"Robots would prefer you to be rude" and "How Not to Order Water from a Robot Waiter" - those were the headlines of two recent articles about new research on human-machine interaction from Colorado School of Mines and Tufts University. IEEE Spectrum and The Next Web covered the findings, which were presented at the ACM/IEEE International Conference on Human Robot Interaction in March.
For the study, researchers from the Mines MIRROR Lab, led by Computer Science Assistant Professor Tom Williams, and Tuft's Human-Robot Interaction Laboratory recruited 49 people to interact with a robot in a variety of situations. The catch - the robot was not programmed to understand indirect speech.
From the IEEE Spectrum article:
And because the researchers programmed the robot to not handle indirect speech acts as humans would, some pretty funny conversations ensued:
Robot: Hello my name is Waiterbot. I will be helping you today.
Participant: Great, can I order something?
Robot: Please tell me your order.
Participant: Um, can I have one water?
Robot: Yes, that is permissible.
Participant: Great.
Robot: Please tell me your order.
Participant: Can I have one water?
Robot: Yes, that is permissible.
Participant: Great, I'll take one water.
Robot: Thank you for sharing that interesting prediction. Please tell me your order.
IEEE Spectrum: How Not to Order Water from a Robot Waiter
The Next Web: Robots would prefer you to be rude