Soberfolks: On-Demand Driver Allocation System for Safe Personal Vehicle Mobility
Authors
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune (India)
Article Information
DOI: 10.51584/IJRIAS.2026.110400014
Subject Category: Transportation
Volume/Issue: 11/4 | Page No: 190-198
Publication Timeline
Submitted: 2026-04-01
Accepted: 2026-04-06
Published: 2026-04-27
Abstract
Urban mobility platforms primarily focus on transporting passengers rather than enabling individuals to safely use their own vehicles when they are temporarily unable to drive due to impairment, fatigue, or medical constraints. This paper presents SoberFolks, an on-demand driver allocation system that dispatches verified drivers equipped with foldable electric scooters to operate users’ personal vehicles.
The system integrates geohash-based spatial indexing, Haversine distance computation, and a queue-based driver allocation strategy to minimize assignment latency while ensuring fairness and scalability. Implemented using a distributed client-server architecture with secure authentication and real-time tracking, the framework demonstrates improved driver discovery efficiency compared to naive proximity search approaches. The proposed model introduces a novel paradigm in urban mobility by combining micro-mobility logistics with ride assistance services.
Keywords
Spatial Indexing, Geohashing, Driver Allocation, Urban Mobility, Real-Time Tracking
Downloads
References
1. Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control. Available: https://www.ijcai.org/proceedings/2020/0609.pdf [Google Scholar] [Crossref]
2. Geohash Index Based Spatial Data Model for Corporate. Available: https://www.researchgate.net/publication/280964271_Geohash_Index_Based_Spatial_Data_Model_for_Corporate [Google Scholar] [Crossref]
3. Comparative Analysis of GeoHash, Google S2 and Uber H3 as Global Geographic Grid Coding Methods. Available: https://www.researchgate.net/publication/280964271_Geohash_Index_Based_Spatial_Data_Model_for_Corporate [Google Scholar] [Crossref]
4. J. Alonso-Mora, S. Samaranayake, A. Wallar, E. Frazzoli, and D. Rus,“On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment.”Proceedings of the National Academy of Sciences (PNAS), 2017.Available: https://www.pnas.org/doi/10.1073/pnas.1611675114 [Google Scholar] [Crossref]
5. Uber Engineering, “H3: Uber’s Hexagonal Hierarchical Spatial Index.” Uber Engineering Blog / Documentation. Available: https://eng.uber.com/h3/ [Google Scholar] [Crossref]
6. Google Developers, “Google Maps Platform – Directions API & Geocoding API Documentation.” Available: https://developers.google.com/maps/documentation [Google Scholar] [Crossref]