| I&T Solution |
AI-Powered Assisted Automated Driving Assessment (AADA)
(REF: S-1977) |
| Trial Project |
|
| Solution Feature |
- Capture driving details via multi-source data, transforming subjective behaviors into quantifiable objective data.
- AI automatically identifies violations and generates initial reports, reducing examiners' basic work; examiners focus on safety and dispute review, balancing efficiency and flexible judgment.
- Trained on real driving test data, with ≥90% accuracy in basic subject evaluation, supporting iterative optimization based on examiners' feedback.
|
| Trial Application and Expected Outcome |
- Conduct real examinee tests in closed sites to verify data collection stability and scoring consistency between AI and senior examiners.
- Compare pure manual and AI-assisted scoring modes, analyze per-test time and fatigue, quantifying the system's workload reduction effect.
- Collect dispute data between AI and examiners for model training, verifying improved accuracy in weak scenarios after iteration.
|
| Info on I&T Solution Provider |
| Solution Provider | : | Hong Kong Productivity Council | | Address | : | HKPC Building, 78 Tat Chee Avenue, Kowloon, Hong Kong | | Contact Person | : | Larry Li |
| Position | : | Associate Principal Consultant | | Tel | : | 27885819 | | Email | : |
yli@hkpc.org |
|
