arXiv subjects

Christian Berger

Publications and source records attributed to Christian Berger.

At least 19 recordsLinked to original sources

arXiv2026

Recommendations for Efficient and Responsible LLM Adoption within Industrial Software Development

Context: Large language models (LLMs) are observed to have a significant positive impact on various software engineering (SE) activities. With improved accessibility, the adoption of powerful LLMs in industry has surged recently. However, there is a lack of actionable best practices for the efficient and responsible adoption of LLMs within industrial software settings. Objectives: We developed seven actionable recommendations to address this research gap. Methods: We conducted a multi-case study with three organisations that use LLMs within their SE activities and synthesised seven recommendations through qualitative thematic analysis. We conducted a complementary online survey with software practitioners from various industries to evaluate the perceived relevance of our recommendations. Results: Our results and recommendations focus on (i) users' preference to use LLMs as AI assistants, (ii) the importance of relevant stakeholders' satisfaction in the LLM-output evaluation, (iii) scoping the applicability of LLMs within SE tasks, (iv) the effect of LLMs on SE workflows, (v) the necessity and directions for developing human oversight mechanisms, and (vi) the necessary skills for practitioners for leveraging LLMs within SE. The online survey indicates a high level of agreement from the participants regarding the perceived relevance of the recommendations. Conclusion: We outline future research directions, including mapping the seven recommendations to the principles of the EU AI Act (AIA) in order to examine how they relate to the current regulatory compliance frameworks.

cs.SE↗

arXiv2025

Self-Consistent Model for Gate Control of Narrow-, Broken-, and Inverted-Gap (Topological) Heterostructures

Even small electrostatic potentials can dramatically influence the band structure of narrow-, broken-, and inverted-gap materials. A quantitative understanding often necessitates a self-consistent Hartree approach. The valence and conduction band states strongly hybridize and/or cross in these systems. This makes distinguishing between electrons and holes impossible and the assumption of a flat charge carrier distribution at the charge neutrality point hard to justify. Consequently the wide-gap approach often fails in these systems. An alternative is the full-band envelope-function approach by Andlauer and Vogl, which has been implemented into the open-source software package kdotpy (arXiv:2407.12651). We show that this approach and implementation gives numerically stable and quantitatively accurate results where the conventional method fails by modeling the experimental subband density evolution with top-gate voltage in thick (26 nm - 110 nm), topologically inverted HgTe quantum wells. We expect our openly-available implementation to greatly benefit the investigation of narrow-, broken-, and inverted-gap materials.

cond-mat.mes-hall↗

arXiv2025

An AUTOSAR-Aligned Architectural Study of Vulnerabilities in Automotive SoC Software

Cooperative, Connected and Automated Mobility (CCAM) are complex cyber-physical systems (CPS) that integrate computation, communication, and control in safety-critical environments. At their core, System-on-Chip (SoC) platforms consolidate processing units, communication interfaces, AI accelerators, and security modules into a single chip. AUTOSAR (AUTomotive Open System ARchitecture) standard was developed in the automotive domain to better manage this complexity, defining layered software structures and interfaces to facilitate reuse of HW/SW components. However, in practice, this integrated SoC software architecture still poses security challenges, particularly in real-time, safety-critical environments. Recent reports highlight a surge in SoC-related vulnerabilities, yet systematic analysis of their root causes and impact within AUTOSAR-aligned architectures is lacking. This study fills that gap by analyzing 180 publicly reported automotive SoC vulnerabilities, mapped to a representative SoC software architecture model that is aligned with AUTOSAR principles for layered abstraction and service orientation. We identify 16 root causes and 56 affected software modules, and examine mitigation delays across Common Weakness Enumeration (CWE) categories and architectural layers. We uncover dominant vulnerability patterns and critical modules with prolonged patch delays, and provide actionable insights for securing automotive CPS platforms, including guides for improved detection, prioritization, and localization strategies for SoC software architectures in SoC-based vehicle platforms.

