提出可动态建模交通交互的决策网络，提升自动驾驶变道与控速表现。
Learning High-Level Decision Making with an Interaction-Aware Attention-Based Network in Autonomous Driving
- 用固定大小潜在空间编码动态车辆特征，支持可调粒度表示。
- 在三种交互场景中性能超越基线，车辆数增多时仍保持稳定。
- 适合需要精细交互理解的复杂驾驶任务，如交叉路口决策。
自动化驾驶中的车道变更与速度控制需应对动态变化的输入规模。当前基于共享编码器的方法（如DeepSet）虽为前沿，但未显式建模交通交互，在高协商需求场景（如交叉口）表现受限。注意力机制虽能捕捉静态与动态代理间的交互，但存在二次方内存与计算开销，且难以控制表征粒度。受Perceiver IO启发，本文提出DecisionPerceiver，将动态代理特征映射至固定大小的潜在空间，通过潜变量数量调控特征粒度，提升大规模网络扩展性。同时，采用更细粒度的动作集设计，进一步增强交互感知带来的性能增益。在三类需不同程度交互感知的驾驶场景中进行广泛评估，结果表明其性能持续领先且具备良好泛化能力。此外，通过不断增加车辆数量的测试验证了该架构的可扩展性。
原文摘要 · Abstract (English)
Reliable learning-based high-level decision making for lane changes and speed control in automated driving must accommodate dynamically sized inputs due to varying scene traffic flow. DeepSet and its variants represent the state of the art among shared-encoder approaches; however, they neglect explicit traffic interaction modeling, limiting performance in negotiation-intensive scenarios such as intersections. Attention-based methods capture interactions among static and dynamic agents, but incur quadratic memory and computational complexity and provide limited control over representation granularity. Inspired by Perceiver IO, an attention-based architecture, DecisionPerceiver, is proposed to project dynamic agent features into a fixed-size latent space, where feature granularity is regulated by the number of latent queries, improving scalability for larger networks. A finer discretization of the action set is further proposed to increase the performance gain due to interaction awareness. Extensive evaluations across three driving scenarios that require different levels of interaction awareness demonstrate consistent performance gains and generalization across various navigation objectives. In addition, the proposed architecture is assessed in scenarios with an increasing number of vehicles to demonstrate scalability.
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。