Research papers · Posted 2024.11.30 · Preprint
LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization
LAMBDA: Covering the Multimodal Critical Scenarios for Automated Driving Systems by Search Space Quantization
Overview
LAMBDA formulates scenario testing as coverage of multiple dangerous subspaces rather than finding one optimum. Density-adaptive partitioning and beam search aim to broaden critical-region coverage within a limited simulation budget.
Author-supplied source information
Author-supplied information on arXiv.
17pages, 21figures
Version: v1