Ride-hailing Systems Research Articles

Simulation analysis of dual-end queuing ride-hailing system considering driver-side queue management

Ride-hailing services have transformed urban transportation through convenience yet introduced new complexities around efficiency and traffic management. This study investigates the dual-queuing problem in ride-hailing from the driver perspective using a multi-agent simulation approach. The focus is dissecting the dynamics between driver search times and passenger wait times, which critically influence operational efficiency especially during peak demand. Exploring these interactions aims to uncover insights that could improve service efficiency and customer satisfaction. Addressing such ride-hailing challenges is vital not just for individual providers but also for advancing sustainable mobility across rapidly growing metropolitan regions. Enhanced efficiency connects to broader urban development narratives around livability, accessibility, and responsible mobility ecosystems.

Gated ensemble of spatio-temporal mixture of experts for multi-task learning in ride-hailing system

Ride-hailing system requires efficient management of dynamic demand and supply to ensure optimal service delivery, pricing strategies, and operational efficiency. Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system poses a burden for the expanding transportation network companies. Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network (CRNN), convolutional neural network (CNN), and recurrent neural network (RNN) for simultaneously forecasting these spatio-temporal tasks in a city as well as across different cities. Furthermore, a task adaptation layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features utilized in prediction. The proposed architecture is tested with data from Didi Chuxing for: (i) simultaneously forecasting demand and supply-demand gap in Beijing, and (ii) simultaneously forecasting demand across Chengdu and Xian. In both scenarios, models from our proposed architecture outperformed the single-task and multi-task deep learning benchmarks and ensemble-based machine learning algorithms.

Investigating work-related distraction’s impact on male taxi driver safety: A hazard-based duration model

With the increasing use of phone-based ride-hailing apps, concerns have arisen regarding road safety and driver distraction. Despite the recognized safety risks of driver distraction, limited research has explored how distractions from various ride-hailing systems affect drivers in the taxi industry. To close this gap, the current research utilized a driving simulator experiment involving 51 male taxi drivers in two road environments (urban street and motorway) and three distracted driving conditions (no distraction, auditory distraction via radio dispatching system, and visual-manual distraction via mobile application). A car-following scenario with sudden brake events was incorporated into the experiments because this is a typical safety–critical situation where attention will determine the outcome. The collected performance indicators include brake reaction time, time headway, and car-following distance. The grouped random parameters Weibull accelerated failure time model was applied to model the duration data under different road conditions. The brake reaction time and time headway are dependent variables, while the car-following distance is a covariate in the models. The results indicate that although taxi drivers show longer brake reaction time when distracted by mobile app and radio system, this does not necessarily equate with greater risk or reduced safety since they compensate for the risk of rear-end crashes by maintaining a longer time headway. In general, taxi drivers’ brake reaction time and time headway are more profoundly affected by mobile apps when distracted in both urban and motorway scenarios. This highlights the elevated risks associated with such technologies. In addition, significant interaction effects revealed the observed heterogeneity, which suggests that drivers’ personal characteristics influence the relationship between distraction type and driving performance. This research provides valuable insights for designing safer ride-hailing operations and systems.

The Application of the Piecewise Linear Method for Non-Linear Programming Problems in Ride-Hailing Assignment Based on Service Level, Driver Workload, and Fuel Consumption

Ride-hailing services have grown rapidly, presenting challenges such as increased traffic congestion, inefficient driver workload distribution, and environmental concerns like higher fuel consumption and emissions. This study develops a non-linear ride-hailing assignment model addressing these issues by considering service level, driver workload, and fuel consumption. A piecewise linear method was employed to handle a non-linear programming model, and the method was modified to function autonomously without operator intervention. The model’s performance was evaluated using a publicly accessible dataset of taxi trips in Manhattan, focusing on indicators such as passenger waiting time, driver workload distribution, and fuel consumption. Numerical simulations demonstrated significant improvements: a 15% reduction in average passenger waiting time, a 20% improvement in balancing driver workloads, and a 10% decrease in overall fuel consumption, contributing to reduced emissions and environmental impact. The modified piecewise linear method proved effective in optimizing ride-hailing assignments, providing a more efficient and sustainable solution. The model also showed robustness in handling large datasets, ensuring scalability and applicability to various urban settings. These findings highlight the model’s potential to enhance operational efficiency and promote sustainability in ride-hailing services. By integrating considerations for service level, driver workload, and fuel consumption, the model offers a holistic approach to addressing the key challenges faced by the ride-hailing industry. This study provides valuable insights for future ride-hailing development and implementations of ride-hailing systems, promoting practices that are both efficient and environmentally friendly.

