分离车辆动力学与环境动态建模，提升自动驾驶泛化能力
Vehicle Dynamics Embedded World Models for Autonomous Driving
- 将车辆自身动力学与环境变化解耦建模，避免干扰
- 在模拟环境中显著提升驾驶性能与对车辆差异的鲁棒性
- 适合需要跨车型适配的自动驾驶系统开发者
世界模型作为自动驾驶的有前景方法，通过模拟人类感知与决策过程，可预测并适应动态环境。现有方法通常从图像输入中联合学习自车动力学与环境状态转移，导致效率低下且对车辆动力学变化敏感。为此，本文提出车辆动力学嵌入的Dreamer（VDD）方法，将自车动力学与环境动态建模解耦，使世界模型能有效泛化于不同参数的车辆。此外，引入部署时策略调整（PAD）和训练时策略增强（PAT）两项策略，进一步提升策略鲁棒性。在模拟环境中的全面实验表明，该模型显著优于现有方法，在驾驶表现与动力学变化鲁棒性上均有提升。
原文摘要 · Abstract (English)
World models have gained significant attention as a promising approach for autonomous driving. By emulating human-like perception and decision-making processes, these models can predict and adapt to dynamic environments. Existing methods typically map high-dimensional observations into compact latent spaces and learn optimal policies within these latent representations. However, prior work usually jointly learns ego-vehicle dynamics and environmental transition dynamics from the image input, leading to inefficiencies and a lack of robustness to variations in vehicle dynamics. To address these issues, we propose the Vehicle Dynamics embedded Dreamer (VDD) method, which decouples the modeling of ego-vehicle dynamics from environmental transition dynamics. This separation allows the world model to generalize effectively across vehicles with diverse parameters. Additionally, we introduce two strategies to further enhance the robustness of the learned policy: Policy Adjustment during Deployment (PAD) and Policy Augmentation during Training (PAT). Comprehensive experiments in simulated environments demonstrate that the proposed model significantly improves both driving performance and robustness to variations in vehicle dynamics, outperforming existing approaches.
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。