Vandaris Counter-UAS · Interceptors

Vandaris

Onboard vision for kinetic intercept.

Bench vision demo below (Pi detection + Δx/Δy). Live sim IBVS under that. Interactive Gen-1 airframe twin at right. Mapping pixel error to motor commands is next—not field-deployed.

Gen-1 interceptor Drag to rotate

Loading concept model…

Gen-1 airframe twin · concept / sim — not flight hardware FEA & SITL →
Working today
Pi 5 + camera · bbox + Δx/Δy from frame center
Sim proof
IBVS canvas · target ~30 Hz control loop
Next
Error → rates → motors on 5" FPV

Vision-guided interception.

The interceptor uses a vision-based perception and visual-servoing pipeline to detect and track aerial targets. This bench prototype demonstrates real-time target detection and calculation of image-plane pixel error (Δx, Δy)—the feedback signal used by the guidance loop to steer toward the tracked target. Detection and error generation only; motors not closed yet.

CV bench · YOLO + image-plane error Prototype · not flight
Computer-vision bench prototype — real-time target detection, tracking, and image-plane error generation for visual servoing.

One control loop, two perspectives.

The same visual-servoing loop, shown from the command picture and the seeker. Left: top-down pursuit geometry. Right: simulated onboard camera driving pixel error toward zero.

Vandaris IBVS · Simulation digital twin Canvas tick @ 30 Hz
TRACKING
ΔX px
ΔY px
Error px
Range m
Closing m/s
Lock confidence 0%
Sim runs0 T+0

Browser IBVS simulator · Command picture + seeker view · Shared telemetry bus

Hardware bench
Python / OpenCV / YOLO on Raspberry Pi 5 — bbox + Δx/Δy (not closed on motors yet)
Embedded target
ARM64 + global shutter camera · 5" FPV airframe ready for mount
Simulation
Browser IBVS sim above · design target ~30 Hz once the servo loop is closed

Last arrow = next milestone · not closed on hardware yet

A · Perception

GPS-denied vision — real-time track and pixel-error from the camera frame (Pi bench demo above; sim IBVS loop below).

B · Guidance

Terminal guidance research for intercept trajectories—aerial and ground-target scenarios—without a human FPV pilot on the final approach.

C · Integration

One software architecture supports multiple scenario classes in simulation—reducing duplicated research paths across air and ground-target studies.

Airframe FEA and SITL intercept footage live on Platform.