ATLAS: AI-Native Receiver Test-and-Measurement by Leveraging AI-Guided Search

2025-08-16

AI Summary

AI-native wireless receivers face deployment challenges due to model opacity and insufficient testing—particularly because exhaustive exploration of the high-dimensional channel parameter space is infeasible and real-world training data is scarce, hindering reliable failure-risk assessment. To address this, we propose an AI-guided online testing framework that dynamically generates high-risk channel configurations via gradient-based optimization. Integrated within the Sionna simulation environment, it jointly leverages the DeepRx receiver, differentiable channel modeling, and tensorized computation for end-to-end performance evaluation. By focusing test efforts on parameter combinations most likely to induce failures, the method significantly improves testing efficiency. Experiments demonstrate a 19% reduction in the number of test samples required per fault detection compared to uniform grid search, while exhibiting superior scalability and robustness across multi-parameter scenarios.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Plan Execution and Monitoring
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Industry adoption of Artificial Intelligence (AI)-native wireless receivers, or even modular, Machine Learning (ML)-aided wireless signal processing blocks, has been slow. The main concern is the lack of explainability of these trained ML models and the significant risks posed to network functionalities in case of failures, especially since (i) testing on every exhaustive case is infeasible and (ii) the data used for model training may not be available. This paper proposes ATLAS, an AI-guided approach that generates a battery of tests for pre-trained AI-native receiver models and benchmarks the performance against a classical receiver architecture. Using gradient-based optimization, it avoids spanning the exhaustive set of all environment and channel conditions; instead, it generates the next test in an online manner to further probe specific configurations that offer the highest risk of failure. We implement and validate our approach by adopting the well-known DeepRx AI-native receiver model as well as a classical receiver using differentiable tensors in NVIDIA's Sionna environment. ATLAS uncovers specific combinations of mobility, channel delay spread, and noise, where fully and partially trained variants of AI-native DeepRx perform suboptimally compared to the classical receivers. Our proposed method reduces the number of tests required per failure found by 19% compared to grid search for a 3-parameters input optimization problem, demonstrating greater efficiency. In contrast, the computational cost of the grid-based approach scales exponentially with the number of variables, making it increasingly impractical for high-dimensional problems.

Problem

• Testing AI-native wireless receivers efficiently
• Explaining ML model failures in signal processing
• Reducing test cases for high-dimensional optimization

Innovation

• AI-guided test generation for pre-trained models
• Gradient-based optimization for efficient testing
• Online probing of high-risk failure configurations