REU Site: Undergraduate Robotics Research in Human-Swarm Interaction

西弗吉尼亚大学(WVU)的本科生研究体验(REU)网站每年将允许8名本科生进行最先进的机器人研究，其中大部分来自阿巴拉契亚地区。通过向他们挑战现实世界的问题，该项目将为本科生提供培训、指导和支持，使他们能够成为独立的研究人员。整个项目管理战略将遵循群体智能的精神：鼓励不同本科生群体之间的频繁互动，以实现原本可能仅靠个人无法实现的目标--例如，推进人类群体互动研究的最先进水平。在整个项目中，教师和研究生导师将鼓励创造性思维和频繁的互动，以提高学生解决问题的能力。这将使他们从被动的学习者转变为未来的独立思考者。这一努力反过来将有助于在机器人重要领域发展一支高素质和多样化的美国科学劳动力队伍。该项目的智力重点是允许一名人类操作员有效地管理大型机器人群，以实现预期的全球目标。在这个REU项目中，本科生将围绕一个受鹰的合作热翱翔和觅食行为启发的群体系统定制三个子项目。首先，将开发一个由50个定制设计的机器人组成的群体测试环境。其次，将研究允许出现期望的机器人群行为的分布式的、非层次化的代理级交互规则。第三，将发明一种新的人-群交互模式，用于管理大型自组织机器人群，而不使用操作员和机器人之间的直接命令和控制结构。通过这些努力，本科生将有机会作为一个团队进行基础研究和动手实验。该项目的成功完成将使许多潜在的机器人应用成为可能，如搜救、环境监测、机器人采矿和建筑。该项目的成果将通过演示视频、同行评议出版物和已开发软件的公开分享广泛传播。该项目由计算机和信息科学与工程局的信息和智能系统部和既定的激励竞争研究计划(EPSCoR)共同资助。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。

This Research Experiences for Undergraduates (REU) Site at West Virginia University (WVU) will allow eight undergraduate students each year, mostly from the Appalachian region, to perform state-of-the-art robotics research. Through challenging them with real-world problems, this project will provide training, mentorship and support to undergraduate students so that they can become independent researchers. The overall project management strategy will follow the spirit of swarm intelligence: encouraging the frequent interactions among a diverse group of undergraduate students to achieve something that might not otherwise be achievable by the individuals alone - for example, advancing the state-of-the-art in human-swarm interaction research). Throughout the project, the faculty and graduate student mentors will encourage creative thinking and frequent interactions to enhance the students' problem solving skills. This will allow them to transition from passive learners to independent thinkers of the future. This effort in turn will contribute to the growth of a high-quality and diverse US scientific workforce in the important area of robotics.The intellectual focus of this project is to allow one human operator to effectively manage a large robot swarm to achieve desired global objectives. Tailored around a swarm system inspired by the cooperative thermal soaring and foraging behaviors of hawks, three sub-projects will be conducted by undergraduate students during this REU project. First, a swarm testing environment with 50 custom designed robots will be developed. Second, distributed, non-hierarchical agent-level interaction rules that will allow the emergence of desirable robot swarm behaviors will be investigated. Third, novel human-swarm interaction modes for managing a large self-organized robot swarm without using a direct command and control structure between the operator and robots will be invented and experimentally demonstrated. Through these efforts, the undergraduate students will have the opportunity to work as a team in performing both fundamental research and hands-on experiments. The successful completion of the project will enable many potential robot applications such as search and rescue, environmental monitoring, and robotic mining and construction. The outcomes from this project will be broadly disseminated through demonstration videos, peer-reviewed publications, and open sharing of the developed software. This project is jointly funded by the Information and Intelligent Systems Division of the Computer and Information Science and Engineering Directorate and the Established Program to Stimulate Competitive Research (EPSCoR).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.