Believable Robot Characters

WINTER 2011 39 The way people interact with robots appears to be fundamentally different from how they interact with most other technologies. People tend to ascribe a level of intelligence and sociability to robots that influences their perceptions of how the interactions should proceed. If a robot, for its part, adheres to this ascription, then the interactions tend to be natural and engaging; if not, they can be discordant. Our goal is to develop autonomous robotic systems that can sustain such natural and engaging social interactions with untrained users. Our approach is to develop believable robot characters. In this context, believable means an illusion of life. Bates (1994) writes, “There is a notion in the Arts of ‘believable character.’ It does not mean an honest or reliable character, but one that provides the illusion of life, and thus permits the audience’s suspension of disbelief .... Traditional character animators are among those artists who have sought to create believable characters ....” Think of animated characters such as the magic carpet in Disney’s Aladdin or the teapot and candlestick in Beauty and the Beast — not people, in any sense, but engaging, lifelike characters. Perhaps a more apt analogy, though, is to view robots as actors performing in a human environment (Hoffman 2011). As early as the 19th century, acting theories, such as Delsarte’s method (Stebbins 1886), placed emphasis on external actions as a key to believability. For example, an actor’s dialogue should be rich in verbal and nonverbal expression of emotions and personality traits. While modern acting methods (Stanislavski