Architecture for Simulating Behavior Mode Changes in Norm-Aware Autonomous Agents
Sean Glaze, Daniela Inclezan
TL;DR
The paper addresses how to model norm-aware autonomous agents whose behavior modes can be set and altered by a human controller, especially in time-sensitive contexts. It proposes a two-component architecture combining an ASP-based reasoning module and a Python controller, leveraging $\mathscr{AOPL}$ for norm specification and policy analysis. The main contributions are an architecture for mode-aware planning and a software system (with a GUI) that simulates plan changes under mode transitions, demonstrated in a Mining Domain and validated by runtime evaluations. This approach enables policy makers to explore how different attitudes toward norm-compliance affect agent behavior and to refine policies accordingly, particularly under emergency scenarios.
Abstract
This paper presents an architecture for simulating the actions of a norm-aware intelligent agent whose behavior with respect to norm compliance is set, and can later be changed, by a human controller. Updating an agent's behavior mode from a norm-abiding to a riskier one may be relevant when the agent is involved in time-sensitive rescue operations, for example. We base our work on the Authorization and Obligation Policy Language AOPL designed by Gelfond and Lobo for the specification of norms. We introduce an architecture and a prototype software system that can be used to simulate an agent's plans under different behavior modes that can later be changed by the controller. We envision such software to be useful to policy makers, as they can more readily understand how agents may act in certain situations based on the agents' attitudes towards norm-compliance. Policy makers may then refine their policies if simulations show unwanted consequences.