The First Law of Robotics (A Call to Arms)
The First Law of Robotics (A Call to Arms)
复制标题
DOI：
10.1007/978-3-642-04879-1_7
复制
发表时间：
1994-08
期刊：
影响因子：
--
通讯作者：
Daniel S. Weld;Oren Etzioni
中科院分区：
文献类型：
--
作者：
Daniel S. Weld;Oren Etzioni
甚至在人工智能出现之前，科幻作家艾萨克·阿西莫夫（Isaac Asimov）就认识到，一个代理人必须把保护人类免受伤害放在比服从人类命令更重要的位置。受阿西莫夫的启发，我们提出了以下基本问题：(1)人们应该如何将富有但非正式的“伤害”概念正式化？(2) agent如何避免执行有害动作，并以计算可处理的方式这样做？(3) agent应如何解决其目标与避免伤害的需求之间的冲突？(4)代理人什么时候应该阻止人类伤害自己？虽然我们在技术细节上解决了其中的一些问题，但本文的主要目标是将注意力集中在阿西莫夫的担忧上：社会将拒绝自主代理，除非我们有一些可靠的手段使它们安全！
Even before the advent of Artificial Intelligence, science fiction writer Isaac Asimov recognized that an agent must place the protection of humans from harm at a higher priority than obeying human orders. Inspired by Asimov, we pose the following fundamental questions: (1) How should one formalize the rich, but informal, notion of “harm”? (2) How can an agent avoid performing harmful actions, and do so in a computationally tractable manner? (3) How should an agent resolve conflict between its goals and the need to avoid harm? (4) When should an agent prevent a human from harming herself? While we address some of these questions in technical detail, the primary goal of this paper is to focus attention on Asimov’s concern: society will reject autonomous agents unless we have some credible means of making them safe!