This paper provides a comprehensive survey of methods for detecting edge cases in automated driving systems, addressing challenges in ensuring reliability. It classifies detection techniques based on automotive system modules and underlying methodologies, introducing "knowledge-driven" approaches to complement data-driven ones. The paper also examines evaluation metrics for detection performance and practical deployment, concluding with key challenges such as data quality and validation. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Provides a structured overview of techniques for improving the safety and reliability of autonomous vehicles by addressing rare scenarios.
RANK_REASON This is a survey paper published on arXiv detailing methods and challenges in edge case detection for automated driving. [lever_c_demoted from research: ic=1 ai=0.7]