Cross-Domain Transfer Learning using Attention Latent Features for Multi-Agent Trajectory Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Loh, Jia Quan, Luo, Xuewen, Ding, Fan, Tew, Hwa Hui, Loo, Junn Yong, Ding, Ze Yang, Susilawati, Susilawati, Tan, Chee Pin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912115449659392
author Loh, Jia Quan
Luo, Xuewen
Ding, Fan
Tew, Hwa Hui
Loo, Junn Yong
Ding, Ze Yang
Susilawati, Susilawati
Tan, Chee Pin
author_facet Loh, Jia Quan
Luo, Xuewen
Ding, Fan
Tew, Hwa Hui
Loo, Junn Yong
Ding, Ze Yang
Susilawati, Susilawati
Tan, Chee Pin
contents With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are often tailored to specific traffic networks at particular time periods. Consequently, deep learning models trained on one network may struggle to generalize effectively to unseen networks. To address this, we proposed a novel spatial-temporal trajectory prediction framework that performs cross-domain adaption on the attention representation of a Transformer-based model. A graph convolutional network is also integrated to construct dynamic graph feature embeddings that accurately model the complex spatial-temporal interactions between the multi-agent vehicles across multiple traffic domains. The proposed framework is validated on two case studies involving the cross-city and cross-period settings. Experimental results show that our proposed framework achieves superior trajectory prediction and domain adaptation performances over the state-of-the-art models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06087
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Domain Transfer Learning using Attention Latent Features for Multi-Agent Trajectory Prediction
Loh, Jia Quan
Luo, Xuewen
Ding, Fan
Tew, Hwa Hui
Loo, Junn Yong
Ding, Ze Yang
Susilawati, Susilawati
Tan, Chee Pin
Artificial Intelligence
Robotics
With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are often tailored to specific traffic networks at particular time periods. Consequently, deep learning models trained on one network may struggle to generalize effectively to unseen networks. To address this, we proposed a novel spatial-temporal trajectory prediction framework that performs cross-domain adaption on the attention representation of a Transformer-based model. A graph convolutional network is also integrated to construct dynamic graph feature embeddings that accurately model the complex spatial-temporal interactions between the multi-agent vehicles across multiple traffic domains. The proposed framework is validated on two case studies involving the cross-city and cross-period settings. Experimental results show that our proposed framework achieves superior trajectory prediction and domain adaptation performances over the state-of-the-art models.
title Cross-Domain Transfer Learning using Attention Latent Features for Multi-Agent Trajectory Prediction
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2411.06087