Using Vision Data in an Object-Level Robot Language — RAPT

Publisher Website
Google Scholar
Abstract
This paper describes the use of verification vision in an ob ject-level language for robot assembly (RAPT). In particular, a representation scheme for making full use of vision infor mation to update the robot system's knowledge about its environment is discussed. By using newly introduced vision commands, the user can specify vision verification tasks in order to determine the difference between the planned posi tions and the actual positions of objects in the robot's envi ronment. A symbolic reasoning system reasons about the spatial constraints at compile time and produces symbolic position expressions of the objects to be verified, which con tain variables to be instantiated by vision data at run time. A framework for handling vision data combines run time and compile time information in a general way so that all ramifi cations of the effect of the changed position determined by verification vision are taken into account. The new vision commands and the framework will be discussed in detail.

This publication has 2 references indexed in Scilit: