CAREER: Computational Ethics in Human-Scale Autonomous Systems

长期以来，创造自主的、更新自己的目标并在日常生活中与人类互动的智能系统一直是系统工程、机器人学和人工智能的推动力。示例系统包括医院中的护理机器人、自动驾驶车辆以及与人类合作的工人机器人。在这些系统中，明确的伦理意识被认为是与人类成功日常互动的必要条件。然而，到目前为止，用于设计配备伦理的自主智能系统(AIS)的算法相对较少，工具更少，特别是在与物理控制回路集成时。这项研究开发了一个包含伦理规范的具体化人工智能系统的计算理论和形式化设计工具。该项目集中于模型检查、控制器综合和从数据中约束学习的设计任务，形式化的伦理准则。这些指导方针的形式包括义务声明(“机器人应当照顾处于更大疼痛中的病人”)、许可(“允许机器人向传染性病人提供口罩”)和禁止(“禁止机器人在护理决策中考虑性别因素”)。调查人员在作为项目一部分开发的道义逻辑中正式规定了这些义务、许可和禁止。软件工程、最优控制和深度学习的方法被用来创建一个设计管道，允许在不同的指导方针下进行透明和严格的实验。针对本科生和高中生的教育计划补充了这项研究的目标，即使来自不同学科的社区和专业人员能够评估自主系统制造商的主张，并确定它们与社区价值的一致性。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The creation of intelligent systems that are autonomous, update their own objectives, and interact with humans in their daily lives, has long been a driving force in systems engineering, robotics, and Artificial Intelligence. Example systems include nursing robots in hospitals, self-driving vehicles, and worker bots collaborating with humans. An explicit ethical awareness in these systems is recognized as a necessary condition for successful daily interaction with humans. However, to this day, there are comparatively few algorithms, and even fewer tools, for designing ethics-equipped Autonomous Intelligent Systems (AIS), especially when integrated with a physical control loop. This research develops a computational theory and formal design tools for ethics-equipped embodied AIS.The project focuses on the design tasks of model-checking, controller synthesis, and constrained learning from data, of formalized ethical guidelines. Such guidelines take the form of statements of Obligation (`The robot ought to care for the patient in greater pain'), Permission (`The robot is permitted to offer a mask to a contagious patient') and Prohibition (`The robot is forbidden from factoring gender into care decisions'). The investigators formalize such Obligations, Permissions and Prohibitions in a deontic logic developed as part of the project. Methods from software engineering, optimal control, and deep learning, are employed to create a design pipeline that allows transparent and rigorous experimentation with different guidelines. An education plan for undergraduate and high-school students complements the research’s goal of enabling communities and professionals from different disciplines to assess the claims of autonomous systems manufacturers and determine their alignment with community values.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.