Can AI Be Used to Check Stop Control Warrants?

person at a computer with back to viewer

For some time I have been thinking about how AI could be used to assist civil engineers and the public works industry. While I have several ideas, one obvious application I’ve thought about is using it to check all-way stop control signal warrants as defined by the Manual of Uniform Traffic Control Devices (MUTCD). Since I was taking a class in AI with homework asking us to create our own GPTs using ChatGPT, I figured I’d use this opportunity to try out the MUTCD stop warrant idea. While an analysis by AI obviously cannot be used in place of an actual engineer’s analysis, I thought others might be interested in seeing the result of this test of its abilities.

I’ll include below the results so even if you don’t have a subscription to ChatGPT you can see how it performed. If you subscribe to ChatGPT, you can try it on your own at by uploading a txt file with data similar to my example below using the “Stop Control Warrant Analysis” GPT – this is different from using ChatGPT as it is a custom GPT I created specifically to analyze stop control warrants per the MUTCD.

To use it I first prepared a text file with the data I figured the GPT would need to perform the analysis. This is the information I put into a TXT file using Notepad then saved it. By the way, this is all made up information for a fictitious intersection:

Name of Intersection: Main and 22nd
Intersection Location: Anytown, IL
Minor Street Name: 22nd street
Major Street Name: Main street
Number of legs in the intersection: 4
Number of crashes in a 12-month period: 40
There is adequate sight distance.
An all-way stop control could not serve as an interim measure.
The number of units per hour in a typical 8-hour day on the major street is 5000
The number of units per hour in a typical 8-hour day on the minor street in that same hour is 300.
The 85th percentile speed limit is not over 40 mph
There is a need to control left turns
These are not through residential collector streets.
Pedestrian and/or bicyclist movements support the installation of all-way stop control.

Next I went to the Stop Control Warrant Analysis GPT and typed in this prompt: “Can you help me figure out if my intersection needs a stop sign? I have attached a text file with my data.” And I uploaded my TXTfile. Below is a screenshot showing this along with the output from the GPT.

Screenshot of GPT output
Output from Stop Control Warrant Analysis GPT – click the image to enlarge it.

I tested it again by starting a new session and uploading a new text file with slightly different data noted below – again all fictitious:

Name of Intersection: River and 22nd
Intersection Location: Anytown, IL
Minor Street Name: 22nd street
Major Street Name: River street
Number of legs in the intersection: 4
Number of crashes in a 12-month period: 4
There is not adequate sight distance.
An all-way stop control could not serve as an interim measure.
The number of units per hour in a typical 8-hour day on the major street is 150
The number of units per hour in a typical 8-hour day on the minor street in that same hour is 100.
The 85th percentile speed limit is not over 40 mph
There is not a need to control left turns
These are not through residential collector streets.
Pedestrian and/or bicyclist movements do not support the installation of all-way stop control.

Below is another screenshot showing my prompt and the response:

screenshot of output of GPT
Output from Stop Control Warrant Analysis GPT – click the image to enlarge it.

For each you can see I have asked the GPT to add the language at the end so if anyone tries this they realize it cannot be used in place of an actual analysis by a professional engineer. I only set it up to test out how well it might work with completing this type of analysis and would not want anyone to think it is doing actual engineering – it isn’t. There also might be better ways to use other technologies to do the same thing. However, all of this was done just by telling it what I wanted it to do and giving it the information it needed to do it.

In the future I will continue to test out different applications to see how useful it might or might not be. And if I have anything that looks interesting I’ll continue to share here. If anyone else has tried creating something for engineering or public works, I’d also be very interested in exploring it.

Share

A Day in the Life of a Civil Engineer – Day 60

Day 60

Culvert Lining Project

Geneva Culvert Lining Project 2011

Today was the day the liner was delivered for our culvert lining project. The placement of it seemed to go well. The contractor will finish grouting the annular space tomorrow. A resident did stop by to tell us we didn't know what we were doing, and it would never work, and he would sue everyone when water backed up into his home. Of course, he had no  information to base his opinion on other than the new pipe is of a smaller diameter than the existing one. So the other staff members tried to explain the hydraulics and design information to give him an idea of why a smaller pipe can carry the same or more water, but he still didn't believe anyone. So he contacted the elected officials to express his concern. I let the engineer who designed the culvert project know about the complaint. 

It's unfortunate, but this seems to happen so much where a group of professionals put in a lot of time designing a project, and then someone stops by and tells everyone they are all wrong, and it will never work. And they never seem to have any facts or information to base their opinion on. 

I have to admit I have seen some poor designs in general executed over the past 30 years, however, none related to culvert sizing. And even those poor designs did not cause failures or damage – they were just not good designs and usually ended up impacting our operations and increasing our costs. So the city had to do more work to make the final product better and improve efficiency and cut costs. But I can't remember where there was property damage that could be attributed to bad design – maybe poor construction but not poor design.

Of course, the bottom line in a something like this is that anyone building or buying a home next to a creek increases their risk of having water entering their home during a storm. Particularly when openings like doors or windows are installed that allow for a way for water to enter the home. Culverts and other stormwater facilities are only designed to carry a certain storm intensity. If a storm occurs that is greater than the design storm, the culvert or other stormwater infrastructure will not convey all the water and could allow water to back up and enter nearby structures. So for our situation, whether we leave the old culvert or install a new one with equal or greater capacity, there will always be a risk that a storm occurs that will not be handled by the culvert and water could back up into homes – that is the risk of owning property next to a body of water.

Intersection Enhancements

We also met with a vendor who sells traffic control products. He did a great job showing us some alternatives for the intersection where we are trying to draw attention to a pedestrian crossing. One product we are particularly interested in is a sign and light called the "Enhancer." Here is the link to a site showing the product: http://www.statewidetrafficsafety.com/enhancer.asp.

Miscellaneous

We did manage to get our staff meeting in today. And I continued on trying to check our budget line items.

 

 

Share

From the Floor at APWA Congress 2010

Due to budget cuts I was only able to attend the APWA Congress for one day since I was speaking on a panel at the show. Normally, I try to attend the entire event because I always come away with many valuable insights and opportunities to reconnect with fellow professionals. This year, in the short time I was able to spend there, I was able to find a contractor who performed sawcutting of sidewalk trip hazards. My division was already familiar with Precision Concrete Cutting and have used their services to eliminate trip hazards. But in order to expand the project, we needed to have more than one proposal for the work. Fortunately Sidewalks Plus was at the show, and I was able to speak with a representative about their process and get their contact information. This allowed us to investigate two bidders and move our project forward. I also was able to discuss a few other pressing issues with representatives from a few other companies. So in addition to speaking, networking, and researching products, I was able to also conduct some business related to existing projects. 

While checking out the products on the floor show, I was also able to video tape a few interviews with vendors. Willie Urish with Tower Sign and Signal had contacted me prior to the show to discuss his product. So we made some time to meet so I could see his product in person. He also allowed me to video tape his product demonstration. His company, based in Illinois, manufactures and sells portable traffic signals for construction jobs.

Share