An architecture for integrated decision-making, motion planning, and control of automated vehicles
Abstract/Contents
- Abstract
- Automated vehicles have immense potential to improve the safety of our roadways. In order to handle the complex task of driving, they need the ability to make decisions regarding other road users, plan a trajectory, and control the vehicle, responding online to an evolving environment. For model-based control, it is important to use models that capture the full range of the vehicle's dynamics. We develop a tire model that is computationally tractable and useful in scenarios ranging from a stop-and-go maneuver to driving at the limits of road-tire friction. A model-based steering controller successfully demonstrates the efficacy of this tire model even when the vehicle is sliding on low-friction surfaces. In addition to being able to control the vehicle, an AV architecture must also be able to make discrete decisions regarding obstacles in the environment. Ultimately, these decisions are carried out by a controller commanding steering and longitudinal inputs, which motivates building a system that makes decisions based on the capabilities of the underlying controller. Our novel architecture partitions the drivable space into discrete options, solves a nonlinear optimization in each option in parallel, and then picks the solution that best satisfies high-level objectives such as safety and efficiency. Finally, frameworks for automated vehicles need to be designed with human values in mind. Safety is a top priority and is codified in legal texts as duty of due care. By leveraging the architecture described above to realize these human values, the vehicle drives safely and comfortably in an overtaking maneuver with oncoming traffic.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2022; ©2022 |
Publication date | 2022; 2022 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Patterson, Vivian Zhang |
---|---|
Degree supervisor | Gerdes, J. Christian |
Thesis advisor | Gerdes, J. Christian |
Thesis advisor | Kochenderfer, Mykel J, 1980- |
Thesis advisor | Sadigh, Dorsa |
Degree committee member | Kochenderfer, Mykel J, 1980- |
Degree committee member | Sadigh, Dorsa |
Associated with | Stanford University, Department of Mechanical Engineering |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Vivian Zhang Patterson. |
---|---|
Note | Submitted to the Department of Mechanical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2022. |
Location | https://purl.stanford.edu/qp353vv8718 |
Access conditions
- Copyright
- © 2022 by Vivian Zhang Patterson
- 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...