Skip to content
This repository has been archived by the owner on Jun 29, 2024. It is now read-only.

Latest commit

 

History

History
22 lines (16 loc) · 1.24 KB

File metadata and controls

22 lines (16 loc) · 1.24 KB

Data-driven Methods for SCSG

Here're some resources about Data-driven Methods for SCSG

Intros:

  • Data-driven approaches primarily leverage existing datasets of real-world driving scenarios, such as traffic incident data, human driving behavior data, or sensor data from test drives. These data sets are mined to extract scenarios as "edge cases," rare but potentially dangerous situations that might not be considered in traditional scenario modeling, including complex interactions, near-miss events, or situations that lead to accidents,

  • It's worth noting that while data-driven methods can generate a wealth of diverse and realistic testing scenarios, they also require large and rich datasets, advanced analytical capabilities, and may face challenges in reproducing exact real-world conditions.

Table of Contents