A hierarchical control framework for vehicle repositioning in ride-hailing systems

This paper introduces a multi-layer control strategy for efficiently repositioning empty ride-hailing vehicles, aiming to bridge the gap between proactive repositioning strategies and micro-management. The proposed framework consists of three layers: an upper-layer employing an aggregated model based on the Macroscopic Fundamental Diagram (MFD) and model predictive control (MPC) to determine optimal vehicle repositioning flows between each pair of regions, a middle-layer converting macroscopic decisions into dispatching commands for individual vehicles, and a lower-layer utilizing a coverage control algorithm for demand-aligned positioning guidance within regions. The upper-layer contributes to the proposed framework by providing a global (macroscopic) view and predictive capabilities including traffic and congestion features. The middle-layer contributes by ensuring and optimal assignment of repositioning vehicles, considering the decision from the upper- and lower- layers. Finally, the lower-layer contributes with operational details at the intersection or node level providing the precision required for microscopic vehicle guidance. Experimental validation using an agent-based simulator on a real network in Shenzhen confirms the effectiveness and efficiency of the framework in improving empty vehicle repositioning strategies for ride-hailing services in terms of average passenger waiting time and abandonment rates.

Mathematical Modeling on Integrated Vehicle Assignment and Rebalancing in Ride-hailing System with Uncertainty Using Fuzzy Linear Programming

The general public frequently uses taxis as local transportation to get from one location to another. Ride-hailing is an innovation in taxi services that lets customers use their smartphones to find drivers, find prices, and submit requests. The two parts of ride-hailing are vehicle assignment and rebalancing. The task of the assignment is to allocate resources as efficiently as possible to fulfil demand. Demand and supply in the area are brought into balance through the rebalancing process. The rebalancing step is frequently carried out independently of the assignment process in ride-hailing pickup systems. However, it can be integrated into a single optimization process to improve system performance. The linear programming approach can integrate assignment and rebalancing. The batch assignment is an assignment algorithm in which each supply and demand is collected within a specific time window. The assignment is done after the vehicles and requests are collected. Fuzzy linear programming is used to deal with environmental uncertainty. Uncertain demand can reduce the reliability of ride-hailing pickup systems in addressing the problem of allocating empty vehicles to areas of high demand. The pickup time may change over time due to traffic conditions. Assignment integration and rebalancing modelling with fuzzy parameters are carried out to obtain a ride-hailing pickup system model that can handle demand uncertainty, pickup travel time, and travel delay times and increase the ride-hailing effectiveness of the pickup system. Numerical simulations were carried out on the assignment and rebalancing integration model without and with uncertainty parameters—numerical simulations based on publicly available taxi travel request data. The model selection for the ride-hailing system can be determined based on the numerical simulation results. This research can potentially advance and expand knowledge, especially in transportation.

A queueing model of dynamic pricing and dispatch control for ride-hailing systems incorporating travel times

A queueing model of dynamic pricing and dispatch control for ride-hailing systems incorporating travel times

A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems

A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems

The stochastic share-a-ride problem with electric vehicles and customer priorities

We introduce a stochastic share-a-ride problem in which a fleet of electric vehicles (EV) in a ride-hailing system are dynamically dispatched to serve passenger and parcel orders in a shared manner. We assume uncertain demands of both passenger and parcel orders and consider that passenger orders have priority over parcel orders. Passengers must be transported directly from their origins to destinations, while parcels can share a vehicle with other orders. The operator of the ride-hailing platform needs to decide whether to accept a newly arrived service request, how to assign orders to vehicles, and how to route and charge the EVs. To develop dynamic policies for the problem, we formulate the problem as a Markov decision process (MDP) and propose a reinforcement learning (RL) approach to solve the problem. We develop action-space restriction and state-space aggregation schemes to facilitate the implementation of the RL algorithm. We also present two rolling horizon heuristic methods to develop dynamic policies for our problem. We conduct computational experiments based on real-world taxi data from New York City. The computational results show that our RL policies perform better than the three benchmark policies in terms of serving more orders and collecting more rewards. Our RL policies are able to make high-quality decisions more efficiently when compared with the rolling horizon policies.

