Introduction

Is Architecture ready for the building industry?
(and vice-versa)

Speakers

Martin Fischer is the Kumagai Professor of Engineering at Stanford University and directs the Center for Integrated Facility Engineering. He is known globally for his work and leadership in developing and applying VDC (Virtual Design and Construction) to increase the productivity of construction project teams, enhance building performance, and create new strategic opportunities for firms in the construction industry. VDC combines a focus on project value with rethinking of workflows supported by digital tools and the timely and productive engagement of the expertise needed to achieve the desired project value. His award-winning research results have been used operationally and strategically by many industrial and government organizations around the world. He has co-authored the book “Integrating Project Delivery” published by Wiley in 2017, written over 100 refereed journal articles and book chapters, and given over 100 keynote lectures on his research. His work has been recognized by the ASCE Peurifoy Construction Research Award and with elections to the National Academy of Construction in the US and the Royal Academy of Engineering Sciences in Sweden.

Iro Armeni is completing her PhD at Stanford University with a PhD minor at the Computer Science, conducting interdisciplinary research between Civil Engineering and Machine Vision. Her area of focus is on automated semantic and operational understanding of buildings throughout their life cycle using visual data, toward establishing a seamless interaction between the physical world and its digital representation. Prior to enrolling in the PhD program, Iro received an MSc in Computer Science (Ionian University-2013), an MEng in Architecture and Digital Design (University of Tokyo-2011), and a Diploma in Architectural Engineering (National Technical University of Athens-2009). She is the recipient of the 2019 ETHZ PostDoctoral Fellowship, the 2017 Google PhD Fellowship on Machine Perception, and the 2009 Japanese Government (MEXT) scholarship. She has also worked as an architect and consultant for both private and public sector.

Silvio Savarese is an Associate Professor of Computer Science at Stanford University and director of the SAIL-Toyota Center for AI Research at Stanford. He earned his Ph.D. in Electrical Engineering from the California Institute of Technology in 2005 and was a Beckman Institute Fellow at the University of Illinois at Urbana-Champaign from 2005–2008. He joined Stanford in 2013 after being Assistant and then Associate Professor of Electrical and Computer Engineering at the University of Michigan, Ann Arbor, from 2008 to 2013. His research interests include computer vision, robotic perception and machine learning. He is recipient of several awards including a Best Student Paper Award at CVPR 2016, the James R. Croes Medal in 2013, a TRW Automotive Endowed Research Award in 2012, an NSF Career Award in 2011 and Google Research Award in 2010. In 2002 he was awarded the Walker von Brimer Award for outstanding research initiative.

Close

Structural Engineering

AI in Structural Engineering Today

Abstract

We present an overview of AI and optimization in the context of structural design. The first section describes the integration between existing Topology Optimization methodologies and high-rise building design and component manufacturing. We proceed to illustrate current CIFE research efforts to automate the design of structural components of commercial steel building structures for improved speed, cost, design time, and safety. We conclude the presentation with automated crane operation methods and the potential integration of this technology with structural design AI.

Speakers

Filippo Ranalli obtained his BS in Civil Engineering from the University of Rome, and completed his MS in Structural Engineering at Stanford University. He is currently pursuing his PhD within the Stanford Sustainable Design and Construction program, under the supervision of Profs. Martin Fischer and Eduardo Miranda. His research focuses on bringing Artificial Intelligence, Optimization, and Computer Science methods to the Structural Engineering practice, with the objective of maximizing the cost-efficiency, safety, and seismic performance of building structures.

Eduardo Miranda obtained his Civil Engineer degree from the National Autonomous University of Mexico, UNAM. He obtained his MSc and PhD degrees in Structural Engineering at the University of California at Berkeley. He is a professor at the Department of Civil and Environmental Engineering at Stanford University. Eduardo specializes in structural engineering with emphasis on performance-based earthquake engineering. Using measurements made on the ground and on instrumented structures he studies how structures respond to earthquakes and conducts research to assess the impacts of earthquakes on structures and on society in general. He then uses this knowledge to develop ways to design and build structures that will have an improved performance. Also interested in developing computer tools for automating analysis, design and construction.

Close

Keynote Talk

How can Computer Vison and Mixed Reality help Architecture, Engineering and Construction?

