Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yuzhou, Olaverri-Monreal, Cristina
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.18262
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910232481890304
author Liu, Yuzhou
Olaverri-Monreal, Cristina
author_facet Liu, Yuzhou
Olaverri-Monreal, Cristina
contents Accurate pedestrian trajectory prediction is crucial for autonomous systems operating in complex environments, such as modular buses and delivery robots in suburban or semi-structured areas. Social Spatio-Temporal Graph Convolutional Neural Networks (Social-STGCNN) have shown strong performance by modeling social interactions; however, producing diverse and well-calibrated future trajectories remains challenging. In this work, we build on a Social-STGCNN backbone and introduce a Conditional Variational Autoencoder (CVAE)-based probabilistic formulation to explicitly model multimodal future trajectories. We evaluate the method on the ETH and UCY pedestrian trajectory datasets as well as on a real-world pedestrian dataset collected by a mobile robot. Results show moderate gains on public benchmarks, but more consistent endpoint accuracy and improved trajectory diversity across different crowd configurations. Evaluation on robot-collected data further demonstrates the approach's effectiveness beyond curated benchmarks and supports its applicability in practical deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18262
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
Liu, Yuzhou
Olaverri-Monreal, Cristina
Robotics
Accurate pedestrian trajectory prediction is crucial for autonomous systems operating in complex environments, such as modular buses and delivery robots in suburban or semi-structured areas. Social Spatio-Temporal Graph Convolutional Neural Networks (Social-STGCNN) have shown strong performance by modeling social interactions; however, producing diverse and well-calibrated future trajectories remains challenging. In this work, we build on a Social-STGCNN backbone and introduce a Conditional Variational Autoencoder (CVAE)-based probabilistic formulation to explicitly model multimodal future trajectories. We evaluate the method on the ETH and UCY pedestrian trajectory datasets as well as on a real-world pedestrian dataset collected by a mobile robot. Results show moderate gains on public benchmarks, but more consistent endpoint accuracy and improved trajectory diversity across different crowd configurations. Evaluation on robot-collected data further demonstrates the approach's effectiveness beyond curated benchmarks and supports its applicability in practical deployments.
title On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
topic Robotics
url https://arxiv.org/abs/2605.18262