LOC Talks
Bevorstehende Talks
Vergangene Talks
Dr. Ekaterina Petrova
Neuro-Symbolic Artificial Intelligence in AEC: Magic, Myth or Means?
Monday, 15th of April 2024, 17:00-18:30, Bestellmeyer Nord 2760
The Dartmouth Summer of 1959 envisioned Artificial Intelligence (AI) as a “program which can solve intellectual problems as well as or better than a human being”. More than six decades later, that vision remains. The strive towards intelligent machines continues in full force and is stronger than ever. In the era of digitalisation and an increasingly virtual world revolving around technological advancements and endowing machines with human-like intelligence, built assets are among the few tangible things left. Even though the built environment is still challenged by time-consuming, inefficient, and costly processes associated with capturing, identifying, analysing, accessing, reusing, and sustainably managing data, the potential of Building Information Modelling (BIM), Digital Twins and AI are indisputable.
This talk will discuss the untapped potential of neuro-symbolic AI for AEC. That entails combining symbolic (knowledge representation, automated reasoning) and subsymbolic (Machine Learning, Natural Language Processing) approaches as means for enabling a better performing built environment by addressing several shortcomings of the two AI approaches when used separately. To demonstrate the reconciliation between symbolic and subsymbolic AI for AEC, the talk will highlight recent implementations and ongoing research conducted at Eindhoven University of Technology in the context of smart building operation, circular construction, material performance assessment and advanced compliance checking.
Please register here.
Prof. Ioannis Brilakis, Ph.D.
Digital Twinning for the Built Environment
Wednesday, 13th July 2022, 18:00-19:30, Vorhoelzer Forum
Digital Twinning methods can produce a reliable digital record of the built environment and enable owners to reliably protect, monitor and maintain the condition of their asset. The built environment is comprised of large assets that need significant resource investments to design, construct, maintain and operate them. Improving productivity, i.e., efficiency and effectiveness, and creating new, disruptive ways to address existing problems throughout their lifecycle can generate significant performance improvements in cost, time, quality, safety, sustainability, and resilience metrics for all involved parties. Creating and maintaining an up-to-date electronic record of built environment assets in the form of rich Digital Twins can help generate such improvements. This talk introduces research conducted at the University of Cambridge on inexpensive methods for generating object-oriented infrastructure geometry, detecting, and mapping visible defects on the resulting Digital Twin, automatically extracting defect spatial measurements, and sensor and sensor data modelling. The results of these methods are further exploited through their application in design for manufacturing and assembly (DfMA), mixed-reality-enabled mobile inspection, and proactive asset protection from accidental damage.
Please register here.
Dr. Pieter Pauwels,Eindhoven University of Technology, Netherlands
Ontologies and linked data: applicability and technology review
Friday, May 13th 2022, 09:45, Vorhoelzer Forum
Linked data and ontologies are often named in the AEC sector as a new set of technologies with lots of potential for connecting different data sets and enabling inference with these data. References are typically made to RDF graphs and OWL ontologies in this regard. While that potential exists, these languages are also simply part of a larger ecosystem of technologies (e.g. SQL, JSON, ML, NLP, etc), in which many other data are also connected, or 'linked', and in which ontologies have been available for many years; albeit in different languages. In this talk, the RDF graph data model and OWL ontologies are explained in detail, and their position in relation to several other valuable technologies is presented, which leads to a better understanding of their applicability in our AEC domain.
Please register here.
Iro Armeni, Stanford Univeristy, California
Automatically generating structured information on the as-is status of facilities from visual data
Monday, July 22nd 2019, 16:15 Uhr, Vorhoelzer Forum
Despite the large production and collection of digital data, the AEC/FM industry lacks accurate, detailed, consistent and up-to-date knowledge of facilities. Advances in sensing technology allow the acquisition of high-fidelity 3D digital replicas of the as-is status. However, the output of such systems does not provide information on the spatial components, attributes and in-between relationships, thus cannot support downstream tasks (e.g., construction progress monitoring, maintenance activities, etc.). In this talk I will describe recent work on the automated extraction and knowledge-based representation of this information from visual data using Machine Vision and AI, as well as how it improves existing processes and enables novel workflows.
Please register online here!
Prof. Fernanda Leite, University of Texas, Austin
Automated Approaches towards BIM-based Intelligent Decision Support in Design
16. Januar 2019, 19:00 Uhr, Vorhoelzer Forum
The architecture, engineering, construction and facility management (AECFM) industry has been experiencing many changes since inexpensive networked, mobile computing devices have become ubiquitous. With the rising amount of information and data generated in the life cycle of capital projects, information modeling and data interoperability have become a critical element in design, engineering, construction, and maintenance of capital facilities. Recent advances in Visualization, Information Modeling, and Simulation (VIMS) have the potential to address a number of these pressing challenges. The objective of this talk is to discuss challenges and ongoing research in three areas of study in VIMS: capturing experiential knowledge in building information modeling (BIM)-based design coordination; 4-dimensional modeling for site-specific safety planning; and automating the BIM upkeep process in the facility operations phase leveraging deep learning and computer vision.
