Humans have been building shelters and structures for millennia, making construction one of the oldest professions. The industry has continuously evolved in the ways we design, plan, and build structures. For decades, technology has been used in the construction industry to increase productivity and efficiency in construction projects and make structures safer. More recently, construction firms have increasingly begun using AI (artificial intelligence) in innovative ways to make construction even more efficient and productive. From optimizing work schedules, to improving workplace safety, to keeping a secure watch on construction facilities, AI in the construction industry is already proving its value and making inroads into this traditionally conservative industry.
What are Artificial Intelligence and Machine Learning?
Artificial intelligence is the capability of a computer system to mimic human cognitive functions such as learning and problem-solving. Through AI, a computer system uses math and logic to simulate the reasoning that people use to learn from new information and make decisions. Machine learning is an application of AI. It’s the process of using mathematical models of data to help a computer learn without direct instruction. This enables a computer system to continue learning and improving on its own, based on experience.
Machine learning is the result of sorting through many algorithms very quickly. By way of example, if you wanted to predict a person’s longevity, one type of learning algorithm might sort through a tree of questions like, ‘how old are you?’. Next, ‘okay, do you exercise?’ And, so on. If your answer is yes, the decision fork leads down one branch, and if you say no, then decision fork leads down another. Think of it like the children’s game of Twenty Questions, except in machine learning these successive questions are autogenerated by the computer.
Applied to construction, both the tree of questions and the attending algorithms are vastly more complex. For instance, a machine learning program may track and evaluate progress in foundation excavation operations to provide early identification of scheduling risks. The algorithms might ‘ask questions’ regarding the volume of cut and fill, equipment uptime, weather reliability, experience from previous projects, and any number of similar inputs to generate a risk score, thus determining if notifications need to be flagged.
AI and Machine Learning for Smart Construction
The potential applications of machine learning and AI in construction are vast. Requests for information, change orders, open issues, and multitudes of other decision forks are standard for the industry. Like a smart assistant, machine learning can filter through mountains of data, scrutinize them for potential triggering events, and then if necessary alert key staff regarding items approaching criticality and thus in need of attention. Several applications are already applying AI this way, with benefits ranging from improved job site safety monitoring to heading off potential material shortages.
Examples of AI in Construction
AI is capable of myriad applications of which we will list but a few. These include managing Big Data, providing course-of-construction oversight, increased on-site productivity, preventing cost overruns, improving building information modeling, mitigating risk, improving jobsite safety, heading off labor shortages, facilitating off-site assembly, and assisting in post-production management.
1. Big Data Management
Big data is being used in every stage of the construction process to increase efficiency and productivity. Data analytics tools are designed to pull information from large data repositories and make it accessible to everyone involved in the construction process, including contractors, architects, tradesmen, and clients.
2. Project Oversight During Course of Construction
Several applications promise that on-site monitoring combined with artificial intelligence hold the key to solving late and over budget construction projects. Utilizing autonomous devices such as drones, sensors, and cameras to monitor job site activity, AI-based applications can process 3Ds captured from construction sites to measure the quantity of materials installed and classify how far along different sub-projects are progressing. The algorithms track the progress in real-time against original plans, budget, and schedule.
If things start to go off track, the management team can step in to deal with minor problems before they become major problems. Algorithms of the future will use an AI technique known as “reinforcement learning” allowing algorithms to learn based on trial and error, assessing countless permutations and their alternatives based on similar projects. This facilitates effective project management since it optimizes the optimal path and corrects itself over time.
3. More Productive Job Sites
Autonomous construction machinery can perform repetitive tasks more efficiently than their human counterparts, with inroads being made in areas such as pouring concrete, bricklaying, welding, and demolition. Some grubbing and excavation activities are already being performed by autonomous or semi-autonomous bulldozers, programmed to carry out job site preparations to exacting specifications. This frees up human workers for other tasks, in turn reducing the overall duration required to complete the project.
4. Prevent Cost Overruns
AI is used on projects to predict construction cost overages based on factors including project size, building type, experience levels of key staff, and multitudes of other variables. Historical data such as gantt charts from previous projects are used in predictive modeling to develop realistic timelines for pending projects. Similarly, for projects have already started, AI can predict upcoming labor or materials shortages thus reducing the time taken to onboard new resources onto projects. As a result, project delivery becomes more expeditious and cost effective.
