At the Computational Design Lab within the School of Architecture at Carnegie Mellon University, I explore the intersections of computation, robotics and machine learning (ML), with a current focus on the application of natural language processing (NLP) and deep learning in computational design. My recent work examines the application of new technologies in design fields; for instance, we have previously studied the use of robotic arms to enable novel fabrication methods (Borunda and Ladron de Guevara, 2018 – Borunda et al., 2019, Ladron de Guevara et al., 2019) how programming languages can enable new design methodologies that would be impossible otherwise (Ladron de Guevara et al., 2019, Ladron de Guevara et al., 2020). My recent work on ML and robotics in creative fields has explored how robots can appropriate a particular style of an artist under a learn-from-demonstration approach (Bidgoli et al., 2020). For the past year, this research has centered on multimodal ML to understand and visualize ambiguous natural language in the context of creative practice, with the aim to learn meaningful representations of words like “elegant”, “magical” or “sharp” that facilitate the localization, extraction and generation of their corresponding visual features in an image. If successful, this would enable a direct application of natural ambiguous language in design processes. My most recent publication yields optimistic results in early explorations of disentangling subjective design intents from images (Ladron de Guevara et al, 2020).

Artificial Intelligence

Ladron de Guevara, M., George, C., Gupta, A., Byrne, D., & Krishnamurti, R. (2020) “Multimodal Word Sense Disambiguation in Creative Practice”. In IEEE International Conference on Machine Learning and Applications.

Video presentation

Bidgoli, A., Ladron De Guevara, M., Hsiung C., Oh J., and Kang E. (2020) “Artistic Style in Robotic Painting; a Machine Learning Approach to Learning Brushstroke from Human Artists.” In Proceedings of the 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). Naples.

Computational Design and Robotic Fabrication 

Ladron de Guevara, M., Borunda, L. R., Byrne, D., & Krishnamurti, R. (2020). Multi-resolution in architecture as a design driver for additive manufacturing applications. International Journal of Architectural Computing.

Ladron de Guevara M., Borunda L., Krishnamurti R. (2019) A Multi-resolution Design Methodology Based on Discrete Models. In: Lee JH. (eds) Computer-Aided Architectural Design. “Hello, Culture”. CAAD Futures 2019. Communications in Computer and Information Science, vol 1028. Springer, Singapore.

Ladron de Guevara M., Borunda L., Ficca, J., Byrne, Daragh., Krishnamurti R. (2019) “Robotic Free-Oriented Additive Manufacturing Technique for Thermoplastic Lattice and Cellular Structures”,  In M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed – Proceedings of the 24th CAADRIA Conference – Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 333-342.

Borunda L., Ladron de Guevara M., Anaya J. (2019) “Design Method for Optimized Infills in Additive Manufacturing Thermoplastic Components”,  In J.P. Sousa, G. C. Henriques, J. P. Xavier (eds.), Architecture in the age of the 4th Industrial Revolution – Proceedings of the eCAADE 37 / SIGraDI 23 Conference – Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 493-502. 

Borunda, L., Ladron de Guevara, M., Anaya, J. and Pugliese, G., (2018) “Optimized Additive Manufacturing Building Components”. In 4th International Conference on Technological Innovation in Building (CITE), Madrid.

Borunda, L., Ladron de Guevara, M., Anaya J., Pugliese G., (2018) “Human-Machine Collaboration Practices for Manufacturing Digitally Designed Complex Surfaces”, In the International Conference on Construction Research – Eduardo Torroja AEC.

%d bloggers like this: