Deep-learning-based data-driven forecasting methods have achieved impressive results for traffic forecasting. Specifically, spatiotemporal graph neural networks have emerged as a promising class of approaches because of their ability to model both spatial and temporal patterns in traffic data. A major limitation of these methods, however, is that they provide forecasts without estimates of data and model uncertainty, which are critical for understanding inherent variations of the data and forecast limitations due to a lack of training data. We develop a scalable deep ensemble approach to...
Traffic simulations are often used by city planners as a basis for predicting the impact of policies, plans, and operations. The complexities underpinning traffic simulations are often not described in detail yet can significantly impact the simulation outcome. Conflating underlying data for simulations is complex and hinders the interest in this type of exploration. This paper aims to elucidate critical features of traffic simulations that drive the generated metrics of the modeled urban environment. Specifically, this paper examines differences in two road graph networks for the...
Miguel Street is a winding, narrow route through the Glen Park neighborhood of San Francisco. Until a few years ago, only those living along the road traveled it, and they understood its challenges well. Now it's packed with cars that use it as a shortcut from congested Mission Street to heavily traveled Market Street. Residents must struggle to get to their homes, and accidents are a daily occurrence. The problem began when smartphone apps like Waze, Apple Maps, and Google Maps came into widespread use, offering drivers real-time routing around traffic tie-ups. An estimated 1 billion...
Using the data from loop detector sensors for near-real-time detection of traffic incidents on highways is crucial to averting major traffic congestion. While recent supervised machine learning methods offer solutions to incident detection by leveraging human-labeled incident data, the false alarm rate is often too high to be used in practice. Specifically, the inconsistency in the human labeling of the incidents significantly affects the performance of supervised learning models. To that end, we focus on a data-centric approach to improve the accuracy and reduce the false alarm rate of...
Traffic signals play an important role in transportation by enabling traffic flow management, and ensuring safety at intersections. In addition, knowing the traffic signal phase and timing data can allow optimal vehicle routing for time and energy efficiency, eco-driving, and the accurate simulation of signalized road networks. In this paper, we present a machine learning (ML) method for estimating traffic signal timing information from vehicle probe data. To the authors best knowledge, very few works have presented ML techniques for determining traffic signal timing parameters from...
This paper explores the addressable market for Urban Air Mobility (UAM) as a multi-modal alternative in a community. To justify public investment, UAM must serve urban mobility by carrying a significant portion of urban traffic. We develop a traffic demand analysis method to estimate the maximum number of people that can benefit from UAM, for a given use case, in a metropolitan region. We apply our method to about three hundred thousand cross-bay commute trips in the San Francisco Bay Area. We estimate the commuter demand shift to UAM under two criteria of flexibility to travel time...
Drone space is defined according to a building model and a buffer space. At least one three-dimensional geometry is identified from the building model. The buffer space is calculated from the three-dimensional geometry. Coordinates for a drone air space are defined based on the buffer space. At least one path segment may be identified based on the coordinates for the drone air space, and the coordinates for drone air space are stored in a map database in association with the at least one path segment.
Traffic forecasting is an important issue in intelligent traffic systems (ITS). Graph neural networks (GNNs) are effective deep learning models to capture the complex spatio-temporal dependency of traffic data, achieving ideal prediction performance. In this paper, we propose attention-based graph neural ODE (ASTGODE) that explicitly learns the dynamics of the traffic system, which makes the prediction of our machine learning model more explainable. Our model aggregates traffic patterns of different periods and has satisfactory performance on two real-world traffic data sets. The results...
