ASU Scholarship Showcase

Human team members show a remarkable ability to infer the state of their partners and anticipate their needs and actions. Prior research demonstrates that an artificial system can make some predictions accurately concerning artificial agents. This study investigated whether an artificial system could generate a robust Theory of Mind of human teammates. An urban search and rescue (USAR) task environment was developed to elicit human teamwork and evaluate inference and prediction about team members by software agents and humans. The task varied team members’ roles and skills, types of task synchronization and interdependence, task risk and reward, completeness of mission planning, and information asymmetry. The task was implemented in MinecraftTM and applied in a study of 64 teams, each with three remotely distributed members. An evaluation of six Artificial Social Intelligences (ASI) and several human observers addressed the accuracy with which each predicted team performance, inferred experimentally manipulated knowledge of team members, and predicted member actions. All agents performed above chance; humans slightly outperformed ASI agents on some tasks and significantly outperformed ASI agents on others; no one ASI agent reliably outperformed the others; and the accuracy of ASI agents and human observers improved rapidly though modestly during the brief trials.

This chapter is not a guide to embodied thinking, but rather a critical call to action. It highlights the deep history of embodied practice within the fields of dance and somatics, and outlines the value of embodied thinking within human-computer interaction (HCI) design and, more specifically, wearable technology (WT) design. What this chapter does not do is provide a guide or framework for embodied practice. As a practitioner and scholar grounded in the fields of dance and somatics, I argue that a guide to embodiment cannot be written in a book. To fully understand embodied thinking, one must act, move, and do. Terms such as embodiment and embodied thinking are often discussed and analyzed in writing; but if the purpose is to learn how to engage in embodied thinking, then the answers will not come from a text. The answers come from movement-based exploration, active trial-and-error, and improvisation practices crafted to cultivate physical attunement to one's own body. To this end, my "call to action" is for the reader to move beyond a text-based understanding of embodiment to active engagement in embodied methodologies. Only then, I argue, can one understand how to apply embodied thinking to a design process.

There is a need for indicators of transportation-land use system quality that are understandable to a wide range of stakeholders, and which can provide immediate feedback on the quality of interactively designed scenarios. Location-based accessibility indicators are promising candidates, but indicator values can vary strongly depending on time of day and transfer wait times. Capturing this variation increases complexity, slowing down calculations. We present new methods for rapid yet rigorous computation of accessibility metrics, allowing immediate feedback during early-stage transit planning, while being rigorous enough for final analyses. Our approach is statistical, characterizing the uncertainty and variability in accessibility metrics due to differences in departure time and headway-based scenario specification. The analysis is carried out on a detailed multi-modal network model including both public transportation and streets. Land use data are represented at high resolution. These methods have been implemented as open-source software running on commodity cloud infrastructure. Networks are constructed from standard open data sources, and scenarios are built in a map-based web interface. We conclude with a case study, describing how these methods were applied in a long-term transportation planning process for metropolitan Amsterdam.