Query as Test: An Intelligent Driving Test and Data Storage Method for Integrated Cockpit-Vehicle-Road Scenarios

2025-06-27

AI Summary

Current data ecosystems for intelligent cockpits, autonomous driving, and smart road networks are highly fragmented; conventional data-stacking-based testing methods suffer from poor coverage of edge cases, inflexibility, and lack of formal expressiveness. Method: This paper proposes a novel “Query-as-Testing” (QaT) paradigm, introducing the Extensible Scenarios Notation (ESN)—a scalable scenario representation framework. ESN uniformly models heterogeneous, multi-source perception data as logical facts and rules using Answer Set Programming (ASP), enabling semantic querying, interpretable logical inference, and on-demand privacy-preserving evaluation. Contribution/Results: QaT supports functional verification and regulatory compliance checking across integrated vehicle–cockpit–road scenarios. It significantly improves edge-case coverage, decision interpretability, and verification efficiency, thereby advancing verification-driven development (VDD) in autonomous systems.

Technology Category

• Knowledge Representation and Reasoning: Qualitative Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

With the deep penetration of Artificial Intelligence (AI) in the transportation sector, intelligent cockpits, autonomous driving, and intelligent road networks are developing at an unprecedented pace. However, the data ecosystems of these three key areas are increasingly fragmented and incompatible. Especially, existing testing methods rely on data stacking, fail to cover all edge cases, and lack flexibility. To address this issue, this paper introduces the concept of "Query as Test" (QaT). This concept shifts the focus from rigid, prescripted test cases to flexible, on-demand logical queries against a unified data representation. Specifically, we identify the need for a fundamental improvement in data storage and representation, leading to our proposal of "Extensible Scenarios Notations" (ESN). ESN is a novel declarative data framework based on Answer Set Programming (ASP), which uniformly represents heterogeneous multimodal data from the cockpit, vehicle, and road as a collection of logical facts and rules. This approach not only achieves deep semantic fusion of data, but also brings three core advantages: (1) supports complex and flexible semantic querying through logical reasoning; (2) provides natural interpretability for decision-making processes; (3) allows for on-demand data abstraction through logical rules, enabling fine-grained privacy protection. We further elaborate on the QaT paradigm, transforming the functional validation and safety compliance checks of autonomous driving systems into logical queries against the ESN database, significantly enhancing the expressiveness and formal rigor of the testing. Finally, we introduce the concept of "Validation-Driven Development" (VDD), which suggests to guide developments by logical validation rather than quantitative testing in the era of Large Language Models, in order to accelerating the iteration and development process.

Problem

• Fragmented and incompatible data ecosystems in intelligent transportation
• Inadequate testing methods lacking flexibility and edge case coverage
• Need for unified data representation and semantic fusion

Innovation

• Query as Test enables flexible logical queries
• Extensible Scenarios Notations unifies multimodal data
• Validation-Driven Development guides with logical validation