Originally published here on July 13, 2023
Over the past few years, artificial intelligence (AI), machine learning (ML), predictive modeling, and cloud technology have significantly changed our nation’s transportation system. Today, transit and emergency response networks nationwide are researching and deploying never-before-seen transit technology based on AI and cloud technology.
However, these agencies and city officials are beginning to understand that there are differences in the type of technology available today, and it’s critical for them to understand the differences, which can significantly impact their budgets. Unfortunately, they often fall into the trap of taking a hardware- and device-centric approach to their technology implementation, which can be disastrous to their communities and budgetary planning.
Understanding the need to improve traffic
All areas of the US transportation system are focused on curbing the growing traffic trend by introducing and leveraging technologies and solutions that utilize data analytics to create a better traffic flow. In addition, carmakers are also promoting more connected vehicle technologies to make cars and trucks on the roads smarter and more efficient by connecting to any number of databases and platforms that can help vehicles read traffic patterns in real-time.
However, a hardware-based approach to building a next-generation transit solution can cost cities five or ten times more in the long run. Sure, there are video-based and device-centric traffic data collection solutions on the market with advanced technology, but implementing these solutions can bring about significant budgetary challenges over time.
Why planning around devices can be costly
Any solution centered around a hardware- or device-centric solution is akin to proudly buying the latest iPhone but sticking with the same operating system for the next 10-15 years. The integrity of the device diminishes with every passing year while the software and web applications continue to innovate past the capacities of the phone.
However, cloud-connected and managed devices are now more maintainable and extensible than their self-contained counterparts. Furthermore, cloud-enabled platforms are more cost-effective because costs associated with updates and scalable upgrades usually directed at purchasing additional hardware and software are immediately eliminated. Operational, maintenance, and upgrade costs are all expenses that disappear. The cost savings include the additional benefits of using cloud resources with an improved cybersecurity and data recovery posture outlined in the service-level agreements.
The correct hardware based on an advanced, agnostic cloud-based platform operating system leveraging AI, ML, and leading data analytics is highly effective.
In fact, in today’s age of highly reliable large-scale communication access, the opportunity exists to eliminate the hardware cost of transit signal priority solutions while maximizing the investment in current solutions. Many of today’s signal controller firmware vendors have software functionality to facilitate placing virtual priority calls. The information needed to place these virtual calls can be found at the transit agency.
To better manage their fleet, agencies typically have implemented tracking devices on each vehicle to report to their computer-aided dispatch and automatic vehicle location (CAD/AVL) software. With vehicle locations known in near real-time, software and networking can now bridge the gap between transit vehicles and city signals to facilitate transit priority in a more reliable, sustainable, and intelligent way.
AI and cloud-based platforms can completely reimagine the mass transit system and make it better than it is now. For example, technology is already demonstrating how to improve coordination between GPS, navigational apps, connected cars, bus transit, and even taxi and ride-sharing services to combine into a single entity effectively.
The need for an agnostic platform
Today’s technology-heavy EVs cannot exist without a reliable network and infrastructure of charging stations. In a similar context, connected vehicles and a device-centric approach cannot solve today’s traffic problems alone, and therefore ITS systems are only as good as the agnostic data-sharing platforms they operate on.
These data-sharing platforms have been proven highly effective, but only when cities and municipalities overseeing transportation systems make them open for proper data sharing. Unfortunately, many municipalities remain locked into contracts with hardware and device providers who claim to operate under “open architecture” yet are unwilling to work under an open data platform, and these cities severely restrict themselves from the true possibilities that a cloud-based platform can provide.
This setup is like hardware and device providers dangling a shiny new toy in front of city and budget owners. Yet, a few years later, they realize they must keep shelling out millions for new hardware and upgrades to maximize data use.
Cloud-based TSP systems take the global picture of a system into account and use machine learning to predict the optimal time to grant the green light to transit vehicles at just the right time. It minimizes interference with crisscrossing routes and simultaneously maximizes the probability of a continuous drive. More importantly, the agnostic cloud-based platform ensures cities leverage a continuously updated system for maximized transit potential.
With this technology now at our fingertips, cities, and municipalities have the technology they need to properly accelerate the buildout of intelligent transit networks to benefit everyone in the region.
2 Comments