Abstract

Geometric computer vision has found many applications in recent years. Highly relevant for AEC are photogrammetry and 3D reconstruction to help with surveying or building digital twins. These 3D models have evolved from purely geometric to include semantic understanding. Simultaneous localization and mapping, so called SLAM, often builds on 3D computer vision techniques to enable mixed reality experiences, but also robotic navigation which are all starting to find applications in AEC. To help users navigate inside a facility, or in the wider world, image-based localization techniques are used to build the AR cloud. In this talk we’ll cover these topics and discuss some of the challenges and limitations.

Speaker

Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007 where leads the Computer Vision and Geometry lab and the director of the Microsoft Mixed Reality and AI Zurich lab. Earlier he was on the faculty at the Dept. of Computer Science of the University of North Carolina at Chapel Hill. He obtained his M.S. and Ph.D. from the KU Leuven in Belgium. His main area of research is computer vision. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 300 peer-reviewed publications. He was general chair of ICCV 2019 and ECCV 2014, was a program chair for CVPR 2009 and has organized many workshops and tutorials at major vision and graphics conferences. Prof. Pollefeys has served on the Editorial Board of the IEEE Transactions on Pattern Analysis and Machine Intelligence, the International Journal of Computer Vision and Foundations and Trends in Computer Graphics and Computer Vision. He is an IEEE Fellow.

Close

Architectural Design

Differentiable Architects

Abstract

The discussion will identify how Artificial Intelligence has helped, is helping, and may help solve future problems in Architectural Design. In general, AI will be called to bridge the gap between architects' and design experts' domain knowledge and statistical patterns in large-scale data. We will discuss current AI-driven approaches for shape and scene modeling, address their advantages and limitations, and suggest potential future opportunities such as using explainable AI models in design or using AI to spark creativity.

Speakers

Alberto Tono is the president of the Computational Design Institute. He served as the Research and Computational Design Leader in Architectural and Engineering organizations, receiving the O1-visa for outstanding abilities with HOK and HDR. Tono obtained his Masters in Building Engineering - Architecture from the University of Padua and the Harbin Institute of Technology. He has been working in the computational design and deep learning space since 2014. Furthermore, he is focused on the improvement of BIM/VDC workflows with a statistical approach. He is an international multi-award-winning “hacker” and speaker, and his work within Architecture and Artificial Intelligence brought him to companies in China, the Netherlands, Italy, and California.

Jiajun Wu is an Assistant Professor of Computer Science at Stanford University, working on computer vision, machine learning, and computational cognitive science. Before joining Stanford, he was a Visiting Faculty Researcher at Google Research. He received his PhD in Electrical Engineering and Computer Science at Massachusetts Institute of Technology and undergraduate degrees in Computer Science and in Economics at Tsinghua University. Wu's research has been recognized through the ACM Doctoral Dissertation Award Honorable Mention, the MIT George M. Sprowls PhD Thesis Award in Artificial Intelligence and Decision-Making, the IROS Best Paper Award on Cognitive Robotics, and fellowships from Facebook, Nvidia, Samsung, and Adobe.

Close

AI4Health

Speaker

Serena Yeung is an Assistant Professor of Biomedical Data Science at Stanford University. She recently completed a TEAM postdoctoral fellowship in AI and healthcare at Harvard University, where she was hosted by Susan Murphy and John Halamka. Her research has been broadly in the areas of computer vision, machine learning, and deep learning, with particular focus on human activity and video understanding, and applications to healthcare. She received my Ph.D. from Stanford University in 2018, where she was advised by Fei-Fei Li and Arnold Milstein. During her Ph.D., Serena spent internships at Facebook AI Research in 2016 and Google Cloud AI in 2017. She also co-taught Stanford's CS231N Convolutional Neural Networks course from 2017-2019, with Justin Johnson and Fei-Fei Li.

Close

Fast Prototyping with VR/AR

Abstract

The AEC industry, being rife with risk around cost and schedule, presents itself as a huge beneficiary of both virtual and augmented reality HMD technology. Being able to simulate designs or practice complex logistics virtually reduces costly mistakes and safety issues. But why aren’t job sites and architectural studios rife with users walking around with these HMDs? While highly beneficial to projects, VR and AR HMDs still manifest critical user experience issues that are hindering ubiquitous use of the technology and require complex engineering to overcome.

Current VR and AR hardware potential limits for the adoption of such systems in the construction industry and beyond will be discussed. Recent efforts to improve the realism, comfort, and accessibility of VR and AR systems will be presented.

