One of the major issues facing the automated driving system (ADS)-equipped vehicle (AV) industry is how to evaluate the performance of an AV as it navigates a given scenario. The development and validation of a sound, consistent, and transparent dynamic driving task (DDT) assessment (DA) methodology is a key component of the safety case framework (SCF) of the Automated Vehicle – Test and Evaluation Process (AV-TEP) Mission, a collaboration between Science Foundation Arizona and Arizona State University.
The DA methodology was presented in earlier work and includes the DA metrics from the recently published SAE J3237 Recommended Practice. This work extends and implements the methodology with an AV developed by OEM May Mobility in four diverse, real-world scenarios: (1) an oncoming vehicle entering the AV’s lane, (2) vulnerable road user (VRU) crossing in front of the AV’s path, (3) a vehicle executing a three-point turn encroaches into the AV’s path, and (4) the AV exhibiting aggressive acceleration through an intersection.
The assessment of each scenario navigation by the May Mobility AV is provided by two versions of the DA Score: (1) a simple, single grade that incorporates the applicable DA metrics violations and severity of the violations, (2) the DA Score modified by weighting factors of the scenario complexity and relevance to the AV’s ODD, along with the test method fidelity.
The objective of the work is to demonstrate the DA methodology in an actual OEM AV application in a variety of scenarios. The aggregation of DA Scores (unweighted and weighted) is a key input to the AV-TEP SCF that provides safety assurance of the AV under development.