Reflection on the course

When I signed up to take AE 410, I expected it to be more of a designing class that will teach more on how to work with SketchUp and AutoCAD. On the contrary, I learned very new concepts in this course which I think opened my eyes on very new topics for me in my major.

The course focused on Artificial Intelligence, BIM and Databases. Before taking this course, I had a very basic idea on how robots are constructing in big factories, but I did not realize how the robots are also being used in construction fields, and how intelligent they are programmed to overcome obstacles and receive commands for several tasks.

Another topic that I was expecting to learn about in this course and that we went through and understood very well was 3D printed buildings. Before taking this course, I really wanted to learn more about the 3D printed buildings advantages, how they are constructed and put together and whether they are used nowadays or are still being developed. We understood it very well from professor Mitchell’s explanation, and my peers’ blogs that introduced new information and have taught me a lot.

Reflection on my professional career and future:

I believe that AI plays a huge role in BIM, and have been and developing the industry in so many aspects. My plan now is to go back to Kuwait after I graduate and hopefully work in one of the Architectural firms. I am very sure that they use BIM and such developed technologies. I also know that in Dubai they are relying on 3D printed buildings, Kuwait work on many projects with Dubai as well as exchanging experiences, so hopefully after learning so much about the 3D printed buildings I can have a hand on one of the projects which I am very excited for.

Another useful tool we used was Microsoft Access creating Databases. Even though I faced few trouble and errors on the assignments, I have a clear idea on Queries and relationships which I really believe I would benefit from it in my professional career. I also learned very much about sensors which I didn’t have a clear background about before this class.

One of the most effective things in this course were the guest speakers that use what we are learning in their daily work. That showed me how important all the topics we learned are and gave me a push to read more about everything and, I was always interested in reading my classmate’s blogs to learn new aspects of the topic.

In conclusion, the class was much deeper in the topics than I anticipated it to be and very useful to me, my major and in my future career for sure. I believe that professor Mitchell’s useful presentation and videos were very helpful. The videos that were showed to us in class, especially the robots working on construction and overcoming obstacles to do specific tasks, in addition to the blogs and guest speakers were very helpful and taught us a lot. The course was very interesting, we had so much fun while learning the new topics, and hopefully we can use all that we learned in our future jobs.

Response to peers
Nick Pawlikowski : It is great that you knew about most of the topics in this course. To me even though I knew few topics, I was not familiar with the great deep information provided in the lectures and blogs by our colleagues. I as well had never worked on Databases and I enjoyed it and like working on it this course I really think it helped me a lot.

Joe Dressel : I agree with most of what you said about the course. I strongly agree that the guest speakers were very helpful, they brought us a lot of prospective as you said and shared their experience on the topics which helped us very much.

Ronald Herazo: I strongly agree that professor Mitchell did a great job teaching this course and really helped us a lot and made it so much fun for us. Most of the topics even though we had a basic idea about, deep information were shared, reading the blog posts helped introduce more information and finally the guest speakers also sharing their experience gave us the best idea possible. 

B-5 Relational Database Theory - Arthur McCloskey

     A relational database is a collection of data items that are organized in a manner that relates the parameters between the data items.  In Hugh Darwen’s book “An Introduction to Relational Database Theory,” he uses tables to explain the theory behind a relational database.  In a way, a table can be seen as a relational database, where the various parameters are presented in a way that lends itself to relation.  However, Darwen argues that, while the visualization is similar, a table is not really a relational database in itself.  In order to be a proper relational database, the columns of a table must be algebraically or operationally related to one another. [1]  This aspect of relational databases are the primary benefit to using them in the organization of big data, especially in the construction and building industry.  The ability to operate on parameters within a database based on known relations allows the user to construct a systematic collection of information that is pertinent in the building.

     To understand the effects that this type of information can have on our industry, the mathematical theory is useful to grasp what should and should not be related.  Eliezer Lozinski explains this theory rather well in his journal “Construction of Relations in Relational Databases.”  He explains that all databases are made up of relations that are made up of a collection of attributes.  These attributes are linked through a set of dependencies to the relation.  This framework for relating the attributes is called a scheme.  The scheme of a relation can be represented graphically, as Lozinski does below.  This rather simplified progression shows how the various schemes can be put together to relate the appropriate attributes.  [2]

Figure 1: Relational Scheme Tree [2]

     The impacts to the construction industry are numerous.  As we heard in the Whiting Turner guest lecture, a lot of firms are pushing to tabulate the entire building, from door hardware to reheat coils.  Relational Databases can take it a step further, by joining the parameters of installed components, we can understand the connections between key parameters and design, maintain, and modify building components better.

