2019/10/30 by Ashutosh Singh, Singh, Ashutosh, Abubakr O. Al-Abbasi +3 · 3 citations
Business, Management and Accounting · Engineering · Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Sharing Economy and Platforms #Systems and Control (eess.SY) #Transportation Planning and Optimization #Transportation and Mobility Innovations #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1910.14002
openalex publication_date 2019/10/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The growth of autonomous vehicles, ridesharing systems, and self driving\ntechnology will bring a shift in the way ride hailing platforms plan out their\nservices. However, these advances in technology coupled with road congestion,\nenvironmental concerns, fuel usage, vehicles emissions, and the high cost of\nthe vehicle usage have brought more attention to better utilize the use of\nvehicles and their capacities. In this paper, we propose a novel multi-hop\nride-sharing (MHRS) algorithm that uses deep reinforcement learning to learn\noptimal vehicle dispatch and matching decisions by interacting with the\nexternal environment. By allowing customers to transfer between vehicles, i.e.,\nride with one vehicle for sometime and then transfer to another one, MHRS helps\nin attaining 30 % lower cost and 20 % more efficient utilization of fleets, as\ncompared to the ride-sharing algorithms. This flexibility of multi-hop feature\ngives a seamless experience to customers and ride-sharing companies, and thus\nimproves ride-sharing services.\n