Abstract
dc:description.abstractWith growing compute and memory demands for state-of-the-art algorithms in the context of autonomous driving, there have been several research efforts to offload certain features to a digital twin hosted on a server through vehicle-to-cloud (V2C) technologies. However, most works provide a functioning implementation without considering the worst-case safety analysis of communication over an unreliable wireless medium. This work proposes the requirements and design, and implements an assisted parking system (APS) feature employing such a digital twin that works for perpendicular parking between two obstacles. Performance and functional requirements are elicited from ISO 16787, and a system-theoretic process analysis (STPA) is conducted to generate loss scenarios that can be used to generate future functional safety requirements. A design is proposed for a one-tenth scale system, and the perception, planning, controls, and vehicle parameter estimation subsystems are implemented and tested in software-in-loop (SIL) testing.
Degree
thesis:*- Department dc:contributor.department
- Computing and Software
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Samuel Michael Ramses Yasa Khzym
- Advisor dc:contributor.advisor
-
- Dr. Mark Lawford, Dr. Alan Wassyng
Subjects
dc:subject × 10Rights
dc:rights- Statement dc:rights
-
- Attribution 2.5 Canada
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Identifier URI
- https://doi.org/10.71548/25510