Human reactions to good and bad robots
Elizabeth Broadbent, Bruce A. MacDonald, Lana Jago, M. Juergens, O. Mazharullah
- Year
- 2007
- Citations
- 25
Abstract
There has been little previous research assessing people’s emotions and cognitions in response to different types of robot behaviour. This study investigated how people think and feel during interactions with robots who behave either well or poorly. 45 participants interacted with a B21r robot in a basic task to lead the robot along a marked path. Each participant was randomly assigned to either the robot following well or the robot following poorly. The most frequently reported emotions were frustration, fear, and happiness, and people commonly reported thoughts about the robot and also about themselves in the interaction. People reported more positive emotions in response to the good robot. Independently of group assignment, positive emotions during the task were associated with more positive evaluations of the robot and negative emotions were associated with more negative evaluations. These results suggest that robot designers should seek to maximize people’s positive emotions and minimize negative emotions to maximise the quality of human-robot interactions. Results also suggest that recognising emotions may be difficult for robots, and direct questioning may be an easier strategy.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002