Vision assisted robotic tele-training

Tao Sang, Elizabeth Croft, Mohammad Sameti

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther


This paper presents a self-calibrated vision system for human-guided robot task-learning. The system assists robot operators in training industrial robots quickly, safely, and accurately. The system can be used in various industrial environments and requires no predetermined model of the working space. The system self-calibrates to compute the initial sensor locations and orientations. Next, the user demonstrates the tool path that is to be followed by the robot arm using a 6 DOF training medium. Finally, the system optimizes the sensor locations so that, at those locations, the sensors can provide to the operator the sufficient images for the operator to observe and perform further remote training of the robot as required.

Original languageEnglish
Title of host publicationIEEE International Conference on Mechatronics and Automation, ICMA 2005
Number of pages6
Publication statusPublished - 17 Nov 2005
EventIEEE International Conference on Mechatronics and Automation 2005 - Niagara Falls, Canada
Duration: 29 Jul 20051 Aug 2005 (Proceedings)


ConferenceIEEE International Conference on Mechatronics and Automation 2005
Abbreviated titleICMA 2005
CityNiagara Falls
Other2005 International Conference on Mechatronics and Automation (ICMA) (formerly ICIMA)
Internet address


  • Camera Calibration
  • Camera Placement
  • Robotics
  • Tele-training
  • Vision

Cite this