THANK YOU FOR SUBSCRIBING
The transportation industry in the optics of a governmental agency has transformed dramatically over the past few years. Once considered a “utility,” the transportation infrastructure is managed and operated today as a part of the smart city technologies in support of enhanced mobility, and quality of life. Beginning in the mid-1980s, intelligent transportation systems (ITS) have been providing sensor-based batch data to a centralized platform to capture vehicular counts and for the management of synchronized traffic control. Today, those systems, along with others are providing transportation practitioners with real-time data on virtually every aspect of the transportation network.
Currently, most agencies across the nation and the world are or have begun developing plans for the utilization of transportation data to drive decisions in areas such as service delivery, pavement management, curb-space management, Mobility as a Service (MaaS), and too many others to list. These reach beyond the traditional congestion management and air quality metrics used over the past 25 years. This focus is primarily based on capacity expansion as the right-of-way and construction of wider facilities is cost-prohibitive.
When an agency employs the use of machine learning, deep learning and artificial intelligence to our transportation technologies it creates numerous opportunities in research, development, and innovation. Those opportunities often appeal to a local college, or university who may provide analytical or computer engineering services via interns to communities. This is a benefit to both organizations as most of academia will “jump” at the opportunity to work with “real data” on “real world” problems.
Applications for the data can vary when analyzed with machine or deep learning and AI. Examples of data collected and analyzed can include Air Quality (NOx, VOC, CO or PM 2.5) and how modifications to the system can effect each of those emission components. Another example is object tracking of trajectory and velocity looking for crash potential. Either of these applications would prove to be a tremendous asset for a governmental agency to provide to its public.
Other efforts within this same research include crash predictive analytics, prioritized routing for first responders and balanced alternative routing options the community. Development of micro-grids for resiliency, redundant communications networks, edge computing and cyber-security on the edge are additional challenges being addressed in these research initiatives.
Each of these research initiatives is foundational to the core activity of creating a safe working environment for connected and autonomous vehicles. The solutions we are considering today, need to be replicable and scalable worldwide. Much like cellular telephone technology and IoT of today, the systems developed need to be accessible, equitable and universal in their interface with the public. It is the primary challenge facing transportation professionals today.
Finally, discussions on the commercialization of data by government agencies are evolving. One perspective of government is, “that the data was acquired through government assets procured with funding generated by tax revenue; therefore the data should be free and without additional cost.” The second perspective is that if any scrubbing or analysis of the data is performed prior to availability, there should be a cost applied to those data. With any number of third-party organizations providing data to the public, access to real-time data for research and development will become a government’s most valued asset.
Transportation infrastructure is the pathway for many agencies working on Smart Cities concepts. It is a technology growing and adapting to the new world paradigm shift, and provides good optics for the public when addressing traffic flow and safety concerns in our communities.
Read Also