Wikipedia is a critical source of information for millions of users across the Web. It serves as a key resource for large language models, search engines, question-answering systems, and other Web-based applications. In Wikipedia, content needs to be verifiable, meaning that readers can check that claims are backed by references to reliable sources. This depends on manual verification by editors, an effective but labor-intensive process, especially given the high volume of daily edits. To address this challenge, we introduce a multilingual machine learning system to assist editors in identifying claims requiring citations. Our approach is tested in 10 language editions of Wikipedia, outperforming existing benchmarks for reference need assessment. We not only consider machine learning evaluation metrics but also system requirements, allowing us to explore the trade-offs between model accuracy and computational efficiency under real-world infrastructure constraints. We deploy our system in production and release data and code to support further research.

Abstract Autonomous vehicles in logistics and industrial environments demand robust and efficient perception systems. This study presents a LiDAR-based perception system designed for such environments, focusing on real-time deterministic obstacle detection and tracking with limited computational power. The proposed multi-stage approach leverages 3D data from LiDAR sensors. First, ground removal is performed to filter out static ground points. Then, a filtering step is applied using precomputed maps of the navigation area to filter out static zones from the LiDAR point clouds. After, object segmentation distinguishes structural elements from potential obstacles, followed by clustering and Principal Component Analysis (PCA) to accurately estimate obstacle pose and volume. An obstacle-tracking method ensures continuous monitoring over time. Extensive experiments in realistic logistics and industrial scenarios have been performed, comparing the proposed approach to state-of-the-art deep-learning-based methods, demonstrating the system’s high performance in both accuracy and efficiency.

The rapid advancements in autonomous vehicle software present both opportunities and challenges, especially in enhancing road safety. The primary objective of autonomous vehicles is to reduce accident rates through improved safety measures. However, the integration of new algorithms into the autonomous vehicle, such as artificial intelligence methods, raises concerns about the compliance with established safety regulations. This paper introduces a novel supervisor architecture based on behavior trees, aligned with established standards and designed to supervise vehicle functional safety in real time. It specifically addresses the integration of algorithms into industrial road vehicles, adhering to the ISO 26262. The proposed supervisor architecture involves the detection of hazards and compliance with functional and technical safety requirements when a hazard arises. This methodology, implemented in this study in a Renault Mégane (currently with SAE level 3 of automation capabilities), not only guarantees compliance with safety standards, but also paves the way for safer and more reliable autonomous driving technologies.

Autonomous vehicles represents a ground-breaking transportation technology which has the potential to provide many benefits to the society. To fully utilize this technology, it is essential that the autonomous vehicle maintains safe behavior under different conditions and in case of failures. Fail-degraded strategies allow the vehicle to react safely to these situations, while maintaining to some extent the vehicle’s autonomous functionality. However, defining a framework for scalable fail-degraded systems, given the system’s complexity, remains to be a challenge. This paper focuses on identifying concepts and tools that enables scalable fail-degraded behavior for autonomous vehicles. The article includes a taxonomy to clarify holistic monitoring and representation concepts. Based on these concepts, scalable monitoring techniques are identified and classified. Afterwards, safety reasoning frameworks and adaptation mechanisms for fail-degraded autonomous vehicles are discussed. According to the discussed literature, several research gaps are identified.