Abstract: The ReWeave project develops a robotic system to repurpose construction and demolition (C&D) waste into functional, attractive walls, enhancing human-robot collaboration. We created a database by scanning broken tiles to extract shape, size, and color information, then developed custom nesting algorithms to optimize tile arrangement. The workflow includes scanning tiles, exporting outlines via ROS, … Read more
This post describes the development of a method to predict metro station locations using Graph Neural Networks (GNNs). Our journey began with a challenge familiar to urban planners: how to strategically place new metro stations to optimize transportation networks. In this case the city of Stockholm was used as testbed. The Challenge of Data Imbalance: … Read more
Exploring architectural identity of the city with 3D GAN and Stable Diffusion with case study of Kazan This research proposes to explore the ability and accuracy in styding and representing architectural identity of the city through the set of artistic experiments with all generated 3d geometry and 2d images in order to meet expectations of … Read more
Beginnings Our project’s concept is to develop a classification model that identifies street intersections (graph nodes) in Stockholm, Sweden, susceptible to flooding during a 100-year flood event. Based on our initial research, we found that graph machine learning operates at three levels: the graph, its edges, and its nodes. With access to a 100-year flood … Read more
TIMBER SENSING TECHNOLOGY A material system combining timber and graphene, replacing traditional sensors through graphene’s sensing capabilities. This innovative approach allows first, real-time tracking of deformations inside the wood. Second, creating a digital twin that improves maintenance efficiency in the operational phase. Third, providing a detailed service life passport, this system supports reuse and reduces … Read more
नमस्ते – مرحبًا – OLÁ – HOLÁ AIM Our aim is to make Human Robot Collaboration accessible to a variety of users via different languages by developing a speech to toolpath interface. RELEVANCE METHOD Workflow As the participant enters the room, they are greeted by a robot with a friendly waving motion. The participant can … Read more
Skyscrapers are human achievements that require innovation in the extraction of land to tower over its neighbors. The third skyscraper future reflects the past imaginary of Fritz Lang’s, Metropolis. This visualization aims to highlight the economic disparities and labor oppression depicted in the film, contrasting them with the modern logics of rentism as embodied by … Read more
What if you can control your Cobot with only hand gestures and you can work effortlessly? That’s what we came up with this experiment of using Multi agent systems to control the engagement of a collaborative robot (ur10e).Our workshop highlights an innovative approach to controlling cobots using hand gestures. This method aims to facilitate effortless … Read more
Building Together, One Word at a Time AIM The aim of this project is to enhance human-robot collaboration through the development of a user-friendly system that creates an inclusive environment. Text-to-speech (TTS) and speech-to-text (STT) systems enable humans and robots to communicate in anintuitive and engaging way. Relevance One major issue was that the human … Read more
This project explores a framework for Human-Robot Collaboration (HRC) and behavioural fabrication, focusing on constructing a Jenga-like tower using small timber blocks. Using the Agent-Based Modeling system (ABxM) from the Institute for Computational Design and Construction (ICD), a communication network was established integrating a human participant, a computer vision system, and an interactive audio interface. … 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
Introduction This presentation outlines the development and evaluation of machine learning models aimed at predicting the availability of bikes at various bicing stations in Barcelona. We’ll discuss the variables involved, the modeling techniques used, and compare the performance of different models. Python is a friendly environment for preparing, training and forecasting machine learning algorithms within … Read more
Introduction Urban transportation planning relies on data science to explain the conditions driving mobility patterns. This exploration of bicing, Barcelona’s resident bike rental program, analyzes the actors impacting discrepancies in bicing data to select machine-learning strategies able to predict biking station vacancies across Barcelona for the year 2024 with an accuracy of 0.02387. With this … Read more
Bicing was launched in 2007 as a viable eco-friendly alternative or complement to traditional private and public transportation. The mobility network has also allowed for increased physical activity and better connectivity between neighbourhoods of Barcelona. It is aimed at anyone with a NIE, over the age of 16. The Bicing 2.0 models were released in 2019 to … Read more
