面向自动驾驶智能体建模的高效等变 Transformer
Efficient Equivariant Transformer for Self-Driving Agent Modeling
用投影几何代数中的多向量表示场景元素，让标准注意力本身携带 SE(2) 等变性，从而省去二次复杂度的成对相对位置编码；做多智能体场景建模、轨迹预测或需要置换/旋转平移等变的视觉任务时，可直接复用这一等变注意力块来降低开销。
原文依据 DriveGATr encodes scene elements as multivectors in the 2D projective geometric algebra
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论准确建模智能体行为是自动驾驶中的一项重要任务。它同时也是一项具有许多对称性的任务，例如对场景中智能体与物体顺序的置换等变，或对整个场景任意旋转平移的等变，即 SE(2) 等变。Transformer 架构是建模这类对称性的常用工具。标准自注意力本身具有置换等变性，而显式的成对相对位置编码一直是引入 SE(2) 等变性的标准做法。然而，该方法带来随智能体数量二次增长的额外开销，限制了其向更大场景和更大批量规模的扩展。在本工作中，我们提出 DriveGATr，一种新的基于 Transformer 的智能体建模架构，它在不引入现有方法计算开销的前提下实现 SE(2) 等变。受几何深度学习近期进展的启发，DriveGATr 将场景元素编码为二维投影几何代数 R*_{2,0,1} 中的多向量，并用堆叠的等变 Transformer 块对其进行处理。关键在于，DriveGATr 通过多向量之间的标准注意力来建模几何关系，从而无需昂贵的显式成对相对位置编码。在 Waymo Open Motion 数据集上的实验表明，DriveGATr 在交通仿真任务上与最优方法相当，并在性能与计算开销之间建立了更优的帕累托前沿。
英文原文摘要 1500 字符
Accurately modeling agent behaviors is an important task in self-driving. It is also a task with many symmetries, such as equivariance to the order of agents and objects in the scene or equivariance to arbitrary roto-translations of the entire scene as a whole; i.e., SE(2)-equivariance. The transformer architecture is a ubiquitous tool for modeling these symmetries. While standard self-attention is inherently permutation equivariant, explicit pairwise relative positional encodings have been the standard for introducing SE(2)-equivariance. However, this approach introduces an additional cost that is quadratic in the number of agents, limiting its scalability to larger scenes and batch sizes. In this work, we propose DriveGATr, a novel transformer-based architecture for agent modeling that achieves SE(2)-equivariance without the computational cost of existing methods. Inspired by recent advances in geometric deep learning, DriveGATr encodes scene elements as multivectors in the 2D projective geometric algebra \mathbb R ^*_ 2,0,1 and processes them with a stack of equivariant transformer blocks. Crucially, DriveGATr models geometric relationships using standard attention between multivectors, eliminating the need for costly explicit pairwise relative positional encodings. Experiments on the Waymo Open Motion Dataset demonstrate that DriveGATr is comparable to the state-of-the-art in traffic simulation and establishes a superior Pareto front for performance vs computational cost.