NRI: A Proactive Approach to Managing Contingencies during Human Robot Collaboration in Manufacturing

人类安全工业机器人的最新进展为创建混合工作单元提供了机会，在这种工作单元中，人类和机器人可以在密切的物理接近度上进行协作。这种能力使得能够实现利用人类和机器人互补优势的系统。在过去的几年里，市场上推出了几种新的低成本机器人，使它们在许多新的制造应用中具有吸引力。这使得混合电池的想法对于中小型制造商来说在经济上是可行的，这些制造商代表了美国制造业的一个非常重要的部分。人类和机器人都可能在混合细胞中犯错误，从而产生偶然情况。除非迅速处理，否则紧急情况可能导致业务效率严重低下。因此，混合电池不太可能具有成本效益，除非能够主动发现和管理紧急情况。这个国家机器人计划（NRI）奖支持基础研究，以实现在小批量生产操作的混合工作单元中人机协作期间产生的意外事件的主动管理。这项研究的结果将使工业机器人能够在小批量生产中引入，并有望使美国制造业在全球市场上具有成本竞争力。研究与研究生和本科生课程的整合将增强机器人和制造课程，丰富参与学生的学习经验。外联活动将教育和告知K-12学生有关机器人和制造业的就业机会。 需要在自动规划、单元监控、重新规划和人机交互方面取得根本性进展，以赋予混合单元有效的应急处理能力。本研究将调查明确考虑管理突发事件的任务规划和资源分配算法的设计计算基础。将开发用于实时监控任务进度的算法，以确保以安全和有效的方式完成任务。实时重新规划算法将被设计为基于观察到的任务执行性能来处理突发事件和细化计划。这项研究还将探索和描述人类和机器人之间有效信息交换的方法，以应对突发事件。

Recent advances in human-safe industrial robots present an opportunity for creating hybrid work cells, where humans and robots can collaborate in close physical proximities. This capability enables realizing systems that utilize complementary strengths of humans and robots. Several new low-cost robots have been introduced in the market over the last few years, making them attractive in many new manufacturing applications. This makes the idea of hybrid cells economically viable for small and medium manufacturers, which represent a very important segment of the manufacturing sector in the United States. Both humans and robots can make errors in a hybrid cell, hence creating contingency situations. Unless handled promptly, a contingency situation may lead to significant operational inefficiencies. Hence, hybrid cells are not likely to cost-effective unless contingency situations are proactively detected and managed. This National Robotics Initiative (NRI) award supports fundamental research to enable proactive management of contingencies arising during human-robot collaboration in hybrid work cells in small production volume manufacturing operations. Results from this research will enable introduction of industrial robots in small production volume operations and are expected to make US manufacturing industry cost competitive in the global market. The integration of the research with graduate and undergraduate courses will enhance the robotics and manufacturing curricula and enrich learning experiences of the participating students. Outreach activities will educate and inform K-12 students about career opportunities in robotics and manufacturing. Fundamental advances are needed in automated planning, cell monitoring, replanning, and human-robot interaction to endow hybrid cells with effective contingency handling capabilities. This research will investigate computational foundations for the design of task planning and resource allocation algorithms that explicitly account for managing contingencies. Algorithms will be developed for real-time monitoring of the task progress to ensure that tasks are completed in a safe and efficient manner. Real-time replanning algorithms will be designed to handle contingencies and refine plans based on the observed task execution performance. This research will also explore and characterize methods for effective information exchange between humans and robots to deal with contingencies.