References & Citations
Computer Science > Machine Learning
Title: GTM: General Trajectory Modeling with Auto-regressive Generation of Feature Domains
(Submitted on 11 Feb 2024 (v1), revised 5 Mar 2024 (this version, v2), latest version 23 Apr 2024 (v3))
Abstract: Vehicle movement is frequently captured in the form of trajectories, i.e., sequences of timestamped locations. Numerous methods exist that target different tasks involving trajectories such as travel-time estimation, trajectory recovery, and trajectory prediction. However, most methods target only one specific task and cannot be generalized to other tasks. Moreover, existing methods often perform poorly on long trajectories, while also underperforming on re-sampled, sparse trajectories.
To address these shortcomings, we propose the General Trajectory Model (GTM) that aims to support different tasks based on regular and sparse trajectories without the need for retraining or extra prediction modules. GTM is designed expressly to achieve adaptability and robustness. First, GTM separates the features in trajectories into three distinct domains, such that each domain can be masked and generated independently to meet specific input and output requirements of a given task. Second, GTM is pre-trained by reconstructing densely sampled trajectories given re-sampled sparse counterparts. This process enables GTM to extract detailed spatio-temporal and road segment information from sparse trajectories, ensuring consistent performance when trajectories are sparse. Experiments involving three representative trajectory-related tasks on two real-world trajectory datasets provide insight into the intended properties performance of GTM and offer evidence that GTM is capable of meeting its objectives.
Submission history
From: Yan Lin [view email][v1] Sun, 11 Feb 2024 15:49:50 GMT (4321kb,D)
[v2] Tue, 5 Mar 2024 07:11:39 GMT (4373kb,D)
[v3] Tue, 23 Apr 2024 06:57:40 GMT (6797kb,D)
Link back to: arXiv, form interface, contact.