CarPLAN: 基于动态场景感知的上下文自适应与鲁棒规划
CarPLAN: Context-Adaptive and Robust Planning with Dynamic Scene Awareness for Autonomous Driving
AI总结：
CarPLAN通过位移感知预测编码和上下文自适应多专家解码器，提升自动驾驶在复杂场景中的鲁棒性和适应性规划能力。
摘要：
模仿学习（IL）因其数据效率和对真实世界驾驶数据的访问而广泛用于自动驾驶中的运动规划。为了安全和鲁棒的现实驾驶，基于IL的规划需要捕捉现实数据中复杂的驾驶情境，并实现上下文自适应决策，而不是仅依赖专家轨迹模仿。本文提出CarPLAN，一种新颖的基于IL的运动规划框架，明确增强了驾驶情境理解，并在多样的交通场景中实现适应性规划。我们的贡献是双方面的：我们引入位移感知预测编码（DPE）以通过预测自动驾驶车辆（AV）与周围场景元素之间的未来位移向量来提高模型的空间意识。这使得规划器在生成轨迹时能够考虑相对间距。除了标准的模仿损失外，我们还引入了一个增强的损失项，捕捉位移预测误差，确保规划决策考虑来自其他代理的相对距离。为了提高模型处理多样化驾驶情境的能力，我们提出了上下文自适应多专家解码器（CMD），该解码器利用专家混合（MoE）框架。CMD在每个Transformer层根据场景结构动态选择最合适的专家解码器，使在动态环境中实现自适应和情境感知的规划。我们在nuPlan基准上评估了CarPLAN，并展示了在所有闭环模拟指标上的最先进性能。特别是，CarPLAN在具有挑战性的场景如Test14-Hard中表现出鲁棒性，验证了其在复杂驾驶条件下的有效性。此外，对Waymax基准的额外实验进一步展示了其在不同基准设置中的泛化能力。
英文摘要：
Imitation learning (IL) is widely used for motion planning in autonomous driving due to its data efficiency and access to real-world driving data. For safe and robust real-world driving, IL-based planning requires capturing the complex driving contexts inherent in real-world data and enabling context-adaptive decision-making, rather than relying solely on expert trajectory imitation. In this paper, we propose CarPLAN, a novel IL-based motion planning framework that explicitly enhances driving context understanding and enables adaptive planning across diverse traffic scenarios. Our contributions are twofold: We introduce Displacement-Aware Predictive Encoding (DPE) to improve the model's spatial awareness by predicting future displacement vectors between the Autonomous Vehicle (AV) and surrounding scene elements. This allows the planner to account for relational spacing when generating trajectories. In addition to the standard imitation loss, we incorporate an augmented loss term that captures displacement prediction errors, ensuring planning decisions consider relative distances from other agents. To improve the model's ability to handle diverse driving contexts, we propose Context-Adaptive Multi-Expert Decoder (CMD), which leverages the Mixture of Experts (MoE) framework. CMD dynamically selects the most suitable expert decoders based on scene structure at each Transformer layer, enabling adaptive and context-aware planning in dynamic environments. We evaluate CarPLAN on the nuPlan benchmark and demonstrate state-of-the-art performance across all closed-loop simulation metrics. In particular, CarPLAN exhibits robust performance on challenging scenarios such as Test14-Hard, validating its effectiveness in complex driving conditions. Additional experiments on the Waymax benchmark further demonstrate its generalization capability across different benchmark settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
