CAREER: Toward Automating Surgical Tasks

职业：实现手术任务自动化

• 批准号: 1149965
• 负责人: Ron Alterovitz
• 金额: $ 44.96万
• 依托单位: University of North Carolina at Chapel Hill
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-03-01 至 2019-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1149965&HistoricalAwards=false
• 关键词: CAREER; Toward; Automating; Surgical; Tasks

This project, developing a new motion planning framework for medical robots that combines automatic planning algorithms, robot control, and human oversight to enable new and safer robotic procedures that are beyond current clinical capabilities, will increase the autonomy of surgical robotic systems. This framework will result in improved speed, accuracy, and precision of existing procedures and enable entirely new classes of procedures that require dexterity and control beyond the capability of a human operator. The funding of this proposed work will introduce and evaluate a new motion planning framework that simultaneously addresses the challenges of deformations, uncertainty, and optimality that arise in medical applications. The research will combine ideas from multiple areas of computer science and engineering, including robotics, computer graphics, finite element methods, optimization theory, Markov decision processes, stochastic modeling, and learning from demonstrations. Expected scientific contributions include new motion planning algorithms that efficiently integrate physically-based simulation, motion planning under uncertainty, and sensor placement, as well as new approaches to integrate user input into feedback-based motion planning. In the long term, these contributions may lead to new avenues of research at the intersection of motion planning, anatomy and biomechanical modeling, learning from demonstrations, and medical robotics.Broader Impacts: A motion planning framework for medical robots will improve patient care and the resulting increased autonomy will reduce surgical errors -- which currently contribute to 1 in 10 post-surgical deaths -- by enabling physicians to focus on high-level tasks rather than low-level motion control. The application of this framework to prostate interventions, lung biopsies, and neurosurgery could affect hundreds of thousands of people annually and have broad societal impact. The ability of computer science to improve healthcare may attract new students to computer science who might previously not have been interested in the field, particularly women and underrepresented groups. The PI will develop new outreach activities centered around an interactive game-like simulation of medical procedures that highlights the impact that computer science can have on medicine, create a new undergraduate course for pre-meds to teach future physicians crucial computer science concepts, and revamp the robotics curriculum to create excitement through labs and provide students with the skills necessary to pursue a career in America's growing healthcare and service robotics industries.

该项目为医疗机器人开发了一种新的运动规划框架，该框架结合了自动规划算法、机器人控制和人类监督，使新的、更安全的机器人程序超越了当前的临床能力，将增加手术机器人系统的自主性。该框架将提高现有程序的速度、准确性和精度，并使需要灵巧性和控制能力超出人类操作员能力的全新程序类别成为可能。这项拟议工作的资金将引入和评估一个新的运动规划框架，同时解决医疗应用中出现的变形、不确定性和最优性的挑战。该研究将结合计算机科学和工程多个领域的思想，包括机器人、计算机图形学、有限元方法、优化理论、马尔可夫决策过程、随机建模和从演示中学习。预期的科学贡献包括新的运动规划算法，有效地集成了基于物理的仿真，不确定性下的运动规划和传感器放置，以及将用户输入集成到基于反馈的运动规划中的新方法。从长远来看，这些贡献可能会导致运动规划，解剖学和生物力学建模，演示学习和医疗机器人交叉研究的新途径。更广泛的影响：医疗机器人的运动规划框架将改善患者护理，由此增加的自主性将减少手术失误——目前，手术失误导致十分之一的术后死亡——使医生能够专注于高水平的任务，而不是低水平的运动控制。将这一框架应用于前列腺干预、肺活检和神经外科，每年可能影响数十万人，并产生广泛的社会影响。计算机科学改善医疗保健的能力可能会吸引以前对该领域不感兴趣的新学生，特别是女性和代表性不足的群体。PI将开发新的推广活动，以互动游戏式的模拟医疗程序为中心，突出计算机科学对医学的影响，为医学预科开设新的本科课程，向未来的医生教授关键的计算机科学概念，并修改机器人课程，通过实验室让学生感到兴奋，并为学生提供在美国不断发展的医疗保健和服务机器人行业中从事职业所需的技能。