"Long before it's in the papers"
January 28, 2015


Competition drives robo-car technology forward

Nov. 5, 2007
Courtesy Carnegie-Mellon University
and World Science staff

A 45-member team from Car­ne­gie Mel­lon Un­ivers­ity in Pitts­burgh won a $2 mil­lion cash prize in a go­vern­ment-spon­sored com­pe­ti­tion for self-driv­ing cars on Cal­i­for­nia road­ways.

The driverless vehicle "Boss." (Courtesy Carnegie-Mellon University)

The un­ivers­ity’s 45-member team cre­at­ed a mod­i­fied 2007 Chevy Ta­hoe, an SUV, to com­pete against 10 oth­er driv­er­less ve­hi­cles in the 55-mile (89-km) race. 

The “robo­tized” ve­hi­cle chugged along at an av­er­age of 14 miles (23 km) per hour while fol­low­ing Cal­i­for­nia traf­fic laws to beat the com­pe­ti­tion, ac­cord­ing to Car­ne­gie-Mel­lon an­nounce­ment.

The race last week­end in Vic­torville, Calif., or­gan­ized by the U.S. De­fense Ad­vanced Re­search Pro­jects Agen­cy, was dubbed the DAR­PA Ur­ban Chal­lenge.

Car­ne­gie-Mel­lon’s “robo­tized” ve­hi­cle, named Boss, ope­rated safely and sta­bly, as did many of the com­peti­tors, said DARPA Di­rec­tor Tony Teth­er. Thus Boss won mostly based on speed, com­plet­ing the course about 20 min­utes ahead of the second-place fin­ish­er, from Stan­ford Un­ivers­ity in Cal­i­for­nia. 

“Robots some­times stun the world, in­spire a lot of peo­ple and change the be­lief of what is pos­si­ble,” said Wil­liam “Red” Whit­ta­ker, a Car­ne­gie Mel­lon robotics pro­fes­sor and team lead­er of the un­ivers­ity’s Tar­tan Rac­ing team. “We’ve seen that here and once the pe­rception of what’s pos­si­ble changes it nev­er goes back. This is a phe­nom­e­nal thing for robotics.”

“I watched these things driv­ing and I for­got af­ter awhile that there was no­body in there,” he added. 

DAR­PA of­fic­ials said the race—whose robo­tic par­ti­ci­pants also shared the road with hu­man driv­ers—show­cased what has been a con­ti­nuing im­prove­ment in the dri­ver­less tech­no­logy since the agen­cy’s first such event. That was held in 2004 in the Ne­vada de­sert. DARPA is pro­mot­ing the tech­nol­o­gy in hopes of mil­i­tary ap­plica­t­ions. Au­ton­o­mous driv­ing will save lives on the bat­tle­field by re­mov­ing sol­diers from supply con­voys and oth­er ve­hi­cles in har­m’s way, Teth­er said.

“Ev­ery­thing that I saw Boss do looked great,” said Chris Urm­son, the team’s di­rec­tor of tech­nol­o­gy. “It was smooth. It was fast. It in­ter­acted with oth­er traf­fic well. It did what it was sup­posed to do.”

As the second-place fin­ish­er, Stan­ford re­ceived $1 mil­lion. Vir­gin­ia Tech’s Vic­tor Tan­go team fin­ished third and re­ceived $500,000. Robots en­tered by teams from the Un­ivers­ity of Penn­syl­va­nia, Cor­nell and MIT al­so fin­ished the race.

Tar­tan Rac­ing in­cludes Car­ne­gie Mel­lon fac­ul­ty, staff and stu­dents in ro­bot­ics and en­gi­neer­ing. It re­ceived ma­jor sup­port from Gen­er­al Mo­tors, Cat­er­pil­lar and Con­ti­nen­tal AG. Strength­en­ing the team were en­gi­neers from GM, Cat­er­pil­lar, Con­ti­nen­tal and In­tel who were em­bed­ded with the team.

* * *

Send us a comment on this story, or send it to a friend


Sign up for

On Home Page         


  • St­ar found to have lit­tle plan­ets over twice as old as our own

  • “Kind­ness curricu­lum” may bo­ost suc­cess in pre­schoolers


  • Smart­er mice with a “hum­anized” gene?

  • Was black­mail essen­tial for marr­iage to evolve?

  • Plu­to has even cold­er “twin” of sim­ilar size, studies find

  • Could simple an­ger have taught people to coop­erate?


  • F­rog said to de­scribe its home through song

  • Even r­ats will lend a help­ing paw: study

  • D­rug may undo aging-assoc­iated brain changes in ani­mals

A 45-member team from Carnegie Mellon University in Pennsylvania won a $2 million cash prize in a government-sponsored competition for self-driving cars on public California roadways. The university’s 45-member team created a modified 2007 Chevy Tahoe, an SUV, to compete against 10 other driverless vehicles in the 55-mile (89-km) race. The “robotized” vehicle chugged along at an average of 14 miles (23 km) per hour while following California traffic laws to beat the competition, according to Carnegie-Mellon announcement. The race last weekend in Victorville, Calif., organized by the U.S. Defense Advanced Research Projects Agency, was dubbed the DARPA Urban Challenge. Carnegie-Mellon’s “robotized” vehicle, named boss, operated safely and stably, as did many of the competitors, said DARPA Director Tony Tether. Thus Boss won mostly based on speed, completing the course about 20 minutes ahead of the second-place finisher, from Stanford University in California. “Robots sometimes stun the world, inspire a lot of people and change the belief of what is possible,” said William “Red” Whittaker, a Carnegie Mellon robotics professor and team leader of the university’s Tartan Racing team. “We’ve seen that here and once the perception of what’s possible changes it never goes back. This is a phenomenal thing for robotics.” Showing the world that autonomous driving technologies are robust and will ultimately make driving safer and more enjoyable has been a major goal of the 45-member Tartan Racing team, he added. “This is really a fantastic accomplishment,” Tether said. “I watched these things driving and I forgot after awhile that there was nobody in there.” DARPA is promoting the technology in hopes of military applications. Autonomous driving technology will save lives on the battlefield by removing soldiers from supply convoys and other vehicles in harm’s way, Tether said. “Everything that I saw Boss do looked great,” said Chris Urmson, the team’s director of technology. “It was smooth. It was fast. It interacted with other traffic well. It did what it was supposed to do.” As the second-place finisher, Stanford received $1 million. Virginia Tech’s Victor Tango team finished third and received $500,000. Robots entered by teams from the University of Pennsylvania, Cornell and MIT also finished the race. Tartan Racing includes Carnegie Mellon faculty, staff and students from the School of Computer Science’s Robotics Institute, as well as Carnegie Mellon’s College of Engineering. It received major support from General Motors, Caterpillar and Continental AG. Strengthening the team were engineers from GM, Caterpillar, Continental and Intel who were embedded with the team.