Comments on Others

Andrew Ng – Your explanation of Structured Query Language was very helpful, particularly with the examples that you gave.  This system would be very useful to a project manager in this way to cut back a lot on the unnecessary work that stems from handling big data. 

Prahlad Singh – I particularly liked your post because of all the benefits you provided to having databases in our industry.  I think that both designers and contractors are constantly overwhelmed with large amounts of data, and any process by which we can eliminate raw number sorting/crunching can make the entire process more efficient.

Ray Powell – Your post was really interesting to read since it connects what we have been learning so far to our next topic.  Both BIM and databases are essential for design firms now and it was really interesting to see how the two can interact to make the design process more efficient.

References

[1] Darwen, Hugh.  “An Introduction to Relational Database Theory.”  Darwen & Ventus Publishing ApS 2010.  Web.  Available: https://dvikan.no/ntnu-studentserver/kompendier/an-introduction-to-relational-database-theory.pdf

[2] Lozinski, Eliezer.  “Construction of Relations in Relational Databases.”  The Hebrew University, Jerusalem, Israel.  Web.  Available: http://delivery.acm.org/10.1145/330000/320155/p208-lozinskii.pdf?ip=129.25.36.43&id=320155&acc=ACTIVE%20SERVICE&key=A792924B58C015C1%2EE0B7266DB2A396BF%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=900189139&CFTOKEN=74586775&__acm__=1487008321_4d9c6ffee5fc5fe79479552f6b170344

B4 - Term Project: Revit Family Database

Project Description & Why it was Chosen:

My project has two main goals: the first is to create a database in Microsoft Access that houses Revit family parameter data, and the second is to create a function in Revit to programmatically generate new families (.rfa files) from the information if the database.  The database would contain all families that exist in a current Revit model, and can be used to perform inventories and cost estimates.  It would store the parameter values of each family and type in a tabular format which could be edited and synced with the Revit file to update the existing families.  Additionally, new families and types would be able to be generated from the database by inputting family parameters into the appropriate rows and calling a corresponding function in the Revit model.  The function would serve as an automated version of Revit’s family creation tools which pulls family data from the database in order to construct new families. 

I chose this project for several reasons, the first being that it would allow me to practice some programming, which I enjoy but do not get enough of in my curriculum.  The second reason is that the final products, a database that can compile family data and a script that can generate Revit families, seemed to be very useful tools that I and others would be able to make use of beyond the scope of this class.  I also chose this project because it will force me to become familiar with Revit’s API, which I know will be a valuable skill when I enter the workforce. 

Relation to Intelligent Buildings:

                This project is a combination of two central themes of this course: databases and BIM.  As was discussed in class, the future of intelligent buildings will almost certainly involve automation, of both construction and design.  My project serves to automate a small portion of the design process, specifically the modelling and editing of families in Revit.  Editing and creating families in Revit is a tedious process, and reducing it to entering information into a few boxes would increase productivity substantially. 

Challenges:

Some of the groundwork for this project has been laid by others.  Information can be exported and exported between Revit and various external databases via the Revit DB Link plugin.  Function calls already exist within the Revit API and Revit Python Shell that can generate new families programmatically.  The challenges would lie in creating the database, figuring out how to export and import only pertinent information to and from the database, and formatting the script so that family parameter values are drawn from the database.

The estimated order of tasks is as follows:  

1. Learn the basics of the Revit API
2. Learn the basics of MS Access
3. Learn how to export Revit Family data to MS Access
4. Learn how to edit family data in MS Access
5. Learn how to update existing families with altered parameters form database
6. Learn how to create a family programmatically using random values
7. Learn how to get information from outside Revit API in a script
8. Integrate family generation script with database import script
9. Learn how to perform computations for inventory and cost estimation in MS Access

Comments:

On Hayley Selden's post:
Hayley,  AI in homes is something I've been interested previously, and I've wondered what the home environment would look like 20 years or so in the future.  I'm eager to see what you come up with, specifically what aspects of the home environment should be optimized, what information should the AI provide to the resident and at what level of detail, and what choices the AI should be allowed to make for the resident.

