CAREER: Human-Aware Autonomy for Team-Oriented Environments

职业：面向团队的环境的人类意识自治

• 批准号: 1350160
• 负责人: Julie Shah
• 金额: $ 39.86万
• 依托单位: Massachusetts Institute of Technology
• 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: 2014-08-01 至 2020-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1350160&HistoricalAwards=false
• 关键词: CAREER; Human; Aware; Autonomy; Team

Robots are an increasingly common presence in human environments, working alongside people in factories, hospitals, and military field operations. However, today people must change how they work to accommodate robots in their workspace. This poses a significant barrier to adoption of robot technology by creating inefficiencies. This project provides an integrated research and educational approach to develop intelligent robotic technologies that more seamlessly integrate with human work environments. The technical approach translates qualitative and quantitative insights from human studies into explicit computational models, and exploits these models to redesign robot algorithms for learning, decision-making, and control. The research effort specifically investigates three types modifications to robot behavior: (1) modifying robot motion planning using anticipatory signals of human motion, (2) customizing robot task plans using statistical models of human task execution, and (3) inferring and applying human domain expertise to expedite automated planning for mixed human-robot teams. Human subject experimentation is planned to assess ease-of-interaction, worker trust, and task performance, and the approach is validated using metrics to quantitatively assess the degree to which a robot's behavior preserves natural human workflow. By designing robot autonomy that minimizes disruption to human workflow, the approach supports graceful transitions from robotic work back to human work and vice versa.

机器人在人类环境中越来越常见，在工厂，医院和军事领域与人们一起工作。然而，今天的人们必须改变他们的工作方式，以适应机器人在他们的工作场所。这通过创造低效率而对机器人技术的采用构成了重大障碍。该项目提供了一个综合的研究和教育方法，以开发智能机器人技术，更无缝地与人类的工作环境相结合。该技术方法将人类研究中的定性和定量见解转化为明确的计算模型，并利用这些模型重新设计机器人学习，决策和控制算法。研究工作具体研究了三种类型的修改机器人的行为：（1）修改机器人运动规划使用人类运动的预期信号，（2）定制机器人任务计划使用人类任务执行的统计模型，（3）推断和应用人类领域的专业知识，以加快混合人类机器人团队的自动规划。人类受试者的实验计划，以评估易于互动，工人的信任，和任务的性能，并使用指标，以定量评估的程度，机器人的行为保留自然的人类工作流程的方法进行验证。通过设计机器人自主性，最大限度地减少对人类工作流程的干扰，该方法支持从机器人工作到人类工作的优雅过渡，反之亦然。