Ujin Kwon · 권우진

Applied algorithms, vehicle software, telemetry runtimes, and analysis tools. Maintainer · Autoware autoware_carla_interface

Additional work · In development · Low-vision coaching HUD

HERO is a coaching-only parking-assistance project for a Hyundai Ioniq. It connects the Monoscale camera-perception stack to a driver interface designed around low-vision legibility. The system provides guidance and does not intervene in vehicle control.

Vision-Only Perception

  • Metric ground-plane odometry estimates vehicle motion from one or more cameras and IMU without vehicle-mounted LiDAR.
  • Plane-sweep dense occupancy reconstructs parking-space geometry from raw fisheye images in C++/CUDA.
  • A deterministic CARLA evaluation and replay path measures odometry and occupancy against ground truth.
  • The perception implementation and measurements are documented separately on the Monoscale project page.

Low-Vision Coaching HUD

  • Angular legibility budgets connect display geometry to the driver's usable visual angle.
  • Guidance includes a parking corridor, stop line, gear state, and explicit degraded-state messaging.
  • ROS 2 coaching logic is separated from the Qt presentation layer.
  • The current geometry layer includes 26 tests for display and guidance calculations.

Architecture

Camerasdual-view CARLA image streams
→
Monoscalemetric ground-plane odometry and dense occupancy
→
Coaching Stateparking geometry, gear, stopping, degraded state
→
HUDlow-vision-oriented Qt presentation

Engineering Status

In development. The current implementation includes scenario-driven HUD states, geometry tests, and visual-acuity simulation outputs for interface review.