The aim of the Computational Urban Design course is to empower students with the capacity to fully understand and exploit computational thinking in order to design complex algorithmic pipelines from raw data to design.
It exploits Grasshopper 3D as the main computational tool due to its intuitiveness, and its large use in the AEC and the planning field. Despite no prior knowledge of programming is required, throughout the course students will master advanced computational logics that will enhance their design workflows.
In the third term of the Computational Urban Design course, we delve into the urgent and inspiring debate on the role of Artificial Intelligence in the field of architecture. Building upon the foundational skills acquired in the previous seminars, the course aims to explore the implications and potentialities of state-of-the-art (SOTA) online ML models within the context of computational design. Technically, students will be guided to create tailored pipelines, integrating ML models within Rhinoceros 3D through Grasshopper and CPython scripts, to implement AI algorithms in three-dimensional environments. The primary objective is to increase awareness of the breadth of ML products available and stimulate curiosity about unconventional applications for architects and planners, diverging from mainstream methodologies.
Through a blend of theoretical insights and hands-on exercises, participants will actively engage in crafting AI-assisted architectural outputs, fostering a creative and exploratory design approach. Overall, the course will emphasise on the application aspect of ML models in 3D modelling, rendering, and visualisation, setting the stage for a separate course dedicated to the underlying principles of machine learning. By the end of this term, students will not only have acquired the technical skills to integrate AI into their design processes but also positioned themselves at the forefront of shaping future directions in AI-assisted architecture. Finally, the course concludes a one-year long exploration to empower students to leverage cutting-edge technologies in redefining the boundaries of architectural design and planning.
At course completion, the student will:
– fluently use Rhinoceros and Grasshopper 3D,
– implements design solutions taking advantages of computational tools
– manage and visualise complex geometries and data
– read and export data in various format
– integrate Grasshopper 3D with others software
Introduction According to the World Health Organization, around 1.19 million people die each year due to traffic accidents, and another 20 to 50 million suffer non-fatal injuries, many of which result in disability. Beyond the human toll, the economic costs related to treatment and care for those involved in traffic accidents are significant, estimated to … Read more
“Can we understand urban environments and street characteristics from Google Street View panorama images using Machine Learning and Stable Diffusion techniques?” Project OverviewThis computational design project aims to develop a pipeline utilizing Grasshopper and Python to visualize clusters of panoramic streetscape images. The project leverages t-Distributed Stochastic Neighbor Embedding (t-SNE) for dimensionality reduction, facilitating the … Read more
Grasshopper is an incredibly versatile tool that in recent years has expanded into fields far beyond the origins in three-dimensional parametric design. One of these fields is that of GIS analysis, which has traditionally been approached through software such as QGIS. The advantages of Grasshopper and Rhinoceros3D over QGIS include the versatility and customisability of … Read more
Objective | Information from a Photo Photos are widely used to quickly capture context but are not easy to relate to spatial data. To remedy this challenge for users of 3D modeling software, we created a tool that integrates Python and Grasshopper to extract the location and time information from a photo and output variable … Read more