On Drew Hovey's post:
Drew, the crossover between "Green" and "Intelligent" buildings is an interesting one that I have not considered much before.  We constantly hear in our classes, and in the media to an extent, about how the building industry is trending toward green building and that the future of the industry lies in intelligent buildings, but I haven't though much about how these two aspects match up.  Certainly the sensor and monitoring capabilities of intelligent buildings would further enable sustainable building design, construction, and operation, but to what extent?  I'm excited to read more about your topic as it develops.

On Maria Raggousis's post:
Maria, I think your and Rachel's approach to this topic is solid.  I think that segmenting the topic in to robotics in construction vs robotics in homes (or in operation) is the way to go since the applications are very different.  I too had trouble believing that robots would be able to take over many tasks is the construction industry, and still remain somewhat skeptical.  I am eager for your paper to potentially convince me otherwise!

Chaudhari, Joseph. A Group. Week 2 Blog (AI - Future - Software - Computers)

Joseph Chaudhari (A Group)

Week 2

17 January 2017

Topics To Be Discussed: Artificial Intelligence | Computer | Software | Future

1.      Artificial Intelligence: A robot can take up to 200 commands or inputs per second as of 2015. Artificial intelligence and the future will greatly aide and improve current and upcoming generations of robots [3]. The results of expert coding and artificial intelligence can be seen in the 2015 DARPA robot challenge video. Robots can perform tasks almost as efficiently as human, just in a slower manner. These robots can also perform tasks autonomously, which is useful in situations where user to bot communication breaks down (like when there is a solid physical barrier between the two). Getting more into the nitty gritty of artificial intelligence and its uses, it can be seen to have great application to the world of call centers and help lines. For example, I used to be a director at a call center in New Delhi, India, where I had up to 22 employees at any time on the “floor” answering calls. If I were to have had artificially intelligent robots or answering machines working for me instead of employees, I could have been relieved of many headaches such as communication problems (our customer base was primarily American and most of the customers wanted to believe they were speaking to another American) and I could have saved a good deal of money in salaries (in the long run AI may have proven to be cheaper and definitely more worth-while since my call center was robbed by the employees once). There is not a single field of work that I can think of that will not be effected, whether it be positive (easier, work, money saved, safer environment) or negative (loss of jobs, loss of human connectivity and workplace comradery), by artificial intelligence.

2.      Computers / Future / Software: This article brings to mind thoughts that may not go through one’s head very often partially because our technology and computer systems are constantly evolving and we are typically focused on “what’s next”. One of these thoughts triggered by the article, 72 stunning things in the future that will be common ten years from now that don’t exist today, is that of disappearing technology. Things such as fax machines, desktop computers, the yellow pages, and video rental stores simply have no place in today’s technologically oriented society [4]. All of the devices listed in the previous sentence were very relevant ten years ago; that being said, what will happen ten years from now? Will things like the iPhone, apps like Uber and Lyft, and social media tools like Snapchat and Facebook disappear to allow devices that bring even more ease and connectivity to society to come forth? According to this same article, here are some of the new, and already familiarized, products that will be common in the next ten years. Drones. Drones are already well known in society. I am a drone, and helicopter, pilot and enthusiast. They are very useful tools in the film, defense, and infrastructure industries. Drones can also be used to hold concerts now as they can be equipped with speakers and deployed in great number to create noise load enough to entertain large crowds [4]. 3D Printers. These devices are already used in the construction industry in China. Entire houses of a uniform design can be printed and assembled in a matter of weeks now. Things closer to home will also be greatly affected by 3D printers. For example, women’s makeup, shoes, and silver-ware can be printed by these marvelous machines [4]. To change the subject slightly, Moore’s Law states that the number of transistors on a computer chip will double every year, while cost decreases. This was said in 1965 and basically remains true. This has a direct impact on the processing power of a computer. So, computer processing power will increase nearly two-fold every year resulting in some serious future computer power [1]. Computers will become “smarter” as software advances. For instance, since 2011 Android and Google vocal recognition has become much better thanks to Google’s department Google Brain [2]. The team at Google Brain developed the software in such a way so that the software could, itself, learn and adapt to incoming soundwaves and interpret them independently, effectively, and quickly. As software continues to evolve, things such as a human’s daily meal routine, traffic pattern, and evening home lighting (based on human mood interpreted by used actions) could be generated without direct user input and with the aid of appropriate sensors.

