NRI: INT: Balancing Collaboration and Autonomy for Multi-Robot Multi-Human Search and Rescue

每年，美国都有数千人失踪。协同搜救行动为找到生还的失踪人员提供了最好的机会。然而，具有挑战性的地形和其他搜索限制对人类搜索者来说是一个障碍。因此，该项目寻求实现人类搜索者和无人驾驶飞行器(UAV)之间的合作，以改进搜索，同时减少人力。具体地说，这个项目的问题是：我们如何选择和分配搜索任务，以确保人与机器人的长期合作，同时部署机器人以实时补充人类搜索人员？该项目旨在通过优化、行为建模、人机交互和计算来回答这个问题，并在SAR社区支持的大型原型中进行评估。最后，SAR以外的影响包括：(1)以协作机器人为重点的教育；(2)协作环境中人-机器人交互的理论；(3)适合广泛应用的便携式、低成本、低功耗的计算基础设施；(4)围绕协作机器人促进经济机会的技术；以及(5)为工程学中代表性不足的群体的学生提供的实地经验。本项目侧重于以下方面的新理论和技术：(1)利用具有风险意识的多机器人规划进行人在环(HITL)控制的微创、自适应、多无人机控制系统；(2)分布式计算，机会主义地利用和平衡多机器人的交互、通信、计算和决策；以及(3)人类搜索者和无人机之间的接口，允许从完全自主到手动操作的控制，包括用于勘探和开发战略的可测试接口。该项目解决了对多机器人多人团队的可扩展性至关重要的基本挑战：(1)无人机的规划和控制系统，该系统可以在适应不确定的人类计划的同时，以合作和分布式的方式自主收集信息；(2)人-机器人交互的接口，允许适当地平衡探索和开发；以及(3)实时支持，以分析、存储和共享数据，这些数据受制于现实世界部署中典型的电力和连接限制。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。

Each year, thousands of people go missing in the United States. Coordinated search and rescue (SAR) operations provide the best chance to locate a missing individual alive. However, challenging terrain and other search constraints represent a barrier to human searchers. This project therefore seeks to enable collaboration between human searchers and unmanned aerial vehicles (UAVs) to improve searches while reducing human effort. Specifically, this project asks: How do we select and assign search tasks that ensure long-term human-robot collaboration, while deploying robots to complement human searchers in real-time? This project aims to answer this question through optimization, behavioral modeling, human-robot interaction, and computation, with evaluation in large-scale prototypes supported by the SAR community. Finally, impacts beyond SAR include: (1) education focused on co-robots; (2) theory for human-robot interaction in collaborative settings; (3) portable, low-cost, low-power computational infrastructure suitable for a wide range of applications; (4) technologies that foster economic opportunity around co-robots; and (5) field experiences for students from groups underrepresented in engineering.This project focuses on new theory and technologies for: (1) a minimally invasive, adaptive, multi-UAV control system leveraging risk-aware multi-robot planning for human-in-the-loop (HITL) control; (2) distributed computing that opportunistically exploits and balances multi-robot interaction, communication, computation, and decision-making; and (3) an interface between human searchers and UAVs that allows control from complete autonomy to manual operation, including testable interfaces for exploration vs. exploitation strategies. This project addresses fundamental challenges critical to the scalability of multi-robot multi-human teams: (1) planning and control systems for UAVs that can autonomously gather information in a cooperative and distributed way while adapting to uncertain human plans; (2) interfaces for human-robot interactions that allows collaboration that appropriately balances exploration with exploitation; and (3) real-time support to analyze, store, and share data subject to the power and connectivity constraints typical of real-world deployments.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.