In Europe, more than 25,000 people lose their lives on the road each year, while another 135,000 are seriously injured. The main culprits are speed, driving with alcohol or drugs, lack of seat belt use, distraction and fatigue. Europe is the safest region in the world with 49 deaths per million inhabitants, but as the EU aims to reduce road safety deaths to almost zero by 2050, there is still a lot to do.
The type of automated cars on the road today provide assistance in steering, braking, and acceleration while the driver is still behind the wheel and constantly monitors driving. These are known as level two on the autonomy scale, but vehicles could reach up to level five on the six-level scale in the future, becoming a fully autonomous car.
However, we are not there yet and we have to do it step by step, says Anna Anund from the Swedish National Institute for Road and Transport Research (VTI).
She and her team are developing sensor-based systems as part of the ADAS & ME project to advance to level three, where the driver can rest and is only expected to drive when the car prompts.
These systems would also automatically transfer control between the vehicle and the driver to ensure road safety, especially when the driver is drowsy, stressed, distracted or anxious.
“We want to make sure that we do not return control to drivers who are not fit to drive, and also that we can use the automated functionality to take over if the driver is not fit to drive,” says Anund. “What we would like to achieve is a safe and acceptable transition to avoid serious accidents with people who are seriously injured or even killed.”
Many drivers are in no condition to drive right out of the box – sometimes they are fatigued, sometimes they fall asleep while driving in the middle of the night, sometimes they are worried, stressed or distracted, he explains. The driver’s condition, but also other factors, such as his health, the road on which he is traveling, the weather conditions and the time of day, influence driving and increase the risk of accidents.
According to information published by the European Commission, driver fatigue is an important factor in 10-20% of road accidents. However, because fatigue or drowsiness is difficult to measure, it has received relatively little attention over the years alongside traffic and car accidents , Anund continues.
The ADAS & ME team is specifically looking at seven different driving scenarios on various vehicles , including cars, trucks, buses, and motorcycles.
In a typical scenario, a car needs to take control of emergency braking when a driver on a highway is talking on his cell phone and the vehicle ahead brakes abruptly. In another, a motorcycle is able to detect that a rider has passed out and turns on the hazard lights, slows down, and stops on the side of the road.
The systems use many types of sensors to monitor the condition of drivers, such as eye trackers and sensors to measure heart rate and changes in voice or face images, most of which are located on the dash, the steering wheel or vehicle seat. These sensors exist and it’s a matter of using them together in a driving context, says Anund.
The expert and her team have found that a group of drivers at risk of fatigue are bus drivers, whose divided shifts affect their sleepiness and performance during afternoon trips.
“We know that around 40% of city bus drivers have to struggle to stay awake 2-4 times a month or more often due to high levels of stress,” Anund explains.
This could be alleviated by allowing an automated bus to support the driver, for example by automatically engaging at bus stops, while ensuring that the driver is still in control in unforeseen circumstances. Helping the vehicle and driver work together can lead to safer roads, he says.
Individual
He also points out that each person varies and reacts differently in both normal and impaired states, such as drowsiness, so systems must work on an individual level. To accurately measure heart rate variability, for example, information such as age and gender should be included or the driver’s baseline status should be used as a reference.
“It is important to develop systems that incorporate your individual preferences and behaviors,” Anund argues. “Therefore, we will also focus on individualizing the detection system, but also the HMI (human-computer interaction).”
If the user can design how he wants the communication between the human being and the vehicle to take place, then there is more trust and acceptance, he explains.
Another road safety problem is driving under the influence of alcohol. Around 25% of all road traffic deaths in Europe are alcohol related. As drivers’ blood alcohol concentration increases, so does the accident rate.
One of the recommendations to the EU suggested in a 2014 report by Ecorys, a research and consulting company, is to make alcohol-blocking devices, in which drivers must undergo a breathalyzer test before they can start driving. are required for certain categories of drivers. or vehicles, such as repeat offenders for driving under the influence, professional drivers, or good commercial vehicles.
Previous studies have shown that alcohol ignition interlocks are 40% to 95% more effective in preventing re-offending from drunk driving than traditional measures such as license withdrawal or fines. The risk of recidivism is reduced by between 28% and 65% when these devices are installed and increases again if they are removed.
Julian Sofroniev, CEO of the Bulgarian company Global Technology Biodit, which makes biometric security products, said: “These devices are really important. We could save more than 25,000 lives by preventing car engines from starting when people have high blood alcohol levels. “
Biodit is developing a device that combines alcohol detection with biometric identification to prevent a drunk driver from starting a vehicle, through a project called PREVENT.
The idea is that the ignition lock replaces the start / stop button and is pressed by the driver when entering a vehicle. The device would use a laser to measure different physiological parameters, like heartbeat or sweat, for example, and if they’ve had too much to drink, the car’s ignition just won’t start.
“In these cases, you could call a taxi, but you definitely can’t use your car,” Sofroniev said.
To avoid the risk of someone other than the driver doing the test, the device will also use finger vein recognition, where vein patterns are compared to records, to confirm the identity of the driver. Blood vessel patterns are unique to each individual and are nearly impossible to fake because they lie beneath the surface of the skin.
In its first stage of research, PREVENT confirmed the market need for such a device. Consequently, Sofroniev and his team continue to develop their device and expect it to hit the market by the end of next year.
Original article
This article was originally published in Horizon, the EU Research and Innovation Magazine
