Stanford engineers have taught MARTY, their driverless DeLorean, to drift through a kilometer-long autocross course with the agility and precision of a human driver. Completing the course, called “MARTYkhana,” has led to mathematical insights that could improve how autonomous software handles hazardous conditions.
About the Stanford MARTYkhana Project
MARTYkhana – a riff on the “gymkhana” autocross racing format regarded as the master test of a driver’s ability – is hardly a stunt. Conducting research in high-speed, complicated driving conditions like this is a bread-and-butter approach of the Dynamic Design Lab, where mechanical engineer Chris Gerdes and his students steer autonomous cars into challenging driving situations that only the top human drivers can reliably handle. On-board computers measure the car’s response over dozens of runs, and the engineers translate those vehicle dynamics into software that could one day help your car quickly dodge a pedestrian that darts into the road.
Go behind the scenes of MARTYkhana: https://youtu.be/tradNtWvPS4