CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures
Hits 1 to 20 of 627
Reformat results as: short short into frame detailed detailed into frame
This paper presents the results of an interactive installation in which visitors can provide any variety of objects to a collaborative robotic manipulator (UR5) which recognizes part geometry and attempts to construct a dry-stacked wall from the material offerings. A visual and auditory interface provides suggestions and error messages to participants to facilitate an understanding of the acceptable material morphologies which can be used within the constraints of the system.
In this work, we present progress on the application of contemporary ML techniques to the design process in the architecture, engineering, and construction (AEC) industry. We introduce a technique to partially circumvent the data hungriness of neural networks, which is a significant impediment to their application outside of the ML research community. We also show results on the applicability of this technique to real-world drawings and present research that addresses how some fundamental attributes of drawings as images affect the way they are interpreted in deep neural networks. Our primary contribution is a technique to train a neural network to segment real-world architectural drawings after using only generated pseudodrawings.
For more results click below: