Teaching machines to direct traffic through deep reinforcement learning

#artificialintelligence

As your car slowly creeps in line behind countless others stuck at a stop light, you think to yourself, "Why aren't these lights changing faster?" Traffic control scientists have long tried to solve this signaling problem. Unfortunately, the complexity of traffic situations makes the job extremely hard. A recent study suggests that machines can learn how to plan traffic signals just right to reduce wait times and make traffic queues shorter. Automating traffic control is notoriously tricky because it involves two challenging tasks: modeling traffic flow and then optimizing it.


Teaching Machines to Direct Traffic through Deep Reinforcement Learning

#artificialintelligence

The dreaded time of day when traffic conditions seem bent on making you late. As your car slowly creeps in line behind countless others stuck at a stop light, you think to yourself, "Why aren't these lights changing faster?" Traffic control scientists have long tried to solve this signaling problem. Unfortunately, the complexity of traffic situations has made the job extremely hard. A recent study suggests that machines can learn how to plan traffic signals just right to reduce wait times and make traffic queues shorter.


Worst traffic spot in US found on I-95 in northern Virginia

FOX News

That spot is the stretch of southbound Interstate 95 from the Fairfax County Parkway to Fredericksburg. The study published Wednesday by Seattle-based traffic data firm Inrix found the average traffic jam on that stretch lasted 33 minutes and covered six miles. Inrix counted 1,394 traffic jams there during the two-month period it conducted the study in March and April. While I-95 represented the single worst traffic spot, Inrix found that overall the D.C. area ranks third to New York and Los Angeles in terms of overall traffic congestion. The study analyzed more than 100,000 hotspots in 25 of the nation's most traffic-congested cities.


Study: Second Bridge Needed to Ease Traffic Congestion

U.S. News

The proposal from the Brent Spence Strategic Corridor Study recommends using the Brent Spence Bridge to carry northbound Interstate 71 traffic and northbound local traffic and using a new double-deck six-lane bridge to carry northbound I-75 traffic as well as southbound I-71, I-75 and local traffic.


Scientists investigate using artificial intelligence for next-generation traffic control

AITopics Original Links

The development of artificial intelligence-based approaches to junction control is one of many new and promising technologies that can make better use of existing urban and road capacity, while reducing the environmental impacts of road traffic. The research carried out by the University of Southampton team has used computer games and simulations to investigate what makes good traffic control. This work has shown that – given the right conditions – humans are excellent at controlling the traffic and can perform significantly better than the existing urban traffic control computers in use today. This was tested for the BBC's'One Show' programme, where presenter Marty Jopson controlled a'real traffic light junction at the InnovITS proving ground using a laptop, while 30 volunteer drivers tried to negotiate the junction. Dr Simon Box of the University of Southampton Transportation Research Group adds: "The demonstration carried out at innovITS Advance indicates that the human brain, carefully employed, can be an extremely effective traffic control computer.