Matching Items (2)
Filtering by
- All Subjects: Bicycle
- Creators: Kuby, Mike
- Creators: Ren, Yi
Description
Bicyclist and pedestrian safety is a growing concern in San Francisco, CA,
especially given the increasing numbers of residents choosing to bike and walk. Sharing
the roads with automobiles, these alternative road users are particularly vulnerable to
sustain serious injuries. With this in mind, it is important to identify the factors that
influence the severity of bicyclist and pedestrian injuries in automobile collisions. This
study uses traffic collision data gathered from California Highway Patrol’s Statewide
Integrated Traffic Records System (SWITRS) to predict the most important
determinants of injury severity, given that a collision has occurred. Multivariate binomial
logistic regression models were created for both pedestrian and bicyclist collisions, with
bicyclist/pedestrian/driver characteristics and built environment characteristics used as
the independent variables. Results suggest that bicycle infrastructure is not an important
predictor of bicyclist injury severity, but instead bicyclist age, race, sobriety, and speed
played significant roles. Pedestrian injuries were influenced by pedestrian and driver age
and sobriety, crosswalk use, speed limit, and the type of vehicle at fault in the collision.
Understanding these key determinants that lead to severe and fatal injuries can help
local communities implement appropriate safety measures for their most susceptible
road users.
especially given the increasing numbers of residents choosing to bike and walk. Sharing
the roads with automobiles, these alternative road users are particularly vulnerable to
sustain serious injuries. With this in mind, it is important to identify the factors that
influence the severity of bicyclist and pedestrian injuries in automobile collisions. This
study uses traffic collision data gathered from California Highway Patrol’s Statewide
Integrated Traffic Records System (SWITRS) to predict the most important
determinants of injury severity, given that a collision has occurred. Multivariate binomial
logistic regression models were created for both pedestrian and bicyclist collisions, with
bicyclist/pedestrian/driver characteristics and built environment characteristics used as
the independent variables. Results suggest that bicycle infrastructure is not an important
predictor of bicyclist injury severity, but instead bicyclist age, race, sobriety, and speed
played significant roles. Pedestrian injuries were influenced by pedestrian and driver age
and sobriety, crosswalk use, speed limit, and the type of vehicle at fault in the collision.
Understanding these key determinants that lead to severe and fatal injuries can help
local communities implement appropriate safety measures for their most susceptible
road users.
ContributorsMcIntyre, Andrew (Author) / Salon, Deborah (Thesis advisor) / Kuby, Mike (Committee member) / Chester, Mikhail (Committee member) / Arizona State University (Publisher)
Created2016
Description
Bicycle stabilization has become a popular topic because of its complex dynamic behavior and the large body of bicycle modeling research. Riding a bicycle requires accurately performing several tasks, such as balancing and navigation which may be difficult for disabled people. Their problems could be partially reduced by providing steering assistance. For stabilization of these highly maneuverable and efficient machines, many control techniques have been applied – achieving interesting results, but with some limitations which includes strict environmental requirements. This thesis expands on the work of Randlov and Alstrom, using reinforcement learning for bicycle self-stabilization with robotic steering. This thesis applies the deep deterministic policy gradient algorithm, which can handle continuous action spaces which is not possible for Q-learning technique. The research involved algorithm training on virtual environments followed by simulations to assess its results. Furthermore, hardware testing was also conducted on Arizona State University’s RISE lab Smart bicycle platform for testing its self-balancing performance. Detailed analysis of the bicycle trial runs are presented. Validation of testing was done by plotting the real-time states and actions collected during the outdoor testing which included the roll angle of bicycle. Further improvements in regard to model training and hardware testing are also presented.
ContributorsTurakhia, Shubham (Author) / Zhang, Wenlong (Thesis advisor) / Yong, Sze Zheng (Committee member) / Ren, Yi (Committee member) / Arizona State University (Publisher)
Created2020