Junzo Hasegawa

Image preprocessor of model-based vision system for assembly robots

A special purpose image preprocessor for the visual system of assembly robots has been developed. The main function unit is composed of look-up tables to utilize the advantage of semiconductor memory for large scale integration, high speed and low price. More than one units may be operated in parallel since it is designed on the standard IEEE 796 bus. The operation time of the preprocessor in line segment extraction is usually 200 ms per 500 segments, though it differs according to the complexity of scene image. The gray-scale visual system supported by the model-based analysis program using the extracted line segments recognizes partially visible or overlapping industrial workpieces, and detects these locations and orientations. In recognition test using plastic workpieces, the recognition time was about 9 seconds for five pieces. In most of conventional model-based vision systems, the feature extraction time was extremely longer than that of the model-based analysis. The image preprocessor we have developed reduces the time ratio of feature extraction and model-based analysis to about 1/10.

TL-10: a programming language for assembly robots

TL-10, Toyoto Robot Language-10, is a BASIC-like robot language. It has functions that define locations and subroutine parameters, which are useful in the accumulation and the transference of robot applied technology. It also has functions to communicate with other computers such as those for vision systems. The important features are described and illustrated by examples.