This is part of the Multilateral Manipulation by Human-Robot Collaborative Systems project. Robotic surgeries nowadays are still performed "manually" by surgeons. However, a lot of surgical procedures are repetitive and take long time, which can cause fatigue and may affect surgery outcome. We are interested in automating some of the surgical procedures with intelligent robotic systems and algorithms. Specifically, we would like to develop surgical robots that can assist and collaborate with surgeons.

​

In this project, we developed algorithms for a surgical robot to autonomously assist human operator in a tissue resection task. We used the da Vinci Research Kit (dVRK) as our robot platform. The robot can either help the operator to hold the tissue sample, or cutting along the desired path while the operator holds the tissue. Below is a video showing the procedure. We implemented the algorithm under a shared-control framework, where the operator can supervise the robot and take control from the robot at any time. The robot's motion is learned from human demonstration. We showed that the task performance can be improved with the robot's assistance.

​

Paper Reference:

K. Shamaei, Y. Che, A. Murali, S. Sen, S. Patil, K. Goldberg, and A. M. Okamura. "A paced shared-control teleoperated architecture for supervised automation of multilateral surgical tasks." In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1434-1439. IEEE, 2015.