cs.SE↗

arXiv2025

PCICF: A Pedestrian Crossing Identification and Classification Framework

We have recently observed the commercial roll-out of robotaxis in various countries. They are deployed within an operational design domain (ODD) on specific routes and environmental conditions, and are subject to continuous monitoring to regain control in safety-critical situations. Since ODDs typically cover urban areas, robotaxis must reliably detect vulnerable road users (VRUs) such as pedestrians, bicyclists, or e-scooter riders. To better handle such varied traffic situations, end-to-end AI, which directly compute vehicle control actions from multi-modal sensor data instead of only for perception, is on the rise. High quality data is needed for systematically training and evaluating such systems within their OOD. In this work, we propose PCICF, a framework to systematically identify and classify VRU situations to support ODD's incident analysis. We base our work on the existing synthetic dataset SMIRK, and enhance it by extending its single-pedestrian-only design into the MoreSMIRK dataset, a structured dictionary of multi-pedestrian crossing situations constructed systematically. We then use space-filling curves (SFCs) to transform multi-dimensional features of scenarios into characteristic patterns, which we match with corresponding entries in MoreSMIRK. We evaluate PCICF with the large real-world dataset PIE, which contains more than 150 manually annotated pedestrian crossing videos. We show that PCICF can successfully identify and classify complex pedestrian crossings, even when groups of pedestrians merge or split. By leveraging computationally efficient components like SFCs, PCICF has even potential to be used onboard of robotaxis for OOD detection for example. We share an open-source replication package for PCICF containing its algorithms, the complete MoreSMIRK dataset and dictionary, as well as our experiment results presented in: https://github.com/Claud1234/PCICF

cs.CV↗

arXiv2025

BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems

Large language models (LLMs) are growingly extended to process multimodal data such as text and video simultaneously. Their remarkable performance in understanding what is shown in images is surpassing specialized neural networks (NNs) such as Yolo that is supporting only a well-formed but very limited vocabulary, ie., objects that they are able to detect. When being non-restricted, LLMs and in particular state-of-the-art vision language models (VLMs) show impressive performance to describe even complex traffic situations. This is making them potentially suitable components for automotive perception systems to support the understanding of complex traffic situations or edge case situation. However, LLMs and VLMs are prone to hallucination, which mean to either potentially not seeing traffic agents such as vulnerable road users who are present in a situation, or to seeing traffic agents who are not there in reality. While the latter is unwanted making an ADAS or autonomous driving systems (ADS) to unnecessarily slow down, the former could lead to disastrous decisions from an ADS. In our work, we are systematically assessing the performance of 3 state-of-the-art VLMs on a diverse subset of traffic situations sampled from the Waymo Open Dataset to support safety guardrails for capturing such hallucinations in VLM-supported perception systems. We observe that both, proprietary and open VLMs exhibit remarkable image understanding capabilities even paying thorough attention to fine details sometimes difficult to spot for us humans. However, they are also still prone to making up elements in their descriptions to date requiring hallucination detection strategies such as BetterCheck that we propose in our work.

cs.CV↗

arXiv2025

The DevSafeOps Dilemma: A Systematic Literature Review on Rapidity in Safe Autonomous Driving Development and Operation

Developing autonomous driving (AD) systems is challenging due to the complexity of the systems and the need to assure their safe and reliable operation. The widely adopted approach of DevOps seems promising to support the continuous technological progress in AI and the demand for fast reaction to incidents, which necessitate continuous development, deployment, and monitoring. We present a systematic literature review meant to identify, analyse, and synthesise a broad range of existing literature related to usage of DevOps in autonomous driving development. Our results provide a structured overview of challenges and solutions, arising from applying DevOps to safety-related AI-enabled functions. Our results indicate that there are still several open topics to be addressed to enable safe DevOps for the development of safe AD.

cs.SE↗

arXiv2025

Large Language Models in Code Co-generation for Safe Autonomous Vehicles

Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive context, there is a need to systematically assess this new setup: LLMs entail a well-documented set of risks for safety-related systems' development due to their stochastic nature. To reduce the effort for code reviewers to evaluate LLM-generated code, we propose an evaluation pipeline to conduct sanity-checks on the generated code. We compare the performance of six state-of-the-art LLMs (CodeLlama, CodeGemma, DeepSeek-r1, DeepSeek-Coders, Mistral, and GPT-4) on four safety-related programming tasks. Additionally, we qualitatively analyse the most frequent faults generated by these LLMs, creating a failure-mode catalogue to support human reviewers. Finally, the limitations and capabilities of LLMs in code generation, and the use of the proposed pipeline in the existing process, are discussed.

