From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

• URL: http://arxiv.org/abs/2604.02198v1
• Date: Thu, 02 Apr 2026 15:52:35 GMT
• Title: From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems
• Abstract summary: Current EASA guidelines mandate complete coverage of the AI/ML constituent's Operational Design Domain (ODD)<n>No standardized engineering method exists to bridge the gap between abstract ODD definitions and verifiable evidence.<n>This paper proposes a method that integrates parameter discretization, constraint-based filtering, and criticality-based dimension reduction into a structured, multi-step ODD coverage verification process.
• Score: 0.7285647284266376
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards. Current EASA guidelines mandate demonstrating complete coverage of the AI/ML constituent's Operational Design Domain (ODD) -- a requirement that demands proof that no critical gaps exist within defined operational boundaries. However, as systems operate within high-dimensional parameter spaces, existing methods struggle to provide the scalability and formal grounding necessary to satisfy the completeness criterion. Currently, no standardized engineering method exists to bridge the gap between abstract ODD definitions and verifiable evidence. This paper addresses this void by proposing a method that integrates parameter discretization, constraint-based filtering, and criticality-based dimension reduction into a structured, multi-step ODD coverage verification process. Grounded in gathered simulation data from prior research on AI-based mid-air collision avoidance research, this work demonstrates a systematic engineering approach to defining and achieving coverage metrics that satisfy EASA's demand for completeness. Ultimately, this method enables the validation of ODD coverage in higher dimensions, advancing a Safety-by-Design approach while complying with EASA's standards.

Related papers

• Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems [0.7285647284266376]
  This work presents a method for representativeness assessment of AI/ML constituent ODDs in the context of aviation safety assurance.<n>As quantitative measures, the chi-squared goodness-of-fit test is examined and found unsuitable for the large data sets arising in this setting.<n>The method is demonstrated using the example of AI-based airborne collision avoidance.
  arXiv  Detail & Related papers  (2026-08-21T08:32:53Z)
• Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents [0.0]
  Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language--leads to critical risks such as scope creep and open-loop failures.<n>This study proposes Agentic Problem Frames (APF), a systematic engineering framework that shifts focus from internal model intelligence to the structured interaction between the agent and its environment.
  arXiv  Detail & Related papers  (2026-02-22T06:32:32Z)
• Defining Operational Conditions for Safety-Critical AI-Based Systems from Data [0.7816377212023298]
  The Operational Design Domain (ODD) is required in many domains for the certification of AI-based systems.<n>This paper presents a novel Safety-by-Design method to a posteriori define the ODD from previously collected data using a multi-dimensional kernel-based representation.<n>This approach is validated through both Monte Carlo methods and a real-world aviation use case for a future safety-critical collision-avoidance system.
  arXiv  Detail & Related papers  (2026-01-29T18:46:02Z)
• Incremental Validation of Automated Driving Functions using Generic Volumes in Micro- Operational Design Domains [0.0]
  This paper introduces a structured method of subdividing the Operational Design Domains (ODDs) into manageable sections and deriving test cases with abstract object representations.<n>Obstacles are represented as generic cubes of varying sizes, providing a simplified yet robust means of evaluating perception performance.<n>Results demonstrate how edge cases in obstacle detection can be systematically explored and how perception quality can be evaluated.
  arXiv  Detail & Related papers  (2025-12-12T07:59:58Z)
• Improving AEBS Validation Through Objective Intervention Classification Leveraging the Prediction Divergence Principle [0.0]
  This work proposes a rule-based classification approach leveraging the Prediction Divergence Principle ( PDP)<n>The findings suggest that combining this approach with human labeling may enhance the transparency and consistency of classification, thereby improving the overall validation process.
  arXiv  Detail & Related papers  (2025-07-10T15:55:05Z)
• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>This Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation [52.83870601473094]
  Embodied agents exhibit immense potential across a multitude of domains.<n>Existing research predominantly concentrates on the security of general large language models.<n>This paper introduces a novel input moderation framework, meticulously designed to safeguard embodied agents.
  arXiv  Detail & Related papers  (2025-04-22T08:34:35Z)
• Data-Driven Distributionally Robust Safety Verification Using Barrier Certificates and Conditional Mean Embeddings [0.24578723416255752]
  We develop scalable formal verification algorithms without shifting the problem to unrealistic assumptions. In a pursuit of developing scalable formal verification algorithms without shifting the problem to unrealistic assumptions, we employ the concept of barrier certificates. We show how to solve the resulting program efficiently using sum-of-squares optimization and a Gaussian process envelope.
  arXiv  Detail & Related papers  (2024-03-15T17:32:02Z)
• Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing [57.49021927832259]
  Deep Neural Networks (DNNs) are powerful tools that have shown extraordinary results in many scenarios. However, their intricate designs and lack of transparency raise safety concerns when applied in real-world applications. Formal Verification (FV) of DNNs has emerged as a valuable solution to provide provable guarantees on the safety aspect.
  arXiv  Detail & Related papers  (2023-12-10T13:51:25Z)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• SMT-Based Safety Verification of Data-Aware Processes under Ontologies (Extended Version) [71.12474112166767]
  We introduce a variant of one of the most investigated models in this spectrum, namely simple artifact systems (SASs) This DL, enjoying suitable model-theoretic properties, allows us to define SASs to which backward reachability can still be applied, leading to decidability in PSPACE of the corresponding safety problems.
  arXiv  Detail & Related papers  (2021-08-27T15:04:11Z)
• Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification [81.32981236437395]
  We present a semi-formal verification approach for decision-making tasks based on interval analysis. Our method obtains comparable results over standard benchmarks with respect to formal verifiers. Our approach allows to efficiently evaluate safety properties for decision-making models in practical applications.
  arXiv  Detail & Related papers  (2020-10-19T11:18:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.