用分块扩散模型生成更真实、更快的交通轨迹。
TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
- 将轨迹建模为离散路段序列，用分块扩散加速去噪过程。
- 在三个城市数据集上，生成速度比之前快2.8倍，精度高。
- 无需训练即可跨场景迁移，支持未知出行方式生成。
生成高保真合成GPS轨迹在交通规划、城市设计和假设情景模拟中日益重要，尤其在隐私限制导致真实移动数据难以获取的背景下。现有轨迹生成模型在效率与道路网络拓扑忠实度之间存在权衡：连续空间方法生成快但忽略道路结构，而拓扑感知方法依赖基于搜索的自回归解码，限制了生成速度。本文提出TrajDLM，一种基于分块扩散语言模型的拓扑感知轨迹生成框架。该模型将轨迹建模为离散道路段序列，结合分块扩散主干网络实现高效去噪，利用道路网络编码器生成拓扑感知嵌入，并通过拓扑约束采样确保轨迹连贯性与真实性。在三个城市规模数据集上，TrajDLM在细粒度局部相似性指标上表现优异，生成速度较先前工作最高提升2.8倍，并展现出强大的零样本跨域迁移能力，包括未见出行模式。结果表明，分块离散扩散是一种可扩展的准确且高效的轨迹生成方法。代码已开源：https://github.com/cruiseresearchgroup/TrajDLM/
原文摘要 · Abstract (English)
Generating high-fidelity synthetic GPS trajectories is increasingly important for applications in transportation, urban planning, and what-if scenario simulation, especially as privacy concerns limit access to real-world mobility data. Existing trajectory generation models face a trade-off between efficiency and faithfulness to road network topology: continuous-space methods enable fast generation but ignore the road network, while topology-aware approaches rely on search-based autoregressive decoding that limits generation speed. We propose TrajDLM, a topology-aware trajectory generation framework based on block diffusion language models that bridges this gap. TrajDLM models trajectories as sequences of discrete road segments, combining a block diffusion backbone for efficient denoising, topology-aware embeddings from a road network encoder, and topology-constrained sampling to ensure coherent and realistic trajectories. Across three city-scale datasets, TrajDLM achieves strong performance on fine-grained local similarity metrics while being up to $2.8\times$ faster than prior work, and demonstrates strong zero-shot transfer across domains, including unseen transportation modes. These results highlight the effectiveness of block-wise discrete diffusion as a scalable approach to accurate and efficient trajectory generation. Our code is available at https://github.com/cruiseresearchgroup/TrajDLM/
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。