Student Seminar Series
DATE: Wednesday October 19, 2016, 12:00pm
LOCATION: MSB 1147 (Colloquium Room).
SPEAKERS: Rex Cheung, Dept Statistics UC Davis
TITLE: “Detecting and Predicting Driving State with Driver Behavior Data”
ABSTRACT: Predicting driving behavior is an important component for developing safer and more reliable driver assistance systems. Modern technologies such as the Google Self-Driving Car and the Mobileye system are good examples on using sensors or cameras to detect road conditions and send out instructions to the cars and drivers when potential dangers are about to occur. However, these technologies can be less reliable when driving in extreme weather conditions, such as heavy rain or darkness at night. They can be expensive to implement as well. Thus many researchers in the engineering field have attempted to analyze driver behavior to predict what will happen next. This project proposes the use of driver behavior data to predict the possibility of an upcoming traffic accident, i.e. what is the next driving state.
A driving state usually consists of a few different levels, examples including safe and unsafe, turning left and right, going straight or turning, etc. The solution to building this algorithm will be done in two stages: first, we will build a detection algorithm that can detect the driving state given the current driving data. Then we will build a prediction algorithm that can predict the future driving states given the current states and driving behavior. The novelty of this work lies in the usage of a multi-class semi-supervised classifier as the detection algorithm, as well as the prediction algorithm itself. This is an ongoing work in collaboration with Professor Kazushi Ikeda and Professor Takatomi Kubo from Nara Institute of Science and Technology.
This seminar series is organized by PhD Students Irene Kim and Clark Fitzgerald.