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

Meyer, Max-Arno; Zouari, Mehdi; Bannenberg, Sebastian; Deppe, Markus; Christiaens, Sébastien; Lee, Sung-Yong; Andert, Jakob · 2024 · Crossref

DOI: 10.1007/s10515-024-00481-6

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the inefficiency and lack of standardization in scenario-based verification and validation for automated driving functions (ADFs). Current test case specifications are often tool-specific, proprietary, and written in natural language, which hinders the exchange, reuse, and automation of tests across different platforms. To resolve this, the authors propose a novel, machine-readable test specification format implemented as an XML schema (TCXSD). This format is designed to be tool-agnostic, compliant with ISO/IEC/IEEE 29119, and capable of integrating logical or concrete scenarios via references to ASAM OpenSCENARIO XML. The goal is to enable seamless automation from specification to execution in both simulation and real-world testing environments. The study develops the TCXSD data structure, which organizes test cases into attributes, global variable declarations, pre- and post-conditions, test procedures, and expected results. The format supports complex, event-based test procedures using nested conditionals and loops, allowing for dynamic interactions between the vehicle under test and its environment. To demonstrate the format’s utility, the authors implemented a cloud-based software-in-the-loop (SIL) workflow using the dSPACE SIMPHERA simulator. A Python-based importer module was developed to parse TCXML files, validate them against the schema, and automatically map the data to the simulator’s proprietary structure via REST APIs. The workflow was tested using a highway ramp-on function, where a logical test case was generated and imported into the cloud environment. The experimental results demonstrate that the TCXSD format successfully enables the automated import and execution of logical test cases in a cloud simulation environment. By decoupling the test specification from specific tools, the format allows for the reuse of scenario data and the integration of intelligent parameter variation methods to explore the parameter space efficiently. The study shows that the combination of the machine-readable format, automated import interfaces, and cloud-based parallel execution creates a highly efficient scenario-based test procedure. The workflow achieved a technology readiness level of 7, indicating its operational viability. The significance of this work lies in providing a standardized, interoperable solution for scenario-based testing in the automotive industry. By establishing a universal format for test specifications, the paper facilitates the automation of the entire testing lifecycle, from requirement traceability to execution and evaluation. This approach reduces manual effort, minimizes errors associated with natural language specifications, and accelerates the verification of ADFs. The proposed format serves as a candidate for future industry standards, addressing the critical need for harmonized test data exchange and supporting the safety assessment of automated driving systems.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• driverless ads

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Applied Guidance: standards test procedures
• Methodological Resource: tool software
• Theoretical Contribution: computational model