Search Results

Cooperative vehicle safety can help prevent vehicle collisions by providing timely warnings to the driver or initiating automatic preventive actions based on vehicle dynamics information exchanged between vehicles. The information is shared wirelessly through the emerging DSRC (Dedicated Short Range Communication) standards. The vehicle dynamics information that is shared, such as vehicle velocity and location, is collected from the vehicle's internal sensor communication network and from Global Navigation Satellite Systems (GNSS), which includes the Global Positioning System (GPS). GNSS is a critical component of this safety system since it has the needed ability to accurately determine a vehicle's location coordinates in most driving environments. However, its performance can suffer from obstructions in dense urban areas. Deficiencies of GNSS can be overcome by complimenting GNSS with other sensors.

Unmanned aerial vehicles (UAVs) stand to play a significant role in future sensing and information gathering missions. The scope of these mission scenarios is expanding to include those missions for which the sensor and carrier vehicle will be in close proximity to the surrounding environment, such as in urban operations. Several unique problems related to guidance, navigation and control are introduced that separate these tasks from the existing paradigm for information gathering missions at standoff range. This paper examines the challenges related to autonomous sensor planning missions in these close proximity environments and discusses solution strategies to achieve maximal sensing effectiveness. Specifically, results from vision-based navigation research are discussed and the concept of a geometric sensing effectiveness criterion is introduced and subsequently utilized for motion planning.

The goal of this project was to investigate how to make driver distraction state classification more efficient by applying selected machine learning techniques to existing datasets. The data set used in this project included both overt driver behavior measures (e.g., lane keeping and headway measures) and indices of internal cognitive processes (e.g., driver situation awareness responses) collected under four distraction conditions, including no-distraction, visual-manual distraction only, cognitive distraction only, and dual distraction conditions. The baseline classification method that we employed was a support vector machine (SVM) to first identify driver states of visual-manual distraction and then to identify any cognitive-related distraction among the visual-manual distraction cases and other non-visual manual distraction cases.