Autonomous vehicles are six times safer than human driven ones, D-RISK study suggests

AVs are twice as likely to detect a collision risk when trained using one-in-a-million accident cases, says 'edge case' project

DRISK profiles

Autonomous vehicles (AV) trained using extreme one-in-a-million accident data and ‘near-miss’ scenarios can achieve a six-fold improvement on the detection of a collision risk posed by other road users compared to vehicles being trained using traditional approaches.

That is a key finding finding of D-RISK, a government backed project part funded by the Centre for Connected and Autonomous Vehicles (CCAV), comprising dRISK.ai, DG Cities, Claytex and Imperial College...