Engineers customized and raced two fully autonomous rally cars to test a new technique to keep a driverless vehicle under control as it maneuvers at the edge of its handling limits.
The technique uses advanced algorithms and onboard computing, in concert with installed sensing devices, to increase stability while maintaining performance.
“An autonomous vehicle should be able to handle any condition, not just drive on the highway under normal conditions.”
“An autonomous vehicle should be able to handle any condition, not just drive on the highway under normal conditions,” says Panagiotis Tsiotras, a professor in Georgia Tech’s Daniel Guggenheim School of Aerospace Engineering.
Tsiotras is an expert on the mathematics behind rally-car racing control. “One of our principal goals is to infuse some of the expert techniques of human drivers into the brains of these autonomous vehicles.”
The cars, which are about three feet long and weigh 48 pounds, utilize special electric motors to achieve the right balance between weight and power. The cars carry a motherboard with a quad-core processor, a potent GPU, and a battery.
Each vehicle also has two forward-facing cameras, an inertial measurement unit, and a GPS receiver, along with sophisticated wheel-speed sensors. The power, navigation, and computation equipment is housed in a rugged aluminum enclosure able to withstand violent rollovers.
“Aggressive driving in a robotic vehicle—maneuvering at the edge—is a unique control problem involving a highly complex system,” says project leader Evangelos Theodorou, an assistant professor in aerospace engineering. “However, by merging statistical physics with control theory, and utilizing leading-edge computation, we can create a new perspective, a new framework, for control of autonomous systems.”
Traditional robotic-vehicle techniques use the same control approach whether a vehicle is driving normally or at the edge of roadway adhesion, Tsiotras says. The Georgia Tech team developed the new method—known as model predictive path integral control (MPPI)—to address the non-linear dynamics involved in controlling a vehicle near its friction limits.
An important aspect in the team’s autonomous-control approach centers on the concept of “costs”—key elements of system functionality. Several cost components must be carefully matched to achieve optimal performance.
In the case of the test vehicles, the costs consist of three main areas: the cost for staying on the track, the cost for achieving a desired velocity, and the cost of the control system. A sideslip-angle cost was also added to improve vehicle stability.
The cost approach is important to enabling a robotic vehicle to maximize speed while staying under control, says James Rehg, a professor in the School of Interactive Computing who is collaborating with Theodorou and Tsiotras.
It’s a complex balancing act, Rehg says. For example, when the researchers reduced one cost term to try to prevent vehicle sliding, they found they got increased drifting behavior.
“What we’re talking about here is using the MPPI algorithm to achieve relative entropy minimization—and adjusting costs in the most effective way is a big part of that,” he explains. “To achieve the optimal combination of control and performance in an autonomous vehicle is definitely a non-trivial problem.”
The US Army Research Office sponsored the project. The team recently presented results at the International Conference on Robotics and Automation.
Source: Georgia Tech