Table 1 Mean classification errors across participants in the Turing test. HRI and HHI trials were balanced. The false negative rate (FNR) indicates how often an HRI was misclassified; the false positive rate (FPR) indicates how often an HHI was misclassified. Note that with an artificial agent which perfectly emulates human movements, participants could only guess the nature of the interaction partner (chance level: 50%). Numbers in parentheses are not significantly different from a random guess.

From: A dual recurrent neural network model of human-like motion for artificial agents and its evaluation in a VR mirror game turing test