Self-driving cars: near-miss driving data can expedite AV algorithm training

New University of Michigan-led research could boost safety performance of AVs.

The safety performance of AV algorithms greatly increases by using simulation data that better incorporates near-miss incidents with outright failures, according to new research led by University of Michigan Engineering.  Testing this approach in the Mcity Test Facility demonstrated a 90% improvement in a vehicle’s safety performance. Read more about the research on the U-M Transportation Research Institute website.