For VR to be successful it needs to be integrated in the collaboration ecosystem of any project team and organization. It needs to be embedded in the daily work practice and process. Examples from the AEC Global Teamwork will demonstrate how we reimagine collaboration in distributed project teamwork and highlight transformative impacts of VR immersive experiences at individual and team level, and on product and process.

Speakers

Anton Dy Buncio is the co-founder and COO of VIATechnik, a built-environment technology firm disrupting the AEC industry through innovative VDC consulting, implementation and education. Anton leads VIATechnik’s research and development studio that specializes in advisory, software development, educational programs, and data analytics. Anton graduated from Stanford University with a degree in Management Science & Engineering. Prior to founding VIATechnik, Anton worked at the global management consulting firm Bain & Company in both San Francisco and Sydney.

Robert Konrad is the CEO and co-founder of Zinn Labs, a company creating automatically refocusing reading glasses for those that have lost the ability to refocus with age. Robert finished his PhD from the Electrical Engineering Department at Stanford University, advised by Professor Gordon Wetzstein, as part of the Stanford Computational Imaging Lab. His research lay at the intersection of computational displays and human physiology with the specific focus on making virtual and augmented reality systems more visually comfortable and realistic. He has worked to support depth cues in such systems, namely focus and ocular parallax cues, and create computationally efficient cinematic VR capture systems. He received his Bachelor’s Degree from the ECE department at the University of Toronto in 2014, and his Master’s Degree from the EE Department at Stanford University in 2016.

Renate Fruchter is the founding director of the Project Based Learning Laboratory (PBL Lab), lecturer in the Department of Civil and Environmental Engineering, and Senior Research Engineer thrust leader of “Collaboration Technologies” at the Center for Integrated Facilities Engineering (CIFE), at Stanford. She received her Civil Engineering Diploma from the Institute for Civil Engineering, Bucharest, Romania. She received her M.Sc. and Ph.D. from the Technion – Israel Institute of Technology. Her R&D focuses on collaboration technologies in support of cross-disciplinary, geographically distributed teamwork in education and corporate settings. She studies the relation between technology-people-place-process. She is the developer of the innovative "Architecture, Engineering, Construction (AEC) Global Teamwork" course launched in 1993 engaging university and industry partners worldwide. Her latest projects focus on: (1) big data analytics and visualization towards harmonizing occupant well-being and building sustainable performance; and (2) accelerating creativity and engagement in global teamwork through VR, AI, and parametric modeling.

Close

As-Is Information

It's All About Trust.

Abstract

Effective construction progress management enables accurate resource allocation on a project, which in turn drives design, cost, schedule, and quality on projects. Due to the absence of (automated) data-driven analysis, industry experts currently rely on their knowledge and experience to make resource allocation decisions. Recently, AI tools that support faster decision making have appeared and, although, speed is important to maintain a project informed, trustworthy decisions are preferred. While AI can accelerate conclusions from complex data, industry experts need to be able to trust their decisions. This discussion will explore the current workflow for progress management while also considering the impact of AI within the context of trust and certainty.

Speakers

Andrew Cameron, as a Project Manager with Hensel Phelps, has been involved in the successful completion of a wide range of projects having worked his way up through the field, office, project engineer, and area superintendent positions. He started his career in the Mid Atlantic District as an intern on one of the largest design-build projects to date, The Pentagon. Throughout his career, Andrew has worked on numerous federal projects, the Marriott Marquis in Washington, D.C., SFO Terminal 3 East, and currently on the $1.2 Billion SFO Harvey Milk Terminal 1. Andrew cares deeply about client happiness and satisfaction during the construction process. He actively works to bring new technology into the construction field and as a member of The Society for Construction Solutions – Bay Area, is constantly meeting and working with innovative AEC technology companies and individuals.

Iro Armeni is completing her PhD at Stanford University with a PhD minor at the Computer Science, conducting interdisciplinary research between Civil Engineering and Machine Vision. Her area of focus is on automated semantic and operational understanding of buildings throughout their life cycle using visual data, toward establishing a seamless interaction between the physical world and its digital representation. Prior to enrolling in the PhD program, Iro received an MSc in Computer Science (Ionian University-2013), an MEng in Architecture and Digital Design (University of Tokyo-2011), and a Diploma in Architectural Engineering (National Technical University of Athens-2009). She is the recipient of the 2019 ETHZ PostDoctoral Fellowship, the 2017 Google PhD Fellowship on Machine Perception, and the 2009 Japanese Government (MEXT) scholarship. She has also worked as an architect and consultant for both private and public sector.

