Bayesian Nonparametric Modeling of Driver Behavior using HDP Split-Merge Sampling Algorithm

TL;DR

This paper presents a Bayesian nonparametric approach using HDP split-merge sampling to model driver behavior from vehicle sensor data, enabling personalized destination and road condition predictions.

Contribution

It introduces a novel hierarchical topic modeling framework combined with HDP split-merge sampling for analyzing driver-specific road network behaviors.

Findings

Effective modeling of driver behavior using GPS and car signals.

Ability to predict destinations and road conditions based on learned models.

Demonstrates the sparsity of individual road networks can inform predictions.

Abstract

Modern vehicles are equipped with increasingly complex sensors. These sensors generate large volumes of data that provide opportunities for modeling and analysis. Here, we are interested in exploiting this data to learn aspects of behaviors and the road network associated with individual drivers. Our dataset is collected on a standard vehicle used to commute to work and for personal trips. A Hidden Markov Model (HMM) trained on the GPS position and orientation data is utilized to compress the large amount of position information into a small amount of road segment states. Each state has a set of observations, i.e. car signals, associated with it that are quantized and modeled as draws from a Hierarchical Dirichlet Process (HDP). The inference for the topic distributions is carried out using HDP split-merge sampling algorithm. The topic distributions over joint quantized car signals characterize the driving situation in the respective road state. In a novel manner, we demonstrate how the sparsity of the personal road network of a driver in conjunction with a hierarchical topic model allows data driven predictions about destinations as well as likely road conditions.