cs.SE↗

arXiv2025

On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software

Automated Driving System (ADS) is a safety-critical software system responsible for the interpretation of the vehicle's environment and making decisions accordingly. The unbounded complexity of the driving context, including unforeseeable events, necessitate continuous improvement, often achieved through iterative DevOps processes. However, DevOps processes are themselves complex, making these improvements both time- and resource-intensive. Automation in code generation for ADS using Large Language Models (LLM) is one potential approach to address this challenge. Nevertheless, the development of ADS requires rigorous processes to verify, validate, assess, and qualify the code before it can be deployed in the vehicle and used. In this study, we developed and evaluated a prototype for automatic code generation and assessment using a designed pipeline of a LLM-based agent, simulation model, and rule-based feedback generator in an industrial setup. The LLM-generated code is evaluated automatically in a simulation model against multiple critical traffic scenarios, and an assessment report is provided as feedback to the LLM for modification or bug fixing. We report about the experimental results of the prototype employing Codellama:34b, DeepSeek (r1:32b and Coder:33b), CodeGemma:7b, Mistral:7b, and GPT4 for Adaptive Cruise Control (ACC) and Unsupervised Collision Avoidance by Evasive Manoeuvre (CAEM). We finally assessed the tool with 11 experts at two Original Equipment Manufacturers (OEMs) by conducting an interview study.

cs.SE↗

arXiv2025

OptiLog: Assigning Roles in Byzantine Consensus

Byzantine Fault-Tolerant (BFT) protocols play an important role in blockchains. As the deployment of such systems extends to wide-area networks, the scalability of BFT protocols becomes a critical concern. Optimizations that assign specific roles to individual replicas can significantly improve the performance of BFT systems. However, such role assignment is highly sensitive to faults, potentially undermining the optimizations' effectiveness. To address these challenges, we present OptiLog, a logging framework for collecting and analyzing measurements that help to assign roles in globally distributed systems, despite the presence of faults. OptiLog presents local measurements in global data structures, to enable consistent decisions and hold replicas accountable if they do not perform according to their reported measurements. We demonstrate OptiLog's flexibility by applying it to two BFT protocols: (1) Aware, a highly optimized PBFT-like protocol, and (2) Kauri, a tree-based protocol designed for large-scale deployments. OptiLog detects and excludes replicas that misbehave during consensus and thus enables the system to operate in an optimized, low-latency configuration, even under adverse conditions. Experiments show that for tree overlays deployed across 73 worldwide cities, trees found by OptiLog display 39% lower latency than Kauri.

cs.DC↗

arXiv2024

Highly efficient broadband THz upconversion with Dirac materials

The use of the THz frequency domain in future network generations offers an unparalleled level of capacity, which can enhance innovative applications in wireless communication, analytics, and imaging. Communication technologies rely on frequency mixing, enabling signals to be converted from one frequency to another and transmitted from a sender to a receiver. Technically, this process is implemented using nonlinear components such as diodes or transistors. However, the highest operation frequency of this approach is limited to sub-THz bands. Here, we demonstrate the upconversion of a weak sub-THz signal from a photoconductive antenna to multiple THz bands. The key element is a high-mobility HgTe-based heterostructure with electronic band inversion, leading to one of the strongest third-order nonlinearities among all materials in the THz range. Due to the Dirac character of electron dispersion, the highly intense sub-THz radiation is efficiently mixed with the antenna signal, resulting in a THz response at linear combinations of their frequencies. The field conversion efficiency above 2$\%$ is provided by a bare tensile-strained HgTe layer with a thickness below 100 nm at room temperature under ambient conditions. Devices based on Dirac materials allow for high degree of integration, with field-enhancing metamaterial structures, making them very promising for THz communication with unprecedented data transfer rate.

physics.optics↗

arXiv2024

Predicting Pedestrian Crossing Behavior in Germany and Japan: Insights into Model Transferability

Predicting pedestrian crossing behavior is important for intelligent traffic systems to avoid pedestrian-vehicle collisions. Most existing pedestrian crossing behavior models are trained and evaluated on datasets collected from a single country, overlooking differences between countries. To address this gap, we compared pedestrian road-crossing behavior at unsignalized crossings in Germany and Japan. We presented four types of machine learning models to predict gap selection behavior, zebra crossing usage, and their trajectories using simulator data collected from both countries. When comparing the differences between countries, pedestrians from the study conducted in Japan are more cautious, selecting larger gaps compared to those in Germany. We evaluate and analyze model transferability. Our results show that neural networks outperform other machine learning models in predicting gap selection and zebra crossing usage, while random forest models perform best on trajectory prediction tasks, demonstrating strong performance and transferability. We develop a transferable model using an unsupervised clustering method, which improves prediction accuracy for gap selection and trajectory prediction. These findings provide a deeper understanding of pedestrian crossing behaviors in different countries and offer valuable insights into model transferability.

