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.

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.

The paper contextualizes the approach with respect to the current state of the art of the usage of artificial neural networks both in architecture and beyond. It illustrates the cyber physical system that is at the core of this research, with a focus on the employed neural network–based computational method. Finally, the paper discusses the repercussions of these design tools on the contemporary design paradigm.

CityMatrix was introduced to address these challenges. Machine learning techniques were applied to achieve real-time prediction of multiple urban simulations, and thousands of city configurations were simulated. The simulation results were used to train a convolutional neural network (CNN) to predict the traffic and solar performance of unseen city configurations. The prediction with the CNN is thousands of times faster than the original simulations and maintains a high-quality representation of the results. This machine learning approach was applied as a versatile, quick, accurate, and computationally efficient method not only for real-time feedback, but also for optimized design recommendations. Users involved in the evaluation of this project had a better understanding of the embodied trade-offs of the city and achieved their goals in an efficient manner.