ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Han, DongHeun, Kim, Byungmin, Lee, RoUn, Kim, KyeongMin, Hwang, Hyoseok, Kang, HyeongYeop
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909673738731520
author Han, DongHeun
Kim, Byungmin
Lee, RoUn
Kim, KyeongMin
Hwang, Hyoseok
Kang, HyeongYeop
author_facet Han, DongHeun
Kim, Byungmin
Lee, RoUn
Kim, KyeongMin
Hwang, Hyoseok
Kang, HyeongYeop
contents Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended force levels. We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions, faithfully reflecting the user's grip force intention. Instead of mimicking predefined motion datasets, ForceGrip uses generated training scenarios-randomizing object shapes, wrist movements, and trigger input flows-to challenge the agent with a broad spectrum of physical interactions. To effectively learn from these complex tasks, we employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization. This progressive strategy ensures stable hand-object contact, adaptive force control based on user inputs, and robust handling under dynamic conditions. Additionally, a proximity reward function enhances natural finger motions and accelerates training convergence. Quantitative and qualitative evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods. Demo videos are available as supplementary material and the code is provided at https://han-dongheun.github.io/ForceGrip.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation
Han, DongHeun
Kim, Byungmin
Lee, RoUn
Kim, KyeongMin
Hwang, Hyoseok
Kang, HyeongYeop
Robotics
Graphics
Human-Computer Interaction
Machine Learning
Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended force levels. We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions, faithfully reflecting the user's grip force intention. Instead of mimicking predefined motion datasets, ForceGrip uses generated training scenarios-randomizing object shapes, wrist movements, and trigger input flows-to challenge the agent with a broad spectrum of physical interactions. To effectively learn from these complex tasks, we employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization. This progressive strategy ensures stable hand-object contact, adaptive force control based on user inputs, and robust handling under dynamic conditions. Additionally, a proximity reward function enhances natural finger motions and accelerates training convergence. Quantitative and qualitative evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods. Demo videos are available as supplementary material and the code is provided at https://han-dongheun.github.io/ForceGrip.
title ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation
topic Robotics
Graphics
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2503.08061