Generating tutoring feedback in an intelligent training system on a robotic simulator

Abstract

Manipulating the Space Station Remote Manipulator (SSRMS), known as "Canadarm II", on the International Space Station (ISS) is a very challenging task. The astronaut does not have a direct view of the scene of operation and must rely on cameras mounted on the manipulator and at strategic places of the environment where it operates. In this paper, we present Roman Tutor, an intelligent robotic simulator we are developing to address this kind of problem. We also show how a new approach for robot path planning called FADPRM could be used to provide amazingly useful tutoring feedback for training on such a manipulator and under this big constraint of restricted sight. © Springer-Verlag Berlin Heidelberg 2006.