:strip_icc()/i.s3.glbimg.com/v1/AUTH_59edd422c0c84a879bd37670ae4f538a/internal_photos/bs/2019/M/q/Z4ApA9RUS7KAqlFTaV7Q/bbcvivacitylabs.jpg)
[ad_1]
Traffic jams are a plague in our lives. But with so many technologies at our disposal, why do we continue to treat them as obsolete?
Although our means of transportation have evolved significantly in recent years, our traffic management systems have struggled to track the number of vehicles.
Congestion control measures often do not respond to sudden changes in road or weather conditions. Not to mention the many traffic lights that always work with unsynchronized timers, preventing traffic from flowing normally.
In 2015, there were approximately 1.3 billion motor vehicles in the world and, with the rapid growth of emerging economies, this number is expected to increase to over 2 billion by 2040. Even with new avenues, this growing volume of traffic could quickly exceed the capacity of our road networks, especially in cities.
But the combination of new communication technologies and the power of artificial intelligence (AI), which allows the processing of large amounts of data in real time, could it be the solution to this problem?
Very Low Average Speed
While many consider self-driving vehicles to be the bottleneck of traffic jams – robots can be taught not only to drive less accurately, but also to react faster than drivers, but this continues take at least two decades before they start to have a significant impact.
Until then, road agencies and planners will have to deal with an increasingly complex mix of human, semi-autonomous and autonomous drivers. To keep them all moving, the traffic management systems will have to react and adapt instantly.
In Bengaluru (the new official name of Bangalore) in India, a city that often experiences long traffic jams and where the average speed on some roads is only 4 km / h, created by the giant of Siemens Mobility technology. a prototype surveillance system that uses AIs through security cameras scattered along the tracks.
The cameras identify the number of vehicles in real time and transmit the information to a control center, where algorithms calculate traffic density. From this data, the system changes the rate of the traffic lights.
But that requires data. A lot of data. Fortunately, there are many. Traffic monitoring systems, road infrastructure, cars and motorists via cell phones are a wealth of information.
Millions of cameras are scattered along our roads while moving vehicles induce small electrical currents in metal devices hidden under the asphalt, thus providing more information on traffic conditions . Drivers can send instant updates on delays through the navigation software that they use on their smartphones and cars.
Some of these surveillance technologies – such as the induction loop – have existed since the 1960s, while others, such as cameras capable of tracking traffic and reading boards, are more recent. The challenge is to optimize all this information and make it useful.
"Since Isaac Newton, we are trying to influence the world by building mathematical models," says Gabor Orosz, an badociate professor of engineering at the University of Michigan in the United States. "If we have the data, we can offer solutions, and the same goes for the traffic."
Today, initiatives are underway to harness the AI 's ability to understand vast amounts of information and to change the way we move in our cities.
Recently, researchers from the Alan Turing Institute in London and the Toyota Mobility Foundation in Japan have launched a joint project to improve traffic management systems through the use of technology. ;artificial intelligence.
Scientists are simulating more and more complex scenarios, helping algorithms learn to predict changes in traffic. Although the system is still in the testing phase, it is expected that it can be used quickly in the real world.
"Through deep machine learning, we can improve predictability," says William Chernicoff, head of research and innovation at the Toyota Mobility Foundation. "Urban mobility managers can then make faster and more efficient decisions regarding the time of signaling, the suggested routes for system users and the allocation of capabilities."
In Pittsburgh, USA, researchers are already collaborating with city administrators on a similar initiative launched in the city since 2012. A traffic control system developed by researchers at the Institute of Robotics from Carnegie Mellon University has been deployed to town by a company called Rapid Flow Tech.
His technology, Surtrac, is used at 50 intersections in Pittsburgh and, since its launch, has reduced latency by nearly 40%, according to the company. The company also claims that travel times in the city have decreased by 25%. Emissions of polluting gases have also decreased by up to 20%.
The system uses video cameras to automatically detect the number of road users, including pedestrians and types of vehicles at a junction. The software, powered by artificial intelligence, processes this information second by second to find the best way to ensure smooth traffic by resynchronizing traffic lights, depending on what is ideal for maintaining traffic moving. Decisions can be taken autonomously or shared with other crosses to help them understand what is going on.
While vehicles are increasingly connected to using cell phones and other wireless technologies, they also allow these systems to power up with more information. According to Griffin Schultz, CEO of Rapid Flow, connected vehicles will be able to share information about their speed, their driver behavior and even the potential defects of the surrounding infrastructure in the future.
"At the moment we are learning, but it will be much more common in the future," he predicts. "It's not just cars, but this technology will help all types of road users in a multimodal transport company."
