A photo of a story in the new scientist magazine, with a headline “robot predicts when you’re going to smile and smiles first“. The story begins “a humanoid robot can predict if someone will smile a second before they do, and match the smile itself. Its creators hope the technology will make interactions with robots more lifelike. Although artificial intelligence can now mimic human language language to an impressive degree, interactions with physical robots often fall into the uncanny valley and feel unsettling, because robots can’t replicate the complex nonverbal cues and mannerisms that are vital for communication. Now, Hod Lipson at Columbia University in New York and his colleagues have created a robot called Emo that uses AI models and high resolution cameras to predict peoples facial expressions and try to replicate them. It can anticipate whether someone will smile about 0.9 seconds before they do, and smile itself in sync.”
https://sb-9g02l2bbpw.b-cdn.net/media_attachments/files/112/417/553/113/268/456/original/8c5ad2864e572185.png