Date of Award
6-1-2021
Degree Name
Doctor of Philosophy
Department
Computer Science
First Advisor
Hexmoor, Henry
Second Advisor
Bouvier, Dennis
Abstract
This dissertation creates and examines algorithmic models for automated machine-to-machine negotiation in localized multi-agent systems at the edge of the Internet of Things. It provides an implementation of two such models for unsupervised resource allocation for the application domain of autonomous vehicle traffic as it pertains to lane changing and speed setting selection. The first part concerns negotiation via abstract argumentation. A general model for the arbitration of conflict based on abstract argumentation is outlined and then applied to a scenario where autonomous vehicles on a multi-lane highway use expert systems in consultation with private objectives to form arguments and use them to compete for lane positions. The conflict resolution component of the resulting argumentation framework is augmented with social voting to achieve a community supported conflict-free outcome. The presented model heralds a step toward independent negotiation through automated argumentation in distributed multi-agent systems. Many other cyber-physical environments embody stages for opposing positions that may benefit from this type of tool for collaboration. The second part deals with game-theoretic negotiation through mechanism design. It outlines a mechanism providing resource allocation for a fee and applies it to autonomous vehicle traffic. Vehicular agents apply for speed and lane assignments with sealed bids containing their private feasible action valuations determined within the context of their governing objective. A truth-inducing mechanism implementing an incentive-compatible strategyproof social choice functions achieves a socially optimal outcome. The model can be adapted to many application fields through the definition of a domain-appropriate operation to be used by the allocation function of the mechanism. Both presented prototypes conduct operations at the edge of the Internet of Things. They can be applied to agent networks in just about any domain where the sharing of resources is required. The social voting argumentation approach is a minimal but powerful tool facilitating the democratic process when a community makes decisions on the sharing or rationing of common-pool assets. The mechanism design model can create social welfare maximizing allocations for multiple or multidimensional resources.
Access
This dissertation is Open Access and may be downloaded by anyone.