Off-line Programming Techniques Research Articles

Spatial contours for vision and CAD model matching

Off-line programming techniques for artificial vision systems attempt to exploit existing databases. Sparing the reference image of a real part, the learning process is essentially based on 3D geometrical models, little adapted to image analysis. We suggest an intermediate description using spatial outlines, including global and local data. The former eliminate a large number of potential cases and the latter ensure the validity of the remaining solutions. This is a composite approach for the pattern matching process. The learning phase supplies us with a vision-oriented description obtained from a CAD model. Inversely, during the recognition phase, a CAD-oriented description is extracted from an image sequence. Tested on polyhedric samples and applied in the robotic field, this description has proved to be simple, robust and precise for part identification and localization using monocular vision.

Experimental investigation of the performance of a reconfigurable fixturing system

A reconfigurable fixturing system has been developed for computer-integrated assembly environments. The fixturing system employs a number of fixture modules that are set-up, adjusted and changed automatically by the assembly robot without human intervention. A commercially available computer-aided design (CAD) package with the help of a dedicated software program is used for the design, analysis, and verification of the fixture layout. The robot program for setting-up, adjusting, and dismantling the designed fixture is generated automatically. This paper presents and discusses the accuracy of such a reconfigurable fixturing system in view of the off-line programming techniques. The experimental techniques to measure the accuracy and repeatability for setting-up the fixture are presented. The measured results of the robot positioning various types of locating fixture modules are presented and compared with the intended position settings. From the comparison, the accuracy that is to be expected from such an approach to fixturing and measures for improvement are discussed. The cycle times involved in setting-up the fixture modules are also presented and analysed. These results provide an initial guide for manufacturing industries interested in employing such systems in their computer-integrated assembly environment.

Towards a New Generation of Multisensory Light-weight Robots with Learning Capabilities

Key items in the development of a new smart robot generation are explained by hand of DLR's recent activities in robotics research. These items are the design of multisensory gripper systems, ultra-light-weight links and joint drive systems with integrated joint torque control, learning and self-improvement of the dynamical behaviour, modelling the environment using sensorfusion, and new sensor-based off-line programming techniques based on teaching by showing in a (stereo)graphics environment. For each of these issues either simulated or real design results are given.

Geometric tools for the off-line programming of robots

SUMMARYOff-line programming of robots has a number of clear advantages over traditional ‘teach1’ methods which require the robot to be taken out of production. However, off-line programming techniques require extensive geometric facilities which are ideally provided by a geometric modelling system.The use of modelling covers the planning of the robot workcell, as well as the detailed planning of the robot operations. Assembly, in particular, requires detailed geometric information concerning geometric features and solid properties.