That’s Mine! Learning Ownership Relations and Norms for Robots

Abstract

The ability for autonomous agents to learn and conform to human norms is crucial for their safety and effectiveness in social environments. While recent work has led to frameworks for the representation and inference of simple social rules, research into norm learning remains at an exploratory stage. Here, we present a robotic system capable of representing, learning, and inferring ownership relations and norms. Ownership is represented as a graph of probabilistic relations between objects and their owners, along with a database of predicate-based norms that constrain the actions permissible on owned objects. To learn these norms and relations, our system integrates (i) a novel incremental norm learning algorithm capable of both one-shot learning and induction from specific examples, (ii) Bayesian inference of ownership relations in response to apparent rule violations, and (iii) perceptbased prediction of an object's likely owners. Through a series of simulated and real-world experiments, we demonstrate the competence and flexibility of the system in performing object manipulation tasks that require a variety of norms to be followed, laying the groundwork for future research into the acquisition and application of social norms.

Mining International Political Norms from the GDELT Database

“…Norm learning (also known as norm identification or recognition) is an active area of research in multi-agent systems. Researchers have employed various techniques for inferring norms including association rule mining [17,18], case-based reasoning [3,5], reinforcement learning [20], inductive logic programming [7,22] and Bayesian inference [8]. Most work in this area is limited to inferring norms from simulated agent societies.…”

What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper

“…For example, [9] presents a simple simulated autonomous robot setup in which autonomous cars follow traffic signal norms. Tan et al [17] present another simple robotics application of learning ownership norms. Neither of these approaches are applicable to the type of context-specific norm learning considered in this paper.…”

When Exceptions Are the Norm

“…The challenge then is to detect that the role-based norm of cleaning up the container trumps the ownership-based norm of not touching it precisely because it implies consent by the owner to do so. Recently, research progress in explicit norm representations (Sarathy et al 2017a(Sarathy et al , 2017b, norms relating to object affordances (Sarathy and Scheutz 2016), norms relating to ownership (Tan 2019), and other prequisites for consent reference what social norms might be present and how they legitimize behavior, which in turn might suggest how they are triggered and modulated by consent.…”