Abstract: | This article describes a user study of a life-supporting humanoid directed in a multimodal language, and discusses the results.
Twenty inexperienced users commanded the humanoid in a computer-simulated remote home environment in the multimodal language
by pressing keypad buttons and speaking to the robot. The results show that they comprehended the language well and were able
to give commands successfully. They often chose a press-button action in place of verbal phrases to specify a direction, speed,
length, angle, and/or temperature value, and preferred multimodal commands to spoken commands. However, they did not think
that it was very easy to give commands in the language. This article discusses the results and points out both strong and
weak points of the language and our robot. |