The Sequential Pricing of Ride-Hailing System with Rental Service in the Context of Fleet Electrification

The Sequential Pricing of Ride-Hailing System with Rental Service in the Context of Fleet Electrification

Scalable reinforcement learning approaches for dynamic pricing in ride-hailing systems

Dynamic pricing is a widely applied strategy by ride-hailing companies, such as Uber and Lyft, to match the trip demand with the availability of drivers. Deciding proper pricing policies is challenging and existing reinforcement learning (RL)-based solutions are restricted in solving small-scale problems. In this study, we contribute to RL-based approaches that can address the dynamic pricing problem in real-world-scale ride-hailing systems. We first characterize the dynamic pricing problem with a clear distinction between historical prices and current prices. We then translate our dynamic pricing problem into Markov Decision Process (MDP) and prove the existence of a deterministic stationary optimal policy. Our solutions are based on an off-policy reinforcement learning algorithm called twin-delayed deep determinant policy gradient (TD3) that performs offline learning of the optimal pricing policy using historical data and applies the learned policy to the next time slot, e.g., one week. We enhance TD3 by creating three mechanisms to reduce our model complexity and enhance training effectiveness. Extensive numerical experiments are conducted on both small grid networks (16 zones) and the NYC network (242 zones) to demonstrate the performance of the proposed algorithm. The results show our algorithm can efficiently find the optimal pricing policy for both the small and large networks, and can significantly enhance the platform profit and service efficiency.

An three-in-one on-demand ride-hailing prediction model based on multi-agent reinforcement learning

The ride-hailing behaviors of customers are often impacted by various factors including time, geographic distance between locations and weather conditions, causing imbalance between the supply and demand of on-demand ride-hailing dispatch. An effective on-demand ride-hailing dispatching management approach can dispatch idle vehicles and utilize traffic resources more reasonably, increase drivers’ income, and improve customers’ satisfaction and experience. In order to overcome the disadvantages in on-demand ride-hailing systems, we propose a three-in-one multi-agent reinforcement learning based online algorithm for ride-hailing demand prediction, called ERPM, which can achieve intelligent prediction in an effective and efficient fashion. ERPM tackles the problem that the training phase of traditional reinforcement learning models is difficult to converge due to the high dimensions of input and output data after partitioning the areas that provide platform services into grids, and uses the Actor–Critic strategy to perform on-demand ride-hailing dispatching actions, which are evaluated and optimized to intelligently predict the demand of ride-hailing in the grid areas. In addition, ERPM achieves intelligent parameter update by applying newly designed loss function, learning rate and optimization algorithm, and design an accurate on-demand ride-hailing prediction algorithm on the basis of maximizing the GMV (gross merchandise volume), i.e., the revenues of all on-demand ride-hailing orders served. Compared with traditional machine learning models, the proposed ERPM model is proved to be capable of capturing more complex features of supply and demand from the high dimensions to obtain higher prediction accuracy. Empirical studies are performed on the real Didi Chuxing data, by evaluating the results from extensive experiments, it can be observed that ERPM achieves the highest accuracy of demand prediction on daily GMV and a higher order response rate than the commonly-used famous methods, i.e., for GMV, ERPM outperforms DQN by 9.7% and the Naive model by 14.8%, for the order response rate of ERPM is 1.4% and 4.1% higher than that of DQN and Naive, MAPE (Mean Absolute Percentage Error) of DQN and Naive is 1.61 and 5.94 times higher than that of ERPM, and R2 of ERPM is improved by 8.70% and 64.8% when compared to that of DQN and Naive, respectively.

