“Self-driving cars with artificial intelligence pose a risk of accidents between sunrise and sunset”

Which is safer: self-driving cars controlled by artificial intelligence (AI) or cars driven by humans? Contrary to the common belief that self-driving cars are safer, recent research suggests that cars driven by humans are safer under certain conditions. With current technology, the safety comparison between AI and human drivers ends in a “tie.”

On Wednesday, Professor Muhammad Abdel-Atty’s team at the University of Central Florida announced results that while self-driving cars are generally safer in normal driving environments, human drivers outperform AI in dark conditions such as at dawn or dusk. These results were published in the journal Nature Communications.

The research team analyzed crash data from 2,100 self-driving cars and 35,000 human-driven cars. Their study shows that self-driving cars are safer in typical driving situations such as clear weather and a consistent lane. Even in rainy weather, the probability of an accident in self-driving cars is only one-third as high as in human-driven cars.

However, the risk of crashes for self-driving cars in dark environments such as dawn or dusk was 5.25 times higher than for human-driven cars. The research team attributed this to the slower response of the autonomous driving sensors and cameras to changes in light. For example, long shadows at dusk can confuse the sensors and make it difficult to detect objects or hazards.

In addition, self-driving cars are 1.98 times more likely to be involved in accidents when turning at intersections. This is due to the limited detection range of autonomous driving sensors, which limits their ability to detect general road conditions. The reliance on pre-programmed algorithms also makes it difficult for self-driving cars to effectively handle unexpected scenarios.

Teuk-Gyo Koo [email protected]