5G and Edge AI: tackling traffic management
The way we move may have transformed over time, but the way traffic is handled has not changed. The INRIX Global Traffic Scorecard dashboard indicates that the 20 most congested cities in the world lost between 164 and 210 hours of congestion per capita through 2018. The exponential increase of vehicles in urban cities is the main reason for the congestion. Better public transport is the solution, but alongside that we also need to look at how improving the efficiency of traffic management can improve the scene. Traffic authorities have tried initiatives to turn reactive management into proactive traffic management, but have been limited by network speeds and edge processing capabilities. 5G and AI offer a huge opportunity here for traffic management.
When 5G hits the road
With denser and more complex road networks, newer technologies and bigger data, 5G will provide greater visibility and control over traffic. This, in turn, will help clear transit networks faster, further reduce blockages, eliminate cascading effects, and make roads safer for all riders. With 5G, edge devices will become even more powerful to transmit and process larger amounts of data through AI analytics servers, which can only benefit traffic management.
Said to be 70 times faster than 4G, it will provide combined visibility into the movement of all road users – people as well as traffic – enabling better overall planning. With a multitude of sensors, cameras and even drones, 5G will transform road networks into a fleet of mini-clouds communicating with each other, including autonomous vehicles. The huge amount of data generated by sensors in autonomous or self-driving vehicles can be easily supported by 5G to enable inter-vehicle and inter-sensor communication.
Crucial information will be collected by the sensors of these vehicles to make decisions and change course, based on recorded observations. Martti, the autonomous vehicle from VTT Technical Research Center in Finland, has been tested to detect icy road conditions in advance as well as inter-vehicle transmission of 3D views.
AI and big data solutions
The power of Artificial Intelligence (AI) and Big Data combined with the supremacy of 5G technology will provide a robust solution combining high reliability and ubiquitous network access. The low latency offered by 5G is key here, with AI models using real-time network information and historical data to detect the possibility of incidents and instantly design optimized response plans to deliver at high speed. Traffic metadata from across the road network can be captured in real time using a combination of traditional and edge-based AI systems. This combination of 5g and AI will hold the answer to traffic management transformation over the next decade. It could also signal the much-needed boost for autonomous vehicles within a collaboratively connected system. Let’s look at two specific AI-based solutions and their effect on vehicle activity.
AI and smart traffic lights
AI-based traffic light controls will have a great impact on vehicle activity, greatly reducing conflicts in vehicle movement and increasing the capacity of the road network. The integrated configuration for efficient traffic management would involve a self-adaptive traffic light system, a perimeter system and a main monitoring system. Video captured using IP cameras is relayed to the edge-based AI system which analyzes the data before sending it for backend monitoring. Pre-trained deep learning models feed processed information back to self-adaptive traffic lights in real time to create traffic flow.
With traffic lights adapting to real-time traffic changes, movement on the road can be controlled by traffic light timing that adjusts to the nearest second. The changing traffic scenario and timing at intersections can be shared through interoperable communication so that all intersections are prepared to optimize incoming traffic flow. A pilot system deployed in Pittsburgh, Pennsylvania, reportedly reduced travel time by 26%, idling time by 41% and emissions by 21%. Interestingly, the adaptive traffic light system also reduced the total number of fatal incidents by 13-36%.
AI for traffic incidents
With incidents being unforeseen and sometimes catastrophic, integrating AI into building an integrative sustainable traffic incident management system with smart traffic signals can transform traffic monitoring. This is where the blended technology confederation comes in. Big data from IP cameras, GPS, cell phone tracking, probe vehicles and loop detectors are fused together to arrive at more accurate inferences than if the huge information were studied independently. AI algorithms then continuously and instantly analyze the merged data to detect any incidents.
Traffic simulators can study archived and real-time data at the time and place of the incident to analyze the impact. AI models predicting the duration of incidents can also indicate specific points needing attention as well as the overall effect on road sub-networks. Additionally, deep learning models can explore the correlation between intensity and overall impact, helping to prioritize the incident and its response. The integration of data analytics helps in testing various traffic scenarios from which an efficient, real-time and automated traffic incident response plan can be drawn.
In Delhi, sensors from more than 7,500 CCTV cameras, timed traffic lights and a thousand LED signs collect real-time data that AI processes into instant insights, which authorities use to improve management traffic. Data collected from smart cameras installed city-wide in Milton Keynes, England is run on a deep learning model to predict traffic conditions 15 minutes in advance with 89% accuracy.
Streamlined traffic management
To meet the promise of 5G, road and transport network management systems must also evolve over time. There will inevitably be more complexity with data coming from a wide variety of sources. The process of all systems working together to be ubiquitous and instantly responsive at the same time will require precision implementation. Amidst technological adaptability, it is important that smart grid decisions are self-sustaining and understandable. This will provide leeway for human decisions and interventions alongside technology when the need arises. Although we may have turned a century since the construction of the world’s first highway, it’s only now that the world revs up its engine for driving.