Encoding Agent Trajectories as Representations with Sequence Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tsiligkaridis, Athanasios, Kalinowski, Nicholas, Li, Zhongheng, Hou, Elizabeth
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917801229287424
author Tsiligkaridis, Athanasios
Kalinowski, Nicholas
Li, Zhongheng
Hou, Elizabeth
author_facet Tsiligkaridis, Athanasios
Kalinowski, Nicholas
Li, Zhongheng
Hou, Elizabeth
contents Spatiotemporal data faces many analogous challenges to natural language text including the ordering of locations (words) in a sequence, long range dependencies between locations, and locations having multiple meanings. In this work, we propose a novel model for representing high dimensional spatiotemporal trajectories as sequences of discrete locations and encoding them with a Transformer-based neural network architecture. Similar to language models, our Sequence Transformer for Agent Representation Encodings (STARE) model can learn representations and structure in trajectory data through both supervisory tasks (e.g., classification), and self-supervisory tasks (e.g., masked modelling). We present experimental results on various synthetic and real trajectory datasets and show that our proposed model can learn meaningful encodings that are useful for many downstream tasks including discriminating between labels and indicating similarity between locations. Using these encodings, we also learn relationships between agents and locations present in spatiotemporal data.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09204
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Encoding Agent Trajectories as Representations with Sequence Transformers
Tsiligkaridis, Athanasios
Kalinowski, Nicholas
Li, Zhongheng
Hou, Elizabeth
Machine Learning
Artificial Intelligence
Computation and Language
Spatiotemporal data faces many analogous challenges to natural language text including the ordering of locations (words) in a sequence, long range dependencies between locations, and locations having multiple meanings. In this work, we propose a novel model for representing high dimensional spatiotemporal trajectories as sequences of discrete locations and encoding them with a Transformer-based neural network architecture. Similar to language models, our Sequence Transformer for Agent Representation Encodings (STARE) model can learn representations and structure in trajectory data through both supervisory tasks (e.g., classification), and self-supervisory tasks (e.g., masked modelling). We present experimental results on various synthetic and real trajectory datasets and show that our proposed model can learn meaningful encodings that are useful for many downstream tasks including discriminating between labels and indicating similarity between locations. Using these encodings, we also learn relationships between agents and locations present in spatiotemporal data.
title Encoding Agent Trajectories as Representations with Sequence Transformers
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.09204