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.

Agency
National Science Foundation (NSF)
Institute
Division of Information and Intelligent Systems (IIS)
Application #
1149965
Program Officer
Reid Simmons
Project Start
Project End
Budget Start
2012-03-01
Budget End
2019-02-28
Support Year
Fiscal Year
2011
Total Cost
$499,542
Indirect Cost
Name
University of North Carolina Chapel Hill
Department
Type
DUNS #
City
Chapel Hill
State
NC
Country
United States
Zip Code
27599