Matching Items (2)
154964-Thumbnail Image.png
Description
Traditional methods for detecting the status of traffic lights used in autonomous vehicles may be susceptible to errors, which is troublesome in a safety-critical environment. In the case of vision-based recognition methods, failures may arise due to disturbances in the environment such as occluded views or poor lighting conditions. Some

Traditional methods for detecting the status of traffic lights used in autonomous vehicles may be susceptible to errors, which is troublesome in a safety-critical environment. In the case of vision-based recognition methods, failures may arise due to disturbances in the environment such as occluded views or poor lighting conditions. Some methods also depend on high-precision meta-data which is not always available. This thesis proposes a complementary detection approach based on an entirely new source of information: the movement patterns of other nearby vehicles. This approach is robust to traditional sources of error, and may serve as a viable supplemental detection method. Several different classification models are presented for inferring traffic light status based on these patterns. Their performance is evaluated over real-world and simulation data sets, resulting in up to 97% accuracy in each set.
ContributorsCampbell, Joseph (Author) / Fainekos, Georgios (Thesis advisor) / Ben Amor, Heni (Committee member) / Artemiadis, Panagiotis (Committee member) / Arizona State University (Publisher)
Created2016
155142-Thumbnail Image.png
Description
ABSTRACT

This study examines the methodology for converting protected, permissive, and protected/permissive left-turn operation to flashing yellow arrow left-turn operation. This study addresses construction-related considerations, including negative offsets, lateral traffic signal head position, left-turn accident rates, crash modification factors and crash reductions factors. A total of 85 intersections in Glendale, Arizona

ABSTRACT

This study examines the methodology for converting protected, permissive, and protected/permissive left-turn operation to flashing yellow arrow left-turn operation. This study addresses construction-related considerations, including negative offsets, lateral traffic signal head position, left-turn accident rates, crash modification factors and crash reductions factors. A total of 85 intersections in Glendale, Arizona were chosen for this study. These intersections included 45 “arterial to arterial” intersections (a major road intersecting with a major road) and 40 “arterial to collector” intersections (a major road intersecting with a minor road).

This thesis is a clinical study of the field conversion to flashing yellow arrow traffic signals and is not a study of the merits of flashing yellow arrow operation. This study included six categories: 1. High accident intersections (for inclusion in Highway Safety Improvement Program (HSIP) funding); 2. Signal head modifications only; 3. Signal head replacement with median modifications; 4. Signal head and mast arm replacement; 5. Signal head, signal pole and mast arm replacement; and 6. Intersections where flashing yellow arrow operation is not recommended. Compliance with the Manual on Uniform Traffic Control Devices (MUTCD) played a large part in determining conversion costs because the standard for lateral position of the left-turn traffic signal greatly influenced the construction effort. Additionally, the left-turning vehicle’s sight distance factored into cost considerations. It’s important for agencies to utilize this study to understand all of the financial commitments and construction requirements for conversion to flashing yellow arrow operation, and ultimately to appreciate that the process is not purely a matter of swapping traffic signal heads.
ContributorsChambers, Susan Elizabeth (Author) / Kaloush, Kamil (Thesis advisor) / Mamlouk, Michael (Thesis advisor) / Hartig, Daniel (Committee member) / Lou, Yingyan (Committee member) / Arizona State University (Publisher)
Created2016