Skip to content
Daniel Johnston Aerospace engineering — guidance, navigation and control

Work

Two pieces, each taken far enough to produce numbers: MasterGA, a genetic algorithm for flight-control gain tuning that measures its own settings, and VTX-1, a UAV sized and generated from a parametric twin, now in build.

A two-variable search space with three wide decoy wells and one small true well. A population of 24 points settles in the lower-right decoy; when it stalls, a scout scatters samples over the least-visited ground and moves the search to the upper-left decoy, and a second scout moves it to the true well in the upper right.

MasterGA

A genetic algorithm that tunes its own settings, grown out of a flight-control capstone.

A modular genetic-algorithm system in MATLAB: plug-in plants and fitness profiles, a preset ladder from a 100-evaluation smoke test to a calibrated multi-hour run, and a meta-GA that tunes the GA's own settings and measures what they cost.

  • MATLAB
  • Simulink
  • Genetic algorithms
  • Optimisation
  • Flight control
Optimisation and control Working — v0.1
A plan-view drawing of the VTX-1 Pathfinder, nose up, generated from its parametric twin: a straight, constant-chord wing spanning the full width, with ailerons along its outer panels; two motors and propeller discs just ahead of the leading edge; the camera, video transmitter and flight controller on the centre line ahead of the wing; the two batteries, dashed, under the wing, with the centre of gravity marked between them; and a carbon boom running back to the V-tail.

VTX-1 Pathfinder

A fixed-wing surveillance UAV, sized from first principles and built from a parametric twin.

A twin-motor V-tail aircraft for autonomous area survey, sized in MATLAB, generated as a fully parametric digital twin, and printed and assembled from that twin.

  • MATLAB
  • Fusion 360
  • Python
  • ArduPlane
  • 3D printing
Aircraft design and manufacture In build