︎

︎  arpastrana@princeton.edu

︎ @arpastrana
︎ @arpastrana

︎ Publications

Rafael is a Ph.D. candidate at Princeton. He develops auto-differentiable tools for structural design. Some examples include JAX FDM and COMPAS CEM.

Rafael holds a Master of Advanced Studies in Architecture and Digital Fabrication from the Swiss Federal Institute of Technology (ETH) Zurich. For over 3 years, he worked at Bollinger + Grohmann where he was responsible for the structural analysis and geometric rationalization of art installations in Europe and in Australia.

Rafael colaborated with the Block Research Group. There he contributed to the development of a COMPAS package to streamline the generatation of the fabrication data for one of the full-scale prototypes of the functionally-integrated, funicular floors at the NEST HiLo.

At Gramazio Kohler Research, and in collaboration with Autodesk, Rafael participated in the deployment of a reinforcement learning model that automatically overcame geometrical and material inaccuracies occurring during the robotic assembly of timber structures.