Interactive physical agents for story gathering

Abstract

Robots are typically thought of as autonomous devices which require little to no human interaction to complete their goals. In this study we investigated what would happen if the success of a robot was contingent upon its interaction with a human. How do we leverage humans to make robots more intelligent, efficient and successful? Is it worth it to involve human heavily in the goals of a system? This thesis we presents a method for the creation of a physical agent to facilitate interaction and documentary gathering within a ubiquitous media framework as a method for studying human dependent systems. We built a robot and sent it out to autonomously capture stories about its environment. The robot had a specific story capture goal and leveraged humans to attain that goal. The robot gathered a 1st person view of stories unfolding in real life. We evaluated this agent by way of determining "complete" vs. "incomplete" interactions. "Complete" interactions were those that generated viable and interesting videos, which could be edited together into a larger narrative. It was found that 30% of the interactions captured were "complete" interactions. Results suggested that changes in the system would only produce incrementally more "complete" interactions, as external factors like natural bias or busyness of the user come into play. The types of users who encountered the robot were fairly polar; either they wanted to interact or did not - very few partial interactions went on for more than 1 minute. Users who partially interacted with the robot were found to treat it rougher than those who completed the full interaction. It was also determined that this type of limited-interaction system is best suited for short-term interactions. At the end of the study, a movie was produced from the videos captured, proving that they were viable for story-making.