Autonomous driving paper index
SA-TRP: Stochasticity-Aware Test Reduction and Prioritization for Autonomous Driving Systems - Benchmark dataset
One-line summary
Benchmark of binary safety outcomes for two industrial ADS stacks (openpilot/MetaDrive, Autoware/CARLA) re-executed across their commit histories under many random seeds.
Engineering notes
Benchmark of binary safety outcomes for two industrial ADS stacks (openpilot/MetaDrive, Autoware/CARLA) re-executed across their commit histories under many random seeds.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。
Original abstract
Benchmark of binary safety outcomes for two industrial ADS stacks (openpilot/MetaDrive, Autoware/CARLA) re-executed across their commit histories under many random seeds. Spans 365 days of public history (May 2025 - May 2026) per stack; after excluding non-runtime and non-buildable commits, 252 (openpilot/MetaDrive, ≈L2) and 228 (Autoware/CARLA, ≈L4) commits are usable — 30,321 and 3,677 valid runs across 13 and 10 scenario categories.
Links and sources
Need this topic turned into a technical roadmap?
Full Self Driving can prepare a custom autonomous driving literature review, code map, dataset map, and B2B technology assessment.
Request B2B research
Comments