NRI: Small: Collaborative Research: Adaptive Motion Planning and Decision-Making for Human-Robot Collaboration in Manufacturing

NRI：小型：协作研究：制造中人机协作的自适应运动规划和决策

• 批准号: 1317445
• 负责人: Julie Shah
• 金额: $ 31.97万
• 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: 2013
• 资助国家: 美国
• 起止时间: 2013-09-15 至 2017-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1317445&HistoricalAwards=false
• 关键词: NRI; Small; Collaborative; Research; Adaptive

This project addresses manufacturing tasks that cannot be fully automated because of either the limitations of current algorithms or prohibitive cost and set-up time. Such tasks generally require workers to collaborate in close proximity and adapt to each other's decisions and motions. This project explores accomplishing these tasks through human-robot collaboration. Recent hardware developments in robotics have made human-robot collaboration physically possible, but robots still require new algorithms to ensure safety, efficiency, and fluency when working with people. Creating such algorithms is difficult because there can be high uncertainty in what a person is going to do and how they are going to do it. This project explores the integration of reasoning about how a person moves and how he or she makes decisions into a robot motion planning and decision-making framework. The research centers on the development of new algorithmic frameworks for modeling, simulating, and planning for human-robot collaboration, which requires advances in robot training, task modeling, human motion understanding, high-dimensional motion planning with uncertainty, and metrics to assess human-robot joint action. The results of this project have the potential to significantly improve American competitiveness in manufacturing; especially for small-batch manufacturing and burst production, where the cost and set-up time of fully-autonomous solutions is prohibitive. The work will be disseminated in research papers and integrated into curricula. The project is guided by an advisory board from the manufacturing industry, which provides another avenue for dissemination.

该项目解决了由于当前算法的局限性，或者成本不佳和设置时间的局限性，无法完全自动化的制造任务。这样的任务通常要求工人在靠近近处进行协作并适应彼此的决策和动议。该项目通过人机协作探讨完成这些任务。机器人技术的最新硬件发展使人类机器人的合作在身体上成为可能，但是机器人仍然需要新的算法来确保与人合作时的安全性，效率和流利性。创建这样的算法很困难，因为一个人将要做什么以及他们将如何做到这一点可能存在很大的不确定性。该项目探讨了关于一个人如何移动以及他或她如何将决策纳入机器人运动计划和决策框架的集成。该研究集中于用于建模，模拟和计划人类机器人协作的新算法框架的发展，这需要在机器人培训，任务建模，人类运动理解，不确定性的高维运动计划以及评估人类机器人联合行动的指标上取得进步。该项目的结果有可能提高美国在制造业中的竞争力；特别是对于小批量制造和爆发生产，完全自治解决方案的成本和设置时间是过于刺激的。这项工作将在研究论文中传播，并融入课程中。该项目由制造业的顾问委员会指导，该委员会提供了另一种传播途径。