Abhinav Suryavanshi completed Machine Learning for Automotive Safety

Built a perception validation dossier end to end for a synthetic Aurora-7 detector: defined a correct IoU>=0.5 detection rule, computed aggregate precision/recall and the VRU false-negative rate, then sliced recall by lighting, visibility, and rarity to surface the night and occlusion failure modes. The final ship verdict was evidence-based and internally consistent, with SOTIF chains and mitigations tied directly to the measured safety gaps and the Tempe crash reference.

• Leakage-Free Detection Definition
• Safety-Critical Metric Selection
• Per-Condition Failure Triage
• SOTIF Functional-Insufficiency Reasoning