EAGER: Toward Ethical Intelligent Autonomous Systems, A Case-Supported Principle-Based Behavior Paradigm
EAGER:迈向道德智能自治系统,基于案例支持的基于原则的行为范式
基本信息
- 批准号:1449155
- 负责人:
- 金额:$ 20.49万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2014
- 资助国家:美国
- 起止时间:2014-09-01 至 2022-08-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Intelligent autonomous systems (IAMs) are on the verge of being widely deployed in domains in which they will interact closely with people (e.g., personal assistance, healthcare, driverless cars, search and rescue), and they will be expected to navigate this ethically-charged landscape responsibly. As correct ethical behavior not only involves not doing certain things, but also doing certain things to bring about an ideal state of affairs, ethical issues concerning the behavior of IAMs are likely to elude simple, static solutions and exceed the grasp of their designers. The PI argues that the behavior of such systems should be guided by explicit ethical principles abstracted from particular cases where a consensus of ethicists exists. Laying the foundations for such technology is the focus of this exploratory research. Project outcomes will help alleviate concerns with intelligent autonomous systems, since the behavior of such systems guided by ethical principles is likely to be more acceptable in real-world environments than that of such systems without this dimension. Indeed, ethical intelligent autonomous systems capable of functioning with more autonomy might be permitted to assist human beings in a wider range of domains. The PI expects that an important byproduct of this work is that a more thorough understanding of the ethical theory involved is likely to result, as it is made concrete. To ensure correct ethical behavior, IAMs should weigh alternative possible actions against each other to determine which is ethically preferable at any given moment. The PI will leverage his previous research in developing and deploying principles that weigh the ethical preference of actions, and justify action choices for autonomous systems across multiple domains, to develop a paradigm of case-supported principle-based behavior (CPB) in which intensionally defined ethical action preference is abstracted from particular cases of ethical dilemmas and used to order ethically significant actions. The PI will refine and codify CPB using the domain of eldercare robots as a test bed by, first employing a virtual component based upon simulation and then reifying this simulation in a laboratory setting. In particular, the PI will define a comprehensive set of ethically significant actions for an eldercare robot. He will then develop and validate via an Ethical Turing Test an ethical principle that can be used to order this set by ethical preferences, and use this principle to guide the behavior of a simulated Unbounded Robotics UBR-1 robot with this set of behaviors situated in a Gazebo simulation of an assisted-living facility. He will next reify this simulation with an actual UBR-1 robot in a laboratory setting. Finally, he will refine and codify the requirements, methods, implementation specifics, and testing aspects of the case-supported principle-based behavior paradigm. Besides developing and implementing a general methodology for ensuring ethical behavior in intelligent autonomous systems, this research will provide evidence that ethical principles and decision-making can be computed and function effectively in domains where machines are likely to interact with human beings.
智能自治系统(IAM)即将被广泛部署在与人密切交互的领域(例如,个人援助,医疗保健,无人驾驶汽车,搜索和救援),他们将被期望负责任地驾驭这一充满道德色彩的景观。 由于正确的道德行为不仅包括不做某些事情,而且还包括做某些事情以实现理想的事务状态,有关IAM行为的道德问题可能会逃避简单的静态解决方案,并超出其设计者的掌握。 PI认为,这种系统的行为应该由明确的伦理原则指导,这些原则是从伦理学家达成共识的特定案例中抽象出来的。 为这种技术奠定基础是这项探索性研究的重点。 项目成果将有助于减轻对智能自主系统的担忧,因为在道德原则指导下的此类系统的行为在现实世界环境中可能比没有这一维度的此类系统更容易接受。 事实上,能够以更大的自主性运作的伦理智能自主系统可能被允许在更广泛的领域帮助人类。 PI预计,这项工作的一个重要副产品是,随着它的具体化,可能会对所涉及的伦理理论有更透彻的理解。为了确保正确的道德行为,IAM应该权衡各种可能的行动,以确定在任何特定时刻哪种行动在道德上是可取的。 PI将利用他以前的研究,开发和部署权衡行为的道德偏好的原则,并证明跨多个领域的自主系统的行为选择,以开发案例支持的基于原则的行为(CPB)的范式,其中内涵定义的道德行为偏好是从道德困境的特定案例中抽象出来的,并用于订购道德上重要的行动。 PI将使用老年人护理机器人领域作为测试平台,首先采用基于模拟的虚拟组件,然后在实验室环境中具体化该模拟,从而对CPB进行改进和编码。 特别是,PI将为老年人护理机器人定义一套全面的道德上重要的行动。 然后,他将通过一个道德图灵测试开发和验证一个道德原则,该原则可用于通过道德偏好来排序这一组,并使用该原则来指导一个模拟的无界机器人UBR-1机器人的行为,该机器人具有位于辅助生活设施的Gazebo模拟中的这一组行为。 接下来,他将在实验室环境中使用实际的UBR-1机器人来实现这一模拟。 最后,他将提炼和编纂的需求,方法,实现细节,和测试方面的案例支持的基于原则的行为范例。 除了开发和实施一种通用方法来确保智能自治系统中的道德行为外,这项研究还将提供证据,证明道德原则和决策可以在机器可能与人类互动的领域中有效地计算和运作。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Michael Anderson其他文献
Space, Movement, and Visibility in Pompeian Houses
庞贝古宅的空间、运动和可视性
- DOI:
10.4324/9781315610153 - 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
Michael Anderson - 通讯作者:
Michael Anderson
Diagrammatic Reasoning and Mathematical Morphology
图解推理和数学形态学
- DOI:
- 发表时间:
2000 - 期刊:
- 影响因子:0
- 作者:
Michael Anderson - 通讯作者:
Michael Anderson
Total leukocyte control for elective coronary bypass surgery does not improve short-term outcome.
