PROJECT TITLE :

Toward Perceiving Robots as Humans: Three Handshake Models Face the Turing-Like Handshake Test

ABSTRACT :

Within the Turing take a look at a computer model is deemed to “assume intelligently” if it can generate answers that are indistinguishable from those of somebody's. We developed an analogous Turing-like handshake take a look at to work out if a machine will turn out equally indistinguishable movements. The check is run through a telerobotic system in that an interrogator holds a robotic stylus and interacts with another party - artificial or human with varying levels of noise. The interrogator is asked which party looks to be more human. Here, we compare the human-likeness levels of 3 completely different models for handshake: (one) Tit-for-Tat model, (a pair of) λ model, and (3) Machine Learning model. The Tit-for-Tat and also the Machine Learning models generated handshakes that were perceived as the foremost human-like among the three models that were tested. Combining the simplest aspects of each of the 3 models into a single robotic handshake algorithm might permit us to advance our understanding of the method the nervous system controls sensorimotor interactions and any improve the human-likeness of robotic handshakes.