用自生成闭环轨迹做示范，让自动驾驶模型更稳更准。
RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
- 用模型自己跑出的闭环轨迹当训练数据，缓解部署时误差累积。
- 在真实模拟中驾驶得分提升41%，碰撞减少54%，效果优于旧方法。
- 无需大量强化学习数据，适合端到端自动驾驶等复杂场景。
自动驾驶策略通常通过开环行为克隆人类示范进行训练。然而，这种策略在闭环部署时会遭遇协变量偏移，导致误差不断累积。本文提出闭环滚动生成示范（RoaD），通过利用策略自身生成的闭环轨迹作为额外训练数据，有效缓解协变量偏移问题。在生成轨迹时，RoaD引入专家引导，使轨迹偏向高质量行为，从而生成既具信息量又真实的示范数据用于微调。该方法在数据量上比强化学习少几个数量级，且避免了先前闭环监督微调（CL-SFT）方法的严苛假设，适用于更广泛的场景，包括端到端驾驶。我们在大规模交通仿真基准WOSAC上验证了RoaD的有效性，其表现与先前的CL-SFT方法相当或更优；在基于神经重建的高保真仿真器AlpaSim中，驾驶评分提升41%，碰撞率下降54%。
原文摘要 · Abstract (English)
Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed loop, leading to compounding errors. We introduce Rollouts as Demonstrations (RoaD), a simple and efficient method to mitigate covariate shift by leveraging the policy's own closed-loop rollouts as additional training data. During rollout generation, RoaD incorporates expert guidance to bias trajectories toward high-quality behavior, producing informative yet realistic demonstrations for fine-tuning. This approach enables robust closed-loop adaptation with orders of magnitude less data than reinforcement learning, and avoids restrictive assumptions of prior closed-loop supervised fine-tuning (CL-SFT) methods, allowing broader applications domains including end-to-end driving. We demonstrate the effectiveness of RoaD on WOSAC, a large-scale traffic simulation benchmark, where it performs similar or better than the prior CL-SFT method; and in AlpaSim, a high-fidelity neural reconstruction-based simulator for end-to-end driving, where it improves driving score by 41\% and reduces collisions by 54\%.
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。