Self-Driving Car Travels 1,500 Miles Across Mexico Through Highways, Streets And Construction Sites

Paul Rojas, a math professor at the University of Nevada, Reno, along with three German colleagues from self-driving vehicle research company Autonomous GmbH, were able to complete a record-setting autonomous drive of 1,500 miles across Mexico.

The team utilized a retrofitted 2010 Volkswagen Passat for the journey, which started from the United States border at Nogales and ended in Mexico City. The trip was the longest autonomous drive ever made in Mexico.

The onboard computer of the self-driving vehicle contained several TB worth of data on the highways that the car would take on the journey, along with specialized software. Before starting the trip, the team drove for six days around Nevada, Arizona, California and Mexico to gather data from the vehicle's onboard sensors, which includes seven radars, nine video cameras, seven laser scanners and a high-precision GPS unit. After a total of 4,000 miles, the team spent 10 more days to check the collected data if there were any glitches.

Over the 1,500-mile journey, the vehicle passed through both highways and city streets on the Sonoran Desert, Mexico's west coast, and Guadalajara, before reaching its target destination, which is the National Polytechnic University in Mexico City. The team also passed through many construction sites along the way, with Mexican highways having potholes and construction work in about 5 percent of the segments, Rojas said.

The team averaged 250 miles to 300 miles daily, which is the maximum distance that occupants of autonomous vehicles can go that they could stay alert. Every night, the team downloaded the collected driving data and backed up the car's system, to ensure that everything remained in top condition.

The goal of the 1,500-mile journey according to Rojas, is to help in the development of autonomous car systems that do more than just safely drive passengers to specified locations. Rojas is looking to develop a system that can also predict driver and pedestrian behavior.

"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," Rojas said.

A representative of the University of Nevada, Reno revealed that Rojas is looking to begin another journey on the autonomous vehicle in January, which will stretch from Reno to Las Vegas. Afterwards, Rojas will shift his focus on installing self-driving technology on an electric vehicle.

ⓒ 2024 TECHTIMES.com All rights reserved. Do not reproduce without permission.
Join the Discussion
Real Time Analytics