Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems
cs.LG
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 50 pages, 43 figures, Technical Report
License: http://creativecommons.org/licenses/by/4.0/
The gist: The conventional testing process quickly fails when applied to ML-based systems such as obstacle detection in vehicles: if an obstacle is not detected in a test, classical bug fixing is impossible
Terminology
Abstract
The conventional testing process quickly fails when applied to ML-based systems such as obstacle detection in vehicles: if an obstacle is not detected in a test, classical bug fixing is impossible and an AI system will always retain shortcomings. Test results can therefore only be interpreted statistically, which in turn requires test sets that are not only complete with respect to the operational design domain (ODD) of the system, but also representative of it. To this end, we introduce probabilistically extended ontologies (PEONs): ontologies describing the ODD, augmented with a probability distribution over the partitioning they induce. Instead of unmaintainable conditional probability tables, only marginal distributions and functionally described dependencies need to be specified; algorithms based on couplings and optimal transport complete this specification to a Bayesian network. From a PEON we derive the sampling of representative test cases, rigorous end-of-test criteria for given quality targets and significance levels, and methods for re-evaluating existing test results and for assessing the balance of training data. We demonstrate the practical modelling of a complex ODD using the example of automatic train operation.
Sources
- Explaining and Harnessing Adversarial Examples
- Feature-Guided Black-Box Safety Testing of Deep Neural Networks
- Towards Dependability Metrics for Neural Networks
- A Stochastic Approach to Classification Error Estimates in Convolutional Neural Networks
- Scenic: A Language for Scenario Specification and Data Generation
- One Ontology to Rule Them All: Corner Case Scenarios for Autonomous Driving
- Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches
- A Comprehensive Review on Ontologies for Scenario-based Testing in the Context of Autonomous Driving
- Certified Control: An Architecture for Verifiable Safety of Autonomous Vehicles
- Grid Saliency for Context Explanations of Semantic Segmentation
- A Survey Of Methods For Explaining Black Box Models
- Machine Learning Testing: Survey, Landscapes and Horizons
- A Comprehensive Survey on Imbalanced Data Learning
- Computational Optimal Transport
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks