Kay-Ulrich Scholl

Cornelius Buerkle, Fabian Oboril, Johannes Burr et al.

Our transportation world is rapidly transforming induced by an ever increasing level of autonomy. However, to obtain license of fully automated vehicles for widespread public use, it is necessary to assure safety of the entire system, which is still a challenge. This holds in particular for AI-based perception systems that have to handle a diversity of environmental conditions and road users, and at the same time should robustly detect all safety relevant objects (i.e no detection misses should occur). Yet, limited training and validation data make a proof of fault-free operation hardly achievable, as the perception system might be exposed to new, yet unknown objects or conditions on public roads. Hence, new safety approaches for AI-based perception systems are required. For this reason we propose in this paper a novel hierarchical monitoring approach that is able to validate the object list from a primary perception system, can reliably detect detection misses, and at the same time has a very low false alarm rate.

Cornelius Bürkle, Fabian Oboril, Kay-Ulrich Scholl

The automotive industry is currently expanding digital display options with every new model that comes onto the market. This entails not just an expansion in dimensions, resolution, and customization choices, but also the capability to employ novel display effects like overlays while assembling the content of the display cluster. Unfortunately, this raises the need for appropriate monitoring systems that can detect rendering errors and apply appropriate countermeasures when required. Classical solutions such as Cyclic Redundancy Checks (CRC) will soon be no longer viable as any sort of alpha blending, warping of scaling of content can cause unwanted CRC violations. Therefore, we propose a novel monitoring approach to verify correctness of displayed content using telltales (e.g. warning signs) as example. It uses a learning-based approach to separate "good" telltales, i.e. those that a human driver will understand correctly, and "corrupted" telltales, i.e. those that will not be visible or perceived correctly. As a result, it possesses inherent resilience against individual pixel errors and implicitly supports changing backgrounds, overlay or scaling effects. This is underlined by our experimental study where all "corrupted" test patterns were correctly classified, while no false alarms were triggered.

Sezen Perçin, Xin Su, Qutub Sha Syed et al.

Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge during inference, improving factual consistency and reducing hallucinations. Despite its promise, RAG systems face practical challenges-most notably, a strong dependence on the quality of the input query for accurate retrieval. In this paper, we investigate the sensitivity of different components in the RAG pipeline to various types of query perturbations. Our analysis reveals that the performance of commonly used retrievers can degrade significantly even under minor query variations. We study each module in isolation as well as their combined effect in an end-to-end question answering setting, using both general-domain and domain-specific datasets. Additionally, we propose an evaluation framework to systematically assess the query-level robustness of RAG pipelines and offer actionable recommendations for practitioners based on the results of more than 1092 experiments we performed.

Harshal Nandigramwar, Syed Qutub, Kay-Ulrich Scholl

As AI systems become increasingly capable and ubiquitous, ensuring the safety of these systems is critical. However, existing safety tools often target different aspects of model safety and cannot provide full assurance in isolation, highlighting a need for integrated and composite methodologies. This paper introduces BlueGlass, a framework designed to facilitate composite AI safety workflows by providing a unified infrastructure enabling the integration and composition of diverse safety tools that operate across model internals and outputs. Furthermore, to demonstrate the utility of this framework, we present three safety-oriented analyses on vision-language models for the task of object detection: (1) distributional evaluation, revealing performance trade-offs and potential failure modes across distributions; (2) probe-based analysis of layer dynamics highlighting shared hierarchical learning via phase transition; and (3) sparse autoencoders identifying interpretable concepts. More broadly, this work contributes foundational infrastructure and findings for building more robust and reliable AI systems.

Qutub Syed Sha, Michael Paulitsch, Karthik Pattabiraman et al.

As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow. Soft errors causing bit flips during inference have significantly impacted DNN performance, altering predictions. Traditional range restriction solutions for CNNs fall short for transformers. This study introduces the Global Clipper and Global Hybrid Clipper, effective mitigation strategies specifically designed for transformer-based models. It significantly enhances their resilience to soft errors and reduces faulty inferences to ~ 0\%. We also detail extensive testing across over 64 scenarios involving two transformer models (DINO-DETR and Lite-DETR) and two CNN models (YOLOv3 and SSD) using three datasets, totalling approximately 3.3 million inferences, to assess model robustness comprehensively. Moreover, the paper explores unique aspects of attention blocks in transformers and their operational differences from CNNs.

Qutub Syed, Michael Paulitsch, Korbinian Hagn et al.

We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situation Monitor utilizes the Diversity-based Budding Ensemble Architecture (DBEA) and increases the OOD performance by integrating a diversity loss into the training process on top of the budding ensemble architecture, detecting Far-OOD samples and minimizing false positives on Near-OOD samples. Moreover, utilizing the resulting DBEA increases the model's OOD performance and improves the calibration of confidence scores, particularly concerning the intersection over union of the detected objects. The DBEA model achieves these advancements with a 14% reduction in trainable parameters compared to the vanilla model. This signifies a substantial improvement in efficiency without compromising the model's ability to detect OOD instances and calibrate the confidence scores accurately.

Cornelius Buerkle, Florian Geissler, Michael Paulitsch et al.

While the most visible part of the safety verification process of automated vehicles concerns the planning and control system, it is often overlooked that safety of the latter crucially depends on the fault-tolerance of the preceding environment perception. Modern perception systems feature complex and often machine-learning-based components with various failure modes that can jeopardize the overall safety. At the same time, a verification by for example redundant execution is not always feasible due to resource constraints. In this paper, we address the need for feasible and efficient perception monitors and propose a lightweight approach that helps to protect the integrity of the perception system while keeping the additional compute overhead minimal. In contrast to existing solutions, the monitor is realized by a well-balanced combination of sensor checks -- here using LiDAR information -- and plausibility checks on the object motion history. It is designed to detect relevant errors in the distance and velocity of objects in the environment of the automated vehicle. In conjunction with an appropriate planning system, such a monitor can help to make safe automated driving feasible.

Muhammad Jehanzeb Mirza, Cornelius Buerkle, Julio Jarquin et al.

State-of-the-art object detection systems for autonomous driving achieve promising results in clear weather conditions. However, such autonomous safety critical systems also need to work in degrading weather conditions, such as rain, fog and snow. Unfortunately, most approaches evaluate only on the KITTI dataset, which consists only of clear weather scenes. In this paper we address this issue and perform one of the most detailed evaluation on single and dual modality architectures on data captured in real weather conditions. We analyse the performance degradation of these architectures in degrading weather conditions. We demonstrate that an object detection architecture performing good in clear weather might not be able to handle degrading weather conditions. We also perform ablation studies on the dual modality architectures and show their limitations.

Koba Natroshvili, Kai Storr, Fabian Oboril et al.

This paper represents the novel high precision localization approach for Automated Driving (AD) relative to 3D map. The AD maps are not necessarily flat. Hence, the problem of localization is solved here in 3D. The vehicle motion is modeled as piecewise planner but with vertical curvature which is approximated with clothoids. The localization problem is solved with Decentralized Kalman filter with feedback (DKFF) by fusing all available information. The odometry, visual odometry, GPS, the different sensor and mono camera inputs are fused together to obtain the precise localization relative to map. Polylines and landmarks from the map are dealt in the same way because of the line - point geometrical duality. A set of weak filters are accumulated in the strong tracking approach leading to the precise localization results.