Djinious
Drone systemsAerospace & marine

A quadcopter mission, flown before the drone exists

A complete quadcopter wired from library parts into one co-simulation, its flight controller closing the loop around NVIDIA Isaac Sim rigid-body physics — and a real take-off, hover, climb, descent and landing recorded from that loop.

DjiniousWorkshop
Isaac Sim RTX render of the drone airframe in the physics scene, on NVIDIA GB10.
PhysX rigid body in Isaac Sim 6.0.1
6-DOFPhysX rigid body in Isaac Sim 6.0.1
Hover, climb, hover
2 m → 5 mHover, climb, hover
Analytic ⇄ Isaac altitude Δ over hover
< 0.5 mAnalytic ⇄ Isaac altitude Δ over hover
Gated GPU checks green
4/4Gated GPU checks green

The device, before it exists

Real dynamics usually only appear on the bench, after the parts have been bought and the airframe built. Here the drone is a system of functional models from the start: radio, flight controller, ESCs, motors, propellers, battery and airframe, each a real component record with its model attached.

The airframe block hands off to NVIDIA Isaac Sim. Per-rotor thrust and torque from the functional models drive a 6-DOF PhysX rigid body on the GPU, and pose, IMU and GPS stream straight back into the running system.

Compose

The drone wired on the system canvas, every block a functional model exchanging real signals.

DjiniousWorkshop
System canvas wiring a drone's radio, flight controller, ESCs, motors, propellers, battery and airframe into one co-simulation.
System canvas — Drone · Containerized MIL.

The recorded mission

A closed-loop mission recorded from the co-simulation: an FMU flight controller (radio → FC → ESC → motors → props) around rigid-body physics from Isaac Sim, captured with exact sim-time stamps. No keyframes.

  1. Take-off

    The radio sends an altitude command; the motors spin up and the PhysX body leaves the ground.

  2. Hover at 2 m

    The first hold, with a small honest lateral drift left in the data.

  3. Climb and hover at 5 m

    A second altitude command; the airframe follows it and holds.

  4. Controlled descent and touchdown

    The drone comes down under control and lands; the recording then shows it at rest.

Watch the physics agree with the math

Live scopes read the signals streamed back from Isaac Sim across the whole mission — thrust, motor rpm, battery voltage and state of charge, altitude command and airframe position.

DjiniousWorkshop
Live scopes reading propeller thrust, motor rpm, battery voltage and state of charge, altitude command and airframe position over a 60-second mission streamed back from NVIDIA Isaac Sim.
Digital twin · scopes · live — airframe:pos_z ← Isaac.

Validated on the GPU

Every merge to the airframe bridge runs a GPU-gated end-to-end suite against Isaac Sim on NVIDIA DGX Spark · GB10 before it ships.

Bridge reachability

ping → ok.

Hover, finite and level

imu_az = 9.81 m/s².

Isaac ⇄ analytic altitude

Δ < 0.5 m over hover against a deterministic 6-DOF analytic model.

Camera frame

RGBA frame rendered on GB10.