Skip to main content Skip to secondary navigation
Main content start
PhDrift

Jonathan Goh

PhDrift

Electronic stability control systems are standard on cars today, and help to keep a car within the stable handling limits imposed by friction. But what if avoiding an accident requires exceeding these limits? A skilled driver knows how to handle these fast, unstable situations, and even use them to their advantage. Jonathan Goh works on developing control algorithms that allow autonomous cars to robustly understand and drive in these difficult regimes, with the goal of helping to create self-driving cars that can handle anything the world throws at it - no matter how extreme.

The video above shows a recent version of the autonomous controller + trajectory planner in action. In order to deal with the difficult dynamics of drifting, the controller draws on principles from nonlinear control. To improve robustness and performance, it also incorporates elements from adaptive control, namely online parameter estimation. It follows a highly dynamic motion plan that is solved for using constrained nonlinear optimization. Underpining all of this is an appropriate choice of vehicle dynamics model that balances fidelity, simplicity, and intuition. In this example, the trajectory transitions from drifting left at -40 degrees of sideslip to drifting right at +40 degrees of sideslip in about a second. You can see the steering swing from lock to lock in about the same amount of time. These algorithms are tested on MARTY: the world’s first autonomously drifting electric DeLorean. Jonathan has led the development of MARTY from the very beginning. With the help of a great team, this long, strange, wonderful process included hunting for a stock DeLorean; removing the original engine, transmission, and almost-everything-else; fitting a (very) torque-y Renovo Motors electric drivetrain; adding a roll cage; developing a steer-by-wire system; designing and building extensive suspension improvements; what seems like miles of wiring harness and cooling lines; overhauling the interior; and the many, many hours in the garage and machine shop required to realize all of these things. In summary -- a car enthusiast’s dream project come true; a singularly awesome and educational experience that Jonathan is deeply grateful to be having at the DDL. I've chronicled some of the MARTY build process on my personal website. Jonathan hails from Vancouver, BC, and graduated from Princeton University in 2011 with a B.S.E in Mechanical Engineering and Certificates in Engineering Physics, Materials Science, and Visual Arts.

Publications

Towards Automated Vehicle Control Beyond the Stability Limits: Drifting Along a General Path

A Controller for Automated Drifting Along Complex Trajectories

Path-Tracking for Autonomous Vehicles at the Limit of Friction

Simultaneous Stabilization and Tracking of Basic Automobile Drifting Trajectories

Education

B.S.E., Princeton University, 2011
M.S., Stanford University, 2014

Contact