Variable Speed Limit Webinar

Variable speed limits systems have always, at least intuitively, promised benefits for work zones including greater throughput, reduced speed variance, and as a result, fewer crashes. We discussed these systems in a post in October 2015 after a presentation at the National Rural ITS meeting in Utah. The concept made sense and we looked forward to greater use of VSL systems.

A webinar was just offered April 4th by the US DOT Office of Assistant Secretary for Research & Technology entitled, “Variable Speed Limit Systems – Are They For Everyone?” The speakers, and there were several of them, did a great job of explaining the advantages and disadvantages of these systems. Those speakers included Jimmy Chu of FHWA, John McClellan of MnDOT, Bryan Katz of Toxcel, Jiaqi Ma of Leidos, and Vinh Dang of WsDOT.

There wasn’t a lot of new information. Instead they presented a comprehensive history of VSL systems from around the country. They looked at different uses for these systems, including work zones. In all, more than a dozen different projects from 9 different states were discussed. Some projects were relatively small, and others like those in Minneapolis and Seattle, were quite large.

But in almost every case, the results of these systems have not met expectations.  This was true for weather related systems, work zones, and congestion management applications. Reductions in speed variance and crashes were very small if not non-existent. And the reason in every case was a lack of conformance by the traveling public. There was some smoothing, but very little.

Many of the system designers anticipated this and included variable message signs alongside the VSL signs to explain why the speed reduction was justified. But drivers either misunderstood when they were supposed to slow or simply chose to continue at their current speed until they saw the problem for themselves.

Law enforcement is critical for these installations. Without enforcement, compliance will never reach levels that will result in the benefits designers expected. But law enforcement often became distrustful of the data they received, or didn’t get timely notifications at all. They also ran into serious resistance from the courts. So enforcement slowed, and compliance tanked.

There is still hope that these issues will one day be resolved. But for now, variable speed limit systems just aren’t providing the benefits we all hoped to see.  The webinar closed with a short discussion of future considerations. One thought was to combine these systems with a larger big data process (as discussed in our last post). They might look at not just weather, or work zone conditions, but also at traffic speed and volume data approaching the area, timing of major events, and more to improve drivers trust of VSLs.

Another thought was with regard to automated vehicles. Will VSL systems be more effective when the information is sent directly to each vehicle? If a pop-up display recommends slowing to 35, will they be more likely to do so? Or will they continue to ignore them as they apparently do now? Once autonomous (driverless) cars are on the road, the recommendations from these systems will be adopted automatically. But until then, compliance will remain the biggest problem for VSLs.

Machine Learning and Work Zones

Last July we talked about the phenomenon of Poke’mon Go and augmented reality and considered ways in which that new technology might be applied to work zones. Today let’s consider another new technology. This one is not really new but is enjoying renewed interest thanks to Big Data and an abundance of inexpensive computing power. Using machine learning we can now process our data in ways we could not before.

In its simplest form, machine learning is an algorithm or model that goes through data looking for patterns. Then using those patterns it can make predictions for another, similar set of data. Machine learning works well with different types of data. So, for example, it could crunch through traffic speed data and compare it to social media sites focused on local traffic problems. In this way it can find trends or commonalities that don’t come through in conventional data analysis.

Machine learning is a faster and more accurate way of adapting to human factors issues related to work zones. We set up a system before the project starts and configure it for conditions at that time. But conditions change in work zones. So what worked early may not work as well later. Now don’t misunderstand. The system still works. It still warns of queuing ahead. But if the timing of the messages varied depending on changing conditions throughout the day, coming on sooner, or turning off faster, it could improve driver compliance. And the only way to learn that is through machine learning.

Now there is one problem with machine learning, and it is a big problem. It acts as a black box taking in data and spitting out recommendations. But the process is not something you can review after the fact to understand what influenced the outcome. So agencies could not tell their governor why they have made changes. But if you are more interested in being able to adapt to changing conditions quickly and accurately than in being able to explain it, machine learning is the tool for you.

Let’s consider a few possible applications:

  • Algorithms used to trigger messages could learn to de-emphasize input at certain sensors at certain times of the day when that sensors data is not in line with conditions elsewhere.
  • Models could make better recommendations about the best times and days of the week for lane closures while still meeting goals for minimal level of service.
  • In time, machine learning could establish baselines for crashes, fatalities, etc. resulting from a project both with and without work zone ITS systems in place. The system would be justifying itself! Of course, the predictions would have to prove true over time.
  • Predictive analytics reviewing probe and spot speed data may see locations of higher crash frequency or recommend a different geometry or staging in that location.

Is this complicated? Absolutely. But tools are already available to make it easy to get started, to choose the best algorithm, and to scale up and down in size as the situation demands. And Iowa DOT has already doing it at their Center for Transportation Research and Education.

Until now we could only design a system for a project to get the best overall performance. Now we can save even more lives through machine learning. Once our systems begin to learn from their own data, they will perform even better than they are today.