arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07232cs.LG
收藏

UVTM:基于 ST 特征域生成的通用车辆轨迹建模

UVTM: Universal Vehicle Trajectory Modeling with ST Feature Domain Generation

Aalborg University(奥尔堡大学);Beijing Jiaotong University(北京交通大学)

Yan Lin, Jilin Hu, Shengnan Guo, Bin Yang, Christian S. Jensen, Youfang Lin, Huaiyu Wan

AI总结:

本文提出通用车辆轨迹模型 UVTM,通过三个可独立掩码生成的 ST 特征域及由稀疏不完整轨迹重建稠密完整轨迹的预训练方法,提升多任务与缺失特征场景下的轨迹建模能力。

摘要:

车辆移动通常以 GPS 轨迹的形式被记录,即带有时间戳的 GPS 位置序列。此类数据被广泛用于行程时间估计、轨迹恢复和轨迹预测等多种任务。一个通用的车辆轨迹模型可以应用于不同任务,从而无需维护多个专用模型,进而降低计算和存储成本。然而,当轨迹特征的完整性受损时,即在仅有部分特征可用或轨迹稀疏的场景中,构建这样的模型具有挑战性。为应对这些挑战,我们提出了通用车辆轨迹模型(Universal Vehicle Trajectory Model,UVTM),它能够有效适应不同任务,而无需过多重新训练。UVTM 包含两项专门设计。首先,它将轨迹特征划分为三个不同的域。每个域都可以被独立掩码和生成,以适应仅有部分特征可用的任务。其次,UVTM 通过从稀疏且特征不完整的对应轨迹重建稠密、特征完整的轨迹进行预训练,使其即使在轨迹特征完整性受损时也能取得强劲性能。我们在三个真实世界车辆轨迹数据集上进行了涉及四个具有代表性的轨迹相关任务的实验,这些实验揭示了 UVTM 的性能,并提供证据表明它能够实现其目标。

英文摘要:

Vehicle movement is frequently captured in the form of GPS trajectories, i.e., sequences of timestamped GPS locations. Such data is widely used for various tasks such as travel-time estimation, trajectory recovery, and trajectory prediction. A universal vehicle trajectory model could be applied to different tasks, removing the need to maintain multiple specialized models, thereby reducing computational and storage costs. However, creating such a model is challenging when the integrity of trajectory features is compromised, i.e., in scenarios where only partial features are available or the trajectories are sparse. To address these challenges, we propose the Universal Vehicle Trajectory Model (UVTM), which can effectively adapt to different tasks without excessive retraining. UVTM incorporates two specialized designs. First, it divides trajectory features into three distinct domains. Each domain can be masked and generated independently to accommodate tasks with only partially available features. Second, UVTM is pre-trained by reconstructing dense, feature-complete trajectories from sparse, feature-incomplete counterparts, enabling strong performance even when the integrity of trajectory features is compromised. Experiments involving four representative trajectory-related tasks on three real-world vehicle trajectory datasets provide insight into the performance of UVTM and offer evidence that it is capable of meeting its objectives.

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。

↑