Bayesian Nonparametric Modeling of Driver Behavior using HDP Split-Merge Sampling Algorithm
This work addresses driver behavior modeling for automotive applications, but it is incremental as it combines existing methods like HMM and HDP with a specific sampling algorithm.
The paper tackled the problem of modeling driver behavior from sensor data by using a Hidden Markov Model to compress GPS data into road segment states and a Hierarchical Dirichlet Process to characterize driving situations, enabling predictions about destinations and road conditions.
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.