cs.LG↗

arXiv2024

LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks

Today's Large Language Models (LLMs) have showcased exemplary capabilities, ranging from simple text generation to advanced image processing. Such models are currently being explored for in-vehicle services such as supporting perception tasks in Advanced Driver Assistance Systems (ADAS) or Autonomous Driving (AD) systems, given the LLMs' capabilities to process multi-modal data. However, LLMs often generate nonsensical or unfaithful information, known as ``hallucinations'': a notable issue that needs to be mitigated. In this paper, we systematically explore the adoption of SelfCheckGPT to spot hallucinations by three state-of-the-art LLMs (GPT-4o, LLaVA, and Llama3) when analysing visual automotive data from two sources: Waymo Open Dataset, from the US, and PREPER CITY dataset, from Sweden. Our results show that GPT-4o is better at generating faithful image captions than LLaVA, whereas the former demonstrated leniency in mislabeling non-hallucinated content as hallucinations compared to the latter. Furthermore, the analysis of the performance metrics revealed that the dataset type (Waymo or PREPER CITY) did not significantly affect the quality of the captions or the effectiveness of hallucination detection. However, the models showed better performance rates over images captured during daytime, compared to during dawn, dusk or night. Overall, the results show that SelfCheckGPT and its adaptation can be used to filter hallucinations in generated traffic-related image captions for state-of-the-art LLMs.

cs.CV↗

arXiv2024

Tapping in a Remote Vehicle's onboard LLM to Complement the Ego Vehicle's Field-of-View

Today's advanced automotive systems are turning into intelligent Cyber-Physical Systems (CPS), bringing computational intelligence to their cyber-physical context. Such systems power advanced driver assistance systems (ADAS) that observe a vehicle's surroundings for their functionality. However, such ADAS have clear limitations in scenarios when the direct line-of-sight to surrounding objects is occluded, like in urban areas. Imagine now automated driving (AD) systems that ideally could benefit from other vehicles' field-of-view in such occluded situations to increase traffic safety if, for example, locations about pedestrians can be shared across vehicles. Current literature suggests vehicle-to-infrastructure (V2I) via roadside units (RSUs) or vehicle-to-vehicle (V2V) communication to address such issues that stream sensor or object data between vehicles. When considering the ongoing revolution in vehicle system architectures towards powerful, centralized processing units with hardware accelerators, foreseeing the onboard presence of large language models (LLMs) to improve the passengers' comfort when using voice assistants becomes a reality. We are suggesting and evaluating a concept to complement the ego vehicle's field-of-view (FOV) with another vehicle's FOV by tapping into their onboard LLM to let the machines have a dialogue about what the other vehicle ``sees''. Our results show that very recent versions of LLMs, such as GPT-4V and GPT-4o, understand a traffic situation to an impressive level of detail, and hence, they can be used even to spot traffic participants. However, better prompts are needed to improve the detection quality and future work is needed towards a standardised message interchange format between vehicles.

cs.CV↗

arXiv2024

Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks

Today's advanced driver assistance systems (ADAS), like adaptive cruise control or rear collision warning, are finding broader adoption across vehicle classes. Integrating such advanced, multimodal Large Language Models (LLMs) on board a vehicle, which are capable of processing text, images, audio, and other data types, may have the potential to greatly enhance passenger comfort. Yet, an LLM's hallucinations are still a major challenge to be addressed. In this paper, we systematically assessed potential hallucination detection strategies for such LLMs in the context of object detection in vision-based data on the example of pedestrian detection and localization. We evaluate three hallucination detection strategies applied to two state-of-the-art LLMs, the proprietary GPT-4V and the open LLaVA, on two datasets (Waymo/US and PREPER CITY/Sweden). Our results show that these LLMs can describe a traffic situation to an impressive level of detail but are still challenged for further analysis activities such as object localization. We evaluate and extend hallucination detection approaches when applying these LLMs to video sequences in the example of pedestrian detection. Our experiments show that, at the moment, the state-of-the-art proprietary LLM performs much better than the open LLM. Furthermore, consistency enhancement techniques based on voting, such as the Best-of-Three (BO3) method, do not effectively reduce hallucinations in LLMs that tend to exhibit high false negatives in detecting pedestrians. However, extending the hallucination detection by including information from the past helps to improve results.