On the benefits of ex-post pricing for ride-pooling

Today’s digital ride-hailing systems experienced significant growth. In this context, ride-pooling promises more sustainable on-demand transportation by allowing customers with similar transportation requests to share a ride and, accordingly, a more efficient use of resources. In practice, mobility service providers that allow for ride-pooling offer customers an ex-ante fixed price regardless of whether the customers eventually share their rides. This can lead to lost profits for providers or to customers only participating in pooling because they gamble on a cheaper solitary ride, while an eventual pooling might decrease their utility. We study the implementation of an ex-post pricing (EPP) scheme for ride-pooling that accounts for individual customers’ pooling benefits. Within this mechanism, customers receive a maximum price-to-pay information up-front, which may decrease in the event of a profitable pooling. We study the benefit of this mechanism from a customer, fleet operator, and system perspective, and compare it to the existing ex-ante pricing (EAP) mechanism. We prove that it is individually rational and weakly dominant for a customer to participate in a pooling service with EPP, but not for a mechanism with EAP. We substantiate this analysis with complementary numerical studies, implementing a simulation environment based on real-world data that allows us to assess both mechanisms’ benefits. Our results allow to analyze the difference between EAP and EPP pricing from a holistic perspective, and thus to provide decision support for mobility service operators. We analyze in which cases an EPP mechanism Pareto dominates an EAP mechanism and show that an EPP mechanism is preferable from a mobility service provider perspective. Moreover, we show that EPP mechanisms can lead to a win-win situation for operators and customers while improving system performance and reducing emissions up to 32% compared to not pooling customers.

MDN-Enabled SO for Vehicle Proactive Guidance in Ride-Hailing Systems: Minimizing Travel Distance and Wait Time

MDN-Enabled SO for Vehicle Proactive Guidance in Ride-Hailing Systems: Minimizing Travel Distance and Wait Time

Real-Time Coordinated Operation of Power and Autonomous Electric Ride-Hailing Systems

Integration of self-driving functions in electric vehicles is radically changing the transportation systems, and representing an opportunity for power utilities to develop innovative solutions for harnessing the spatio-temporal charging flexibility of autonomous electric vehicles (AEVs). This paper develops a multi-agent reinforcement learning model for intelligent real-time coordinated operation of interdependent autonomous electric ride-hailing system (AERS) and power distribution system (PDS), which enables the coordinated routing and charging of AEVs while ensuring the quality of service by meeting spatio-temporal passenger demand and regularly charging the batteries. The proposed model adopts a modified deep Q-network method with multi-agent rollout to determine the near-optimal solution for the coordinated operation problem that determines the routing and charging of numerous AEVs in real-time. The proposed model is tested on a 13-node transportation network, adopted from the Salt Lake City transportation system, and the IEEE 33-bus test power distribution system to showcase the efficiency of the proposed model in determining the real-time routing and charging decisions for AEVs while meeting the operational constraints of both AERS and PDS.

Online ride-hailing regulation: a simulation study based on evolutionary game theory

ABSTRACT Game theory contributes to the quantitative study of online ride-hailing regulations; however, prior game models of the online ride-hailing market fail to comprehensively consider government regulation strategies as well as multiple stakeholders in various regulation contexts. This study constructs two system dynamic models of evolutionary games among online ride-hailing platforms, drivers, and passengers. One is the basic model not subject to government regulations, while the other considers government regulations systematically regarding penalty policy, incentive policy, policy adaptability, and public participation. By solving and simulating the model, we study evolutionary stable strategies to control fluctuations in the game process. The results show that an unregulated online ride-hailing system is volatile, and government regulations help stabilize the system. The effect of government regulations can be optimized by adopting a dynamic penalty with a greater initial force, considering platforms as agents in incentive policy, improving policy adaptability, and rewarding public participation.

Can Ride-Hailing Platforms be Immune to Dual-Fairness Concerns?

The rapid development of ride-hailing platforms has a substantial impact on urban transportation ecosystems, which raises the issue of fairness concerns both vertically and horizontally. To investigate the effects of dual-fairness concerns on the ride-hailing platform, this article studies a taxi and ride-hailing system, which captures the vertical interactions between the ride-hailing platform and the ride-hailing driver with vertical fairness concern, and the horizontal competition between the ride-hailing driver and the taxi driver with horizontal fairness concern. Two incentive strategies (i.e., revenue and demand sharing strategy and ride-hailing fare subsidy strategy) for the ride-hailing platform are designed to relieve the negative impact of fairness concerns. Government’s regulation on taxi fare is also discussed in this article. By analyzing the dynamic game models that involve these stakeholders, we find that: 1) both the vertical and the horizontal fairness concerns will lower the utility of the ride-hailing platform; 2) the revenue and demand sharing strategy and the ride-hailing fare subsidy strategy can enhance the utility of the ride-hailing platform by relieving the negative impact of horizontal and vertical fairness concerns, respectively; and 3) with the government’s regulation on taxi fare, the negative impact of dual-fairness concerns can be relieved, and a higher social welfare can be achieved.

