The art of driving on the highway… driverless car version

If self-driving vehicles are ever to be popular enough, it is necessary to know if they can handle complex road situations, such as driving on a busy highway. In this sense, researchers at North Carolina State University claim to have developed a technique for unmanned cars to perform calculations faster, which would improve circulation and reduce risk.

“Currently, programs designed to help self-driving vehicles handle lane changes are based on the idea of ​​making problems simple enough for the computer to solve quickly so that the vehicle is able to operate in real time,” explains Ali Hajbabaie, one of the authors of the study. “However, oversimplifying the problem can actually create new obstacles, as real-world scenarios are rarely straightforward.”

“Our approach allows us to tackle a wide range of problems in the ‘real’ world. Instead of focusing on simplifying obstacles, we designed a cooperative algorithm. This approach essentially divides a complex problem into several simple subproblems and sends these to different processors to be processed separately. This process, called parallelization, significantly improves efficiency. »

So far, the researchers have only tested their approach in simulations where subproblems are shared between different cores within the same computer system. But if self-driving vehicles come to use this approach on the road, the cars will network with each other and share these computing subproblems, they say.

To assess the viability of their solution, the researchers sought to confirm two aspects: first, that their technique actually allows autonomous vehicles to solve lane-changing problems in a congested area in real time, and second, to check whether their new ” cooperative” model had an impact on traffic and road safety compared to an existing model that allows navigation of autonomous vehicles.

In terms of computational time, the specialists found that their approach allowed unmanned vehicles to operate through complex integration scenarios on busy roads, all when the level of congestion was “moderate” or still “high”. However, efficiency was reduced when it came to “particularly high” congestion.

When it came to improving safety and calming traffic, however, the new method worked particularly well, the researchers said. Under certain scenarios, especially when congestion was less, both approaches were relatively equally effective. But in most cases, the new approach has proven to be significantly more useful than previous methods. Furthermore, the new technique did not entail any time when the vehicles had to come to a complete stop when they were in “near-accident conditions”.

The results of the second model include several scenarios where thousands of stops and near misses were recorded.

“In terms of theoretical testing, we are very pleased to see how well this technique worked,” says Hajbabaie. “There is still room for improvement, but it’s a good start.”

“The good news is that we are developing these tools and tackling these issues now, so we will be in a good position to ensure that safe autonomous driving systems become more widespread.”

Don’t miss any of our content

Encourage Octopus.ca

Leave a Comment