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 484
Reformat results as: short short into frame detailed detailed into frame
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.
To test the approach, a single catenary arch was generated using form-finding techniques and sequentially built from foam blocks. Moving forward we show the relationship between the joint valence (largest number of joined branches) of a multi-branched structure and the minimum number of robotic arms required for assembly using our initial technique. With only two robotic arms available, the technique was further developed to reduce the required number of arms per arch branch from two to one by attaching caterpillar tracks at the block supporting end effector. This allows a human to load the next block and the arm to move forward along the arch while maintaining equilibrium. Results show that robotic equilibrium scaffold free arch assembly is possible and can reduce scaffold waste and maintain the material efficiency of compression only structures. Future work will explore further applications of assistive robotics in construction replacing static construction aids with dynamic sensory feedback of equilibrium forces.
Referring to variations of the architectural drawing from a domestic typology, the paper uses high-precision digital tools tailored to quantitative image analysis and digital tools that sit outside the remit of architectural production, such as word processing, to present a new range of drawing techniques. By applying a series of traditional analytical procedures to the image, it reveals how these maneuvers can interrogate and dislocate any predetermined formal normalization.
The paper reveals that the interdisciplinary repurposing of precise digital toolsets therefore has explicit disciplinary consequences. These arise as a direct result of the recalibration of scale, the liberation of the bit’s representational capacity, and the pixel’s properties of color and brightness. It concludes by proposing that deliberate instances of translational imprecision are highly productive, because by liberating the fundamental qualitative properties of the fundamental digital units, these techniques shift the disciplinary agency of the architectural drawing
For more results click below: