HARINE PILLAI completed Machine Learning for Automotive Safety

Built a perception validation dossier end to end for a synthetic Aurora-7 detector: defined detection at IoU ≥ 0.5, computed aggregate precision/recall and VRU false-negative rate, and sliced recall by lighting, visibility, and class rarity to expose the night and occlusion failure modes. Closed with a SOTIF-style safety case and a conditional ship recommendation grounded in the candidate’s own metrics and the real Uber Tempe crash pattern.

• Leakage-Free Detection Definition
• Safety-Critical Metric Selection
• Per-Condition Failure Triage
• SOTIF Hazard Framing