References

1. Hanson, Jack. "What Will Computers Look Like in 30 Years?" Future Computers | Future of Computer Technology | Quantum Computers. N.p., n.d. Web. 17 Jan. 2017.

2. "The Great A.I. Awakening." Evernote. N.p., n.d. Web. 17 Jan. 2017.

3. TheVerge. "The 2015 DARPA Robotics Challenge Finals." YouTube. YouTube, 12 June 2015. Web. 17 Jan. 2017.

4. "72 Stunning Things in the Future That Will Be Common Ten Years from Now That Don’t Exist Today." Evernote. N.p., n.d. Web. 17 Jan. 2017.  

Responses:

1.      Ronald Herazo: I am not very familiar with nano neutral networks and am thankful you wrote about them. It is incredible and seemingly fictional to think that we will eventually have a direct link between our thoughts and computers. A question that arises, as I do not know the answer, is how will computers filter our thoughts? For example, if I want to order a new Titleist 917 3-Wood gold club, but I quickly think of pizza, what will the computer do? Or will we just have to really focus on what we are ordering the computer to do? Who knows. Interesting subject of thought though my friend.

URL: https://ae-410-510-ay16-17.blogspot.com/2017/01/assignment-b1-group-ronald-herazo.html

2.      Ray Powell: Intelligent HVAC will be in every newly constructed building in the US within the next ten years (I hope). Your post makes me think of all of the different types of sensors that will be needed in monitoring not only HVAC but ideally all aspects of a building. Monitoring an entire building by means of sensor will be like giving that building a voice and thus making it truly intelligent. Once this can be achieved, structural health monitoring systems will advance to a whole new level with the help of the IOT and sensor companies.

URL: https://ae-410-510-ay16-17.blogspot.com/2017/01/b1-ray-powell-on-future-of-intelligent.html

3.      Andrew Ng: BIM is indeed revolutionary. Technology such as is saves so much time in the design and planning process along with allowing for beautiful and futuristic/modern architectural design to be implemented. Based on the data you presented, BIM must be nearly 90% or more in terms of its usage in firms across the nation. Over the next ten years its use and effectiveness will only increase and evolve.

URL: https://ae-410-510-ay16-17.blogspot.com/2017/01/bim-and-3d-printingtechnologies-of.html

Assignment B1- Wireless sensor technology for SHM

Due to the technological development of the past century, society has seen a surge in infrastructure’s growth and development. It has an immeasurable impact on our quality of lives which in turn enables our society to function and thrive. This dependability on infrastructure makes it of utmost importance to continuously measure and maintain a structure’s functionality and safety. Structures like buildings and bridges are built using strict codes and guidelines to ensure the quality and safety of these structures. However, there are events where the structure undergoes damage through its operational life from extreme loading circumstances caused by natural calamities like earthquakes and typhoons or due to lack of proper maintenance of the structure by the authorities in charge. The Federal Highway Administration (FHWA) reported that 150,000 Bridges are structurally deficient in the United States of America in their 2006 report (Jang, Rice et al. 2010). For this purpose, the Civil Engineering community has been developing new and accurate automated methods which can easily detect and analyze defects allowing the engineers to grasp the structure’s health under various circumstances (Lynch and Loh, 2008). This automated method is defined as Structural Health Monitoring (SHM).

The earlier structural monitoring systems used wired sensors which saw moderate success. The biggest concern with this type of system was the high cost and long time it took to install the cables as installing such lengths of cable consumed more than 75% of the total time to install the SHM system and over 25% of the total system costs (Kottapalli, Venkata A., et al.). Due to this, a need was developed in the civil engineering community to come up with new ways to measure the structural health which were faster and cheaper. The surge in development of microelectromechanical systems (MEMS) and wireless communication led to a lot of research in using wireless sensors in the last decade as (Hill 2003, Culler et al. 2004, Spencer et al 2004, Lynch et al. 2007). This research led to a solution in the form of wireless smart sensors which, due to the easy installation and lack of wires, were significantly cheaper and faster to install than their wired counterparts. 

