AI-Powered Traffic Law Navigator and Rights Assistant

Navigating traffic laws and administrative legal processes in the Philippines presents a significant challenge for ordinary motorists, who frequently lack access to legal counsel and struggle with complex technical legal terms. This information gap often leads to accidental violations, unresolved roadside disputes, and an inability to contest unjust citations. To address these challenges, this study developed the AI-Powered Traffic Law Navigator and Rights Assistant, a conversational mobile application structured around the Input-Process-Output (IPO) framework following a Prototype Software Development Life Cycle (SDLC) model. Built using the Flutter SDK and Dart programming language, the system integrates a structured MySQL relational database of Philippine traffic codes, Land Transportation Office (LTO) regulations, and Metropolitan Manila Development Authority (MMDA) guidelines. The platform employs a supervised machine learning text classification model (utilizing tokenization, normalization, and TF-IDF vectorization paired with classification algorithms) to automatically route multilingual (English, Filipino, Taglish) user descriptions to appropriate violation categories and legal data. Additionally, a generative AI presentation layer utilizes GPT API prompting templates to simplify technical legal jargon and auto-generate structured legal paperwork like explanation letters and affidavits. Real-time location-based features implement the Haversine formula on device GPS coordinates to map and calculate proximity to the nearest LTO branches, traffic units, or barangay halls within a pilot dataset covering the National Capital Region (NCR) and Luzon. Functional evaluations demonstrate that the system effectively maps natural language inputs to correct legal penalties, lowers procedural barriers via rule-based document generation templates, and improves localized civic navigation. Future recommendations emphasize migrating to a web-synchronized framework, integrating Retrieval-Augmented Generation (RAG) to eliminate AI hallucinations, scaling geographic and dialect data across the Visayas and Mindanao regions, and establishing official government API and human-in-the-loop validation pipelines.

Traffic Law Navigation, Supervised Machine Learning, Generative AI, Geolocation, Haversine Formula, Developmental Research, Philippines.

1. Bhavana B. M., Sathyanarayana, S., Bhavana, M. K., Nisarga, G. N., & Harshitha, S. (2025). Traffic Eye: AI-powered traffic rules violation detection and management. International Journal for Research in Applied Science and Engineering Technology. https://doi.org/10.22214/ijraset.2025.76565 [Google Scholar] [Crossref]

2. Cui, J., Ning, M., Li, Z., Chen, B., Yan, Y., Li, H., … & Yuan, L. (2023). Chatlaw: A multi-agent collaborative legal assistant (arXiv:2306.16092). arXiv. https://arxiv.org/abs/2306.16092 [Google Scholar] [Crossref]

3. Dede, D., Sarsıl, M. A., Shaker, A., Altıntaş, O., & Ergen, O. (2023). Next-gen traffic surveillance: AI-assisted mobile traffic violation detection system. arXiv. https://arxiv.org/abs/2311.16179 [Google Scholar] [Crossref]

4. Deffains, P. (2025). Stakeholder expectations for AI integration in legal services. GREDEG Working Paper Series. https://laweconcenter.org/wp-content/uploads/2025/01/GREDEG-WP-2025-01.pdf [Google Scholar] [Crossref]

5. Gillian, L., et al. (2024). Intelligent vehicle violation detection systems. Springer Transportation Research Archives. https://link.springer.com/article/10.1007/s44196-024-00427-6 [Google Scholar] [Crossref]

6. Hajare, M., et al. (2025). AI and IoT based traffic signal and rule enforcement system. IJRASET Journal. https://www.ijraset.com/research-paper/ai-and-iot-based-traffic-signal-and-rule-enforcement-system [Google Scholar] [Crossref]

7. Hegde, N. V., Agarwal, A., & Moharir, M. (2025). A novel AI-driven system for real-time detection of mirror absence, helmet non-compliance, and license plates using YOLOv8 and OCR. arXiv. https://arxiv.org/abs/2511.12206 [Google Scholar] [Crossref]

8. IJARCCE. (2026). UrbanEye experimental results in automated urban violation detection. International Journal of Advanced Research in Computer and Communication Engineering, 15(01). https://doi.org/10.17148/IJARCCE.2026.15133 [Google Scholar] [Crossref]