Smart Transportation Behavior through the COVID-19 Pandemic: A Ride-Hailing System in Iran

During the COVID-19 pandemic, significant changes occurred in customer behavior, especially in traffic and urban transmission systems. In this context, there is a need for more scientific research and managerial approaches to develop behavior-based smart transportation solutions to deal with recent changes in customers, drivers, and traffic behaviors, including the volume of traffic and traffic routes. This research has tried to find a comprehensive view of novel travel behavior in different routes using a new social network analysis method. Our research is rooted in graph theory/network analysis and application of centrality concepts in social network analysis, particularly in the ride-hailing transportation systems under monumental competition. In this study, a big city, with near to ten million habitants (Tehran), is considered. All city areas were studied and clustered based on the primary measures of centrality, including degree centrality, Katz centrality, special vector centrality, page rank centrality, proximity centrality, and intermediate centrality. Our data were the trips of this system in Tehran, where the nodes in this network represent Tehran’s districts, and the connection between the two districts indicates the trips made between those two districts. Also, each link’s weight is the number of trips between the two nodes (district). The districts of Tehran were ranked in the smart transportation network based on six criteria: degree centrality, degree centrality of input, degree centrality of output, special vector centrality, hub, and reference points. Finally, according to comprehensive data-driven analysis, the studied company was suggested to create shared value and sustainability through the platform to perform a legitimate system to meet the new challenges. Our proposed system can help managers and governments to develop a behavior-based smart transportation system for big cities.

Reinforcement Learning from Optimization Proxy for Ride-Hailing Vehicle Relocation

Idle vehicle relocation is crucial for addressing demand-supply imbalance that frequently arises in the ride-hailing system. Current mainstream methodologies - optimization and reinforcement learning - suffer from obvious computational drawbacks. Optimization models need to be solved in real-time and often trade off model fidelity (hence quality of solutions) for computational efficiency. Reinforcement learning is expensive to train and often struggles to achieve coordination among a large fleet. This paper designs a hybrid approach that leverages the strengths of the two while overcoming their drawbacks. Specifically, it trains an optimization proxy, i.e., a machine-learning model that approximates an optimization model, and then refines the proxy with reinforcement learning. This Reinforcement Learning from Optimization Proxy (RLOP) approach is computationally efficient to train and deploy, and achieves better results than RL or optimization alone. Numerical experiments on the New York City dataset show that the RLOP approach reduces both the relocation costs and computation time significantly compared to the optimization model, while pure reinforcement learning fails to converge due to computational complexity.

HMDRL: Hierarchical Mixed Deep Reinforcement Learning to Balance Vehicle Supply and Demand

The imbalance of vehicle supply and demand is a common phenomenon that influences the efficiency of online ride-hailing systems greatly. To address this problem, a three-level hierarchical mixed deep reinforcement learning method (HMDRL) is proposed to reposition idle vehicles. A manager operates at the top level, where action-abstraction is conducted from the time dimension and is adaptive for spatially scalable and time-varying systems. Coordinators locate at the middle level and a parallel coordination mechanism that is independent of the decision order is designed to improve the efficiency of the repositioning. The bottom level is composed of executive workers to reposition vehicles with mixed states and the states contain spatiotemporal information of agents’ neighbor areas. Two reward functions are designed for the manager and the coordinators, respectively, aiming to improve the training effect by avoiding sparse rewards. A simulator based on real orders is designed and HMDRL is compared with six methods. Experimental results demonstrate that HMDRL outperforms all the other methods. In three comparison experiments, the order response rate is increased by 0.62% to 8.29%, 1.5% to 7.78%, 1.18% to 4.75%, respectively.