期刊
IEEE INTERNET COMPUTING
卷 25, 期 6, 页码 15-22出版社
IEEE COMPUTER SOC
DOI: 10.1109/MIC.2021.3107334
关键词
Task analysis; Cognition; Artificial intelligence; Accidents; Internet; Tools; Multi-agent systems
资金
- U.K. Engineering and Physical Sciences Research Council (EPSRC) through the Trustworthy Autonomous Systems Hub [EP/V00784X/1]
- platform grant AutoTrust: Designing a Human-Centred Trusted, Secure, Intelligent and Usable Internet of Vehicles [EP/R029563/1]
- Turing AI Fellowship [EP/V022067/1]
- EPSRC [EP/V00784X/1] Funding Source: UKRI
The translation focuses on the study of computational techniques for reasoning different forms of responsibility in autonomous agents and multiagent systems, exploring the responsibilities of agents or agent groups in collective decision outcomes, task completion, or adherence to norms and social values, as well as the development and application of computational frameworks.
Ensuring trustworthy performance of autonomous agents and multiagent systems (MAS) requires computational methods and formal tools to support reasoning about different forms of responsibility. In particular, such tools are needed to support identifying agents or agent groups that are responsible, blameworthy, accountable, or sanctionable for outcomes of collective decisions, for fulfilling tasks, or for adhering to norms and social values. As a step toward developing computational frameworks to represent, reason about, and distinguish these forms of responsibility in MAS, for the first time, we present sociotechnical characteristics of these notions of responsibility, identify their requirements, and discuss their applicability for coordinating MAS and ensuring their trustworthiness. This is a step toward establishing a research agenda on how computational techniques for reasoning about and distinguishing different forms of responsibility contribute to the transformation toward ethical and trustworthy autonomous systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据