Dragtraffic: A Non-Expert Interactive and Point-Based Controllable Traffic Scene Generation Framework

arXiv:2404.12624v1 Announce Type: cross
Abstract: The evaluation and training of autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results. To address this problem, we propose Dragtraffic, a generalized, point-based, and controllable traffic scene generation framework based on conditional diffusion. Dragtraffic enables non-experts to generate a variety of realistic driving scenarios for different types of traffic agents through an adaptive mixture expert architecture. We use …

abstract accuracy arxiv autonomous autonomous driving autonomous driving systems cases cs.cv cs.ro diverse driving evaluation expert framework generalized however interactive results scalable systems traffic training type