Towards Quality Aware Crowdsourced Road Sensing for Smart Cities
With nearly a billion automobiles on the road today, the current transportation systems have begun to show signs of serious strain, such as congestions, traffic accidents, road surface defects, and malfunctioning traffic regulation infrastructures. Therefore, it is of great importance to collect and disseminate road/traffic condition information accurately, efficiently, and timely. Traditionally, road and traffic monitoring are conducted through either stationary sensors or instrumented probe vehicles. Unfortunately, the prohibitively high deployment cost of such devices makes it impossible to achieve large-scale deployment, leading to limited road coverage and delayed information update. To mitigate these problems, this project develops QuicRoad, a Quality of Information (QoI) aware crowdsourced road sensing system that can collect road/traffic information from a variety of sources, including smartphones, social media and transportation authorities (as well as future connected vehicles), and then distribute the collected information in real time. The PIs team up with local transportation agencies in the Buffalo-Niagara region on applications related to road surface and traffic condition monitoring, border crossing delay estimation, and incident management.
This project integrates across both social and technological research dimensions. In the technological dimension, it leads to a novel Quality of Information (QoI) aware information integration framework that can jointly optimize the estimation of the QoI of various sources, and the information-integration as well as decision-making process. In the social dimension, it answers fundamental questions such as whether and to what degree the road/traffic condition information provided by the proposed QuicRoad system would change the social behavior of the travelers. By seamlessly integrating the technological and social dimensions, the proposed research can not only improve the coverage and quality of assisted driving and road navigation services for travelers, but also support policy-making in traffic planning and operations by transportation authorities. The research will potentially benefit a wide spectrum of real-world road sensing applications aimed at improving road safety, mitigating traffic congestions, and reducing fuel consumption and emissions, and eventually contribute to building a sustainable society.
-
Performance PeriodSeptember 2017 - August 2022
-
SUNY at Buffalo
-
Award Number1737590
-
Lead PIChunming Qiao
-
Co-PIAlex Anas
-
Co-PILu Su
-
Co-PIAdel Sadek
Project Material
- Joint Charging and Relocation Recommendation for E-Taxi Drivers via Multi-Agent Mean Field Hierarchical Reinforcement Learning
- Towards the Inference of Travel Purpose with Heterogeneous Urban Data
- MetaTP: Traffic Prediction with Unevenly-Distributed Road Sensing Data via Fast Adaptation
- Driver Behavior-aware Parking Availability Crowdsensing System Using Truth Discovery
- Heterogeneous Spatio-Temporal Graph Convolution Network for Traffic Forecasting with Missing Values
- Estimation of Road Transverse Slope Using Crowd-Sourced Data from Smartphones
- Road Grade Estimation Using Crowd-Sourced Smartphone Data
- A Reliability-Aware Vehicular Crowdsensing System for Pothole Profiling
- Instantaneous Fuel Consumption Estimation Using Smartphones
- Thanos: Incentive Mechanism with Quality Awareness for Mobile Crowd Sensing
- Forecasting current and next trip purpose with social media data and Google Places
- A deep learning approach for detecting traffic accidents from social media data
- TextTruth: An Unsupervised Approach to Discover Trustworthy Information from Multi-Sourced Text Data
- Online Truth Discovery on Time Series Data
- Travel purpose inference with GPS trajectories, POIs, and geo-tagged social media data
- VehSense: Slippery Road Detection Using Smartphones
- City-wide Traffic Volume Inference with Loop Detector Data and Taxi Trajectories
Chunming Qiao is a SUNY Distinguished Professor and Chair of the CSE Department. He has lead the Lab for Advanced Network Design, Evaluation and Research (LANDR) at UB since 1993. His current research interests cover not only the safety and reliability of various cyber physical systems (such as transportation systems with connected and autonomous vehicles, critical infrastructures involving power grid and communications networks, and cloud services), but also algorithms and protocols for Internet of Things, including smartphone based systems and applications. He has published extensively with an h-index of over 69 (according to Google Scholar). Several of his papers have received the best paper awards from IEEE and Joint ACM/IEEE venues. He also has 7 US patents and served as a consultant for several IT and Telecommunications companies since 2000. His research has been featured in BusinessWeek, Wireless Europe, CBC and New Scientists. He was elected to IEEE Fellow for his contributions to optical and wireless network architectures and protocols.