Empowerment As Replacement for the Three Laws of Robotics
Empowerment As Replacement for the Three Laws of Robotics
复制标题
赋权替代机器人三定律
DOI：
10.3389/frobt.2017.00025
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
D. Polani
中科院分区：
文献类型：
--
作者：
Christoph Salge;D. Polani
随着机器人的日益普及，需要对机器人的行为制定通用的指导方针。我们不太关注机器人如何在技术上实现预定的目标，而是更多地关注机器人首先应该做什么。特别是，我们感兴趣的问题是启发式应该是什么样子，它激发了机器人与人类代理的互动行为。我们提出了一个具体的、可操作的建议，关于如何将赋权的信息论概念作为一种通用的启发式来量化自我保护、保护人类伴侣和响应人类行为等概念。虽然我们在其他地方详细研究了涉及单智能体的场景，但在这里，我们提出了原理证明场景，展示了如何根据这些观点解释授权，使人们能够以一种可操作的方式指定具有与阿西莫夫机器人三定律相似目标的核心概念。重要的是，这条路线不依赖于必须在机器人中建立对人类语言和惯例的明确的口头理解。此外，它还结合了考虑各种不同情况和机器人体现类型的能力。
The greater ubiquity of robots creates a need for generic guidelines for robot behaviour. We focus less on how a robot can technically achieve a predefined goal, and more on what a robot should do in the first place. Particularly, we are interested in the question how a heuristic should look like which motivates the robot's behaviour in interaction with human agents. We make a concrete, operational proposal as to how the information-theoretic concept of empowerment can be used as a generic heuristic to quantify concepts such as self-preservation, protection of the human partner and responding to human actions. While elsewhere we studied involved single-agent scenarios in detail, here we present proof-of-principle scenarios demonstrating how empowerment interpreted in light of these perspectives allows one to specify core concepts with a similar aim as Asimov's Three Laws of Robotics in an operational way. Importantly, this route does not depend on having to establish an explicit verbalized understanding of human language and conventions in the robots. Also, it incorporates the ability to take into account a rich variety of different situations and types of robotic embodiment.
通过耦合赋权最大化获得内在动机的一般同伴 NPC
DOI：
10.1109/cig.2016.7860406
发表时间：
2016
期刊：
--
影响因子：
--
作者：
Guckelsberger C
通讯作者：
Guckelsberger C
扩展感觉运动权变理论：预测、规划和行动生成
影响因子：
1.6
作者：
通讯作者：
--