N E W S
Stanford autonomous car learns to handle unknown conditions
Stanford researchers have developed a neural network that integrates past driving experiences from driving trials from a skilled amateur driver and physics-based systems. The neural network system outperformed the physics-based system in both high-friction and low-friction scenarios and did particularly well in situations that mixed these two conditions. Link.
E V E N T S
February 26, 2020
Model Fidelity and Trajectory Planning for AVs Driving at the Limit
John Subosits, Ph.D. candidate with the Dynamic Design Lab will present at our first webinar of the year. Subosits' work includes modeling the dynamics of vehicles operating at the limits of friction and trajectory optimization. His research projects include experimental quantification of the advantages of actuator coordination and higher fidelity vehicle models for trajectory planning at the limits, online trajectory replanning, and capturing the effects of road topography on the vehicle’s limits.
Stanford rises to academia's BIg 3 of autonomy
The work of Stanford researchers in autonomous, connected and electric vehicles is highlighted here along with Carnegie Mellon and University of Michigan as one of the three main education centers sparking innovation in the field today. Link.