cs.CV↗

arXiv2024

Semantic-Aware Representation of Multi-Modal Data for Data Ingress: A Literature Review

Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While the trend is to use ever-larger datasets for training, managing this data efficiently has become a significant practical challenge in the industry-double as much data is certainly not double as good. Rather the opposite is important since getting an understanding of the inherent quality and diversity of the underlying data lakes is a growing challenge for application-specific ML as well as for fine-tuning foundation models. Furthermore, information retrieval (IR) from expanding data lakes is complicated by the temporal dimension inherent in time-series data which must be considered to determine its semantic value. This study focuses on the different semantic-aware techniques to extract embeddings from mono-modal, multi-modal, and cross-modal data to enhance IR capabilities in a growing data lake. Articles were collected to summarize information about the state-of-the-art techniques focusing on applications of embedding for three different categories of data modalities.

cs.LG↗

arXiv2024

kdotpy: $\mathbf{k}\cdot\mathbf{p}$ theory on a lattice for simulating semiconductor band structures

The software project kdotpy provides a Python application for simulating electronic band structures of semiconductor devices with $\mathbf{k}\cdot\mathbf{p}$ theory on a lattice. The application implements the widely used Kane model, capable of reliable predictions of transport and optical properties for a large variety of topological and non-topological materials with a zincblende crystal structure. The application automates the tedious steps of simulating band structures. The user inputs the relevant physical parameters on the command line, for example materials and dimensions of the device, magnetic field, and temperature. The program constructs the appropriate matrix Hamiltonian on a discretized lattice of spatial coordinates and diagonalizes it. The physical observables are extracted from the eigenvalues and eigenvectors and saved as output. The program is highly customizable with a large set of configuration options and material parameters.

cond-mat.mes-hall↗

arXiv2024

Comparing Optical Flow and Deep Learning to Enable Computationally Efficient Traffic Event Detection with Space-Filling Curves

Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series data obtained from video, radar, and LiDAR is computationally demanding, particularly when meta-information or annotations are missing. We compare Optical Flow (OF) and Deep Learning (DL) to feed computationally efficient event detection via space-filling curves on video data from a forward-facing, in-vehicle camera. Our first approach leverages unexpected disturbances in the OF field from vehicle surroundings; the second approach is a DL model trained on human visual attention to predict a driver's gaze to spot potential event locations. We feed these results to a space-filling curve to reduce dimensionality and achieve computationally efficient event retrieval. We systematically evaluate our concept by obtaining characteristic patterns for both approaches from a large-scale virtual dataset (SMIRK) and applied our findings to the Zenseact Open Dataset (ZOD), a large multi-modal, real-world dataset, collected over two years in 14 different European countries. Our results yield that the OF approach excels in specificity and reduces false positives, while the DL approach demonstrates superior sensitivity. Both approaches offer comparable processing speed, making them suitable for real-time applications.

cs.CV↗

arXiv2024

AirDnD -- Asynchronous In-Range Dynamic and Distributed Network Orchestration Framework

The increasing usage of IoT devices has generated an extensive volume of data which resulted in the establishment of data centers with well-structured computing infrastructure. Reducing underutilized resources of such data centers can be achieved by monitoring the tasks and offloading them across various compute units. This approach can also be used in mini mobile data ponds generated by edge devices and smart vehicles. This research aims to improve and utilize the usage of computing resources in distributed edge devices by forming a dynamic mesh network. The nodes in the mesh network shall share their computing tasks with another node that possesses unused computing resources. This proposed method ensures the minimization of data transfer between entities. The proposed AirDnD vision will be applied to a practical scenario relevant to an autonomous vehicle that approaches an intersection commonly known as ``looking around the corner'' in related literature, collecting essential computational results from nearby vehicles to enhance its perception. The proposed solution consists of three models that transform growing amounts of geographically distributed edge devices into a living organism.

cs.SE↗