Structural health monitoring using sensors is essential to understand and maintain a structure’s reliability and safety. Due to the limitations of visual inspections and lack of funding to install expensive options like wired sensors, it is essential to find and develop new methods such as wireless sensor technology. Even though wireless sensors are not a perfect solution since they consume a lot of power as compared to other methods and are unreliable at times due to packet losses in areas with bad wireless internet quality, research must be done to look into the feasibility of self-reliant methods to monitor these structures. With the increasing popularity of green energy like solar and wind energies, it is essential to look into making hardware that can maximize the potential of such sources making wireless technology a feasible replacement for our current methods for SHM.

Sources: 

1) Lynch, Jerome P., and Kenneth J. Loh. "A summary review of wireless sensors and sensor networks for structural health monitoring." Shock and Vibration Digest 38, no. 2 (2006): 91-130.

2)Jang, Shinae, Hongki Jo, Soojin Cho, Kirill Mechitov, Jennifer A. Rice, Sung-Han Sim, Hyung-Jo Jung, Chung-Bang Yun, Billie F. Spencer Jr, and Gul Agha. "Structural health monitoring of a cable-stayed bridge using smart sensor technology: deployment and evaluation." Smart Structures and Systems 6, no. 5-6 (2010): 439-459.

3)Kottapalli, Venkata A., Anne S. Kiremidjian, Jerome P. Lynch, E. D. Carryer, Thomas W. Kenny, Kincho H. Law, and Ying Lei. "Two-tiered wireless sensor network architecture for structural health monitoring." In Smart Structures and Materials, pp. 8-19. International Society for Optics and Photonics, 2003.

Alexander Koo made an interesting point about artificial intelligence that "Narrow AI can already outperform humans at their specific task. Strong AI would therefore completely change the possibilities of modern day technology. There is currently no computers being able to exhibit full artificial intelligence."  A surge in technological advancement in AI would definitely enable reliable and cheaper ways to use wireless sensors for SHM as a strong AI would probably will be able to find better ways to minimize power consumption or packet loss problems that we are facing right now.

https://ae-410-510-ay16-17.blogspot.com/2017/01/assignment-b-1-alexander-koo-team.html

Ronald Herazo talked about the surge in technology for personal computing and how nano neural networks will be standard in the future which means every brain will be "connected". Although sounds good in theory, i am a little skeptical about the scope of this technology. Like i discussed, Something as simple as wireless sensor technology is pretty common for us these days yet it is still hard to use it efficiently. The technology Ronald talked about can come by very soon, but unless it can be used efficiently for large scale purposes, it would remain as a "tech-demo", something which sounds cool in theory yet has no real life uses, at least not until these problems are taken care of.

https://ae-410-510-ay16-17.blogspot.com/2017/01/assignment-b1-group-ronald-herazo.html

Christopher Sager talked about BIM and its uses in construction practices and i wholeheartedly agree on his views. A giant database which can reliably be used for data gathering and using that data to predict future problems is what wireless sensor technology aims to do for SHM. A large portion of construction companies now use BIM extensively to save both time and money as well as boosts personnel safety on field. 

https://ae-410-510-ay16-17.blogspot.com/2017/01/b1-group-b-blog-post-week-1-christopher.html

Week 1: Assignment B1

As engineering students we all have some deep desire to discover the future. I think we find the future of computers particularly interesting as millennials. Artificial intelligence is one of the futuristic leaps computers have made. In the 1940's scientists thought artificial intelligence was magical and way to far in the future to even think about it [1]. However in our lifetimes we have seen google translate, image recognition, speech recognition, and many more technological advances improve with artificial intelligence. Artificial intelligence is the ability for computers to learn from experience and use that knowledge to make decisions much like a human.

In the past couple years A.I. has been used in our everyday lives without us even realizing it. From blocking spam emails to pre-organizing your photos, artificial intelligence is more common today than it every was before. This coming year it will become more main stream in the business world. For example, engineering firms might begin using A.I. to determine where bridge failures will occur based off of the sounds cars make as they drive across [2]. Even automobile industries such as Tesla Motors are using A.I. to move towards self-driving cars [2]. Te cars make decision based off of information they have learned, like how far to stop behind a car to avoid a collision. We heard in class that the success of A.I. is the ability of a human to talk to the computer and not know that they are talking to a computer. I think we are moving towards this.

Although we have moved into a future where our smart phones suggest apps we might use based off of our location, I doubt that we have moved into the future most Americas dreamed about in the 1940's. I think we won't reach that point until our computers can talk to us just like humans as scary as that seems.

