A Turing-Like Handshake Test for Motor Intelligence

Abstract

In the Turing test, a computer model is deemed to think intelligently if it can generate answers that are not distinguishable from those of a human. This test is limited to the linguistic aspects of machine intelligence. A salient function of the brain is the control of movement, with the human hand movement being a sophisticated demonstration of this function. Therefore, we propose a Turing-like handshake test, for machine motor intelligence. We administer the test through a telerobotic system in which the interrogator is engaged in a task of holding a robotic stylus and interacting with another party (human, artificial, or a linear combination of the two). Instead of asking the interrogator whether the other party is a person or a computer program, we employ a forced-choice method and ask which of two systems is more human-like. By comparing a given model with a weighted sum of human and artificial systems, we fit a psychometric curve to the answers of the interrogator and extract a quantitative measure for the computer model in terms of similarity to the human handshake.