Elsewhere in the world, smart infrastructure is helping transportation networks become more connected. Siemens Mobility operates in cities and counties around the world to identify travel patterns to enhance everyone's experience on the street.
"There are real projects around the world and their applications are constantly expanding," says Markus Schlitt, director of Intelligent Traffic Systems at the company.
"In the cities of the future, the traffic will be so complex that, without artificial intelligence, we would be stuck in a traffic jam," Schlitt said. "By using the data, we can identify patterns that would not be visible without AI." Through this continuous learning, we can constantly update traffic patterns and thus the flow of vehicles, reducing waiting times and emissions. "
In Hagen, Germany, artificial intelligence is used to optimize the control of traffic lights and reduce the waiting time at an intersection. The simulations indicate that the system can reduce waiting times at traffic lights up to 47% compared to preprogrammed times.
But it's not just drivers who benefit from the use of AI. Siemens Mobility operates a fleet of 1,400 e-bikes in Lisbon, using machine learning to badyze various data sources, such as weather, to forecast future demand in each of the 140 rental stations.
In this way, the company can guarantee not only the availability of bicycles, but also free spaces for the return of these. This data is used with the latest traffic information to facilitate the replacement of Bibi sockets in rental stations and to define the ideal launcher for service technicians.
"This not only reduces operating costs, but also improves the end user experience," Schlitt said. "So, if you have to move to Lisbon, you can be sure that there will always be an electric bike available in the train stations."
As brilliant as technology is, we can not rely on it alone. Mischa Dohler, from the IT department of King & # 39; s College London and co-founder of traffic monitoring technology company Worldsensing, tested artificial intelligence and machine learning in Bogotá, Colombia.
He states that technology has already yielded excellent results, including the use of signs and road signs to redirect traffic in case of an accident, reduce congestion and time spent by drivers looking for parking spaces.
But he says that if AI helps make this type of adaptive transport network possible, the human element remains important. He calls this "explainable planning of the impact badysis". Basically, this allows humans to make decisions at the same time as the AI or to adapt in case of a problem. Although they are intellectually and technically capable, the drivers themselves must be open to the idea that their traffic systems are controlled by computers.
"When cities rely on algorithms to implement policies, IT policies eclipse this policy," says Jed Carter, editor of the online magazine Moving World. "It becomes even more difficult for citizens to understand why they have been redirected, photographed or stored when the reasons for such actions are related to computer code."
But implementing smart technologies on the road is not just about avoiding traffic jams. Mark Nicholson of Vivacity Labs, who coordinated a British government-backed project and deploying smart traffic lights in Milton Keynes, England, said the latest technologies had many other benefits.
Cost is one of them. As technology becomes more and more important in traffic management, less human intervention is needed in basic tasks such as tracking traffic surveillance cameras.
Automated systems can also differentiate more and more a large number of road users. Thus, depending on the circumstances, cyclists, buses or emergency vehicles can be prioritized.
By keeping the traffic flowing, they also reduce the energy consumption of the vehicles at standstill or standby, thus improving the quality of the air and benefiting the environment. Finally, they help drivers find parking spaces faster, which promotes their productivity.
"With automation, we can focus on the essentials," Nicholson said. "For example, it improves the air quality around a school, avoids the pbadage of trucks or other heavy vehicles, plans where we will build a new deviation or poses new practical problems, on the road. how we will redirect traffic after an accident. "
For Nicholson, the main benefit of technology is to enable humans to maximize their potential. But how He saves us from wasting time on tedious traffic control activities, he says. So, with the help of AI, we can focus on what we do best, as in situations that require adaptive thinking and creative solutions.
The results of the Milton Keynes project are promising. City-wide smart cameras capable of identifying and clbadifying users and vehicles have provided extremely accurate data, providing urban planners and urban authorities with information on rush hour the most frequented and the availability of parking spaces.
Vivacity has installed 411 of its intelligent signaling cameras at key Milton Keynes junctions. In addition to counting and sorting users, sensors can measure the time it takes for vehicles to move between intersections and provide real-time photos for future planning.
The company sends the data to a machine learning model that records typical daily patterns and combines it with the way traffic reacts to transient changes in the road network. The system evolves and adapts over time, improving its predictive power and minimizing the level of human intervention required. It also provides historical and real-time data, as well as daytime traffic forecasts.
As a result, he was able to predict traffic conditions 15 minutes in advance with 89%.
"The system not only helps citizens check real-time parking availability, but also lays the groundwork for future Milton Keynes-connected, self-contained transportation technologies," Nicholson said.
What seems clear is that giving the green light to AI will allow us to keep moving forward.
"It's only the beginning – we do not take full advantage of the capabilities and benefits of AI," adds Markus Schlitt of Seimens Mobility.
Source link
