Nissan Connect
MIL Diagnostics
CV-based malfunction indicator light diagnosis. FPNLite on-device detection, AR overlay, VIN-based severity classification. The product that needed 20+ garage visits across three cities before a single line of spec was written.
eliminated · post v2
vs pre-launch
v1 → v2
FPNLite · on-device
The team's diagnosis was wrong. Post-launch, unnecessary service visits were increasing. Internal consensus: user education problem to drivers don't understand MIL warnings. My diagnosis after 20+ garage visits across Chennai, Bengaluru, and Hyderabad: system over-signalling problem. The platform was flagging transient electrical faults (vibration, temperature variance, loose contacts) as persistent critical faults. Drivers were behaving rationally to responding to a broken signal. Fixing user education would have been expensive and wrong. The v2 pattern detection fix took one sprint.
System design architecture to FPNLite detection pipeline to severity classification
End-to-end customer journey to MIL trigger to resolution
FPNLite model training pipeline to 12,000+ images · 6 lighting conditions
Patent filed: Intelligent Systems for Identifying Malfunctions to Application ID: 202441039454 to Status: Filed. Covers VIN-based variant lookup combined with on-device CV detection and severity classification logic.
Patent wall to Application ID 202441039454
| v1 Logic | v2 Logic | Impact |
|---|---|---|
| Single fault → persistent flag | 3 occurrences in 15-min window required | False positives −64% |
| All MIL signals treated equally | Severity classifier · Critical/Safe/Self-resolvable | Unnecessary visits −70% |
| Text description only | AR Core overlay · visual label on physical symbol | Self-resolution rate 2× |
| Voltage variance flagged as fault | ±0.2V transient filter applied | Vibration false positives eliminated |