A standards-derived rubric shows causal XAI is required for hazard identification, incident investigation, and data management in ADS safety cases, while other methods suffice elsewhere.
Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Changes in Chain-of-Causation explanations under sensor perturbations correlate with 5.3× higher trajectory deviation in a driving VLA, and enabling such explanations yields 11.8% better accuracy.
citing papers explorer
-
Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety
A standards-derived rubric shows causal XAI is required for hazard identification, incident investigation, and data management in ADS safety cases, while other methods suffice elsewhere.
-
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
Changes in Chain-of-Causation explanations under sensor perturbations correlate with 5.3× higher trajectory deviation in a driving VLA, and enabling such explanations yields 11.8% better accuracy.