cs.AI updates on arXiv.org 07月28日 12:42
PatchTraj: Dynamic Patch Representation Learning for Time-Frequency Trajectory Prediction
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出PatchTraj,一种基于动态补丁的轨迹预测框架,解决现有方法在建模人类运动动力学和时间表示上的不足,通过多尺度轨迹分割和跨模态注意力机制实现高效轨迹预测。

arXiv:2507.19119v1 Announce Type: cross Abstract: Pedestrian trajectory prediction is crucial for autonomous driving and robotics. While existing point-based and grid-based methods expose two key limitations: insufficiently modeling human motion dynamics, as they fail to balance local motion details with long-range spatiotemporal dependencies, and the time representation lacks interaction with the frequency domain in modeling trajectory sequences. To address these challenges, we propose PatchTraj, a dynamic patch-based trajectory prediction framework that unifies time-domain and frequency-domain representations. Specifically, we decompose the trajectory into raw time sequences and frequency components, employing dynamic patch partitioning for multi-scale trajectory segmentation to capture hierarchical motion patterns. Each patch is processed by an adaptive embedding layer with scale-aware feature extraction, followed by hierarchical feature aggregation to model both fine-grained and long-range dependencies. The outputs of two branches interact via cross-modal attention, enabling complementary fusion of temporal and spectral cues. Finally, a Transformer encoder-decoder integrates both modalities to autoregressively predict future trajectories. Extensive experiments on ETH-UCY, SDD, NBA, and JRDB datasets demonstrate that our method achieves state-of-the-art performance with high efficiency.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

轨迹预测 动态补丁 多尺度分割 跨模态注意力 Transformer
相关文章