Demand-aware route planning for shared mobility services

Wang, Jiachuan; Cheng, Peiyao; Zheng, Libin; Feng, Chao; Chen, Lei; Lin, Xuemin; Wang, Zheng

doi:10.14778/3384345.3384348

Cited by 41 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…that it might pick up when transporting the original request; similar ideas are proposed by Wang et al (2020), but assigning several requests at a time.…”

Section: Rebalancing and Predictive Methodsmentioning

confidence: 99%

Anticipatory routing methods for an on-demand ridepooling mobility system

2021

View full text Add to dashboard Cite

On-demand mobility systems in which passengers use the same vehicle simultaneously are a promising transport mode, yet difficult to control. One of the most relevant challenges relates to the spatial imbalances of the demand, which induce a mismatch between the position of the vehicles and the origins of the emerging requests. Most ridepooling models face this problem through rebalancing methods only, i.e., moving idle vehicles towards areas with high rejections rate, which is done independently from routing and vehicle-to-orders assignments, so that vehicles serving passengers (a large portion of the total fleet) remain unaffected. This paper introduces two types of techniques for anticipatory routing that affect how vehicles are assigned to users and how to route vehicles to serve such users, so that the whole operation of the system is modified to reach more efficient states for future requests. Both techniques do not require any assumption or exogenous knowledge about the future demand, as they depend only on current and recent requests. Firstly, we introduce rewards that reduce the cost of an assignment between a vehicle and a group of passengers if the vehicle gets routed towards a high-demand zone. Secondly, we include a small set of artificial requests, whose request times are in the near future and whose origins are sampled from a probability distribution that mimics observed generation rates. These artificial requests are to be assigned together with the real requests. We propose, formally discuss and experimentally evaluate several formulations for both approaches. We test these techniques in combination with a state-of-the-art trip-vehicle assignment method, using a set of real rides from Manhattan. Introducing rewards can diminish the rejection rate to about nine-tenths of its original value. On the other hand, including future requests can reduce users’ traveling times by about one-fifth, but increasing rejections. Both methods increase the vehicles-hour-traveled by about 10%. Spatial analysis reveals that vehicles are indeed moved towards the most demanded areas, such that the reduction in rejections rate is achieved mostly there.

show abstract

“…that it might pick up when transporting the original request; similar ideas are proposed by Wang et al (2020), but assigning several requests at a time.…”

Section: Rebalancing and Predictive Methodsmentioning

confidence: 99%

Anticipatory routing methods for an on-demand ridepooling mobility system

2021

View full text Add to dashboard Cite

show abstract

“…Intelligent Transportation System (ITS) for societal improvements [ 1 , 5 , 10 , 14 , 19 ] has emerged in various sectors with a proliferation in topics such as shared mobility [ 13 , 21 ], secured ITS, efficient vehicle utilization [ 27 ], and so forth. Officials and government agencies of several countries, including developing countries, have shown a keen interest in promoting the shared mobility practices in smart cities due to the associated economic and environmental benefits.…”

Section: Related Workmentioning

confidence: 99%

Shared Mobility Intelligence Using Permissioned Blockchains for Smart Cities

Benedict

2022

New Gener. Comput.

View full text Add to dashboard Cite

Suggesting tourists/residents about the pollution-free locations and controlling the number of passengers in a shareable vehicle have become crucial tasks to smart city officials as they plummet health issues such as asthma or COVID-19. Recently, city authorities, transport logistic designers, and policymakers have tasked researchers/entrepreneurs to innovate in shared mobility systems. This paper proposes a Blockchain-Enabled Shared Mobility (BESM) architecture that allocates seats to residents/tourists in a shareable vehicle based on air quality and COVID-19 information of traveling locations. BESM involves smart city authorities, vehicle owners, hospital authorities, and residents using permissioned-blockchains to collaboratively decide on allocating travel seats. Experiments were carried out at the IoT Cloud research laboratory to manifest the allocation of seats. For instance, BESM excluded in allocating seats to asthma patients and limited the number of travelers in the cities where COVID-19 cases or pollution levels were higher in numbers using BESM. The pollution levels of cities were monitored using air quality monitoring sensors or predicted using a few prediction algorithms such as Random Forests (RF), Linear Regression (LR), Quantile Regression (QR), Ridge Regression (RR), Lasso Regression (LaR), ElasticNet Regression (ER), Support Vector Machine (SVM), and Recursive Partitioning (RP). In succinct, the article unfolded the primordial importance of the proposed BESM architecture for promoting efficient shared mobility aspects in smart cities.

show abstract

“…Recently, many spatiotemporal prediction models are proposed to predict the number of events (e.g., online car-hailing requests [1], [2], [3], or street crimes [4], [5]) within a region (e.g., a gird of 1km×1km) in a period (e.g., next 30 minutes) [6], [7], [8]. With the help of predicted information of events, we can improve the platform revenue of online car-hailing systems (e.g., Uber [9]), or reduce crimes effectively through optimizing patrol route of police [5].…”

Section: Introductionmentioning

confidence: 99%

“…One common assumption of spatiotemporal prediction models is that the distribution of spatial events within a region is uniform [1], [6], [2], which is in fact almost never true in real scenarios. In addition, the selection of region size is mostly decided by experts' experience or simple experimental tests without detailed analysis in many existing research studies:…”

Section: Introductionmentioning

confidence: 99%

“…• "We use 20×30 = 600 grids to cover the cities and one grid represents a 0.01 (longitude)×0.01 (latitude) square" [1] • The authors use 32×32 grids to cover Beijing area and 16×8 grids for New York City area [6]. • "For the prediction model, DeepST, we set the default grid size as 2km×2km ..." [2] Under the uniform region assumption, the spatiotemporal prediction models are optimized to minimize the model error in model grids (i.e., the difference between the predicted and actual number of spatial events in grids used in the prediction model), which may lead to dramatic real errors in some smaller regions (i.e., the difference between the predicted and the actual number of spatial events in smaller and homogeneous grids). Then, the overall performance of frameworks utilizing spatiotemporal prediction models will not be optimized for real applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models [Technical Report]

Jin¹,

Cheng²,

Chen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

With the development of traffic prediction technology, spatiotemporal prediction models have attracted more and more attention from academia communities and industry. However, most existing researches focus on reducing model's prediction error but ignore the error caused by the uneven distribution of spatial events within a region. In this paper, we study a region partitioning problem, namely optimal grid size selection problem (OGSS), which aims to minimize the real error of spatiotemporal prediction models by selecting the optimal grid size. In order to solve OGSS, we analyze the upper bound of real error of spatiotemporal prediction models and minimize the real error by minimizing its upper bound. Through in-depth analysis, we find that the upper bound of real error will decrease then increase when the number of model grids increase from 1 to the maximum allowed value. Then, we propose two algorithms, namely Ternary Search and Iterative Method, to automatically find the optimal grid size. Finally, the experiments verify that the error of prediction has the same trend as its upper bound, and the change trend of the upper bound of real error with respect to the increase of the number of model grids will decrease then increase. Meanwhile, in a case study, by selecting the optimal grid size, the order dispatching results of a state-of-the-art predictionbased algorithm can be improved up to 13.6%, which shows the effectiveness of our methods on tuning the region partition for spatiotemporal prediction models.

show abstract

Demand-aware route planning for shared mobility services

Cited by 41 publications

References 30 publications

Anticipatory routing methods for an on-demand ridepooling mobility system

Anticipatory routing methods for an on-demand ridepooling mobility system

Shared Mobility Intelligence Using Permissioned Blockchains for Smart Cities

GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models [Technical Report]

Contact Info

Product

Resources

About