CAREER: Advancing Autonomy for Soft Tissue Robotic Surgery and Interventions

这项由教师早期职业发展（CAREER）资助的研究将为我们在机器人技术和与医疗保健相关的自主性方面的基础知识做出贡献。自主机器人手术系统有可能显着提高效率，安全性和一致性，超过目前的远程操作机器人辅助手术。肾肿瘤切除术和肠道手术等软组织手术的并发症率分别高达18%和30%。 机器人手术有一个显著的学习曲线，医院之间的手术结果差异很大，外科医生的术后并发症也有很大差异。该项目将使新一代手术机器人的开发具有更高的自主性，从而降低并发症发生率并改善独立于外科医生经验的结果。这项研究有可能通过提供一致的专家级结果来实现最高水平医疗保健的民主化，通过提高效率来减轻不断上涨的医疗成本，并通过保护医疗工作者来帮助未来的流行病。因此，本研究的结果将有利于美国的社会福利和经济。机器人和自主权的多学科研究和教育活动，以及从计算机视觉，传感，人工智能到医疗保健等相关的各种知识社区，将有助于激励来自传统上在科学，技术，工程和数学（STEM）中代表性不足的群体的各种学生，并大大增加对机器人研究的参与。目前的自动化操作方法无法模仿训练有素的人类在不同的，非结构化的，可变形的环境中执行复杂的操作任务。这些关于可变形组织跟踪的研究和实验将产生用于在非结构化环境中识别和跟踪细微组织目标的新技术。对变形预测的研究将产生理解组织行为和如何补偿变形的方法。该项目的控制设计活动将通过提供最大化自主性的新策略来解决自主机器人控制器的不足，同时提供故障安全操作。该项目由跨部门的机器人基础研究项目支持，该项目由工程部（ENG）和计算机与信息科学与工程部（CISE）共同管理和资助。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The research supported by this Faculty Early Career Development (CAREER) grant will make contributions to our fundamental knowledge in robotics and autonomy related to healthcare. Autonomous robotic surgery systems have the potential to significantly improve efficiency, safety, and consistency over current tele-operated robotically assisted surgery. Complication rates of soft tissue surgery such as kidney tumor resections and bowel surgery reach up to 18 and 30 percent, respectively. There is a significant learning curve in robotic surgery, surgical outcomes vary greatly between hospitals, and postoperative complications differ significantly by surgeon. This project will enable the development of a new generation of surgical robots with increasing levels of autonomy that reduce complication rates and improve outcomes independent of surgeon’s experience. This research has the potential to democratize access to the highest level of healthcare by providing consistent expert-level results, mitigate the rising healthcare costs by increasing efficiency, and help in future pandemics by protecting healthcare workers. Thus, results from this research will benefit the US society welfare and economy. The multi-disciplinary research and education activities in robotics and autonomy and related diverse set of intellectual communities ranging from computer vision, sensing, artificial intelligence, to healthcare will help to inspire a diverse set of students from groups that have been traditionally underrepresented in science, technology, engineering, and mathematics (STEM) and to substantially increase participation in robotics research. Present day approaches to automated manipulation are unable to emulate highly trained humans in the performance of complex manipulation tasks in varying, unstructured, and deformable environments. These research and experiments on deformable tissue tracking will yield new techniques for identifying and tracking subtle tissue targets in unstructured environments. The research on deformation prediction will produce methodologies for understanding tissue behavior and how to compensate for deformations. The control-design activities of this project will address shortfalls in autonomous robot controllers by providing new strategies maximizing autonomy, while providing fail-safe operation. This project is supported by the cross-directorate Foundational Research in Robotics program, jointly managed and funded by the Directorates for Engineering (ENG) and Computer and Information Science and Engineering (CISE).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.