Robotic surgery has significantly improved the quality of surgical procedures. In the past, researches have been focused on automating simple surgical actions, however there exists no scalable framework for automation in surgery. In this paper, we present a knowledge-based modular framework for the automation of articulated surgical tasks, for example, with multiple coordinated actions. The framework is consisted of ontology, providing entities for surgical automation and rules for task planning, and “dynamic movement primitives” as adaptive motion planner as to replicate the dexterity of surgeons. To validate our framework, we chose a paradigmatic scenario of a peg-and-ring task, a standard training exercise for novice surgeons which presents many challenges of real surgery, e.g. grasping and transferring. Experiments show the validity of the framework and its adaptability to faulty events. The modular architecture is expected to generalize to different tasks and platforms.
|Titolo:||A knowledge-based framework for task automation in surgery|
|Data di pubblicazione:||2019|
|Appare nelle tipologie:||04.01 Contributo in atti di convegno|