[1] Lewis-kraus, Gideon. "The Great A.I. Awakening." The New York Times. The New York Times, 14 Dec. 2016. Web. 17 Jan. 2017. <http://www.nytimes.com/2016/12/14/magazine/the-great-ai-awakening.html>.
[2] Shankland, Stephan. "Artificial Intelligence Has a Big Year Ahead." CNET. N.p., 14 Dec. 2016. Web. 17 Jan. 2017. <https://www.cnet.com/news/2017-artificial-intelligence-mainstream-businesses-adopt-ai/>.

Comments to Other's Posts:

Maissoun Ksara: I think it is so interesting to see the actual numbers behind drones constructing buildings. To be 10 times cheaper and 5 times faster, I wouldn't see a reason to not continue to improve this function of drones. I think it is important to note the loss of jobs. Construction workers account for a large amount of our population and that would make them unnecessary. 

Peter Dannemann: Quicabot is a robot I have never heard of and I'm so glad I read your post. I think it is so interesting that it can inspect a building faster and better than a human. As a coop I inspected a few buildings with an experienced coworker and it is not a very thorough process. It is easy to miss a vital flaw or to focus on something that isn't too important. I think the only question I may have about Quicabot is how it would handle a malfunction and what that might look like in a building inspection report. 

Egla Qori: I found your post very interesting. I was unaware that 3D printing was printing real concrete structure, I had no idea it had moved past models. This would be particularly helpful by using 3D printing to construct materials before getting to the job site saving time and labor costs. I think 3D printing takes the human error out of construction projects allowing engineers to design with a lower factor of safety, saving money in the long run. 

Assignment B1 - Taryn Francischetti - A-Team

The future is not far off. Many people argue that we are already living in it. Technology is advancing faster than ever. Futurist Thomas Frey argues that things such as artificial intelligence and software embedded in all things will be common place ten years from now [1]. This is going to be a major factor on the building industry if machines will be building the building itself.

Software has already been produced such as the video that shows the video of SAM, the bricklaying robot, working with a mason on site [2]. Robots with AI intelligence such as SAM greatly increase safety on job sites. SAM can do many real time calculations to ensure that all bricks will be placed in the exact same way. The building will have very few errors in construction, if there are any at all, due to the consistency of a robot's work. This variability will be even further reduced if the robot is able to learn through artificial intelligence. For example, MIT researchers have created a new AI system where the machine learns in real time such as the way a human can research the answer to a question [3]. This allows the robot to quickly solve a problem that could be encountered during the building process.

AI can also be used for other things than just building. It can also be used for building inspections such as the robot that does building inspections [4]. This could make building inspections in hazardous conditions much safer. With AI, the robot could easily document the problem and even suggest ways to fix it. Eventually, the robot could be able to deal with a problem all the way from diagnosis to repair. This would be able to ensure worker safety as the robot would make it so human beings are not being put in harms way. The only down side of AI on job sites is the loss of jobs. Many people would have to be retrained to maintain the robot or learn something new completely. The robots on the job site will eventually be able to complete buildings very quickly and humans could become almost obsolete. This was already done on many production things such as the assembly lines for cars.  The future of buildings becomes a very intriguing place as AI becomes more and more popular. There are pros and cons for robots but the future of these being common place is not far off.

References
[1] http://www.futuristspeaker.com/business-trends/72-stunning-things-in-the-future-that-will-be-common-ten-years-from-now-that-dont-exist-today/?nocache=1

[2] https://www.youtube.com/watch?v=jYo4PAWRIHE

[3] http://www.kurzweilai.net/a-machine-learning-system-that-trains-itself-by-surfing-the-web

[4] https://www.youtube.com/watch?v=ycWStiPjQU0

Comments
Ronald Herazo - I did not know that wireless connections were being worked on such as WiGig. If large amounts of data could wirelessly be transferred, it would greatly increase productivity on job sites. Laptops work fairly well but many of them are not able to complete, or connect to, databases without being wired. I've also only every considered perceptual computing to be a thing of the future. It would be amazing if hand gestures were incorporated into computer-user interface within the next ten years. His post can be found here.

