PROJECT TITLE :

A Distributed Model-Free Algorithm for Multi-hop Ride-sharing using Deep Reinforcement Learning

ABSTRACT:

The proliferation of self-driving technology, ridesharing platforms, and autonomous vehicles will bring about a change in the way that ride hailing platforms plan out their respective service offerings. However, these technological advancements, along with increased traffic on the roads, environmental concerns, fuel consumption, emissions from vehicles, and the high cost of using vehicles, have brought more attention to the need for more efficient use of vehicles and the capacities they possess. In this paper, we propose a novel distributed multi-hop ride-sharing (MHRS) algorithm that makes use of deep reinforcement learning to learn optimal vehicle dispatch and matching decisions by interacting with the external environment. MHRS is an abbreviation for multi-hop ride-sharing, which stands for multi-hop ride-sharing system. MHRS helps achieve 30% lower costs and 20% more efficient utilization of fleets when compared to ride-sharing algorithms because it enables customers to transfer between vehicles. This means that customers can ride with one vehicle for a period of time and then transfer to another vehicle. Customers and ride-sharing companies benefit from a seamless experience thanks to the adaptability of the multi-hop feature, which also leads to an improvement in ride-sharing services.