Prof. Frédéric Bosché, Heriot-Watt Universität, Edinburgh
Scan-vs-BIM for Construction Control
12. Dezember 2018, 18:00 Uhr, Oskar-von-Miller Forum
When Laser Scanning and Building Information Modelling (BIM) technologies were emerging, the construction industry showed signifi cant interest in what were to be eventually called “Scan-to-BIM”: the process of using a laser scanned point clouds to develop BIM models of existing assets. However, with the use of BIM for design, another important use of these technologies is what some of us have called “Scan-vs-BIM”: the comparison of laser scanned point clouds (capturing the as-is states of constructions) to BIM models (representing the as-designed states of constructions). Scan-vs-BIM offer signifi cant opportunities for further automation in construction project delivery for example for progress or quality control. This talk will present the Scan-vs-BIM concept, illustrate its process and benefi ts. The talk will then expand on the subject of using the output of Scan-vs-BIM processing to enhance dimensional quality control with a view to evolve dimensional quality control from a traditionally point-based measurement process to a surface-based measurement process.
Dr. Ilka May
BIM for Europe
The economic benefits of digitalization are well recognized. The wider use of technology, digital processes, automation and higher-skilled workers contribute greatly to Europe’s economic, social and environmental future. The European construction sector is undergoing its own digital revolution: Building Information Modelling (BIM) represents the construction sector’s moment of digitalization. Since February 2016 Europe is host to the greatest regional concentration of government-led BIM programmes in the world. The "EU BIM Task Group", formed in 2016 and co-funded by the European Commission, has over 20 European member states with representatives of public procurers, public building and infrastructure owners and policy makers. It aims to bring together these national efforts into a common and aligned European approach to develop a world-class digital construction sector.
Prof. Dr. Lutz Plümer
The 3D Modeling of Interiors featuring Combinatorics and Stochastics
Three-dimensional urban and building models in the sense of CityGML capture the geometry, represent the structure and semantically model relevant components such as doors, windows and balconies.
Building Information Models are models for supporting building planning, construction and facility management. They also represent those objects that are not observable from the outside.
The three-dimensional modeling of interior spaces forms a "missing link" between both worlds. Their geometrical detection is complex and difficult. Laser scanners or image-based processes require that every single room must be entered. In addition, the way from the 3D point cloud to the interior model is methodically sophisticated and requires that furniture is identified and "calculated". We present an approach that requires no additional geometry acquisition inside buildings.
Fabian Scheurer
Beyond BIM
The “digital transformation” has become a widely discussed topic – even in the construction sector, where digital methods play an increasingly important role in planning and in the construction work itself. However, the direct connection between “Building Information Modeling” (BIM) and computer-controlled construction work is still a construction site itself. There are still too many fault locations in the digital process.
The German-Swiss office Design-To-Production has been designing digital process chains from design to production for ten years now – successfully. The interdisciplinary team around the architect Arnold Walz and the computer scientist Fabian Scheurer helps architects, engineers, and construction companies to bridge the gap between the idea and its realization, consequently relying on digital modeling and computer-controlled production processes. Once, technologies like this were mainly needed for geometrically complex building projects such as the Centre Pompidou in Metz (Shigeru Ban) or the Mercedes Benz Museum (UN Studio), but they are now also of interest for standard construction projects. For an efficient implementation, however, there have to be new processes in the field of planning and construction: Beyond BIM.
Rafael Sacks
Adopting BIM and Lean in the Construction Industry
Assoc. Prof. Sacks studied at the University of the Witwatersrand, the Massachusetts Institute of Technology, and the Technion, Israel Institute of Technology. He has many years of industrial experience in structural engineering design and in software development for the construction industry. He is currently Associate Professor of Construction Management at the Technion, Israel Institute of Technology. To date, he is the author or co-author of two books, 37 papers in international peer-reviewed academic journals, 42 peer-reviewed conference papers, and a number of research reports. He is a co-author of the leading text on Building Information Modeling, entitled “The BIM Handbook: A Guide to Building Information Modeling for Owners, Managers, Architects, Engineers, Contractors and Fabricators”.
Arto Kiviniemi
Experiences from the BIM-Adoption in Finland and UK– Clients as the drivers of innovation
Dr. Arto Kiviniemi, Professor of Digital Architectural Design, is one of the internationally leading experts in the integrated Building Information Modelling (BIM) which he has developed both in Finland and internationally since 1996. In 1997-2002 Arto lead the Finnish national R&D programme which created the foundation for Finland’s position as one of the leading countries adopting BIM. In May 2010 he moved to UK, first to the University of Salford, where he initiated the first MSc BIM programme in the UK, and in September 2013 he started in his current position at the University of Liverpool.