不听话的机器人已经出现了
Robots are learning to DISOBEY humans: Humanoid machine says no to instructions if it thinks it might be hurt
If Hollywood ever had a lesson for scientists it is what happens if machines start to rebel against their human creators.
如果说好莱坞曾经给科学家们一个教训,那一定是机器人开始反抗它们的创造者——人类.
Yet despite this, roboticists have started to teach their own creations to say no to human orders.
尽管这样,机器人已经开始学着拒绝人类的命令了.
They have programmed a pair of diminutive humanoid robots called Shafer and Dempster to disobey instructions from humans if it puts their own safety at risk.
他们已经编程了一对小型的类人机器人,名字叫谢弗和邓普斯特,如果人类的指令对它们自己有危险,他们就会违背命令.
The results are more like the apologetic robot rebel Sonny from the film I, Robot, starring Will Smith, than the homicidal machines of Terminator, but they demonstrate an important principal.
相比那些会杀人的终结者机器人,这个试验的结果更像是威尔·史密斯主演的《我与机器人》中的那个会道歉的机器人索尼,但是它们都遵守重要的原则.
Engineers Gordon Briggs and Dr Matthais Scheutz from Tufts University in Massachusetts, are trying to create robots that can interact in a more human way.
马塞诸塞州塔夫茨大学的工程师戈登·布里格斯和马特赫兹博士正试图创造出更能以人性化方式交流的机器人.
In a paper presented to the Association for the Advancement of Artificial Intelligence, the pair said: 'Humans reject directives for a wide range of reasons: from inability all the way to moral qualms.
在人工智能发展协会上发表的一篇论文中,两人说："人类会因为各种各样的原因拒绝执行指令：从没有能力做到对道德的顾虑."
'Given the reality of the limitations of autonomous systems, most directive rejection mechanisms have only needed to make use of the former class of excuse - lack of knowledge or lack of ability.
"鉴于自主系统的局限性,大多数指令排斥反应机制只需利用以前的理由——缺少知识或者能力."
