CAREER: Shared Control for Skill Transfer in Human-Robot Haptic Interactions

这项研究的主要目标是通过触觉设备提高技能转移、康复和协作的有效性。为此，PI将制定针对训练、康复和协作设计的触觉系统中人类和机器人之间共享控制的要求。由两个具有力感应能力的商业触觉设备组成的实验试验台将在整个项目中使用。PI将研究两种用于技能转移的共享控制系统架构。在第一种情况下，人类充当新手或患者，机器人充当专家。对专家系统(触觉装置)的控制方案进行了理论和实验分析。研究工作的第二阶段将探索人-机器人-人的界面。在这里，PI将专注于专家-新手和治疗师-患者团队，机器人系统充当两者之间的调解人。这项研究和教育计划的智力价值在于，将利用人的因素和控制系统设计来开发有效的人-机器人系统，用于技能转移和康复。一系列基本的人-机器人交互问题将在理论和实验上得到解决：(1)人与机器人之间有效的技能转移的系统架构的设计；(2)作为人-机器人交互模型的人-人团队之间的技能转移；(3)通过有效地控制对系统每个成员的反馈来促进有效的技能转移的控制算法的设计和实现。这项工作的更广泛影响是通过更高效和更有效的机器人辅助康复实践来改善医疗保健，增强国防和外科应用的技能培训，以及提高对人-机器人相互作用的理解，以进行技能转移。具体的教育目标是使用触觉设备创建创新的实验室模块，以加强学生对重要工程概念的学习，重振机器人入门课程，包括触觉和机器人实践实验，以及高中推广活动，包括实习、校园生活和使用触觉的演示，以鼓励学生在科学和工程领域追求职业生涯。这些教育目标中的每一个都与PI现有的NSF对课程改进的支持密切相关，并进一步支持了她将研究和教育结合到一个连贯和综合的职业计划中的承诺

The primary goal of this research effort is to improve the effectiveness of skill transfer, rehabilitation, and collaboration via haptic devices. To do so, the PI will formulate requirements for shared control between humans and robots in haptic systems designed for training, rehabilitation, and collaboration. An experimental test-bed comprised of two commercial haptic devices with force sensing capabilities will be employed throughout the project. The PI will study two shared control system architectures for skill transfer. In the first, the human acts as the novice or patient, and the robot serves as the expert. Control schemes for the expert system (the haptic device) will be designed and analyzed theoretically and experimentally. The second phase of the research effort will explore human-robot-human interfaces. Here, the PI will focus on expert-novice and therapist-patient teams, with a robotic system acting as the mediator between the two. The intellectual merit of this research and education plan is that human factors and control system design will be used to develop effective human-robot systems for skill transfer and rehabilitation. A set of fundamental human-robot interaction issues will be addressed theoretically and experimentally: (1) the design of system architectures for effective skill transfer between humans and robots, (2) skill transfer between human-human teams as a model for human-robot interaction, and (3) the design and implementation of control algorithms that promote efficient skill transfer by effectively controlling feedback to each member of the system. The broader impacts of this work are improved health care through more efficient and effective robot assisted rehabilitation practices, enhanced skill training for defense and surgical applications, and improved understanding of human-robot interactions for skill transfer. Specific education goals are to create innovative laboratory modules using haptic devices to enhance student learning of important engineering concepts, reinvigorate an introductory robotics course to include hands-on experiments with haptics and robotics, and high school outreach that includes internships, days-on-campus, and demonstrations using haptics to encourage students to pursue careers in science and engineering. Each of these educational goals ties closely to the PI's existing NSF support for curriculum enhancement, and further supports her commitment to combining research and education into a cohesive and integrated career plan