Christopher Sager - I disagree that the future of drones being able to decipher buildings and being able to put a building together. Drone technology has come very far in the last few years. For example, drones are now able to fly places based off of photo recognition and fly without a person controlling it. Technology is probably not too far off for the drone to be able to fly a component of a building and put it in place. Granted, there may have to be more than one type of drone to complete the task such as one acting as a crane and one welding but with time, fewer robots will be needed as their software becomes more and more intelligent. His post can be found here.

Nick Pawlikowsi - I found the section on the steel 3D printing robot very fascinating. It is extremely advantageous for the building materials to be produced and assembled on site, let alone at the same time. Many costs decrease such as production and specifically transportation costs of the materials. This would also help further in the construction of the building as multiple components could easily be assembled together instead of separate pieces having to be assembled after the fact. There has been more than one instance where shop drawings were misinterpreted and building failure has occurred. His article can be found here.

Assignment B1: Maissoun Ksara - A-Team

Tags: AI, future, software, computer

Our drive for a more advanced and innovative society is increasing like wildfire. Research and development of more technologically capable tools is a priority in many fields, one of them being the construction industry [3]. In the video “How will artificial intelligence benefit the construction industry?” the Arup director Tim Chapman defines artificial intelligence (AI) to be the ability for machines to think. It deals with the engineering of intelligent machines or computer programs that understand human behavior and intelligence [1]. 

AI will have a significant impact on construction in terms of design processes and making the construction process more streamlined and efficient. The Association of Equipment Manufacturers states that robots are being increasingly used for tasks such as demolition, welding, bricklaying, and concrete dispensing on jobsites today [2]. When I first watched the video in class that involved bricklaying performed by the robotic arm, I was excited because I saw how beneficial this technology would be in the future of construction. Using AI also means avoiding human risk for errors and an increased accuracy. Further, it creates more safety on the jobsite. Since safety is one of the most important values of various construction firms, AI gives an extra edge. 

In the article “Artificial intelligence has a big year ahead”, a discussed use of AI is in predicting bridge failures. A combination of data and software is all it takes to prevent a bridge failure in simple steps. Not only does this save lives, but also a large amount of time and labor. 

In his TedXUCLouvain talk, Pierre Latteur describes the impact of robotics in construction as the newest revolution. He specifically talks about drones to carry out tasks like bricklaying using a  completely automated process. Figure-1 below shows an example of how using only 2 drones, a 16 square meter masonry unit can be build in only 2 hours with a total cost of only 4 euros per square meter. Latteur says this is 10 times cheaper and 5 times faster.  

Figure-1: Drone Building

Several challenges exist in this sector, including positioning problems of the drone carrying masses under the influence of wind. Also, as the concrete elements get larger and heavier, there are more challenges with accurate positioning of the element. I was first skeptical about topic because I was wasn’t sure if the drones would be strong enough to carry the concrete loads. I also have questions about the grip strength of the drones and several safety concerns without UAV’s flying around a jobsite. All in all, this seems like an exciting and highly innovative tool for the future of construction.

Comments to others:

Peter Dannemann: I have never heard of Quicabot before and I’m very glad I came across this! It seems crazy and exciting to me that Quicabot can inspect a building in half the time a human can, with more reliability. I can’t help but think what the construction industry would look like in several years. It would be completely taken over by robots. In the event of a malfunction, I am curious to know how this would impact the construction. This would put a building in risk of collapse due to a software error, or even a hacker. Despite this, I see much potential in this field. 

Egla Qori: 3-D printing is a concept that I believed was applicable in many fields, however, construction was not one of them. I think it is absolutely fascinating how entire homes can be 3-D printed. Using this technology, the possibilities are endless to designing and constructing entirely innovative and efficient structures. As you mentioned the egg-shaped form, the printer removes the risk of human error in designing it and proves total safety. New shapes can be created that were never introduced before.

Nick Pawlikowski: Reading about the work that MX3D has done in 3-D printing blows my mind. Sometimes I forget that we live in “the future”, since advances like this are quickly taking over. I wonder what the cost of 3-D printing a whole structure is compared to conventional methods of building. It makes sense that there is still a decade of work needed for full development. I’m excited to see where this technology goes in the coming years.

References

1. http://www-formal.stanford.edu/jmc/whatisai/node1.html
2. https://www.aem.org/news/october-2016/how-artificial-intelligence-could-revolutionize-construction/
3. http://www.conexpoconagg.com/news/august-2016/artificial-intelligence-in-the-construction-indust/