A Markov Model for Driver Turn Prediction

SAE technical papers on CD-ROM/SAE technical paper seriesPublished 14 April 2008

John Krumm

DOI10.4271/2008-01-0195

Source URL

Citations155

SJR score0.23

SNIP0.41

TL;DR

An algorithm for making short-term route predictions for vehicle drivers using a simple Markov model to make probabilistic predictions by looking at a driver’s just-driven path is described.

Abstract

<div class="htmlview paragraph">This paper describes an algorithm for making short-term route predictions for vehicle drivers. It uses a simple Markov model to make probabilistic predictions by looking at a driver's just-driven path. The model is trained from the driver's long term trip history from GPS data. We envision applications including driver warnings, anticipatory information delivery, and various automatic vehicle behaviors. The algorithm is based on discrete road segments, whose average length is 237.5 meters. In one instantiation, the algorithm can predict the next road segment with 90% accuracy. We explore variations of the algorithm and find one that is both simple and accurate.</div>

Keywords

Social SciencesEngineeringComputer Science

Lecture notes in computer scienceInferring High-Level Behavior from Low-Level Sensors

517 Citations2003Donald J. Patterson, Lin Liao +2 more

A method of learning a Bayesian model of a traveler moving through an urban environment that simultaneously learns a unified model of the traveler’s current mode of transportation as well as his most likely route, in an unsupervised manner is presented.

Lecture notes in computer sciencePredestination: Inferring Destinations from Partial Trajectories

454 Citations2006John Krumm, Eric Horvitz

A method called Predestination is described that uses a history of a driver's destinations, along with data about driving behaviors, to predict where a driver is going as a trip progresses, to produce a probabilistic map of destinations.

Medical Entomology and ZoologyRandom Signals: Detection Estimation and Data Analysis

434 Citations1988K. Sam Shanmugan, A.M. Breipohl

Review of Probability and Random Variables Random Processes and Sequences Response of Systems to Random Inputs Special Classes of Random Processs Signal Detection Linear Minimum MSE Filtering Statistics Estimating Parameters of Random processes from Data.

SAE technical papers on CD-ROM/SAE technical paper seriesRoute Prediction from Trip Observations

232 Citations2008Jon E. Froehlich, John Krumm

This paper develops and tests algorithms for predicting the end-to-end route of a vehicle based on GPS observations of the vehicle’s past trips using a large corpus of real world GPS driving data acquired from observing over 250 drivers for an average of 15.1 days each.

Learning to Predict Driver Route and Destination Intent

193 Citations2006Reid Simmons, B. Browning +2 more

A novel approach to predicting driver intent that exploits the predictable nature of everyday driving and high performance suggests that the method can be harnessed for improved safety monitoring, route planning taking into account traffic density, and better trip duration prediction.

Vehicle route prediction and time of arrival estimation techniques for improved transportation system management

86 Citations2004A. Karbassi, Matthew Barth

A route prediction and time-of-arrival estimation methodology that has been implemented with a real-world multiple-station car-sharing system and it was determined that the estimation procedure could be improved if the frequency of position/time data was increased.

SAE technical papers on CD-ROM/SAE technical paper seriesMap Matching with Travel Time Constraints

84 Citations2007John Krumm, Eric Horvitz +1 more

A new algorithm is introduced that finds a sequence of road segments which simultaneously match the measured locations and which are traversable in the time intervals associated with the measurements.

SAE technical papers on CD-ROM/SAE technical paper seriesReal Time Destination Prediction Based On Efficient Routes

75 Citations2006John Krumm

This paper presents a novel method for predicting the location of a driver’s destination during the drive based on the common intuition that drivers tend to chose efficient routes, and quantifies this preference for efficiency probabilistically based on a database of driving trips gathered with GPS receivers.