Saved in:
Bibliographic Details
Main Authors: Wang, Honghui, Zhi, Weiming, Batista, Gustavo, Chandra, Rohitash
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.09021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914708586496000
author Wang, Honghui
Zhi, Weiming
Batista, Gustavo
Chandra, Rohitash
author_facet Wang, Honghui
Zhi, Weiming
Batista, Gustavo
Chandra, Rohitash
contents Pedestrian trajectory prediction plays an important role in autonomous driving systems and robotics. Recent work utilizing prominent deep learning models for pedestrian motion prediction makes limited a priori assumptions about human movements, resulting in a lack of explainability and explicit constraints enforced on predicted trajectories. We present a dynamics-based deep learning framework with a novel asymptotically stable dynamical system integrated into a Transformer-based model. We use an asymptotically stable dynamical system to model human goal-targeted motion by enforcing the human walking trajectory, which converges to a predicted goal position, and to provide the Transformer model with prior knowledge and explainability. Our framework features the Transformer model that works with a goal estimator and dynamical system to learn features from pedestrian motion history. The results show that our framework outperforms prominent models using five benchmark human motion datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09021
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning
Wang, Honghui
Zhi, Weiming
Batista, Gustavo
Chandra, Rohitash
Robotics
Pedestrian trajectory prediction plays an important role in autonomous driving systems and robotics. Recent work utilizing prominent deep learning models for pedestrian motion prediction makes limited a priori assumptions about human movements, resulting in a lack of explainability and explicit constraints enforced on predicted trajectories. We present a dynamics-based deep learning framework with a novel asymptotically stable dynamical system integrated into a Transformer-based model. We use an asymptotically stable dynamical system to model human goal-targeted motion by enforcing the human walking trajectory, which converges to a predicted goal position, and to provide the Transformer model with prior knowledge and explainability. Our framework features the Transformer model that works with a goal estimator and dynamical system to learn features from pedestrian motion history. The results show that our framework outperforms prominent models using five benchmark human motion datasets.
title Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning
topic Robotics
url https://arxiv.org/abs/2309.09021