Automotive safety validation in simulation
Abstract/Contents
- Abstract
- Fully automated driving will require intelligent systems capable of understanding, reacting to, and interacting with the intricate complexities of the real world. With the onset of autonomous driving it becomes increasingly necessary to develop advanced tools for establishing trust in intelligent safety systems that act without or despite human input. This thesis presents novel contributions to simulation-based validation, including human driver behavior and sensor models, distributions over driving scenes, and a new technique for the accelerated validation of advanced automotive active safety systems such as autonomous vehicles. Advances to human driver behavior models include the introduction of behavioral cloning models based on Bayesian networks that better capture driver behavior over short horizons. A general input architecture for deep sensor models is introduced and used to develop a stochastic model over an automotive radar's power field. Original contributions are made to the representation of distributions over driving scenes and situations, which must capture a variable number of traffic participants on arbitrary roadways. Finally, this thesis introduces a new method for accelerated validation using importance sampling over clusters of critical situations, prioritizing simulation of critical scenes and avoiding countless simulations of benign driving scenarios while backing out the correct performance statistics.
Description
Type of resource | text |
---|---|
Form | electronic; electronic resource; remote |
Extent | 1 online resource. |
Publication date | 2018 |
Issuance | monographic |
Language | English |
Creators/Contributors
Associated with | Wheeler, Tim Allan | |
---|---|---|
Associated with | Stanford University, Department of Aeronautics and Astronautics. | |
Primary advisor | Kochenderfer, Mykel J, 1980- | |
Thesis advisor | Kochenderfer, Mykel J, 1980- | |
Thesis advisor | Ermon, Stefano | |
Thesis advisor | Pavone, Marco, 1980- | |
Advisor | Ermon, Stefano | |
Advisor | Pavone, Marco, 1980- |
Subjects
Genre | Theses |
---|
Bibliographic information
Statement of responsibility | Tim Allan Wheeler. |
---|---|
Note | Submitted to the Department of Aeronautics and Astronautics. |
Thesis | Thesis (Ph.D.)--Stanford University, 2018. |
Location | electronic resource |
Access conditions
- Copyright
- © 2018 by Tim Allan Wheeler
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...