With geo-aware brains and no driver, this modified Audi TT-S experimental vehicle is built to drift around corners and then regain control of itself. It could be the forerunner of future handling systems that could allow drivers to avoid accidents.
"We're trying to understand how to control a car at the limits of its performance," says Ganymed Stanek, a senior engineer at VW's Electronics Research Lab (ERL) in Palo Alto, which worked with Stanford University on the car. The vehicle was developed by the same team that produced Junior, an autonomous VW Passat that was awarded second-place in DARPA's robot-car race in 2007.
The new autonomous TT-S is markedly different from Junior, however. Junior was environmentally-aware; it had cameras that could see objects and road features, and it paired that data with GPS data. All that processing required two on-board Linux computers running quad-core Pentium chips and programmed in C and C++.
The new TT-S, unofficially dubbed "Shelly," uses a different system. It has no cameras, only GPS, and a smaller, less powerful computing box running Sun's Java Real Time System running on Solaris. Why? Despite Junior's speedy processors, it still takes the car between 20-50 milliseconds to react to inputs from its sensory equipment. Because the TT-S "Shelly" is traveling at much higher speeds—the team has pushed it over 140 mph—even 20 milliseconds is too much of a delay. Most of its drifts are performed around 40 mph.
"For controlling the wheels at the limits of friction in the Audi TT-S, we require reaction times of a few milliseconds," says Stanek. So in most scenarios, the TT-S can adjust course in just a few microseconds, he says. The utlimate test of the TT-S will come when the team runs the vehicle over the course over the Pike's Peak hill climb race next year.