArduPilot primary, PX4 supported. Open Architecture & vendor-agnostic.

Integration Flow

Step1

Configure

Ontology-driven mission and scenario configuration on enterprise data platform.

Step 2

Simulate

PhantomSIM runs high-fidelity, multi-domain simulation across air and marine.

Step 3

Train

PhantomNOISE applies real hardware noise profiles to sim data; temporal ML model trains.

Step 4

Deploy

ONNX inference package pushed to edge compute (Pi 4/5, Jetson Orin, VOXL, etc).

Step 5

Navigate

Real-time position corrections broadcast to autopilot via MAVLink. No GNSS required.

Host Platform Requirements

  • COMPUTE Pi 4 (8 GB) min · Pi 5 / Jetson Orin / VOXL
  • CPU ARM Cortex-A72 quad-core @ 1.5 GHz
  • SENSING Triple-redundant IMU (e.g., Cube Orange)
  • INFERENCE 10–50+ Hz, < 100 ms latency
  • AUTO PILOT ArduPilot (primary) · PX4 (supported) · OSA / MOSA
  • INTERFACE MAVLink position correction broadcast · OSA / MOSA
  • DOMAINS Air · Maritime · Subsea · Ground · Orbit
Platform Applicability

Single ML pipeline — pluggable simulator architecture extends to additional platforms without re-architecting the data or training stack.

CURRENT

Air

CURRENT

Maritime

ROADMAP

Subsea

ROADMAP

Ground

ROADMAP

Orbit

Get Started

Ready to put PhantomNAV
on your platform?