用可微分仿真器端到端训练自动驾驶控制器，提升泛化与鲁棒性。
Autonomous Vehicle Controllers From End-to-End Differentiable Simulation
- 基于可微分仿真器的解析梯度方法，利用环境动态梯度作为先验指导学习。
- 在Waymo数据集上实现更快、更鲁棒的控制策略，性能显著优于行为克隆。
- 仅需专家轨迹即可训练，适合缺乏动作标签的实际场景应用。
当前自动驾驶控制器学习方法多依赖行为克隆，仅基于历史数据训练，泛化能力差。模拟器虽能拓展数据，但常被视为黑箱，仅用于更新全局状态，导致强化学习算法效率低、样本利用率差且无先验知识。本文利用可微分模拟器，设计解析策略梯度（APG）方法，在大规模Waymo Open Motion Dataset上训练自动驾驶控制器。框架将可微分模拟器融入端到端训练流程，使环境动态的梯度成为有效先验，辅助智能体学习更扎实的策略。结合循环结构，高效传播长时序轨迹中的时间信息。该方法仅需广泛获取的专家轨迹，无需稀缺的动作标签，即可学习出稳健、准确且快速的策略。相比行为克隆，表现出显著更高的性能与对动态噪声的鲁棒性，整体驾驶行为更具人类直观性。
原文摘要 · Abstract (English)
Current methods to learn controllers for autonomous vehicles (AVs) focus on behavioural cloning. Being trained only on exact historic data, the resulting agents often generalize poorly to novel scenarios. Simulators provide the opportunity to go beyond offline datasets, but they are still treated as complicated black boxes, only used to update the global simulation state. As a result, these RL algorithms are slow, sample-inefficient, and prior-agnostic. In this work, we leverage a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers on the large-scale Waymo Open Motion Dataset. Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of the environment dynamics serve as a useful prior to help the agent learn a more grounded policy. We combine this setup with a recurrent architecture that can efficiently propagate temporal information across long simulated trajectories. This APG method allows us to learn robust, accurate, and fast policies, while only requiring widely-available expert trajectories, instead of scarce expert actions. We compare to behavioural cloning and find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
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。