Ryan Herring

Virtual trip lines for distributed privacy-preserving traffic monitoring

Automotive traffic monitoring using probe vehicles with Global Positioning System receivers promises significant improvements in cost, coverage, and accuracy. Current approaches, however, raise privacy concerns because they require participants to reveal their positions to an external traffic monitoring server. To address this challenge, we propose a system based on virtual trip lines and an associated cloaking technique. Virtual trip lines are geographic markers that indicate where vehicles should provide location updates. These markers can be placed to avoid particularly privacy sensitive locations. They also allow aggregating and cloaking several location updates based on trip line identifiers, without knowing the actual geographic locations of these trip lines. Thus they facilitate the design of a distributed architecture, where no single entity has a complete knowledge of probe identities and fine-grained location information. We have implemented the system with GPS smartphone clients and conducted a controlled experiment with 20 phone-equipped drivers circling a highway segment. Results show that even with this low number of probe vehicles, travel time estimates can be provided with less than 15% error, and applying the cloaking techniques reduces travel time estimation accuracy by less than 5% compared to a standard periodic sampling approach.

Learning the Dynamics of Arterial Traffic From Probe Data Using a Dynamic Bayesian Network

Estimating and predicting traffic conditions in arterial networks using probe data has proven to be a substantial challenge. Sparse probe data represent the vast majority of the data available on arterial roads. This paper proposes a probabilistic modeling framework for estimating and predicting arterial travel-time distributions using sparsely observed probe vehicles. We introduce a model based on hydrodynamic traffic theory to learn the density of vehicles on arterial road segments, illustrating the distribution of delay within a road segment. The characterization of this distribution is essentially to use probe vehicles for traffic estimation: Probe vehicles report their location at random locations, and the travel times between location reports must be properly scaled to match the map discretization. A dynamic Bayesian network represents the spatiotemporal dependence on the network and provides a flexible framework to learn traffic dynamics from historical data and to perform real-time estimation with streaming data. The model is evaluated using data from a fleet of 500 probe vehicles in San Francisco, CA, which send Global Positioning System (GPS) data to our server every minute. The numerical experiments analyze the learning and estimation capabilities on a subnetwork with more than 800 links. The sampling rate of the probe vehicles does not provide detailed information about the location where vehicles encountered delay or the reason for any delay (i.e., signal delay, congestion delay, etc.). The model provides an increase in estimation accuracy of 35% when compared with a baseline approach to process probe-vehicle data.

Estimating arterial traffic conditions using sparse probe data

Estimating and predicting traffic conditions in arterial networks using probe data has proven to be a substantial challenge. In the United States, sparse probe data represents the vast majority of the data available on arterial roads in most major urban environments. This article proposes a probabilistic modeling framework for estimating and predicting arterial travel time distributions using sparsely observed probe vehicles. We evaluate our model using data from a fleet of 500 taxis in San Francisco, CA, which send GPS data to our server every minute. The sampling rate does not provide detailed information about where vehicles encountered delay or the reason for any delay (i.e. signal delay, congestion delay, etc.). Our model provides an increase in estimation accuracy of 35% when compared to a baseline approach for processing probe vehicle data.

Delay Pattern Estimation for Signalized Intersections Using Sampled Travel Times

Intersection delays are the major contributing factor to arterial delays. Methods to estimate intersection delay patterns by using measured travel times are studied. The delay patterns provide a way to estimate the delay for any vehicle arriving at the intersection at any time, which is useful for providing time-dependent intersection delay information to the driving public. The model requires sampled travel times between two consecutive locations on arterial streets, one upstream and the other downstream of a signalized intersection, without the need to know signal timing or traffic flow information. Signal phases can actually be estimated from the delay patterns, which is a unique feature of the proposed method in this paper. The proposed model is based on two observations regarding delays for signalized intersections: (a) delay can be approximately represented by piecewise linear curves due to the characteristics of queue forming and discharging and (b) there is a nontrivial increase in delay after the start of the red time that enables detection of the start of a cycle. A least-squares–based algorithm is developed to match measured delays in each cycle by using piecewise linear curves. The proposed model and algorithm are tested by using field experiment data with reasonable results.

Enhancing Privacy and Accuracy in Probe Vehicle-Based Traffic Monitoring via Virtual Trip Lines

Traffic monitoring using probe vehicles with GPS receivers promises significant improvements in cost, coverage, and accuracy over dedicated infrastructure systems. Current approaches, however, raise privacy concerns because they require participants to reveal their positions to an external traffic monitoring server. To address this challenge, we describe a system based on virtual trip lines and an associated cloaking technique, followed by another system design in which we relax the privacy requirements to maximize the accuracy of real-time traffic estimation. We introduce virtual trip lines which are geographic markers that indicate where vehicles should provide speed updates. These markers are placed to avoid specific privacy sensitive locations. They also allow aggregating and cloaking several location updates based on trip line identifiers, without knowing the actual geographic locations of these trip lines. Thus, they facilitate the design of a distributed architecture, in which no single entity has a complete knowledge of probe identities and fine-grained location information. We have implemented the system with GPS smartphone clients and conducted a controlled experiment with 100 phone-equipped drivers circling a highway segment, which was later extended into a year-long public deployment.

Optimal Sensor Placement for Freeway Travel Time Estimation

This article presents a modeling framework and a polynomial solution algorithm for determining optimal locations of point detectors used to compute freeway travel times. First, an objective function is introduced to minimize the deviation of estimated and actual travel times of all individual sub-segments of a freeway route. By discretizing the problem in both time and space, we formulate it as a dynamic programming model, which can be solved via a shortest path search in an acyclic graph. Numerical examples are provided to illustrate the model and algorithm using microscopic traffic simulation and GPS data from the Mobile Centuryexperiment recently conducted by the University of California, Berkeley, Nokia and California Department of Transportation (Caltrans).

Sequential Modeling Framework for Optimal Sensor Placement for Multiple Intelligent Transportation System Applications

Traffic sensors have been deployed for decades to freeways to meet the requirements of various traffic/transportation applications, most noticeably traffic control and traveler information applications. A unique feature of traffic sensor deployment is that it is a continuous and evolving process. That is, with new applications that emerge, additional sensors are usually required to be deployed to meet new requirements. This process is also sequential in nature and the new deployment has to consider existing sensors. In this paper, we propose a modeling framework to capture this sequential decision-making process for traffic sensor deployment. The framework is based on our recent findings that (1) optimal sensor deployment for a single application can be determined by a staged process or, more formally, a dynamic programming (DP) method and (2) new sensor locations for new applications can be optimally solved by the DP method via considering existing sensors. We illustrate the framework using two applicati...