Learning algorithms for a soft robot manipulator in a minimally invasive surgery scenario
In minimally invasive surgery, tools go through narrow openings and manipulate soft organs to perform surgical tasks. There are limitations to current robot-assisted surgical systems due to the rigidity of robot tools. The aim of the STIFF-FLOP European project is to develop a soft robotic arm to perform surgical tasks by actively controlling the selected body parts of the robot. The flexibility of the robot allows the surgeon to move within organs to reach remote areas of the body and perform challenging procedures in laparoscopy.
The surgeon controls the end-effector during the surgical task, leaving the motion of the whole arm to the control and learning modules. The latter should drive the body of the robot along the trajectory followed by the surgeon, without applying pressure to or damaging the internal organs of the patients. The proposed learning algorithm works in the null space of the surgical manipulator, to avoid interfering with the surgeon and exploiting redundancy in an optimal way.