A Distributed Model-Free Ride-Sharing Approach for Joint Matching, Pricing, and Dispatching Using Deep Reinforcement Learning

Significant development of ride-sharing services presents a plethora of opportunities to transform urban mobility by providing personalized and convenient transportation while ensuring the efficiency of large-scale ride pooling. However, a core problem for such services is route planning for each driver to fulfill the dynamically arriving requests while satisfying given constraints. Current models are mostly limited to static routes with only two rides per vehicle (optimally) or three (with heuristics) (Alonso-Mora et al. , 2017), at least in the initial allocation while not ascertaining that opposite-direction rides are not grouped together. In this paper, we present a dynamic, demand aware, and pricing-based vehicle-passenger matching and route planning framework that (1) dynamically generates optimal routes for each vehicle based on online demand, pricing associated with each ride, vehicle capacities and locations. This matching algorithm starts greedily and optimizes over time using an insertion operation, (2) involves drivers in the decision-making process by allowing them to propose a different price based on the expected reward for a particular ride as well as the destination locations for future rides, which is influenced by supply-and-demand computed by the Deep Q-network. (3) allows customers to accept or reject rides based on their set of preferences with respect to pricing and delay windows, vehicle type and carpooling preferences. These (1-3) in tandem with each other enforce grouping rides with the most route-intersections together. (4) Based on demand prediction, our approach re-balances idle vehicles by dispatching them to the areas of anticipated high demand using deep Reinforcement Learning (RL). Our framework is validated using millions of trips extracted from the New York City Taxi public dataset; however, we consider different vehicle types and designed customer utility functions to validate the setup and study different settings. Experimental results show the effectiveness of our approach in real-time and large scale settings.