An official website of the United States government
Urban public transit planning is crucial in reducing traffic congestion and enabling green transportation. However, there is no systematic way to integrate passengers' personal preferences in planning public transit routes and schedules so as to achieve high occupancy rates and efficiency gain of ride-sharing. In this paper, we take the first step tp exact passengers' preferences in planning from history public transit data. We propose a data-driven method to construct a Markov decision process model that characterizes the process of passengers making sequential public transit choices, in bus routes, subway lines, and transfer stops/stations. Using the model, we integrate softmax policy iteration into maximum entropy inverse reinforcement learning to infer the passenger's reward function from observed trajectory data. The inferred reward function will enable an urban planner to predict passengers' route planning decisions given some proposed transit plans, for example, opening a new bus route or subway line. Finally, we demonstrate the correctness and accuracy of our modeling and inference methods in a large-scale (three months) passenger-level public transit trajectory data from Shenzhen, China. Our method contributes to smart transportation design and human-centric urban planning.
more »
« less
Dynamic Integration of Heterogeneous Transportation Modes Under Disruptive Events
An integrated urban transportation system usually consists of multiple transport modes that have complementary characteristics of capacities, speeds, and costs, facilitating smooth passenger transfers according to planned schedules. However, such an integration is not designed to operate under disruptive events, e.g., a signal failure at a subway station or a breakdown of a bus, which have rippling effects on passenger demand and significantly increase delays. To address these disruptive events, current solutions mainly rely on a substitute service to transport passengers from and to affected areas using adhoc schedules. To fully utilize heterogeneous transportation systems under disruptive events, we design a service called eRoute based on a hierarchical receding horizon control framework to automatically reroute, reschedule, and reallocate multi-mode transportation systems based on real-time and predicted demand and supply. Focusing on an integration of subway and bus, we implement and evaluate eRoute with large datasets including (i) a bus system with 13,000 buses, (ii) a subway system with 127 subway stations, (iii) an automatic fare collection system with a total of 16,840 readers and 8 million card users from a metropolitan city. The data-driven evaluation results show that our solution improves the ratio of served passengers (RSP) by up to 11.5 times and reduces the average traveling time by up to 82.1% compared with existing solutions.
more »
« less
- Award ID(s):
- 1521722
- PAR ID:
- 10059942
- Date Published:
- Journal Name:
- ACM/IEEE International Conference on Cyber-Physical Systems
- ISSN:
- 2375-8317
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)In this paper we advocate a forward-looking, ambitious and disruptive smart cloud commuting system (SCCS) for future smart cities based on shared AVs. Employing giant pools of AVs of varying sizes, SCCS seeks to supplant and integrate various modes of transport in a unified, on-demand fashion, and provides passengers with a fast, convenient, and low cost transport service for their daily commuting needs. To explore feasibility and efficiency gains of the proposed SCCS, we model SCCS as a queueing system with passengers' trip demands (as jobs) being served by the AVs (as servers). Using a 1-year real trip dataset from Shenzhen China, we quantify (i) how design choices, such as the numbers of depots and AVs, affect the passenger waiting time and vehicle utilization; and (ii) how much efficiency gains (i.e., reducing the number of service vehicles, and improving the vehicle utilization) can be obtained by SCCS comparing to the current taxi system. Our results demonstrate that the proposed SCCS system can serve the trip demands with 22% fewer vehicles and 37% more vehicle utilization, which shed lights on the design feasibility of future smart transportation system.more » « less
-
Urban anomalies have a large impact on passengers' travel behavior and city infrastructures, which can cause uncertainty on travel time estimation. Understanding the impact of urban anomalies on travel time is of great value for various applications such as urban planning, human mobility studies and navigation systems. Most existing studies on travel time have been focused on the total riding time between two locations on an individual transportation modality. However, passengers often take different modes of transportation, e.g., taxis, subways, buses or private vehicles, and a significant portion of the travel time is spent in the uncertain waiting. In this paper, we study the fine-grained travel time patterns in multiple transportation systems under the impact of urban anomalies. Specifically, (i) we investigate implicit components, including waiting and riding time, in multiple transportation systems; (ii) we measure the impact of real-world anomalies on travel time components; (iii) we design a learning-based model for travel time component prediction with anomalies. Different from existing studies, we implement and evaluate our measurement framework on multiple data sources including four city-scale transportation systems, which are (i) a 14-thousand taxicab network, (ii) a 13-thousand bus network, (iii) a 10-thousand private vehicle network, and (iv) an automatic fare collection system for a public transit network (i.e., subway and bus) with 5 million smart cards.more » « less
-
The ability to accurately predict public transit ridership demand benefits passengers and transit agencies. Agencies will be able to reallocate buses to handle under or over-utilized bus routes, improving resource utilization, and passengers will be able to adjust and plan their schedules to avoid overcrowded buses and maintain a certain level of comfort. However, accurately predicting occupancy is a non-trivial task. Various reasons such as heterogeneity, evolving ridership patterns, exogenous events like weather, and other stochastic variables, make the task much more challenging. With the progress of big data, transit authorities now have access to real-time passenger occupancy information for their vehicles. The amount of data generated is staggering. While there is no shortage in data, it must still be cleaned, processed, augmented, and merged before any useful information can be generated. In this paper, we propose the use and fusion of data from multiple sources, cleaned, processed, and merged together, for use in training machine learning models to predict transit ridership. We use data that spans a 2-year period (2020-2022) incorporating transit, weather, traffic, and calendar data. The resulting data, which equates to 17 million observations, is used to train separate models for the trip and stop level prediction. We evaluate our approach on real-world transit data provided by the public transit agency of Nashville, TN. We demonstrate that the trip level model based on Xgboost and the stop level model based on LSTM outperform the baseline statistical model across the entire transit service day.more » « less
-
Rapid urbanization has posed significant burden on urban transportation infrastructures. In today's cities, both private and public transits have clear limitations to fulfill passengers' needs for quality of experience (QoE): Public transits operate along fixed routes with long wait time and total transit time; Private transits, such as taxis, private shuttles and ride-hailing services, provide point-to-point transits with high trip fare. In this paper, we propose CityLines, a transformative urban transit system, employing hybrid hub-and-spoke transit model with shared shuttles. Analogous to Airlines services, the proposed CityLines system routes urban trips among spokes through a few hubs or direct paths, with travel time as short as private transits and fare as low as public transits. CityLines allows both point-to-point connection to improve the passenger QoE, and hub-and-spoke connection to reduce the system operation cost. To evaluate the performance of CityLines, we conduct extensive data-driven experiments using one-month real-world trip demand data (from taxis, buses and subway trains) collected from Shenzhen, China. The results demonstrate that CityLines reduces 12.5%-44% average travel time, and aggregates 8.5%-32.6% more trips with ride-sharing over other implementation baselines.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
