SafePath AI – AI-Powered Safety Navigation System
Author
Arun Kumar S, Arjun Chokkalingam K, Arunkumar C, Darshan JB, Dharshan K, E. Subramanian
Abstract
Conventional navigation applications optimise travel time and distance and give limited support to travellers who also want to weigh personal-safety information. This paper describes SafePath AI, a full-stack web prototype that combines news-derived crime incident data, road-network route alternatives, emergency-facility discovery and live proximity alerts in one interface. The frontend uses React and Vite; the backend uses Node.js and Express with MongoDB and an in-memory fallback. A scheduled pipeline reads RSS feeds of Indian news publishers, filters crime-related items with keyword rules, locates them with a hand-built gazetteer, merges duplicates and applies a rolling ten-day eligibility rule. Candidate routes from the OpenStreetMap-based OSRM service are ranked by a transparent weighted score that combines time-decayed incident and historical-crime proximity with distance and with proxy terms for lighting, traffic and crowding. The system contains no trained machine-learning model; “AI” here means rule-based decision support. The backend automated test suite of 99 tests passed, but no accuracy, latency or user-study results are reported and some data sources are sample data. SafePath AI supports decisions only and cannot guarantee the safety of any route.
Keywords
SafePath AI; safety-aware navigation; crime news analysis; route risk assessment; emergency services; OpenStreetMap; decision support
Full Text:
References
Barrington-Leigh, C., & Millard-Ball, A. (2017). The world’s user-generated road map is more than 80% complete. PLoS ONE, 12(8), e0180698. https://doi.org/10.1371/journal.pone.0180698
Chainey, S., Tompson, L., & Uhlig, S. (2008). The utility of hotspot mapping for predicting spatial patterns of crime. Security Journal, 21(1–2), 4–28. https://doi.org/10.1057/palgrave.sj.8350066
Galbrun, E., Pelechrinis, K., & Terzi, E. (2016). Urban navigation beyond shortest route: The case of safe paths. Information Systems, 57, 160–171. https://doi.org/10.1016/j.is.2015.10.005
Luxen, D., & Vetter, C. (2011). Real-time routing with OpenStreetMap data. In Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 513–516). ACM. https://doi.org/10.1145/2093973.2094062
Shah, S., Bao, F., Lu, C.-T., & Chen, I.-R. (2011). CrowdSafe: Crowd sourcing of crime incidents and safe routing on mobile devices. In Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 521–524). ACM. https://doi.org/10.1145/2093973.2094064