Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Taketsugu, Hiromu, Oba, Takeru, Maeda, Takahiro, Nobuhara, Shohei, Ukita, Norimichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916659201048576
author Taketsugu, Hiromu
Oba, Takeru
Maeda, Takahiro
Nobuhara, Shohei
Ukita, Norimichi
author_facet Taketsugu, Hiromu
Oba, Takeru
Maeda, Takahiro
Nobuhara, Shohei
Ukita, Norimichi
contents Humans can predict future human trajectories even from momentary observations by using human pose-related cues. However, previous Human Trajectory Prediction (HTP) methods leverage the pose cues implicitly, resulting in implausible predictions. To address this, we propose Locomotion Embodiment, a framework that explicitly evaluates the physical plausibility of the predicted trajectory by locomotion generation under the laws of physics. While the plausibility of locomotion is learned with an indifferentiable physics simulator, it is replaced by our differentiable Locomotion Value function to train an HTP network in a data-driven manner. In particular, our proposed Embodied Locomotion loss is beneficial for efficiently training a stochastic HTP network using multiple heads. Furthermore, the Locomotion Value filter is proposed to filter out implausible trajectories at inference. Experiments demonstrate that our method enhances even the state-of-the-art HTP methods across diverse datasets and problem settings. Our code is available at: https://github.com/ImIntheMiddle/EmLoco.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
Taketsugu, Hiromu
Oba, Takeru
Maeda, Takahiro
Nobuhara, Shohei
Ukita, Norimichi
Computer Vision and Pattern Recognition
Humans can predict future human trajectories even from momentary observations by using human pose-related cues. However, previous Human Trajectory Prediction (HTP) methods leverage the pose cues implicitly, resulting in implausible predictions. To address this, we propose Locomotion Embodiment, a framework that explicitly evaluates the physical plausibility of the predicted trajectory by locomotion generation under the laws of physics. While the plausibility of locomotion is learned with an indifferentiable physics simulator, it is replaced by our differentiable Locomotion Value function to train an HTP network in a data-driven manner. In particular, our proposed Embodied Locomotion loss is beneficial for efficiently training a stochastic HTP network using multiple heads. Furthermore, the Locomotion Value filter is proposed to filter out implausible trajectories at inference. Experiments demonstrate that our method enhances even the state-of-the-art HTP methods across diverse datasets and problem settings. Our code is available at: https://github.com/ImIntheMiddle/EmLoco.
title Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17267