Experiments in Artificial Theory of Mind: From Safety to Story-Telling.

Alan F T Winfield

doi:10.3389/frobt.2018.00075

Alan F T Winfield

Open Access

https://doi.org/10.3389/frobt.2018.00075

Copy DOI

Abstract

Theory of mind is the term given by philosophers and psychologists for the ability to form a predictive model of self and others. In this paper we focus on synthetic models of theory of mind. We contend firstly that such models—especially when tested experimentally—can provide useful insights into cognition, and secondly that artificial theory of mind can provide intelligent robots with powerful new capabilities, in particular social intelligence for human-robot interaction. This paper advances the hypothesis that simulation-based internal models offer a powerful and realisable, theory-driven basis for artificial theory of mind. Proposed as a computational model of the simulation theory of mind, our simulation-based internal model equips a robot with an internal model of itself and its environment, including other dynamic actors, which can test (i.e., simulate) the robot's next possible actions and hence anticipate the likely consequences of those actions both for itself and others. Although it falls far short of a full artificial theory of mind, our model does allow us to test several interesting scenarios: in some of these a robot equipped with the internal model interacts with other robots without an internal model, but acting as proxy humans; in others two robots each with a simulation-based internal model interact with each other. We outline a series of experiments which each demonstrate some aspect of artificial theory of mind.

Highlights

Theory of mind is the term given by philosophers and psychologists for the ability to predict the actions of self and others (Carruthers and Smith, 1996)
Experiments in Artificial Theory of Mind on aspects of theory of mind present in young (4 month old) infant humans the author describes an implementation of visual attention, finding faces and the recognition and tracking of eyes, and discrimination between animate and inanimate, on the MIT Cog robot (Brooks et al, 1999)
A very recent paper Machine Theory of Mind describes a machine learning approach in which one agent observes another’s behaviors and learns a predictive model of that agent (Rabinowitz et al, 2018); the simulated agents of this work learn the rules underlying the behavior of the observed agent, this is a theory theory (TT) approach

Summary

Introduction

Theory of mind is the term given by philosophers and psychologists for the ability to predict the actions of self and others (Carruthers and Smith, 1996). In this paper we avoid this difficult question by focusing instead on synthetic models of theory of mind. We contend firstly that such models—especially when tested experimentally—can provide valuable insights into both natural and artificial cognition, and secondly that artificial theory of mind can provide intelligent robots with powerful new capabilities, in particular social intelligence for human-robot interaction. Artificial theory of mind has been recently highlighted as one of the Grand Challenges of Science Robotics: “The three most significant challenges that stem from building robots that interact socially with people are modeling social dynamics, learning social and moral norms, and building a robotic theory of mind” (Yang et al, 2018)

Objectives

Methods

Conclusion