Lane sensing and path prediction for preventing vehicle road-departure accidents.
dc.contributor.author | Lin, Chiu-Feng | |
dc.contributor.advisor | Ulsoy, A. Galip | |
dc.date.accessioned | 2016-08-30T17:12:13Z | |
dc.date.available | 2016-08-30T17:12:13Z | |
dc.date.issued | 1995 | |
dc.identifier.uri | http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:9542893 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/129630 | |
dc.description.abstract | This dissertation focuses on the estimation of the Time to Lane Crossing (TLC), a metric to assess the lane tracking margin of a vehicle. Characterization of the TLC uncertainty is also studied. The result is used by a driver assistance system to prevent road-departure accidents. For TLC estimation, algorithms for down range road geometry perception and vehicle path prediction are also developed. Furthermore, uncertainties of the vehicle path prediction and road geometry perception are also studied such that the uncertainty of the TLC can be characterized. The TLC is obtained by first acquiring the intersection of the predicted vehicle path and the perceived road geometry and then estimating the time required for the vehicle to reach the intersection. The predicted vehicle path and the road geometry are expressed with polynomial equations. The uncertainty characterization for TLC estimation utilizes the uncertainty of the polynomial coefficients to assess the uncertainty of the acquired TLC. To acquire down range road geometry, a least square curve fit and two Kalman filter algorithms are developed. The uncertainty characterization for the acquired geometry is developed based on Kalman filtering theory. For the vehicle path prediction, a two degree of freedom vehicle model is used. Front wheel steering angle and vehicle yaw rate are assumed to be measured. The lateral vehicle velocity and external disturbances acting on the vehicle are estimated through an observer. Uncertainty characterization is associated with the equation for path projection; the measurement/estimation covariance for the vehicle dynamics and the front wheel steering angle are assumed. The results show that the developed algorithms are successful for assessing the TLC for typical highway driving. Results also show that accurate road geometry perception is more significant than accurate path prediction. However, an accurate path prediction is also necessary to obtain a satisfactory TLC. Preliminary simulations also show that TLC seems promising for an active safety system, which is yet to be verified in the future study. | |
dc.format.extent | 112 p. | |
dc.language | English | |
dc.language.iso | EN | |
dc.subject | Accidents | |
dc.subject | Departure | |
dc.subject | Lane | |
dc.subject | Path | |
dc.subject | Prediction | |
dc.subject | Preventing | |
dc.subject | Road | |
dc.subject | Sensing | |
dc.subject | Vehicle | |
dc.title | Lane sensing and path prediction for preventing vehicle road-departure accidents. | |
dc.type | Thesis | |
dc.description.thesisdegreename | PhD | en_US |
dc.description.thesisdegreediscipline | Applied Sciences | |
dc.description.thesisdegreediscipline | Automotive engineering | |
dc.description.thesisdegreediscipline | Mechanical engineering | |
dc.description.thesisdegreegrantor | University of Michigan, Horace H. Rackham School of Graduate Studies | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/129630/2/9542893.pdf | |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.