Robots disobedience already a fact

Can robots actively disobey humans? Researchers from Tufts University in Massachusetts are training robots to making a decisions and being able to disobey humans. It could mark the era of self-aware AI.

What if Artificial Intelligence become too clever? What if robots would be able to say “no” to human? Is it safe? Researchers at Tufts University’s Human-Robot Interaction Lab have been developing a specific type of programming for robots that enables them to understand that they can reject a command from a human if they have a good enough reason for it. For example, if robot existence is under threat because of human order, robot can refuse to fulfil its commitments. Just like here:
https://youtu.be/a_PRFwy5Jiw

Although the idea of teaching robots to disobey is designed to protect it before damage itself or other property, some researches see in it a potential thread – ability to disobey.

The team of researchers at Tuft’s University respond:

The overall goal here is not just to teach robots when they should (and should not) follow orders, but also to provide a framework within which the robot is able to effectively communicate why it rejected an order. This is important, because it allows the human to provide additional instructions that might satisfy whichever felicity condition caused the failure in the first place.

What is your opinion about teaching robots to disobey for their own good?

Source:techworm.net