Autonomous driving vehicles are not yet taking off. Although they can be seen in half a dozen cities in the United States and China, their deployment is progressing slowly and any incident represents a brake on their development. However, the automation route brings advantages. 90% of accidents occur due to human error and any technological development that corrects this deficiency can reduce an event rate that last year cost the lives of 1,145 people in Spain. according to the General Directorate of Trafficalready 1.19 million in the world, according to the World Health Organization. A study published today Tuesday in Nature Communications shows that autonomous vehicles are safer and less likely to be involved in accidents than cars driven by humans, except in two circumstances: in turns or in low visibility conditions.
Mohamed Abdel-Aty and Shengxuan Ding, researchers in Transportation, Electrical and Automotive Engineering and Computer Science at the Central Florida University, They reached this conclusion after analyzing data from 2,100 self-driving vehicles and 35,133 cars with humans at the wheel over six years. The most advanced driving systems, according to the study, reduce by between 50% and 20% the possibilities of rear-end, frontal and lateral collisions, as well as leaving the road, which are the cause of nine out of 10 accidents in Spain. .
In all these cases, autonomous driving systems have proven to be more effective than humans. “This is because they are equipped with sensors and software Advanced (programs) that can quickly analyze the surrounding environment and make decisions based on the data received. There are many potential benefits to traffic safety, such as reducing human error, fatigue and distraction,” the authors argue.
However, in low visibility conditions, at dawn or dusk, and in maneuvers that involve turns, humans improve the effectiveness of autonomous systems by two to five times. “These are the areas where autonomous driving technology may need further refinement to match or exceed human driving capabilities,” the authors explain.
In this way, according to the study, technology does not surpass the driver in all circumstances and autonomous cars still have to face challenges to increase their ability to perceive and detect dangers, as well as develop programming for decision-making and mechanisms. fail-safe. The latter still represent 56% of the problems with autonomous driving.
“The development of automated vehicle safety involves advanced detectors, robust algorithms and intelligent design considerations. Key strategies include improving weather and lighting sensors, as well as effective data integration,” the authors explain in a joint email. They refer to technological solutions, such as the combined use of cameras and sensors Lídar (laser), GNSS (satellite navigation) and radar, which improve autonomous capabilities in scenarios with cloudiness, snow, rain and darkness, when a delay in detection of potential dangers and, if properly reacted, can be fatal.
“Sensor fusion,” the researchers add, “allows cross-verification of information, which reduces errors. However, processing this data in real time is challenging and requires advanced computing power, which increases the cost and complexity of these systems.”
“It is a major challenge to generate sufficient information and achieve exhaustive detection of the surrounding environment given the limited ranges of the sensors. Furthermore, some autonomous vehicles are programmed to follow predefined rules and scenarios that may not cover all possible driving situations,” the authors warn.
In this sense, the researchers highlight that human drivers can “predict the movements of pedestrians and act with caution based on their driving experience, while autonomous vehicles may have difficulty recognizing a person’s intentions, which can cause emergency braking or accidents due to lack of understanding of social cues and psychological reasoning.”
To improve this deficiency, Mohamed Abdel-Aty and Shengxuan Ding propose “advanced sensing and perception systems, predictive algorithms, and vehicle-to-everything communication.” This last concept is known as V2X (vehicle ax) and refers to the fact that the devices not only detect the potential danger and initiate a maneuver to save it, but also share it with other cars and road safety systems so that they can anticipate it. “Both automated vehicles and human drivers face challenges with limited visibility, but the former can use advanced technologies and data for better safety assistance,” the authors explain.
Research is advancing to provide vehicles with human-like senses and improve latency (response time). Two works published by Nature they reflect the development of a processor to respond quickly to an event with minimal information and a new system (algorithm) to improve the precision of machine vision with lower latency. In the same field he works Institute of Microelectronics (Imse) in the Andalusian capital, from the Higher Council for Scientific Research (CSIC) and the University of Seville.
“Current driver assistance systems, such as those from MobileEye – which are integrated into more than 140 million cars worldwide – work with standard cameras that take 30 frames per second, that is, one image every 33 milliseconds. Additionally, they require a minimum of three frames to reliably detect a pedestrian or car. This brings the total time to initiate the braking maneuver to 100 milliseconds. Our system allows us to reduce this time to below one millisecond without the need to use a high-speed camera, which would entail an enormous computational cost,” explains Davide Scaramuzza, professor of robotics at the University of Zurich (Switzerland) and event camera investigator.
Bernabé Linares, a research professor at Imse, develops vision systems that resemble human perception and are fundamental for autonomous driving vehicles. “The biological retina does not take images. All information goes through the optic nerve and the brain processes it. In the conventional camera, each pixel is autonomous and, at most, is made to interact with its neighbors to adjust the luminosity. But a digital image at the exit of a tunnel can be all white or black while we, except in very extreme conditions, can see what is inside and outside,” he explains.
Another solution is to apply artificial intelligence to locate the most dangerous places and include that information in autonomous driving systems to condition their maneuvers. It is the line of work of Quynh Nguyen, an epidemiologist and statistician at the University of Maryland School of Public Health who has published a study in British Medical Journal (BMJ) of Injury Prevention. “It is crucial to understand how the physical environment can increase or decrease fatal crashes and which communities are most affected by this,” Nguyen argues.
The American Chemical Society (ACS) proposes the use of paints that make objects more visible to eyes of vehicles. In this sense, they have developed a “highly reflective black tint that could help autonomous cars see dark objects and make mechanical driving safer.”
Researchers at the University of Iowa have investigated the possibility of providing vehicles with an external light signal that indicates to pedestrians when it is safe to cross in front of an autonomous vehicle because it has identified the person and is preparing to stop.
All developments are moving towards full autonomy (Level 5), in which no human intervention will be required. According to researchers at the University of Central Florida, “it may become possible, although it is many years away due to significant challenges. These include the development of advanced algorithms and sensors and the necessary infrastructure upgrades to effectively support automated vehicle technology.”
You can follow The USA Print in Facebook and x or sign up here to receive our weekly newsletter.
