Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/24995
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Haykin, Simon | - |
dc.contributor.author | Feng, Shuo | - |
dc.date.accessioned | 2019-10-07T14:31:58Z | - |
dc.date.available | 2019-10-07T14:31:58Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://hdl.handle.net/11375/24995 | - |
dc.description.abstract | As an essential part of the emerging people-centric Internet of Things, connected and autonomous vehicles (CAVs) have the potential to reshape future transportation systems and impact the physical and/or social environment. While CAVs are currently being developed all over the world, they are unfortunately faced with various potential threats that could endanger the entire CAV network. Among others, risk-related concerns such as motion perturbation and jamming attacks are extremely critical to the survival of CAV networks and urgently need effective countermeasures. This research addresses the aforementioned challenges by employing cognitive dynamic systems (CDS). Inspired by certain features of the human brain, CDS is a very powerful research tool to study complex systems operating in an open and possibly adversarial environment. As a special function of CDS, cognitive risk control (CRC) actualizes the concept of predictive adaptation to bring risk under control when encountered with unexpected uncertainty. The primary research objective of this thesis is to apply CDS to CAV networks with emphasis on improved driving safety and system security. The function of CRC is utilized in respective vehicular systems in order to achieve robust target-tracking and anti-jamming vehicle-to-vehicle communication performance. For validation, extensive simulation results have shown that the proposed methods have desirable performance in the face of motion perturbation and/or jamming attacks under various scenarios. This thesis contributes to the body of knowledge by presenting the following four achievements: the first theoretical work that integrates the research tool of CDS with the engineering application of CAVs; the first experimental work of CRC being applied to a practical vehicular system; the first experimental work on V2V communication that involves anti-jamming, power control, and channel selection at the same time; and a brand-new design of coordinated vehicular radar and communication systems that builds upon all the research efforts made previously. | en_US |
dc.language.iso | en_US | en_US |
dc.title | Cognitive Dynamic System for Connected and Autonomous Vehicles | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | Computational Engineering and Science | en_US |
dc.description.degreetype | Thesis | en_US |
dc.description.degree | Doctor of Philosophy (PhD) | en_US |
dc.description.layabstract | As an essential part of the emerging Internet of Things, connected and autonomous vehicles have the potential to reshape future transportation systems and change the commute style in people's everyday life. Unfortunately, they are typically faced with various threats and attacks that could endanger the entire vehicle network. The recent development of cognitive dynamic systems has provided a very powerful research tool to study complex systems operating in an open and possibly adversarial environment. The key goal of this thesis is to apply cognitive dynamic systems to connected and autonomous vehicles with emphasis on improved driving safety and system security. The function of cognitive risk control is utilized in respective vehicular systems in order to achieve robust target-tracking and anti-jamming vehicle-to-vehicle communication performance. For validation, extensive simulation results have shown that the proposed methods have desirable performance in the face of motion perturbation and/or jamming attacks under various scenarios. | en_US |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Feng_Shuo_201909_PhD.pdf | 2.29 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.