选择性冠状动脉搭桥手术的总白细胞控制并不能改善短期结果。
- DOI:
10.1016/j.athoracsur.2004.11.038 - 发表时间:
2005 - 期刊:
- 影响因子:0
- 作者:
R. Salamonsen;James Anderson;Michael Anderson;M. Bailey;G. Magrin;F. Rosenfeldt - 通讯作者:
F. Rosenfeldt
Towards Diagram Processing: A Diagrammatic Information System
走向图处理:图解信息系统
- DOI:
10.1007/978-1-4471-0109-3_24 - 发表时间:
1999 - 期刊:
- 影响因子:0
- 作者:
Michael Anderson - 通讯作者:
Michael Anderson
Invasive disease due to Streptococcus pneumoniae in an area with a high rate of relative penicillin resistance.
在相对青霉素耐药率较高的地区,由肺炎链球菌引起的侵袭性疾病。
- DOI:
10.1093/infdis/156.5.732 - 发表时间:
1987 - 期刊:
- 影响因子:0
- 作者:
G. Istre;M. Tarpay;Michael Anderson;Ami Pryor;D. Welch - 通讯作者:
D. Welch
Michael Anderson的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Michael Anderson', 18)}}的其他基金
Cognitive and neurobiological mechanisms underlying memory control.
记忆控制背后的认知和神经生物学机制。
- 批准号:
MC_UU_00030/1 - 财政年份:2022
- 资助金额:
$ 20.49万 - 项目类别:
Intramural
ULTRA-SPEED ATOMIC FORCE MICROSCOPY FOR CRYSTALLISATION
用于结晶的超高速原子力显微镜
- 批准号:
EP/W036479/1 - 财政年份:2022
- 资助金额:
$ 20.49万 - 项目类别:
Research Grant
Geometry and Analysis of Einstein Metrics
几何和爱因斯坦度量分析
- 批准号:
1607479 - 财政年份:2016
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
"Improved Methodologies for Field Experiments: Maximizing Statistical Power While Promoting Replication."
“改进现场实验方法:在促进复制的同时最大化统计能力。”
- 批准号:
1461491 - 财政年份:2015
- 资助金额:
$ 20.49万 - 项目类别:
Standard Grant
Conference on Cycles, Calibrations and Nonlinear Partial Differential Equations
循环、标定和非线性偏微分方程会议
- 批准号:
1242837 - 财政年份:2012
- 资助金额:
$ 20.49万 - 项目类别:
Standard Grant
Geometric and Analytic Aspects of Einstein Metrics
爱因斯坦度量的几何和分析方面
- 批准号:
1205947 - 财政年份:2012
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
EAGER: A General Ethical Dilemma Analyzer
EAGER:通用道德困境分析器
- 批准号:
1151305 - 财政年份:2011
- 资助金额:
$ 20.49万 - 项目类别:
Standard Grant
Geometric Structures on Low Dimensional Manifolds
低维流形上的几何结构
- 批准号:
0604735 - 财政年份:2006
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
Crystal Growth of Nanoporous Materials
纳米多孔材料的晶体生长
- 批准号:
EP/D053161/1 - 财政年份:2006
- 资助金额:
$ 20.49万 - 项目类别:
Research Grant
相似国自然基金
Toward a general theory of intermittent aeolian and fluvial nonsuspended sediment transport
- 批准号:
- 批准年份:2022
- 资助金额:55 万元
- 项目类别:
相似海外基金
CAREER: Toward Smart Surface Acoustic Wave Devices with Gate-Tunability
职业:开发具有栅极可调谐性的智能表面声波器件
- 批准号:
2337069 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
CAREER: Hybrid Surface Coating Toward Corrosion-Controlled Magnesium-Based Implants
职业:针对腐蚀控制镁基植入物的混合表面涂层
- 批准号:
2339911 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
CAREER: A Bottom Up pAproach Toward Understanding the Sunlight Driven Mechanisms and Pathways for the Release of Metals from Petroleum.
职业:一种自下而上的方法来了解阳光驱动的机制和从石油中释放金属的途径。
- 批准号:
2340743 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
The Information-Attention Tradeoff: Toward an Understanding of the Fundamentals of Online Attention
信息与注意力的权衡:了解在线注意力的基本原理
- 批准号:
2343858 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
CAREER: Toward Power Delivery Network-aware Hardware Security
职业:迈向电力传输网络感知硬件安全
- 批准号:
2338069 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Continuing Grant
Toward Trustworthy Generative AI by Integrating Large Language Model with Knowledge Graph
通过将大型语言模型与知识图相结合,迈向可信赖的生成式人工智能
- 批准号:
24K20834 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Tuning Precision Fabricated Liquid Crystal Adsorbents - Toward Tailored Adsorption of Per- and Polyfluorinated Alkyl Substances
调整精密制造的液晶吸附剂 - 针对全氟和多氟烷基物质的定制吸附
- 批准号:
24K17729 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Toward next-generation flexible and interpretable deep learning: A novel evolutionary wide dendritic learning
迈向下一代灵活且可解释的深度学习:一种新颖的进化广泛的树突学习
- 批准号:
23K24899 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
Mentored Excellence Toward Research and Industry Careers 2
指导卓越研究和行业职业 2
- 批准号:
2322416 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Standard Grant
Toward a more complete understanding of coastal upwelling dynamics
更全面地了解沿海上升流动力学
- 批准号:
2343008 - 财政年份:2024
- 资助金额:
$ 20.49万 - 项目类别:
Standard Grant