There is an increasing demand for space robotic systems which can reduce the number of potentially hazardous EVA's on manned space missions. In addition, telerobotic maneuvers can easily become long and tiresome for the operator. This paper describes a robotic system which accepts motion and control commands which can be generated autonomously. The system developed has been designed to perform an autonomous grapple based on guidance control feedback provided by images from a single camera mounted on the slave robot's end effector. The vision system consists of three parts. The first part is signature based, trained on an arbitrary grapple interface (i.e. no special targets are required for guidance); it provides estimates for the 3D attitude of the interface by interpolating sampled signature correlations. These signatures are essentially the distribution of line orientations obtained by radial integration of the Fourier transform of a pre-processed edge image. The second part estimates the range and bearing of the interface based on the first and second moments of the preprocessed edge image of the interface. And the third stage of the algorithm verifies the results. The robot path follows a linear translation trajectory which is repeatedly adjusted for errors via the vision system. The end effector's attitude is adjusted along the trajectory such that the grapple interface always remains in center view of the camera.
A smart telerobotic system driven by monocular vision
Ein smartes Telerobotersystem mit Lenkung über ein monokulares Sichtsystem
1994
8 Seiten, 8 Bilder, 5 Tabellen, 13 Quellen
Aufsatz (Konferenz)
Englisch
Smart Telerobotic System Driven by Monocular Vision
NTIS | 1994
|A smart telerobotic system driven by monocular vision
NTRS | 1994
|A vision-based telerobotic control station
NTRS | 1990
|