--- title: "Alarming Robot Anticipates Your Smile, Returns Horrific Imitation" description: "Researchers have developed a robot that can anticipate your smile and return it almost instantly. The work, published as a study in the journal Science Robotics, is intended to help human-looking robots act more naturally. Named \"Emo,\" the bot can predict your smile about 840 milliseconds before it actually appears. Then just as the smile […]" date: "2024-03-28" modified: "2024-03-28" authors: - name: "Frank Landymore" job_title: "Contributing Writer" link: "https://futurism.com/authors/flandymore" url: "https://futurism.com/the-byte/robot-anticipates-smile-horrific-imitation" categories: - "Robotics" - "Robots and Machines" tags: - "artificial intelligence" - "robotics" - "the digest" --- # Alarming Robot Anticipates Your Smile, Returns Horrific Imitation ![The robot, dubbed "Emo," uses cameras in its eyes to predict your smile less than a second before it actually appears.]() *\Image: Yuhang Yu / Futurism\* ## Beaming Bot Researchers have developed a robot that can anticipate your smile and return it almost instantly. The new work, published as a [study in the journal *Science Robotics*](), is intended to help human-looking robots appear more natural. The actual expressions this one makes, however, look anything but. Named "Emo," the bot can predict your smile less than a second before it actually appears using cameras lodged into its pupils. Then just as the smile creeps up your face, as shown in an amusing [video from *New Scientist*](), Emo grimaces its horrific imitation of one in return, making sure to keep eye contact the entire time. "I'm a jaded roboticist, but I smile back at this robot," study coauthor Hod Lipson, at Columbia University, [told *New Scientist*](). ## Need For Speed Like it or not, it seems inevitable that we're all going to have to get comfortable with the idea of interacting with AI powered robots — including humanoid ones. But while large language models like ChatGPT are good at imitating human speech and holding a conversation, robots are still pretty bad at doing our mannerisms. There's just something slightly *off* about them, a phenomenon known as the uncanny valley. According to the researchers, one of the main reasons why is that their facial expressions don't respond quickly enough to a human's. The trick, then, is to get them to happen more or less simultaneously. "Whereas delayed facial mimicry looks disingenuous, facial coexpression feels more genuine because it requires correct inference of the human's emotional state for timely execution," the researchers wrote in the study. ## Simulated Smirk To achieve this, the researchers first had the robot undergo "self modeling." By performing random facial movements in front of a camera, Emo learned how moving the actuators in its face corresponded to actual facial expressions. After several hours of that, they then had Emo watch videos of human facial expressions for a few more hours, which is how it learned to predict them. There's no arguing that it's gotten very good at the anticipation part, even if the smiles leave something to be desired. But perhaps once these findings are applied to a more mechanically advanced robot, the machines will be the ones grinning from ear to ear — while we'll just have to grin and bear it. "I think predicting human facial expressions accurately is a revolution in \[human robot interaction\]," study lead author Yuhang Hu, also at Columbia, said in a [statement]() about the work. "In the future, when interacting with a robot, it will observe and interpret your facial expressions, just like a real person." **More on robots:** *[Robot Dog Shot Three Times During Raid]()* ## Author At Futurism, my work has often centered on bringing a sense of clarity and insight to complex topics ranging from the regulation of emerging technologies to the esoteric ideologies of Silicon Valley executives, while striving not to lose the poetic sense of awe inspired by often-obscure fields like astrophysics and quantum computing. I broke the story of CNET using AI to produce articles that turned out to be riddled with factual errors and plagiarism — a dam-breaking inflection point, as I've reported, that's inspired copycats and endless discourse while beguiling stakeholders ranging from tech giants to purveyors of spam around the web. My work at Futurism has been cited by publications including CBS News, the Los Angeles Times, Vice, Gizmodo, Engadget, the Verge, and Vanity Fair. I grew up in locales ranging from India to China, and now live in the exotic suburbs of Virginia. In my free time, I'm an avid reader of weird sci-fi literature, an aficionado of East Asian cinema, and, regrettably, a relapsed gamer. Allegedly, I’m working on a debut novel, currently untitled. ### Author social links [Bluesky]()