研究人员正在开发先进的方法来提高自动驾驶系统的安全性和效率。一种方法是将神经符号安全护栏与现有的端到端驾驶代理集成，以强制执行明确的安全规则并防止重大碰撞。另一种策略是将机器学习与基于优化的监督相结合，创建混合规划架构，以解释复杂场景并确保可驾驶性。此外，正在探索新的强化学习框架，通过在潜在世界模型中学习来提高样本效率并减少对昂贵现实世界交互的依赖。工作还集中于创建系统的行为分类法和自适应推理框架，这些框架利用空间物理证据和规划关键因素来优化驾驶性能。
AI
arXiv:2608.12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) mod…
Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, whi…
arXiv cs.AI
TIER_1English(EN)·Jean-Pierre Busch, Guido Linden, Jan Bergmann, Lutz Eckstein·
arXiv:2608.12198v1 Announce Type: cross Abstract: Recent research in machine and deep learning has shown the potential of learningbased motion planning approaches to improve the driving behavior of automated vehicles, especially in complex environments. However, their complex nat…
arXiv:2608.11451v1 Announce Type: cross Abstract: Modern end-to-end driving agents can achieve high average performance yet still violate basic traffic rules that a human driver would never miss. The reason is structural: they learn statistical patterns rather than the physical c…
arXiv cs.LG
TIER_1English(EN)·Jiazhuo Li, Linjiang Cao, Qi Liu, Xi Xiong·
arXiv:2608.10386v1 Announce Type: new Abstract: Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world models reduce the reliance on costly environment interactions, policy optimization …
arXiv cs.AI
TIER_1English(EN)·Chaitanya Shinde, Hadi Hajieghrary, Miguel Hurtado·
arXiv:2608.08941v1 Announce Type: cross Abstract: Operational Design Domain (ODD) specifications describe where an automated driving system (ADS) is permitted to operate, but they do not prescribe what the ADS must demonstrably do once deployed within that domain. This gap betwee…
World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods require costly future generation at inference. We present SimWAM, a simple yet effective WAM that uses video generation purely as a tr…
arXiv:2608.10107v1 Announce Type: new Abstract: Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video da…
arXiv cs.CV
TIER_1English(EN)·Guolei Huang, Tengfei She, Yuxuan Lu, Yao Huang, Yuqi Ye, Yongjun Shen·
arXiv:2608.09591v1 Announce Type: cross Abstract: Vision-language models (VLMs) have advanced scene understanding and enabled explicit reasoning in end-to-end autonomous driving. However, existing methods insufficiently integrate spatial-physical evidence into planning reasoning,…
arXiv:2608.07468v1 Announce Type: new Abstract: World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods require costly future generation at inference. We present SimWAM, a simple yet effecti…
