Aastha kumari completed Machine Learning for Automotive Safety

Built a perception validation dossier that correctly defined detection by IoU, computed precision/recall and VRU false-negative rate from a scored table, and exposed the safety-critical collapse in night and occluded VRU recall. The work then translated those findings into SOTIF-style mitigations and an evidence-based ship recommendation tied back to the real Uber Tempe crash.

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