Date of Award
Master of Science (MS)
As intelligent transportation becomes increasingly prevalent in the domain of transportation, it is essential to understand the safety, reliability, and performance of these systems. We investigate two primary areas in the problem domain. The first area concerns increasing the feasibility and reducing the cost of deploying pedestrian detection systems to intersections in order to increase safety. By allowing pedestrian detection to be placed in intersections, the data can be better utilized to create systems to prevent accidents from occurring. By employing a dynamic compression scheme for pedestrian detection, we show the reduction of network bandwidth improved by 2.12× over the baseline case. The second area of investigation regards the performance of autonomous vehicle and platooning models in the presence of stale data. We utilize Sobol sensitivity analysis and a fault injection scheme to characterize the behavior of our test model when stale data is present. The Sobol method proves effective in determining which inputs are the most important to the outputs of the model and the fault injection provides insight into the behavior and convergence of the error introduced by the stale data. The combination of these works seeks to improve the safety and reliability of the intelligent transportation domain
Holt, Cavender, "Improving Intelligent Transportation Safety and Reliability Through Lowering Costs, Integrating Machine Learning, and Studying Model Sensitivity" (2022). All Theses. 3818.