NRI-Small: Perceptually Inspired Dynamics for Robot Arm Motion

为了使机器人高效地与人类协作，在运动创建中必须考虑人类对其运动的感知。由于人类合作者将解释机器人的动作(即使是下意识地)，不考虑人类观察者的机器人运动合成算法可能会产生被错误感知、负面解释(例如，愤怒或威胁)的动作，或者至少错失有效使用这一微妙通信渠道的机会。这个项目的关键思想是发展对人类对运动的感知的理解，这可以应用于机器人轨迹规划和控制算法的开发。该团队将使用人体受试者实验来理解和评估运动的解释，并将这些发现应用于机器人学和运动合成。该研究计划包括人们如何解释动作的经验研究，创建以可控方式生成机器人动作的方法的算法开发，以及允许PI评估方法成功的情景部署。该项目的成功将使人们更深入地了解人们如何解释动作，合成机器人动作的新算法，并展示协作机器人的潜在应用。广泛的影响：感知启发的机器人动作合成算法将使机器人能够更有效地与人类合作。它将使更善于交流的机器人能够充当教师和向导；更容易接近和接受的机器人可以在家庭环境中工作，例如老年人护理；更多合作的机器人可以作为工人的助手；以及更容易指导可以由非专家训练的机器人。该项目将通过将经验性的人体研究与机器人轨迹规划的技术挑战联系起来，加强高技术专业人员的教育和推广工作。

In order for robots to collaborate efficiently and effectively with humans, the human perception of their movement must be considered in motion creation. Because a human collaborator will interpret the movements of a robot (even subconsciously), robot motion synthesis algorithms that do not consider the human observer may create motions that are perceived incorrectly, interpreted negatively (e.g. as being angry or threatening), or at least miss out on the opportunity to use this subtle communication channel effectively. The key idea of this project is to develop an understanding of human perception of movement that can be applied to the development of robot trajectory planning and control algorithms. The team will use human subjects experiments to understand and evaluate the interpretation of movements and apply these findings in robotics and motion synthesis. The research plan interleaves empirical studies of how people interpret motions, algorithm development to create methods that generate robot motions in a controllable manner, and contextualized deployments that allow the PIs to evaluate the success of the methods. The success of the project will provide a deeper understanding of how people interpret movements, new algorithms for synthesizing robot movements, and demonstrations of the potential applications of collaborative robots.Broader Impact: Perceptually inspired robot motion synthesis algorithms will enable robots to collaborate more effectively with people. It will enable more communicative robots that can serve as teachers and guides; more approachable and acceptable robots that can work in domestic situations such as elder care; more cooperative robots that can work as assistants to workers; and easier to instruct robots that can be trained by non-experts. This project will enhance the education and outreach efforts of hte PIs by connecting empirical human studies to the technical challenges of robot trajectory planning.