9. Khan, S. (2025). Safety effectiveness of automated traffic enforcement systems. MDPI Sustainability. https://www.mdpi.com/2673-7590/5/1/25 [Google Scholar] [Crossref]

10. Land Transportation Office. (2019). LTO Memorandum Circular No. 2019-2196: Revised rules and regulations on the implementation of the citation ticket system. Land Transportation Office, Department of Transportation. [Google Scholar] [Crossref]

11. Marcos, F. E. (1973). Presidential Decree No. 96: Amending certain sections of Republic Act No. 4136, otherwise known as the Land Transportation and Traffic Code. Office of the President of the Philippines. https://lawphil.net/statutes/presdecs/pd1973/pd_96_1973.html [Google Scholar] [Crossref]

12. OECD. (2024). AI in justice administration and access to justice. OECD Publishing. https://www.oecd.org/en/publications/governing-with-artificial-intelligence_795de142-en/full-report/ai-in-justice-administration-and-access-to-justice_f0cbe651.html [Google Scholar] [Crossref]

13. Raj, A., Choudhary, S., & Sharma, A. K. (2025). Real-time speed violation detection: AI-powered image processing for traffic law enforcement. International Journal of Science and Innovation in Engineering, 2(5), 860–866. https://doi.org/10.70849/IJSCI [Google Scholar] [Crossref]

14. Ranera, L. T. B. (2024). A comparative analysis and evaluation of NLP document embedding techniques on Philippine Supreme Court case decisions. Philippine Engineering Journal. https://www.journals.upd.edu.ph/index.php/pej/article/view/9723 [Google Scholar] [Crossref]

15. Republic of the Philippines. (1964). Republic Act No. 4136: Land Transportation and Traffic Code. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra1964/ra_4136_1964.html [Google Scholar] [Crossref]

16. Republic of the Philippines. (1995). Republic Act No. 7924: An Act Creating the Metropolitan Manila Development Authority. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra1995/ra_7924_1995.html [Google Scholar] [Crossref]

17. Republic of the Philippines. (1999). Republic Act No. 8750: Seat Belts Use Act of 1999. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra1999/ra_8750_1999.html [Google Scholar] [Crossref]

18. Republic of the Philippines. (2009). Republic Act No. 10054: Motorcycle Helmet Act of 2009. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra2009/ra_10054_2009.html [Google Scholar] [Crossref]

19. Republic of the Philippines. (2013). Republic Act No. 10586: Anti-Drunk and Drugged Driving Act of 2013. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra2013/ra_10586_2013.html [Google Scholar] [Crossref]

20. Republic of the Philippines. (2016). Republic Act No. 10916: Road Speed Limiter Act of 2016. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra2016/ra_10916_2016.html [Google Scholar] [Crossref]

21. Republic of the Philippines. (2019). Republic Act No. 11235: Motorcycle Crime Prevention Act. Congress of the Philippines. https://lawphil.net/statutes/repacts/ra2019/ra_11235_2019.html [Google Scholar] [Crossref]

22. Semantic legal retrieval experiments. (2024). Data and Knowledge Engineering. https://www.sciencedirect.com/science/article/pii/S2667096824000363 [Google Scholar] [Crossref]

23. Smart city deployment studies in Kerala traffic enforcement. (2023). Safe Kerala traffic camera initiative reduces violations. https://en.wikipedia.org/wiki/Kerala_Motor_Vehicles_Department [Google Scholar] [Crossref]

24. Stanford Justice Innovation Lab. (2023). User research report into AI for legal Q&A and access to justice. Stanford University. https://justiceinnovation.law.stanford.edu/projects/ai-access-to-justice/class-report/ [Google Scholar] [Crossref]

25. Voice-enabled legal assistant usability study. (2022). International Journal of Human–Computer Interaction. https://doi.org/10.1080/10447318.2022.XXXXX [Google Scholar] [Crossref]

26. Wicaksono, S. B., Hamdani, M., Yasar, A., & Li, L. (2025). Survey and empirical evaluation of AI models for traffic violation prediction. Transportation Research Procedia. https://doi.org/10.1016/j.trpro.2025.10.029 [Google Scholar] [Crossref]

27. Yuan, L., et al. (2024). LegalAsst: Human-centered AI for legal productivity and assistance. Information Sciences, 679, 121052. https://doi.org/10.1016/j.ins.2024.121052 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet