端到端自动驾驶轨迹规划，用专家混合模型动态响应环境变化。
ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving
- 逐点生成轨迹，通过专家路由动态选择处理场景的专用网络。
- 在NAVSIM数据集上达87.0 PDMS和83.1 EPDMS，性能领先。
- 轻量批重分配策略提升训练速度，适合复杂交通场景建模。
本文提出ARTEMIS，一种结合自回归轨迹规划与专家混合（Mixture-of-Experts, MoE）的端到端自动驾驶框架。传统模块化方法存在误差传播问题，而现有端到端模型多采用静态一次性推理，难以捕捉环境动态变化。ARTEMIS通过逐序列生成轨迹点，在保留关键时间依赖性的同时，将场景相关的查询动态路由至专业专家网络。该设计有效缓解了引导信息模糊时的轨迹质量下降问题，并克服了单一网络架构在处理多样化驾驶场景时的表征局限。此外，我们引入轻量级批重分配策略，显著提升MoE模型训练速度。在NAVSIM数据集上的实验表明，ARTEMIS使用ResNet-34骨干网络时，取得87.0 PDMS和83.1 EPDMS的优异表现，在多个指标上达到当前最优水平。
原文摘要 · Abstract (English)
This paper presents ARTEMIS, an end-to-end autonomous driving framework that combines autoregressive trajectory planning with Mixture-of-Experts (MoE). Traditional modular methods suffer from error propagation, while existing end-to-end models typically employ static one-shot inference paradigms that inadequately capture the dynamic changes of the environment. ARTEMIS takes a different method by generating trajectory waypoints sequentially, preserves critical temporal dependencies while dynamically routing scene-specific queries to specialized expert networks. It effectively relieves trajectory quality degradation issues encountered when guidance information is ambiguous, and overcomes the inherent representational limitations of singular network architectures when processing diverse driving scenarios. Additionally, we use a lightweight batch reallocation strategy that significantly improves the training speed of the Mixture-of-Experts model. Through experiments on the NAVSIM dataset, ARTEMIS exhibits superior competitive performance, achieving 87.0 PDMS and 83.1 EPDMS with ResNet-34 backbone, demonstrates state-of-the-art performance on multiple metrics.
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。