5. Improved Building Modeling through Generative Design
BIM stands for Building Information Modeling and is a workflow process. It’s based around models used for the planning, design, construction, and management of building and infrastructure projects. BIM software is used to model and optimize projects by planning, designing, building, and operating BIM models. Where multiple project teams are involved in project delivery, the 3D models need to take into consideration the architecture, engineering, mechanical, electrical, and plumbing (MEP) drawings plus the coordination of activities amongst the respective sub-teams. The challenges include keeping the sub-teams in sync as well as ensuring that the sub-team’s various models are not in conflict.
The industry uses machine learning in the form of generative design to arrest clashes between the various sub-team’s BIM models, thus preventing duplication and/or rework. There are applications using machine learning algorithms to explore all the variations of a solution and then generate design alternatives. Once the criteria are applied to the model, the generative design software models 3D solutions optimize for those constraints, self-learning from each iteration until it derives the ideal model.
6. Risk Mitigation
Construction projects have inherent risk factors in many forms, including quality, safety, time, and cost risks. AI and machine-learning resources are in use today to monitor and prioritize risk management on through the entire course of construction, allowing the project team to focus their limited resources on those risk factors identified as most critical, with AI automatically assigning priority to same issues. Similarly, in some applications subcontractors are rated based on a risk score so that construction managers can work more closely with those high-risk subcontractors in order to mitigate risk.
7. Improved Jobsite Safety
AI and robotics help take the risks, physical demands and hard labor out of the construction site, leaving human workers to perform the less dangerous aspects of the job. On-site robotics are able handle most heavy lifting tasks, taking strain off worker bodies and making the workplace safer. For example, the Material Unit Lift Enhancer (MULE) robot developed by Construction Robotics can take a 6,000-pound per day lifting capacity off the backs of human workers, in turn increasing the safety and productivity of a site. Finally, AI systems can observe, assess and communicate on-site construction hazards with levels of speed and efficiency that no human can match. AI achieves this by gathering data from real-time footage and assessing that constant information stream for warning signs. Then, these warnings can be fed into comprehensive dashboards for construction site managers who can act to prevent accidents.
8. Addressing Labor Shortages
Construction companies are beginning to use AI and machine learning to better plan for distribution of labor and equipment across jobs. By constantly evaluating job progress and the location of workers and equipment AI enables project managers to quickly determine which job sites have enough workers and equipment to complete the project on schedule, which might be falling behind, and where additional labor could be deployed. An AI-powered rover such as Spot the Dog is capable of autonomously scanning a job site every night to monitor progress, enabling a large contractor to optimize his labor resources available. This is especially true in those geographic areas where skilled labor is in short supply.
9. Off-site Assembly
When structures can be partially assembled off-site and then completed on-site, construction goes faster. Construction companies are increasingly relying on off-site factories staffed by autonomous robots that piece together components of a building, which are then pieced together by human workers on-site. Assembly line production of something like a wall can be completed assembly-line style by autonomous machinery more efficiently than their human counterparts, leaving human workers to finish the detail work like plumbing,
10. Post-construction Applications
Long after the work is finished, building managers can use AI. Advanced analytics and AI algorithms generate useful insights into the operation and performance of a building, bridge, roads, and nearly anything in the built environment by gathering information about a structure using sensors, drones, and other wireless technologies. This implies AI may be used to track the progression of issues, identify when preventative maintenance is required, and even direct human behavior for maximum security and safety.
The Future of AI in Construction
It is anticipated that robotics, AI, and the Internet of Things can reduce building costs by up to 20 percent, and more and more construction professionals are turning to artificial intelligence to solve the productivity problem and other myriad industry issues. The benefits of AI in construction are immense. It will reduce expensive design errors, improve worksite safety and productivity, and ensure timely and on-budget project completion.
In an industry that has been change-resistant for a long time, shifting to AI technology may be a major change for many people. A key concern of AI in the construction industry is that it will replace the human workforce with robots. Of course, that’s not the truth. AI technology seeks to support workers by enabling them to work more efficiently under safer conditions. The new automation technologies will instead create new job opportunities, in turn attracting an ever-increasing pool of talent into the construction sector.
For Further Reading:
• ContractorMagazine.com has an excellent overview of AI in construction at: https://www.contractormag.com/technology/article/21244536/ai-is-transforming-the-construction-industry.
• “AI and the Future of Construction Safety”, an article by The Constructor, is presented at: https://theconstructor.org/construction/ai-the-future-of-construction-safety/568937/.
• ConstructConnect presents thoughts on the subject in their article, “6 Ways to Imagine AI Transforming the Construction Industry”, found at: https://www.constructconnect.com/blog/6-ways-to-imagine-a.i.-transforming-the-construction-industry.