Scientists, in a string of events that a decade ago could only be imagined in sci-fi horror movies where robots take over the world, take the next step to free-thinking robots by creating a robot that passes the “self-aware” test.

Scientists at The Rensselaer AI and Reasoning Lab (Rair) in New York conducted an experiment in which they told three humanoid robots that they were given “dumbing pills,” which would paralyze the robots and make them lose their ability to speak. The wanted end result of the experiment was that the robot would analyze the situation, recognize its own voice, and then provide a correct answer.

Upon being asked which robots had received a dumbing pill, the robot answered, “I don’t know.” Hearing its own voice, the robot changed its answer and then corrected itself, saying, “Sorry, I now know. I was able to prove that I was not given a dumbing pill.”

Scientists say that having a self-aware robot is a nice accomplishment, but the next big hurdle is making a robot that is constantly aware of its own existence and, therefore, able to analyze and comprehend problems rationally like a human being.

“Think about a self-driving vehicle for a moment, say one that’s been built by Uber or Apple or Google,” roboticist Selmer Bringsjord said. “Three people get into it, and they’re all talking at the same time. If the AI doesn’t understand who’s talking and that it’s not him or herself talking — but only recognizes when itself speaks — there is no way to engineer a system that would be able to understand this conversation that good old fashioned taxi drivers have no trouble with. That is unless the driving AI has a concept of itself versus its occupants.”

In short, the human race will not likely have to worry about robots taking over the world until they realize their own constant existence. And, then, there will be another problem to be dealt with.