Skip to Content

Gentlemen, Start Your Robots

Self-reliant roadsters will race for a hefty Pentagon prize.
December 1, 2002

It may sound like a spectacle worthy of a Mad Max sequel, but it will be a real test of real technology. Sometime in 2004, robots will drive the roughly 400 kilometers from Los Angeles to Las Vegas. Competing in a combined on- and off-road race across deserts and mountains, they’ll be advancing the technology of autonomous vehicles and vying to clinch a $1 million cash prize.

Robotic-vehicle contests aren’t new, but this one, cooked up by the U.S. Defense Advanced Research Projects Agency (DARPA), could be the granddaddy of them all. That’s because the route is so long and covers such a variety of terrain, and especially because humans won’t be allowed to help via remote control. (They may, however, follow closely behind for safety.) Until now, contests among autonomous vehicles have been confined to small, closed courses.

The race was designed to inspire solutions to vexing problems that face autonomous vehicles, which the armed forces would like to add to their arsenals. For one thing, the robot racers will be challenged to avoid falling into the ruts, holes, and ditches that even today’s most sophisticated radar and vision systems have difficulty detecting.

One answer, says Ronald C. Arkin, director of the Mobile Robot Laboratory at the Georgia Institute of Technology, could be advanced sensing technologies that extrapolate hidden depressions from visible terrain or ripples in vegetation. Robot contestants will need vision systems that work in darkness, scorching sunlight, and storms, as well as locomotion systems that can speed through different landscapes. “Think of all the movies about road trips,” says Arkin. “All sorts of weird things can happen.”

Entrants could include university, corporate, and government lab teams-or even garage tinkerers, says Anthony J. Tether, DARPA’s director. Many of the contest’s details, such as the exact route and whether repairs will be allowed, have yet to be decided. But it’s clear, says Tether, that the race will be “technically rewarding for the future of autonomous military ground vehicles.”

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.