Artificial Intelligence in Construction
Out of all the emerging technology hitting the market today, artificial intelligence is a new technology that is on track to revolutionize the construction industry. Processes of operating machinery, modeling and estimating, and BIM are just a few of many fields in construction that stand to improve in production and efficiency with the use of AI.
Autonomous equipment is equipment that is aware of its surroundings and is capable of navigating and operating without human interaction. This type of equipment detects its surroundings using GPS, LiDAR, and radar techniques.
Komatsu provides a solution, SmartConstruction, that connects job site information concerning equipment and people. SmartConstruction allows users to survey their job site via drone or 3D scanner to produce a 3D model of the job site’s existing conditions, bring the data into KomConnect to automatically simulate creation of construction plans, and then transmit the data into automated driver less earth-moving vehicles to automate excavation.
D61PXi-23 intelligent Machine Control bulldozer launched in June, 2013. (image by Komatsu)
Komatsu’s intelligent machine control can eliminate human error and prevent safety hazards that can occur when humans are exposed to heavy machinery. Traditional processes like staking and earth moving can be eliminated or significantly expedited with autonomous equipment.
Computational BIM is the process of automating creation of BIM elements, managing parameters and inter-operating with other applications, data sources, and geometry tools.
BuildingSP is disrupting the BIM market with their product GenMEP. GenMEP is an add-on to Autodesk Revit that uses computer algorithms to automatically route MEP systems through Revit models and even point clouds captured from laser scanners without clashes. Users simply tag the start and end points of the MEP systems and GenMEP will automatically route those systems, with the goal of minimizing complexity and maximizing efficiency. GenMEP creates real Revit family content when generating these systems.
GenMEP content created over an existing point cloud scan of an MEP system. (image by BuildingSP)
Another product from BuildingSP is ClashMEP, which uses data created from GenMEP to detect any clashes that occur when modeling new MEP elements in Revit in real-time. BIM modelers can use ClashMEP to check for clashes in real-time without having to leave Revit.
ClashMEP detecting system clashes on Revit objects. (image by BuildingSP)
Computational BIM software like BuildingSP’s GenMEP and ClashMEP prevent human error and save time by removing the human labor necessary to produce all components of complex BIM models manually in Revit, to save materials by building systems more efficiently, and to prevent future coordination issues like clashes.
Autodesk’s Generative Design concept is a way for a user to input design goals and constraints such as material type, weight, strength and cost into a computer to generate alternative design options.
Autodesk’s Project Dreamcatcher synthesizes a series of alternative design solutions to meet the user’s objectives. Designs like the Hack Rod racecar, Airbus A320 plane and Under Armour’s 3D-printed performance training shoe have all been generated with generative design.
Autodesk generative design Hack Rod racecar generated by Dreamcatcher (image by Autodesk)
Using the generative design concept not only allows a human and computer to co-create complex designs, but also allows both a human to learn better design practices from a computer and a computer to learn from a human what does and does not work.
One of the overall goals of artificial intelligence is to develop computer algorithms that can improve automatically through experience. In construction, we can use these algorithms to improve processes in a much faster way than a human brain could ever imagine doing.
AI has a tremendous opportunity to disrupt the AEC space. Komatsu’s SmartConstruction drives the usage of autonomous equipment up with the benefit of having a safer environment. BuildingSP’s GenMEP and ClashMEP will increase productivity by generating modeling systems faster and clash free. Autodesk’s product line on generative design opens a new world of design possibilities for architects and engineers.
The more that AI is used, the more it will test and learn what works and what doesn’t. Although still in its infancy, when looking at the impacts that AI has already presented to the construction industry, it is very exciting to see what is to come.
About the Author
Steven Spann (@StevenSpann) is a JBKnowledge Research & Development Team Software Developer (JBKLabs), which is dedicated to disrupting and accelerating the architecture, engineering, and construction industries by building solutions with the emerging technology. Steven Spann is a programmer, woodworker and a former college baseball player with a degree in Mathematics from Northwestern State University in Louisiana. JBKLabs is available for advisory, research, and custom software development services. Learn more at jbknowledge.com/labs.