Pawan Manigandan completed Machine Learning for Automotive Safety

Built an end-to-end perception validation dossier for a fictional Aurora-7 detector using IoU-based detection rules, synthetic scored metrics, and condition-level VRU recall analysis. The work identified the safety-critical night and occlusion failure slices, framed them as SOTIF functional insufficiencies, and closed with an evidence-based GO-WITH-CONDITIONS recommendation tied to the dossier’s own numbers and the Tempe crash case.

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