Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing
This work addresses the critical need for more efficient safety validation methods for autonomous vehicles, though it is incremental by building on existing statistical models.
The paper tackles the problem of assessing autonomous vehicle safety by showing that road testing alone is insufficient for predicting low accident rates, and demonstrates that Software Reliability Growth Models, when combined with accuracy assessment and recalibration, can improve forecast reliability using Waymo's 51-month disengagement data.
There is an urgent societal need to assess whether autonomous vehicles (AVs) are safe enough. From published quantitative safety and reliability assessments of AVs, we know that, given the goal of predicting very low rates of accidents, road testing alone requires infeasible numbers of miles to be driven. However, previous analyses do not consider any knowledge prior to road testing - knowledge which could bring substantial advantages if the AV design allows strong expectations of safety before road testing. We present the advantages of a new variant of Conservative Bayesian Inference (CBI), which uses prior knowledge while avoiding optimistic biases. We then study the trend of disengagements (take-overs by human drivers) by applying Software Reliability Growth Models (SRGMs) to data from Waymo's public road testing over 51 months, in view of the practice of software updates during this testing. Our approach is to not trust any specific SRGM, but to assess forecast accuracy and then improve forecasts. We show that, coupled with accuracy assessment and recalibration techniques, SRGMs could be a valuable test planning aid.