TSMini is a trajectory similarity learning model that introduces a sub-view modeling mechanism and a k‑nearest‑neighbor‑based loss to capture multi‑granularity trajectory patterns and relative similarity ranks. These innovations allow TSMini to approximate conventional trajectory similarity measures with high accuracy. Experiments demonstrate that TSMini outperforms state‑of‑the‑art models by an average of 15% on widely used similarity metrics.
By Yanchuan Chang, Dingyang Lyu, Xu Cai, Christian S. Jensen, Jianzhong Qi
arXiv:2606. 17978v1 Announce Type: new Abstract: Trajectory similarity is a fundamental task in analyzing mobility patterns, essential for applications such as route pattern extraction, mobility prediction, and anomaly detection.
By Ruixin Song, Md Mahbub Alam, Zahra Sadeghi, Amilcar Soares, Jos\'e F. Rodrigues-Jr, Gabriel Spadon
arXiv:2608. 13495v1 Announce Type: cross Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis.
By Yi-Chung Chen, Philip Jacobson, Tom Lampo, Yiren Lu, Jin Yao, David I. Inouye, Jing Gao, Danhua Guo, Burhan Yaman
WALT introduces a method to align latent trajectories with pretrained driving world models, creating a compact generative trajectory space that preserves action-relevant semantics without altering the original model. The approach uses a dual-branch autoencoder to map raw waypoints into this latent space and transfers visual world knowledge into trajectory representations. Experiments on NAVSIM benchmarks show modest performance gains and a 30.5% reduction in planner FLOPs, indicating that maintaining world representations while extracting action-relevant information can improve trajectory planning efficiency.
By Mingkai Jia, Jiaxin Guo, Zhijian Shu, Jiawei Xu, Mingxiao Li, Jintao Cheng, Ping Tan, Wei Yin
arXiv:2510. 14819v3 Announce Type: replace-cross Abstract: Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis.
By Ji Cao, Yu Wang, Tongya Zheng, Jie Song, Qinghong Guo, Zujie Ren, Canghong Jin, Gang Chen, Mingli Song
arXiv:2609.07206v1 Announce Type: cross
Abstract: Trajectory representation learning underpins a wide range of trajectory analytics tasks; however, most existing self-supervised approaches, whether d...
By Sean Bin Yang, Ying Sun, Jilin Hu, Zongyi Xu, Kristian Torp, Hua Lu, Bin Yang, Christian S. Jensen
arXiv:2507. 00028v2 Announce Type: replace Abstract: The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns.
By Lihuan Li, Hao Xue, Shuang Ao, Yang Song, Flora Salim
arXiv:2603. 27044v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space.
By Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
DGCPath is a Distribution‑Aware Generative Contrastive framework designed for self‑supervised path representation learning. It combines a diffusion‑based view generator, a variational contrastive mechanism that aligns latent features at the distribution level, and a generative cross‑supervision module for view‑level consistency. Experiments on three real‑world trajectory datasets show that DGCPath surpasses state‑of‑the‑art baselines on two downstream tasks, indicating stronger generalization and representation effectiveness.
By Sean Bin Yang, Hao Miao, Zongyi Xu, Jilin Hu, Xiangmeng Wang, Hua Lu, Bin Yang, Christian S. Jensen
arXiv:2607. 09428v1 Announce Type: cross Abstract: Large-scale autonomous-driving datasets contain vast numbers of recorded scenarios, creating a need for efficient retrieval methods that can identify situations similar to a given query.
By Tam\'as Matuszka, Andr\'as Tam\'asy, Bal\'azs Szol\'ar
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.
By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja
arXiv:2608. 14125v1 Announce Type: new Abstract: LeWM is a lightweight visual world model that learns latent dynamics end-to-end from pixels and ranks candidate action sequences by the distance between their predicted endpoints and the goal.
By Xiaodi Huang, Ziyi Ding, Jingtian Wan, Yuchen Liu, Yuan Zhang, Xiao-Ping Zhang, Jiayu Chen, Zhang Zhang, Tao Huang