We analyze two significant decision-making problems namely planning and control in an autonomous driving scenario with an objective of not only improving the safety of drives but also enhancing the vehicle’s capability to make better decisions. We model the decision-making problem of routing in autonomous vehicles and solve for an optimal route when a vehicle approaches an intersection. The proposed solution attempts to balance the congestion in the traffic network, considering the selfish nature of the vehicles. We also analyze decision-making at the level of control and communications. The choices of the framework we use, to model the communication layer of the protocol makes it easier for us to verify and model check the protocol. For example, we implement the process algebra description using Promela language, and we prove the protocol’s correctness guarantees using SPIN model checker. We use a Reinforcement Learning algorithm in the design of the control protocol.
|Advisor:||Somenzi, Fabio, Sankaranarayanan, Sriram|
|Commitee:||Hayes, Bradley, Trivedi, Ashutosh|
|School:||University of Colorado at Boulder|
|School Location:||United States -- Colorado|
|Source:||MAI 58/06M(E), Masters Abstracts International|
|Subjects:||Computer Engineering, Computer science|
|Keywords:||Concurrent processes, Decision making, Optimal routing, Pi-calculus, Reinforcement learning, Safe control|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
supplemental files is subject to the ProQuest Terms and Conditions of use.