Machine-readable specification and intelligent cloud-based execution of logical test cases for automated driving functions

Abstract

The scenario-based verification and validation of highly automated driving functions requires extensive testing using a mix of interconnected test methods with varying degrees of virtualization, ranging from faster-than-real-time scenario exploration in software-in-the-loop simulations to in-vehicle testing. The efficiency of scenario-based test procedures is continuously improving, especially in the simulation domain with the introduction of parallel execution in the cloud, parameter variation algorithms and established standards for driving scenario specification. In contrast, current test case specifications are very tool- and project-specific and often not machine-readable, hindering the exchange, reuse and automation of scenario-based tests across all test platforms. This paper presents a novel machine-readable test specification format for scenario-based testing implemented as an XML schema. Its data structure incorporates logical or concrete scenarios within preconditions, inputs and pass criteria for automated driving functions following established test standards such as ISO/IEC/IEEE 29119. The format enables a tool-agnostic specification, reuse and exchange of scenario-based tests for simulation-based and in-vehicle testing. A cloud-simulation workflow has been developed that exploits the automation potential offered by the format. By means of testing a highway ramp-on function, a logical test case is generated and automatically imported into the simulator. For efficiently exploring the parameter space of the logical test case, a novel parameter variation method is applied. The combination of a dedicated test case format, intelligent scenario exploration methods and a state-of-the-art cloud simulation platform results in a highly efficient scenario-based test procedure.