Driver State Monitoring Systems: A Comprehensive Review Bridging Academic Research and Industrial Deployment

Driving into the Future: A Comprehensive Survey of Autonomous Vehicle Technologies

Autonomous vehicles (AVs) represent a foundational cornerstone of future smart city transportation systems, offering the potential to eliminate human driving errors, reduce traffic fatalities by at least 40%, and optimize energy consumption. While AV technology is advancing rapidly toward highly automated driving (HAV) and driver-out Level 4 (L4) deployment, commercial realization remains hindered by significant technological uncertainties, soaring development costs, and strict safety-critical validation requirements. This provides a comprehensive, holistic survey of autonomous vehicle technology, bridging gaps in the existing literature by tracing its historical evolution to modern platforms equipped with LiDAR, radar, cameras, and  (V2X) communication. Beyond exploring essential architectural components, it evaluates the modern state of research by benchmarking the three dominant autonomous vehicle software architectures: modular pipelines, pure End-to-End (E2E), and hybrid systems across seven quantitative dimensions: planning quality, safety certification, latency, data efficiency, debuggability, Operational Design Domain (ODD) adaptation, and robustness. Comparative analysis of industry-standard benchmarks, including nuScenes and CARLA, reveals that while E2E and hybrid approaches achieve superior planning scores (88–91%) and lower collision rates (1.1–2.0%) than modular pipelines (84–86% planning; 3.95% collisions), pure E2E models lack a viable regulatory path for 2026 L4 deployment due to prohibitive validation mandates. Conversely, hybrid modular-E2E algorithms recover approximately 98% of E2E planning performance, drastically reduce debugging times to 2–6 hours, and retain compliance with ISO 26262:2018 ASIL-D safety standards. This work maps out the market landscape and identifies hybrid architectures as the current Pareto-optimal solution, balancing operational capability, safety assurance, and immediate regulatory feasibility for L3/L4 automation

EFFECT OF THE ROBUSTNESS LAYERS DEFINED BY EURO NCAP FOR THE NEW CRASH AVOIDANCE 2026 PROTOCOL ON PERCEPTION CAPABILITIES OF VEHICLE SENSORS

BUILDING SCIENTIFIC CONSENSUS ON THE CRASH SAFETY PERFORMANCE OF AUTOMATED DRIVING SYSTEMS

Virtual Testing for MASS: A Comprehensive Review of Current Practices, Gaps, and Standardization Needs

This paper presents a comprehensive literature review and landscape analysis of virtual testing for autonomous ship navigation and collision detection/collision avoidance (CDCA), with the objective of consolidating fragmented research and industrial practice into a structured overview that can inform future standards and certification frameworks for Maritime Autonomous Surface Ships (MASS). The review encompasses academic studies, regulatory and class-society publications, national and regional testbed activities, industrial developments and prototype testing initiatives, as well as early operational insights obtained from MASS simulators and sea trials. Methodologically, the study employs structured searches across scientific databases, regulatory documents, industrial white papers, trial reports, and vendor materials to map the current state of the art in testing of autonomous CDCA systems. The analysis covers the types of scenarios (baseline, region-specific, edge and near-miss), test procedures, performance metrics, pass/fail criteria, coverage requirements, existing IMO manoeuvre tests applicability and the practical approaches and validation strategies adopted by developers. The review highlights strong growth in scenario-based testing, digital twins, high-fidelity simulators, and human-in-the-loop arrangements, with increasing focus on safety and reliability indicators tailored to autonomous functions. At the same time, the review identifies critical gaps, including the limited standardization of safety metrics and acceptance criteria, inconsistent handling of critical/near miss or other edge scenarios derived from real traffic data, and challenges in the translation of virtual testing evidence into regulatory or class approval pathways. Drawing from these observations, the paper outlines a high-level concept of an autonomous CDCA virtual testing framework. The paper highlights overarching elements of the framework including consistent scenario development, clear evaluation metrics, harmonized safety and reliability indicators, and mechanisms for linking virtual testing outcomes to broader assurance pathways such as actual MASS trials, regulatory and class approvals, and crew training. The findings establish an important knowledge foundation and identify key areas from a maritime assurance perspective, motivating future efforts towards practical, standardized approaches to virtual testing of autonomous maritime systems.

A Comprehensive Review of End-to-End Autonomous Driving: Architectures and Emerging Trends

This review proposes a novel function-oriented taxonomy by categorizing architectures into perception-integrated and planning-integrated paradigms, and addresses critical challenges, particularly long-tail data scarcity and the deficiency in human-like decision-making.

Anomaly Management in Unmanned Aerial Vehicles: A Systematic Literature Review

Unmanned Aerial Vehicles (UAVs) are increasingly deployed in safety-critical applications such as logistics, surveillance, disaster response, and urban air mobility. While their autonomy enables powerful capabilities, it also introduces vulnerabilities due to hardware faults, software defects, communication failures, and adversarial interference. This survey presents a comprehensive review of research studies closely related to UAV anomalies published between 2015 and 2025, covering 111 papers from academic and industrial sources. We introduce a unified five-pillar taxonomy—anomaly generation, prevention, detection, recovery, and analysis—that organizes existing work across the full anomaly management lifecycle. In contrast to prior surveys that focus primarily on detection algorithms, our review integrates operational and regulatory perspectives, explicitly linking technical anomalies to policy enforcement and compliance requirements. We systematically compare detection techniques, datasets, simulators, and evaluation practices, revealing significant fragmentation in datasets, limited real-world validation, and a lack of standardized real-time benchmarks. Our synthesis highlights key research challenges, including the sim-to-real gap, limited interpretability of learning-based detectors, and the scarcity of policy-aware anomaly management frameworks. Based on these findings, we outline emerging research opportunities for adaptive, explainable, and benchmark-driven anomaly management systems that support safe, transparent, and reliable UAV operations. We release our metadata for all the papers reviewed, as well as filters for easy sorting.