用BEV世界模型实时评估驾驶轨迹，提升端到端自动驾驶安全性。
End-to-End Driving with Online Trajectory Evaluation via BEV World Model
- 构建基于BEV的世界模型，实时预测未来环境状态用于轨迹评估。
- 在CARLA模拟器上实现最优性能，比现有方法更安全高效。
- 适配真实场景，适合研究端到端自动驾驶与在线决策的开发者。
端到端自动驾驶通过将感知、预测与规划整合为可微分框架取得了显著进展。然而，要充分发挥其潜力，有效的在线轨迹评估不可或缺，以确保安全性。通过预测特定轨迹的未来结果，轨迹评估效果显著提升。这可通过世界模型捕捉环境动态并预测未来状态来实现。为此，我们提出端到端驾驶框架WoTE，利用BEV世界模型预测未来BEV状态以进行轨迹评估。所提出的BEV世界模型相比图像级世界模型具有更低延迟，且可无缝使用现成的BEV空间交通仿真器进行监督。我们在NAVSIM基准和基于CARLA模拟器的闭环Bench2Drive基准上验证了该框架，实现了当前最佳性能。代码已开源：https://github.com/liyingyanUCAS/WoTE。
原文摘要 · Abstract (English)
End-to-end autonomous driving has achieved remarkable progress by integrating perception, prediction, and planning into a fully differentiable framework. Yet, to fully realize its potential, an effective online trajectory evaluation is indispensable to ensure safety. By forecasting the future outcomes of a given trajectory, trajectory evaluation becomes much more effective. This goal can be achieved by employing a world model to capture environmental dynamics and predict future states. Therefore, we propose an end-to-end driving framework WoTE, which leverages a BEV World model to predict future BEV states for Trajectory Evaluation. The proposed BEV world model is latency-efficient compared to image-level world models and can be seamlessly supervised using off-the-shelf BEV-space traffic simulators. We validate our framework on both the NAVSIM benchmark and the closed-loop Bench2Drive benchmark based on the CARLA simulator, achieving state-of-the-art performance. Code is released at https://github.com/liyingyanUCAS/WoTE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。