To top
Share on FacebookTweet about this on TwitterPin on PinterestShare on Google+Share on LinkedInEmail this to someone

Google has been experimenting with self-driving cars for several years now, but a team of researchers may have thrown all doubts that critics have had about self-driving cars out the window. Raul Rojas, professor of mathematics, statistics and computer science at the University of Nevada, Reno, “drove” a 2010 Volkswagen Passat (nicknamed “Autonomos,” derived from the Greek “self-rule”) from Nogales, Arizona to Mexico City – a distance of nearly 1,500 miles.

Rojas has been focusing on intelligent systems since 1986; he also led a team that created soccer robots that won the World Championship in 2004 and 2005. The car was modified with seven laser scanners, nine video cameras, seven radars and a GPS unit that helped Rojas and his team on the journey. While the route was already pre-programmed into the GPS, the car was able to brake and change lanes automatically without the need for human interaction with the vehicle.

Rojas and his team drove 4,000 miles in Nevada to test for glitches, and when the car passed the test, they went to Nogales to start the trip. With many companies seeking to get into the largely untapped self-driving car market, this could be a boon for car companies such as Toyota and Tesla. Toyota even suggested that these cars could be on the road as soon as 2020. Tech giants such as Apple and Google have also shown interest, but it is still unclear whether the tech giants will directly manufacture cars or provide the software for car companies to manufacture them.

Rojas and his team did encounter some bumps in the road including fresh pavement without lane markings, which Rojas described as a “significant issue,” but the self-driving car did manage to cover up to 300 miles a day, arriving in Mexico City a week later. The car went through Mexico’s Federal Highway 15, which also crosses another major Mexican city: Guadalajara. A support vehicle followed Autonomos, and the environmental variables were carefully controlled, such as the alertness of the drivers. “We drove each day as long as the drivers could stay alert; we never push through long days,” Rojas said. “We have to watch the road, the controls and the car’s performance.”

While the trip was successful, Rojas also said that self-driving cars weren’t ready to go fully public yet. “Autonomous cars require special maps in order to operate safely, maps in which the number of lanes, the structure of the highway markings and also the position of exits, intersections and possibly of traffic lights are marked,” he said. While these signs are present in most developed countries, developing countries, where the appetite for new tech is increasing the most, must catch up if they want to harness self-driving cars.

He also mentioned that those who do want to manufacture self-driving cars would also have to develop their own hardware and software for these cars to remain completely autonomous, which would mean either further collaboration between tech companies and car companies, or car companies hiring their own in-house IT staff. “Such maps are not commercially available for all countries, and therefore every autonomous car project still has to produce its own maps.”

Rojas also stated that there are factors to consider beyond just the car itself. “One important aspect to be considered is predicting the behavior of other drivers and pedestrians,” he said. One of the biggest challenges, according to Rojas, is the ability to drive in big cities, especially in cities where traffic laws are rarely enforced. “This is especially relevant in cities. If a human can drive with two eyes, I am sure that we will be able to drive autonomously with a computer the size of a notebook and just a handful of video cameras in just a few more years.”

Leave a Reply

We are on Instagram