A High-Fidelity Digital Twin for Robotic Manipulation Based on 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Ziyang, Bao, Lingfan, Peng, Tianhu, Sun, Jingcheng, Zhou, Chengxu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909010965299200
author Sun, Ziyang
Bao, Lingfan
Peng, Tianhu
Sun, Jingcheng
Zhou, Chengxu
author_facet Sun, Ziyang
Bao, Lingfan
Peng, Tianhu
Sun, Jingcheng
Zhou, Chengxu
contents Developing high-fidelity, interactive digital twins is crucial for enabling closed-loop motion planning and reliable real-world robot execution, which are essential to advancing sim-to-real transfer. However, existing approaches often suffer from slow reconstruction, limited visual fidelity, and difficulties in converting photorealistic models into planning-ready collision geometry. We present a practical framework that constructs high-quality digital twins within minutes from sparse RGB inputs. Our system employs 3D Gaussian Splatting (3DGS) for fast, photorealistic reconstruction as a unified scene representation. We enhance 3DGS with visibility-aware semantic fusion for accurate 3D labelling and introduce an efficient, filter-based geometry conversion method to produce collision-ready models seamlessly integrated with a Unity-ROS2-MoveIt physics engine. In experiments with a Franka Emika Panda robot performing pick-and-place tasks, we demonstrate that this enhanced geometric accuracy effectively supports robust manipulation in real-world trials. These results demonstrate that 3DGS-based digital twins, enriched with semantic and geometric consistency, offer a fast, reliable, and scalable path from perception to manipulation in unstructured environments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03200
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A High-Fidelity Digital Twin for Robotic Manipulation Based on 3D Gaussian Splatting
Sun, Ziyang
Bao, Lingfan
Peng, Tianhu
Sun, Jingcheng
Zhou, Chengxu
Robotics
Developing high-fidelity, interactive digital twins is crucial for enabling closed-loop motion planning and reliable real-world robot execution, which are essential to advancing sim-to-real transfer. However, existing approaches often suffer from slow reconstruction, limited visual fidelity, and difficulties in converting photorealistic models into planning-ready collision geometry. We present a practical framework that constructs high-quality digital twins within minutes from sparse RGB inputs. Our system employs 3D Gaussian Splatting (3DGS) for fast, photorealistic reconstruction as a unified scene representation. We enhance 3DGS with visibility-aware semantic fusion for accurate 3D labelling and introduce an efficient, filter-based geometry conversion method to produce collision-ready models seamlessly integrated with a Unity-ROS2-MoveIt physics engine. In experiments with a Franka Emika Panda robot performing pick-and-place tasks, we demonstrate that this enhanced geometric accuracy effectively supports robust manipulation in real-world trials. These results demonstrate that 3DGS-based digital twins, enriched with semantic and geometric consistency, offer a fast, reliable, and scalable path from perception to manipulation in unstructured environments.
title A High-Fidelity Digital Twin for Robotic Manipulation Based on 3D Gaussian Splatting
topic Robotics
url https://arxiv.org/abs/2601.03200