Can AI improve traffic safety and management?
Each year in the UK, approximately 1,700 people are killed in a road traffic incident (RTI) according to statistics from the Department for Transport (DfT). A further 28,000 or so are seriously injured, while between 100,000 and 120,000 suffer slight injuries.
While every death and serious injury is a tragedy, anyone involved in an RTI today is far more likely to survive – and with minor injuries – than they were in the past. This is largely thanks to massive advances in technology made over the past century.
Airbags and seatbelts are two key innovations that have had the biggest impact in reducing fatalities and injuries.
In its report on seatbelt safety, which brings together research carried out over the past 60 years, the Road Safety Observatory relays research from Sweden in the 1960s that showed using a seatbelt could reduce the risk of injury for drivers by 57% at low speeds and 48% at high speeds. Further research in the USA showed that 60% of unbelted fatalities in RTIs wouldn’t have died had they been wearing a seatbelt.
Airbags have added another layer of safety. Indeed, an estimated 50,457 lives were saved by frontal airbags in the USA between 1987 and 2017, according to the US National Highways and Traffic Safety Administration (NHTSA).
The addition of side-impact airbags has further increased safety, with research from the US National Institutes of Health showing a “statistically significant reduction in injuries or deaths when they have been deployed.
In recent years, however, digital technology has started to play a role in further increasing road traffic safety. From ABS to parking sensors, lane-keeping assistance to advanced emergency braking, there are more electronic systems in place than ever to keep drivers, passengers and other road users safe. Soon, AI could also have a role to play.
What digital traffic safety technology is available now?
Much of the technology available today for traffic safety and management is installed in the vehicle and operates independently of other road users. One very common example, which according to the AA is installed on most new cars, is anti-lock braking systems (ABS).
When a driver brakes hard, especially when traveling at high speeds, the wheels can ‘lock’, which leads to the car skidding and the driver losing control. ABS uses speed sensors, which can determine if a wheel is about to lock up, and a system of valves and pumps that rapidly apply and release the brakes. This means the car will still stop quickly in an emergency situation, but won’t skid out of control.
Building on ABS is Electronic Stability Control (ESC), also known as Electronic Stability Program (ESP), a type of software that’s intended to stop accidents happening in the first place. It uses sensors on the wheels to detect the start of a slide, skid or spin and apply small amounts of braking to help the driver regain control. Vehicles equipped with ESC are 25% less likely to be involved in a fatal accident and the software can reduce crashes involving a skid or roll by up to 59%, according to the AA.
The arrival of the 2000s brought in a lot of new camera and radar-related technology, such as lane departure warning systems, which alert the driver when they are drifting between lanes, as well as autonomous emergency braking and pedestrian detection technology.
Much of this technology removes the opportunity for human error and increases reaction time by having the car react automatically to a situation for itself. For example, if a child ran out in front of a moving car it may be quicker for a dedicated software and sensor array to detect a hazard and apply the brakes than it would be for a human to do the same thing.
Lane-keep assistance systems (ALKS) can even take over steering controls from the driver if they have started to drift into another lane, moving the car safely back into the center of the lane automatically.
Outside of the car, there are other high-tech traffic management systems, such as smart motorways. These use CCTV to monitor highway conditions and adjust speed limits or close lanes as needed in order to keep traffic flowing smoothly and safely.
A 2020 paper for the DfT found a “statistically significant” reduction in personal injury collision rates – incidents in which at least one individual was injured.
The future of accident prevention and traffic management
Artificial Intelligence (AI) is now emerging as a key technology in the future of traffic safety and management. While wide availability and use of fully autonomous vehicles may be a long way off, there are other areas where this is being put to use.
In March 2024, Hull City Council in the UK started a pilot program that used AI to control traffic lights with the aim of reducing traffic congestion during peak hours. The trial was a success with results showing that journey times were reduced by 16.9% during peak morning hours and 8% during peak evening hours, according to Hull CC News.
Sean Higgins, Intelligent Transport System Manager at Hull City Council, said: “As we move forward, we envision a city where AI-driven traffic management becomes an integral part of our urban infrastructure. The lessons learned from this initial trial will inform our decisions as we plan for further implementation of the system across Hull.”
It’s not just car and other motor vehicle users who have benefited either, according to councilor Mark Ieronimo, portfolio holder for transportation, roads, and highways, who said: “By dynamically adjusting traffic signals on Anlaby Road based on real-time data, the Council have significantly reduced congestion and optimized the movement of vehicles, cyclists, and pedestrians in this area.
“The positive impact of using AI technologies to aid traffic management is evident, with these figures showing the effectiveness of implementing these technologies.”
Consultancy Public Works Partners recently highlighted some other examples of cities that have already incorporated AI into their traffic management. Dubai, for example, has used AI to introduce 14 AI-powered smart pedestrian crossing systems. These detect and track both pedestrians and vehicles as they approach a crossing. Drivers can then be alerted to the fact they’re likely to encounter a pedestrian at the crossing before they arrive, allowing them to reduce their speed earlier and be more conscious of the person crossing. The city has also implemented patrol vehicles that use AI to detect any signs of degradation in the road infrastructure.
Public Works Partners also highlighted Helsinki’s use of AI, which has led to a 15-30% improvement in traffic flows in the Finnish capital and increased usage of public transport. Both of these initiatives are building towards the city’s goal of becoming carbon neutral by 2035.
“Integrating AI into transportation systems represents a paradigm shift in addressing the perennial challenges of traffic and road safety. By harnessing AI-driven solutions, such as dynamic traffic signal control and ADAS, cities can optimize traffic flow, improve road safety, and mitigate environmental impacts,” Public Works Partners wrote.
“As evidenced by initiatives in cities like Helsinki, Dubai, and Chino, reducing reliance on personal vehicles is a key step in alleviating the burden of congestion and achieving sustainable urban mobility.”
It concluded: “Embracing AI-powered solutions for transportation planning and prioritizing investments in public transit and alternative mobility solutions can pave the way for transformative changes, leading to more efficient, equitable, and sustainable transportation systems for future generations.”
Modern cars are as mechanically safe as they have ever been, with multiple physical technologies in place to keep vehicle occupants safe in the event of a crash. Now is the time for software to help prevent incidents from happening in the first place. While built-in systems that make use of sensors can help at the individual car level, AI-powered systems that keep traffic flowing smoothly or alert drivers to upcoming hazards can help make travel safer for everyone using the road.
Source link
/cdn.vox-cdn.com/uploads/chorus_asset/file/25734145/nasa_satellite_view.jpg)
