Motion prediction and cost evaluation are vital components in the decision-making system of autonomous vehicles. However, existing methods often ignore the importance of cost learning and treat them as separate modules. In this study, we employ a tree-structured policy planner and propose a differentiable joint training framework for both ego-conditioned prediction and cost models, resulting in a direct improvement of the final planning performance. For conditional prediction, we introduce a query-centric Transformer model that performs efficient ego-conditioned motion prediction. For planning cost, we propose a learnable context-aware cost function with latent interaction features, facilitating differentiable joint learning. We validate our proposed approach using the real-world nuPlan dataset and its associated planning test platform. Our framework not only matches state-of-the-art planning methods but outperforms other learning-based methods in planning quality, while operating more efficiently in terms of runtime. We show that joint training delivers significantly better performance than separate training of the two modules. Additionally, we find that tree-structured policy planning outperforms the conventional single-stage planning approach.

翻译：运动预测与代价评估是自动驾驶决策系统中的关键组成部分。然而现有方法常忽略代价学习的重要性，并将其作为独立模块处理。本研究采用树结构策略规划器，提出针对自车条件预测与代价模型的可微分联合训练框架，从而直接提升最终规划性能。在条件预测方面，我们引入以查询为中心的Transformer模型，实现高效的自车条件运动预测；在规划代价方面，我们提出具有潜在交互特征的可学习上下文感知代价函数，促进可微分联合学习。通过真实世界nuPlan数据集及其配套规划测试平台验证，本框架不仅媲美最先进的规划方法，且在规划质量上优于其他基于学习的方法，同时运行效率更高。实验表明，联合训练较两模块独立训练可显著提升性能。此外，我们发现树结构策略规划优于传统单阶段规划方法。