Lei Kang PhD Preliminary Exam

Friday, December 2, 2016 - 9:30am
3310 CS

Speaker Name: 

Lei Kang

Speaker Institution: 

University of Wisconsin - Madison




Dissertation Title: Building Sensing and Control System Blocks for Modern Vehicles

Suman Banerjee (advisor)
Mohit Gupta
Soyoung Ahn


Vehicles are very important in our daily life, but they also cause many problems such as environment pollution, road congestion and fatalities. We propose building smart in-vehicle systems and smartphone enabled vehicular applications to provide various types of assistance to remedy these issues. Such systems sense and model vehicle dynamics from vehicle parameters and third party sensors, based on which they provide guidance and control to assist human drivers and achieve better driving performance. EcoDrive is one such system we built that conduct fuel consumption sensing and control to improve fuel efficiency and reduce carbon emissions.EcoDrive models instant fuel consumption based on vehicle parameters collected from On-board diagnostics (OBD) port. According to the model, it controls the gas pedal position sensor to adjust fuel injection rate according to road segment distance and speed limit. By using careful control of fuel injection rate, it is able to improve fuel efficiency comparing to human drivers. We also implemented a smartphone vehicular application, called DriveSense, that senses vehicle dynamics by built-in sensors and provide feedback to drivers on aggressive events to improve their driving safety awareness. Sensing vehicle dynamics by smartphone sensors require coordinate alignment between the smartphone and the car. We found that even gentle road slopes may cause severe coordinate misalignment and acceleration over/under estimation. To resolve these problems, we propose slope-aware coordinate alignment algorithm and linear acceleration estimation method to reduce alignment training time and improve linear acceleration estimation accuracy. Based on our past experiences on in-vehicle systems and driving behavior study, we propose two future work to further improve driving safety and efficiency by utilizing smartphone sensors. First, we propose to evaluate the performance of smartphone GPS and IMU sensors for capturing driving behaviors, and examine the benefits when combining GPS and IMU sensors. Second, we propose to combine smartphone cameras, GPS and IMU sensors to detect driver phone use.