Alle Publikationen
- <<
- <
- 1
2017
-
(2017) : Learning behavioral norms in uncertain and changing contexts: 2017 8th IEEE International Conference on Cognitive Infocommunications (CogInfoCom): Debrecen, Hungary: IEEE, S. 000301-000306
DOI: https://doi.org/10.1109/CogInfoCom.2017.8268261 Abstract: Human behavior is often guided by social and moral norms. Robots that enter human societies must therefore behave in norm-conforming ways as well to increase coordination, predictability, and safety in human-robot interactions. However, human norms are context-specific and laced with uncertainty, making the representation, learning, and communication of norms challenging. We provide a formal representation of norms using deontic logic, Dempster-Shafer Theory, and a machine learning algorithm that allows an artificial agent to learn norms under uncertainty from human data. We demonstrate a novel cognitive capability with which an agent can dynamically learn norms while being exposed to distinct contexts, recognizing the unique identity of each context and the norms that apply in it.
Keywords: Artificial agent, behavioral norms, behavioural sciences computing, Cognition, Conferences, Dempster-Shafer Theory, deontic logic, Ethics, formal logic, Human behavior, human societies, human-robot interaction, human-robot interactions, ieee xplore, inference mechanisms, learning (artificial intelligence), Libraries, machine learning algorithm, Moral & Ethik, moral norms, norm-conforming ways, Robot kinematics, Social Norms, uncertainty, uncertainty handling 2006
-
(2006): Toward a General Logicist Methodology for Engineering Ethically Correct Robots. In: IEEE Intelligent Systems 21 (4), S. 38-44. DOI: 10.1109/MIS.2006.82
DOI: https://doi.org/10.1109/MIS.2006.82 Abstract: As intelligent machines assume an increasingly prominent role in our lives, there seems little doubt they eventually be called on to make important, ethically charged decisions. We think formal logic offers a way to preclude doomsday scenarios of malicious robots taking over the world. Faced with the challenge of engineering ethically correct robots, we propose a logic-based approach. We’ve successfully implemented and demonstrated this approach. We present it in a general methodology to answer the ethical questions that arise in entrusting robots with more and more of our welfare. A deontic logic formalizes a moral code, allowing ethicists to render theories and dilemmas in declarative form for analysis. It offers a way for human overseers to constrain robot behavior in ethically sensitive environments
Keywords: Artificial intelligence, deontic logic, ethical aspects, ethical robot engineering, ethical sensitive environment, Ethics, formal logic, Humans, ieee xplore, intelligent machine, intelligent robots, Logic, logic-based approach, logicist methodology, Machine intelligence, medical robotics, Moral & Ethik, Natural languages, Protection, robot behavior, Robot sensing systems, Robots
- <<
- <
- 1