Close

Keynote Talk

A Human-Centered Perspective on Collaboration with Robots

Abstract

Today’s society is rapidly advancing towards robotics systems that interact and collaborate with humans, e.g., semi-autonomous vehicles interacting with drivers and pedestrians, medical robots used in collaboration with doctors, or service robots interacting with their users in smart homes. Formalizing interaction is a crucial component in seamless collaboration and coordination between humans and today's robotics systems. In this talk, I will discuss a journey in formalizing human-robot interaction, and how that can help advance the intersection of robotics and the building industry. Specifically, I will first discuss developing data-efficient techniques to learn computational models of human behavior. I will continue with the challenges that arise when agents (including humans and robots) interact with each other. Further, I will argue that in many applications, a full computational human model is not necessary for seamless and efficient interaction. Instead, in many collaborative tasks, conventions —low-dimensional shared representations of tasks — is sufficient for capturing the interaction between agents. I will conclude the talk with challenges around adapting conventions in human-robot applications such as assistive teleoperation and collaborative transport.

Speakers

Dorsa Sadigh is an assistant professor in Computer Science and Electrical Engineering at Stanford University. Her research interests lie in the intersection of robotics, learning and control theory. Specifically, she is interested in developing efficient algorithms for safe, reliable, and adaptive human-robot interaction. Dorsa has received her doctoral degree in Electrical Engineering and Computer Sciences (EECS) at UC Berkeley in 2017, and has received her bachelor’s degree in EECS at UC Berkeley in 2012. She is awarded the NSF CAREER award, the Google Faculty Award, and the Amazon Faculty Research Award.

Close

Robotics in Construction

Robots for Construction

Abstract

This presentation addresses the construction issues that robots can solve now with the use of AI, like 3D scanning the site and automating field machinery. The speakers, Rolando Mendoza and Cynthia Brosque highlight the application of a layout robot deployed in a Mortenson site and Elena Galbally will discuss the AI methods being explored for field robots, including human-robot collaboration interfaces like haptics.

Speakers

Rolando Mendoza is the Director of Virtual Design and Construction (VDC) at Mortenson.

Cynthia Brosque is a Ph.D. Candidate in Civil and Environmental Engineering (CEE). She is conducting research under the supervision of Martin Fischer (CEE-CIFE). Her research interests are Virtual Design and Construction (VDC) and Construction Robotics. She has a Master of Science in Civil Engineering (Stanford University - 2019) and an Architecture Degree (Universidad ORT Uruguay - 2016).

Elena Galbally Herrero is a PhD Candidate at the Department of Computer Science under the supervision of Professor Oussama Khatib, Stanford University.

Close

AI4Law

AI & Contract Law

Abstract

This talk will provide a brief survey of how AI is currently employed by legal practitioners and researchers to analyze written contracts. As an illustration, we will focus on information extraction to identify deficiencies in contractual drafting practices. The presentation will end with a brief discussion of current developments and challenges in the field.

Speakers

Julian Nyarko is an Assistant Professor of Law at Stanford University.

Close

Facility Management

TBD

Abstract

Is AI ready to help us manage a building throughout its lifecycle (design, construction, operations)? This panel aims to take a deeper look into the challenges of facility management and explore how AI is/can/may help manage our buildings better. We will explore this from a wide range of perspectives including: owner/operators, data management/building controls and research/development.

Speakers

Andrew Arnold is the Product Leader at VueOps. He focuses on product design and management for applications, and consultation to help customers establish appropriate lean construction, BIM, integrated project delivery, and operations and maintenance practices. He has assisted BIM for facilities management implementations for large-scale healthcare, aviation, bio-pharmaceutical, and public agency owners. Andrew received his BA in Architecture from U.C. Berkeley, and MA and PhD in construction engineering and management from Stanford University's Center for Integrated Facilities Engineering. His early career in architecture included work on hospitality, health science, and education projects. He also consulted in computerized-aided facilities management CAFM implementations. Andrew has designed and managed BIM application development, including databases of product information, and BIM content management and analysis tools, including quantity takeoff, cost estimating, LEED contribution, and immersive visualization in several AEC technology startups.

