The Dark Side of Ethical Robots

The Dark Side of Ethical Robots
复制标题

道德机器人的阴暗面

DOI:
10.1145/3278721.3278726
复制
发表时间:
2018
期刊:
--
影响因子:
--
通讯作者:
Vanderelst D
Vanderelst D
中科院分区:
--
文献类型:
--
作者:
Vanderelst D

文献摘要

参考文献

被引文献

相似文献

对人工智能进步带来的风险的担忧,促使人们呼吁加大对强大和有益的人工智能的努力,包括机器伦理。最近,机器人学家开始开发所谓的道德机器人。理想情况下,这些机器人会评估自己行为的后果,并在道德上证明自己的选择是正确的。这一新兴领域有望在未来几年内得到广泛发展。然而,在本文中,我们指出了伦理机器人这一新兴领域的固有局限性。我们表明,构建道德机器人也不可避免地使不道德的机器人的建设。在三个实验中,我们证明了修改一个道德机器人是非常容易的,这样它的行为就具有竞争力,甚至是攻击性。原因在于,制造一个道德机器人所需的认知机制总是会被破坏,从而制造出不道德的机器人。我们讨论了这一发现对道德机器人治理的影响。我们的结论是,不道德的行为者可能会损害机器人的道德的风险是如此之大,以至于对在现实世界的安全关键机器人(如无人驾驶汽车)中嵌入道德决策的智慧提出了严重的质疑。
Concerns over the risks associated with advances in Artificial Intelligence have prompted calls for greater efforts toward robust and beneficial AI, including machine ethics. Recently, roboticists have responded by initiating the development of so-called ethical robots. These robots would, ideally, evaluate the consequences of their actions and morally justify their choices. This emerging field promises to develop extensively over the next few years. However, in this paper, we point out an inherent limitation of the emerging field of ethical robots. We show that building ethical robots also inevitably enables the construction of unethical robots. In three experiments, we show that it is remarkably easy to modify an ethical robot so that it behaves competitively, or even aggressively. The reason for this is that the cognitive machinery required to make an ethical robot can always be corrupted to make unethical robots. We discuss the implications of this finding to the governance of ethical robots. We conclude that the risks that unscrupulous actors might compromise a robot's ethics are so great as to raise serious doubts over the wisdom of embedding ethical decision making in real-world safety-critical robots, such as driverless cars.
机器人伦理学——针对人类
DOI: --
发表时间: 2011
期刊:
影响因子: --
作者:
A. Winfield
通讯作者: A. Winfield
DOI: 10.1016/j.cogsys.2017.04.002
发表时间: 2018-05-01
影响因子: 3.9
作者:
Vanderelst, Dieter;Winfield, Alan
通讯作者: Winfield, Alan
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
Patrick Lin;Keith Abney;G. Bekey
通讯作者: G. Bekey
价值驱动的代理:基于案例支持的原则的行为范式的实例化
DOI: --
发表时间: 2017
期刊: AAAI Workshops
影响因子: --
作者:
Michael Anderson;S. Anderson;Vincent Berenz
通讯作者: Vincent Berenz
Patrick Lin、Keith Abney 和 George A. Bekey(编):机器人伦理:机器人技术的伦理和社会影响
DOI: --
发表时间: 2011
影响因子: 1
作者:
Michael Funk
通讯作者: Michael Funk