An Efficient Ride-Sharing Framework for Maximizing Shared Route

Ta, Na; Li, Guoliang; Zhao, Tianyu; Feng, Jianhua; Ma, Hanchao; Gong, Zhiguo

doi:10.1109/tkde.2017.2760880

Cited by 82 publications

(36 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static Ridesharing Problem. Ta et al [12] defined two kinds of ridesharing models to maximize the shared route ratio, under the assumption that at most one rider can be assigned to a driver in the vehicle. Cheng et al [15] proposed a utility-aware ridesharing problem, which can be regarded as a variant of the dial-a-ride problem [28], [29].…”

Section: Related Workmentioning

confidence: 99%

“…(2) Prior studies [10], [12], [13], [14], [15], [16] primarily focus on single objective optimization solutions, such as minimizing the total travel distance from the perspective of drivers [13], [14], or maximizing the served rate of ridesharing system [16]. In contrast, we aim to optimize two objectives: maximize the served rate and minimize the total additional distance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Ridesharing in Peak Travel Periods

Luo

Bao

Choudhury

et al. 2021

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

In this paper, we propose and study a variant of the dynamic ridesharing problem with a specific focus on peak hours: Given a set of drivers and a set of rider requests, we aim to match drivers to each rider request by achieving two objectives: maximizing the served rate and minimizing the total additional distance, subject to a series of spatio-temporal constraints. Our problem can be distinguished from existing ridesharing solutions in three aspects: (1) Previous work did not fully explore the impact of peak travel periods where the number of rider requests is much greater than the number of available drivers. (2) Existing ridesharing solutions usually rely on single objective optimization techniques, such as minimizing the total travel cost (either distance or time). (3) When evaluating the overall system performance, the runtime spent on updating drivers' trip schedules as per newly coming rider requests should be incorporated, while it is unfortunately excluded by most existing solutions. In order to achieve our goal, we propose an underlying index structure on top of a partitioned road network, and compute the lower bounds of the shortest path distance between any two vertices. Using the proposed index together with a set of new pruning rules, we develop an efficient algorithm to dynamically include new riders directly into an existing trip schedule of a driver. In order to respond to new rider requests more effectively, we propose two algorithms that bilaterally match drivers with rider requests. Finally, we perform extensive experiments on a large-scale test collection to validate the effectiveness and efficiency of the proposed methods.Index Terms-Dynamic ridesharing, peak hour, index structure, pruning rules ! • H. Luo, Z. Bao (corresponding author) and J. Culpepper are with the

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic Ridesharing in Peak Travel Periods

Luo

Bao

Choudhury

et al. 2021

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…Results show that carpooling can decrease average payment of passenger, increase income of driver, and improve passenger capacity. In [28] vehicles and ride requests are treated as nodes of a bigraph, then a maximum weighted matching is computed to manage the vehicles and requests. By utilizing the extensive cellular coverage and the high accuracy in position/velocity measurements provided by GPS devices, a traffic monitoring system based on GPS-enabled smartphones is proposed in [29].…”

Section: Related Workmentioning

confidence: 99%

DeepPool: Distributed Model-Free Algorithm for Ride-Sharing Using Deep Reinforcement Learning

Al-Abbasi

Ghosh

Aggarwal

2019

IEEE Trans. Intell. Transport. Syst.

123

View full text Add to dashboard Cite

The success of modern ride-sharing platforms crucially depends on the profit of the ride-sharing fleet operating companies, and how efficiently the resources are managed. Further, ride-sharing allows sharing costs and, hence, reduces the congestion and emission by making better use of vehicle capacities. In this work, we develop a distributed model-free, DeepPool, that uses deep Q-network (DQN) techniques to learn optimal dispatch policies by interacting with the environment. Further, DeepPool efficiently incorporates travel demand statistics and deep learning models to manage dispatching vehicles for improved ride sharing services. Using real-world dataset of taxi trip records in New York City, DeepPool performs better than other strategies, proposed in the literature, that do not consider ride sharing or do not dispatch the vehicles to regions where the future demand is anticipated. Finally, DeepPool can adapt rapidly to dynamic environments since it is implemented in a distributed manner in which each vehicle solves its own DQN individually without coordination.

show abstract

“…It might also be possible to consider more sophisticated crowdsourcing strategies with the goal to minimize the social cost while at the same time ensuring a minimum compensation for the driver. For example, in the context of ride-sharing for passengers, [55] provides a method to select a driver to maximize the overall shared route percentage (SRP) subject to a minimum required value of this parameter for each driver (expectation rate of the driver). This technique could be applied to locate vehicles that, even if they are not at that moment within communication range, could pick up the mobile agent and carry it to the intended destination.…”

Section: Related Work On Spatial Crowdsourcing and Crowdsensingmentioning

confidence: 99%

Spatial crowdsourcing with mobile agents in vehicular networks

Urra

Ilarri

2019

Vehicular Communications

View full text Add to dashboard Cite

In the last years, the automotive industry has shown interest in the addition of computing and communication devices to cars, thanks to technological advances in these fields, in order to meet the increasing demand of "connected" applications and services. Although vehicular ad hoc networks (VANETs) have not been fully developed yet, they could be used in a near future as a means to provide a number of interesting applications and services that need the exchange of data among vehicles and other data sources. In this paper, we propose a spatial crowdsourcing schema for the opportunistic collection of information within an interest area in a city or region (e.g., measures about the environment, such as the concentration of certain gases in the atmosphere, or information such as the availability of parking spaces in an area), using vehicular ad hoc communications. We present a method that exploits mobile agent technology to accomplish the distributed collection and querying of data among vehicles in such a scenario. Our proposal is supported by an extensive set of realistic simulations that prove the feasibility of the approach.

show abstract

An Efficient Ride-Sharing Framework for Maximizing Shared Route

Cited by 82 publications

References 31 publications

Dynamic Ridesharing in Peak Travel Periods

Dynamic Ridesharing in Peak Travel Periods

DeepPool: Distributed Model-Free Algorithm for Ride-Sharing Using Deep Reinforcement Learning

Spatial crowdsourcing with mobile agents in vehicular networks

Contact Info

Product

Resources

About