Ben Coleman is the Chief Architect and Director at Connected Buildings, Honeywell.

Bruce Mace is currently the Executive Director of Facilities & Support Services for the pre-eminent UCSF regional healthcare system in San Francisco, California, ranked by U.S. News and World Report as one of the top seven hospitals in the United States. With a career in 2D/3D design, architecture, construction and project delivery, turning the corner into healthcare operations fifteen years ago was a profound change in perspective and provided a wide-open horizon. Recognizing a strong need to operationalize the data trapped in our shared architecture/project deliveries led to an early vision of the then-evolving object-based, meta-data rich architecture informing the complex computerized maintenance management systems required to safely and successfully operate intricate tertiary and quaternary healthcare facilities.

Rishee K. Jain is an Assistant Professor of Civil & Environmental Engineering at Stanford University and an affiliate scientist at SLAC’s Grid Integration, Systems, and Mobility (GISMo) group. His research focuses on the development of data-driven and socio-technical solutions to sustainability problems facing the urban built environment and lies at the intersection of civil engineering, data analytics and social science. He is a recipient of the CAREER award from the National Science Foundation. Rishee earned his BS in Civil & Environmental Engineering from the University of Texas at Austin and his MS/PhD from Columbia University as part of a joint a IGERT program between civil engineering and urban planning.

Close

Hands-On Sessions

August 19th

Architectural Design

During this session, participants can interact with different demos, providing feedback and asking questions. The demos will encapsulate some of the future visions presented during the presentation.

Structural Engineering

We will present two short follow-along structural optimization examples in Excel and Python, and conclude the session with a discussion on the prospective paths of the structural engineering practice through the integration with AI methods.

Fast Prototyping with VR/AR

During this session we will invite a number of participants to engage in a collaborative immersive VR experience walking through and troubleshooting a virtual building. Please see requirements for VR walk through and sign-up below. The rest of participants will be able to view on screen our collaborative VR interactions. This will be followed by a discussion with all participants in the session. The discussion will focus on two topics: (1) compare the value of the experience in immersive 3D VR vs watching the walk through on a 2D screen. (2) your interests and plans to pilot and/or deploy VR in your project/program/company.

Guidelines and immersive VR participation requirements - get VR-ready and sign-up
We will have 8 spots for the immersive collaborative VR walk through and troubleshooting.
Get VR-ready by Tuesday August 18 - Participants who want to actively participate in the VR walkthrough need to (1) have one of the following VR headsets and a VR-ready computer: Oculus Rift, Oculus Rift S, HTC VIVE. If you have Oculus Quest no need for VR-ready computer. (2) Download and test free 14 day trial - IrisVR Prospect by Tuesday August 18 - https://irisvr.com/prospect/

Sign up by sending an email to fruchter@stanford.edu no later than Tuesday August 18 at 7:00pm PDT (California time). FIRST-COME-FIRST-SERVED – sign-up of the first 8 participants. Your email should indicate what VR equipment you have and that you have installed and tested IrisVR Prospect software and know how to use your controllers to navigate in VR. Dr. Fruchter will email you back Tuesday night PDT - an IrisVR Prospect CODE for the collaborative multiuser session of the building model we will walk through together.

We will be glad to have a second VR walkthrough session and prepare a backup CODE for a second building in case there are more participants – for second group of the next 8 participants who have signed-up.

Close

Hands-On Sessions

August 20th

As-Is Information

Through group collaboration and interactive sessions, we will explore two key takeaways from the main presentation: our current level of confidence and trust we place within our own decision making process ("Trolley Problem") and what questions are more suitable for solving common visual problems in a project ("Find Waldo").

Robotics in Construction

Identifying current and future opportunities and challenges to deploy construction robots: This work session addresses which robots can have the most impact and in which timeframe. Interactive group sessions will discuss and share opportunities and challenges experienced when using construction robots. Groups also exchange views on what will an “ideal” construction robot product and process look like in the next 10 years and what AEC and robot tools we still lack to achieve that “ideal” state.

Facility Management

In this session, we aim to develop a common understanding of the key barriers and challenges for why AI until now has had a (relatively) limited impact on the facility management domain. We will do some exercises on exploring what socio-technical advancement are necessary to overcome these barriers in the context of a case study building from the University of California - San Francisco.

Close