Title: A Computational Framework for Norm-Aware Reasoning in Autonomous Systems

Abstract:

Autonomous agents are increasingly deployed in complex social environments where they not only have to reason about their domain goals but also about norms that can impose constraints on task performance. Integrating task planning with norm aware reasoning is a challenging problem due to the curse of dimensionality associated with product spaces of the domain state variables and norm-related variables. In this work, we propose a Modular Normative Markov Decision Process (MNMDP) framework that is shown to have orders of magnitude increase in performance compared to previous approaches.

Since norms are both context-dependent as well as context-sensitive, we must model context in an expressive, scalable and compact manner to map them to activation conditions for norms. To this end, we propose a generalizable context modeling approach to understand norm activations in social environments. We show how we can combine our context model with our MNMDP framework to support norm understanding as well as norm enforcement in real systems. We demonstrate the effectiveness of our approach through scenarios in simulated social environments and show the significant computational improvements that we obtain when using our proposed approach for computationally modeling social norms.

Committee:

Katia Sycara (Chair)

Stephen Smith

Wenhao Luo