Abstract

Autonomy in robotic surgeries has advantages of improved surgical efficiency, decreased surgeon fatigue, and potentially leads to improved surgical outcomes. This talk presents our latest efforts towards surgical robotic autonomy on 1) Raven II surgical robot sensorless gripping force and state estimation, 2) motion planning based on Recurrent Neural Networks(RNNs), and 3) software design for preoperative planning in endoscopic sinus and skull base surgeries. In force estimation experiments, we compared a  non-parametric estimator (Gaussian Process Regression) with a nonlinear filter (Unscented Kalman Filter) based method and found the results from former is more conservative than the latter. In motion planning, we demonstrated RNN control schemes can be easily adapt to various optimization targets and constraints, such as joint velocity regularization or soft obstacle avoidance. In preoperative planning, we demonstrated the design of an interactive preoperative surgical planning software, which helps us to better understand endoscopic surgeries.

Bio

Yangming Li is an acting instructor at BioRobotics Lab, University of Washington. Prior to this position, he was an associate professor at Institute of Intelligent Machines, Chinese Academy of Sciences, where he received Young Researcher Award (2011) from National Science Foundation of China. He also worked as Postdoc at University of Michigan. He received a PhD from a joint program by University of Science and Technology of China and University of Michigan in 2010. His early research interest was Simultaneous Localization and Mapping, and now he is interested in improving surgical outcomes with robotic surgeries.