Sep 2026· IJCAI/ECAI· pp. 2915-2923· 0 citations· 28 references
Computer Science
TL;DR
RNTrajGen follows a two-stage generation strategy: it first generates a sequence of road segments to ensure strict topological alignment, and then infers the moving ratios of trajectory points along road segments to capture fine-grained movement characteristics.
Abstract
Trajectory generation is a pivotal technique for mitigating data sparsity, but existing methods struggle to simultaneously achieve strict road network alignment and capture realistic movement characteristics. To bridge this gap, we propose RNTrajGen, a two-stage fine-grained trajectory generation framework constrained by road networks. Specifically, we first develop a Road Network Knowledge-Enhanced Encoder (RNKEE) to provide semantically rich representations for trajectory generation. By leveraging graph attention networks, RNKEE encodes static prior knowledge of the road network while integrating self-supervised learning to extract latent movement patterns from real-world trajectories. Subsequently, RNTrajGen follows a two-stage generation strategy: it first generates a sequence of road segments to ensure strict topological alignment, and then infers the moving ratios of trajectory points along road segments to capture fine-grained movement characteristics. Extensive experiments on two real-world datasets demonstrate that RNTrajGen significantly outperforms state-of-the-art baselines, and the generated trajectories exhibit high utility in downstream prediction tasks. Our code is available at https://github.com/jkzh986/RNTrajGen.
With the widespread application of trajectory data in areas such as traffic management and route planning, efficiently computing trajectory similarity for fast retrieval has become a critical challenge. Existing methods for trajectory similarity measurement often face issues of low computational efficiency and poor sca...
Shao-Xuan Gu, Hui Zhang, Lei Li et al.· ACM Transactions on Knowledg...· 0 citations
Trajectory prediction, as a critical component of autonomous driving systems, has attracted considerable attention in recent years. Existing prediction methods typically focus on extracting richer scene representations or introducing trajectory-level guidance through destinations, goals, or motion modes. However, futur...
This work proposes AutoPRL, an effective and efficient self-supervised PRL framework that integrates three key components that improves training efficiency by disentangling the optimization of positive and negative pairs across node- and path-level views, enabling more stable contrastive learning.
Sean Bin Yang, Ying Sun, Yun-Yao Cheng et al.· IEEE Transactions on Knowled...· 0 citations
Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cost but poses a capacity allocation problem: a student must match the teacher's iterative generation with far less sequential computation. Existing trajectory methods ask...
Lang Feng, Péter Karkus, M. Igl et al.· 0 citations
Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networ...
Joseph Natter, Long Vu, Yi-Fan Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.