Menard explains how Artificial Intelligence and Machine Learning are altering traffic | Technology
|Menard explains how Artificial Intelligence and Machine Learning are altering traffic | Technology|
How AI and Machine Learning are reshaping traffic: Menard
Of the many ways that artificial intelligence (AI) and machine learning are poised to improve modern life, the promise to impact public transportation is significant. The world is very different compared to the early days of the pandemic, and people around the world are once again taking advantage of mobility and transit systems for work, play and more.
Transportation is one of the most important areas where modern AI offers a significant advantage over conventional algorithms used in traditional transit system technology.
AI promises to optimize traffic flow and reduce congestion on many of today's busiest highways and thoroughfares. Smart traffic light systems and the cloud technology platforms they operate on are now designed to manage and predict traffic more efficiently, which can save a lot of money and create more efficiency not only for cities themselves, but also for people. Today's artificial intelligence and machine learning can process highly complex traffic data and trends and suggest optimal routes for drivers in real time based on specific traffic conditions.
As a result of dramatically improved processing power, transit system technologies are now used in various Internet of Things (IoT) devices to achieve the real-time image recognition and prediction that took place in legacy data centers. during the last half century. This new architecture focused on decentralization helps increase the implementation of machine learning and AI. Current recognition algorithms offer an improved view of the combination of density, traffic, and overall flow rate. Additionally, these optimized algorithms can leverage data points per region, resulting in an optimized pattern to reduce traffic issues and redistribute flow more optimally. Municipal transit systems may then have better decision-making power, and the control system has a much higher degree of fault tolerance, as previously demonstrated in legacy hub-and-spoke systems.
AI is already impacting transit systems
Because the new platform leverages pre-existing infrastructure, it required no additional hardware installations inside traffic light or bus cabinets. And, unlike traditional location-based check-in and check-out TSP solutions, the platform processes live bus location information through machine learning models and places priority calls based on estimated bus times. arrival. So far, the platform has improved travel times on VTA Route 77 by 18% to 20% overall, which equates to a five to six minute reduction in signal delay.
The cloud-based traffic signal priority system combines asset management and automation to produce a system capable of serving an entire region. Unlike hardware-based systems, this platform uses pre-existing equipment and leverages cloud technology for easy operations. This eliminates the need for vehicle detection hardware at the intersection because the location of the vehicle is known through the CAD/AVL system. This allows for both priority calls from greater distances away from signals and coordinated priority calls between a group of signals. In addition, the system provides real-time information on which buses are currently receiving priority along with daily reports of performance metrics.
The advanced traffic signal priority systems available today consist of two parts, a traffic cabinet unit and a vehicle mounted unit. The transit priority logic is the same, regardless of the means of detection and communication. When a vehicle is within predetermined limits, the system sends a request to the signal controller for prioritization. Since the original systems used fixed detection points, the signal controllers were configured with static estimated travel times. Since travel times depend on various environmental factors, the industry implemented GPS-based wireless communication systems. With this method, vehicles within detection zones replace static detection points, and vehicle speed is used to determine arrival time.
The platform enables cities to leverage current infrastructure investments to implement city-wide TSPs. To enable secure connections to the traffic lights, each city requires only one device for use, which is a computer that resides on the "edge" and serves as a protective link between the city's traffic lights and the platform. It is designed to securely manage the exchange of information between traffic lights and the cloud platform. It is the only additional hardware required, and depending on the configuration of the existing city network, the platform can receive vehicle data directly or through the city network using secure connections.
A sophisticated process for prioritizing traffic
The system's method of making priority calls to traffic lights is more sophisticated and is not limited to fixed point locations. Unlike the current state of the art of placing priority calls based on spotting buses at specific locations starting a pre-programmed arrival time, this platform uses a "vectorized" approach. In mathematics, a vector is an arrow that represents a magnitude and a direction. In the software of this platform, the arrow points in the direction of the traffic light and the magnitude is the travel time.
When the system is configured, road signs, bus routes, and bus stops get a digital representation in this vector. This ends up producing a digital geospatial map where the software can track the bus's progression along the bus routes. This results in a system that can dynamically place transit calls regardless of location. Instead, the system makes precise priority calls based on estimated time of arrival, which is the basis for all TSP registration calls supported by all signal controller vendors. And due to the nature of the tracking algorithm, any significant changes in ETA can be adjusted. For example, if a bus was predicted to skip a bus stop but did not, the system will detect the change and adjust the priority call accordingly.
The combination of Artificial Intelligence, Machine Learning and cloud-based technology has great potential to not only improve the current public transport system, but also to reinvent it all together. This advanced technology is already demonstrating how it can improve the coordination between GPS, navigation applications, connected cars, and even taxi and ride-sharing services to efficiently combine them into a single traffic entity based on real-time data.
In the not-too-distant future, connected autonomous cars and trucks are expected to become more prevalent on roads and highways, offering even greater potential for AI to reduce both the duration and risk of rapid mobility.