An Intelligent Tutor for Tele-Robotics Training

RomanTutor is a tutoring system that uses sophisticated domain knowledge to monitor the progress of students and advise them while they are learning how to operate a space telerobotic system. It is intended to help train operators of the Space Station Remote Manipulator System (SSRMS) including astronauts, operators involved in ground-based control of SSRMS and technical support staff. Currently there is only a single training facility for SSRMS operations and it is heavily scheduled. The training staff time is in heavy demand for teaching students, developing teaching material and new teaching tools. For example, all SSRMS simulation exercises are developed by hand and this process requires a lot of staff time. Once in orbit ISS astronauts currently have only simple web-based material for skill development and maintenance. For long duration space flight astronauts will require sophisticated simulation tools to maintain skills. RomanTutor addresses these challenges by providing a sophisticated portable training tool. It incorporates a model of the system operations curriculum, a kinematic simulation of the robotics equipment and the ISS and a high performance path planner. For each element of the curriculum that the student is supposed to master, RomanTutor is able to generate example tasks for the student to accomplish within the simulation environment.

[1]  Sebastian Thrun,et al.  Anytime Dynamic A*: An Anytime, Replanning Algorithm , 2005, ICAPS.

[2]  Leo Hartman,et al.  Anytime dynamic path-planning with flexible probabilistic roadmaps , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[3]  Roger Nkambou,et al.  Path-Planning for Autonomous Training on Robot Manipulators in Space , 2005, IJCAI.

[4]  Leo Hartman,et al.  Planning 3D Task Demonstrations of a Teleoperated Space Robot Arm , 2008, ICAPS.

[5]  Jean-Claude Latombe,et al.  A Single-Query Bi-Directional Probabilistic Roadmap Planner with Lazy Collision Checking , 2001, ISRR.

[6]  Luke S. Zettlemoyer,et al.  Task-sensitive cinematography interfaces for interactive 3D learning environments , 1998, IUI '98.

[7]  Dinesh Manocha,et al.  Fast distance queries with rectangular swept sphere volumes , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[8]  Fahiem Bacchus,et al.  Using temporal logics to express search control knowledge for planning , 2000, Artif. Intell..

[9]  Mark H. Overmars.  Recent Developments in Motion Planning , 2002, International Conference on Computational Science.

[10]  Jean-Claude Latombe,et al.  Robot motion planning , 1970, The Kluwer international series in engineering and computer science.

[11]  Steven M. LaValle,et al.  On the Relationship between Classical Grid Search and Probabilistic Roadmaps , 2004, Int. J. Robotics Res..

[12]  David Salesin,et al.  Declarative Camera Control for Automatic Cinematography , 1996, AAAI/IAAI, Vol. 1.