Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Xiuwei, Ma, Angyuan, Li, Hankun, Yu, Bingyao, Zhu, Zheng, Zhou, Jie, Lu, Jiwen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.08547
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910176927285248
author Xu, Xiuwei
Ma, Angyuan
Li, Hankun
Yu, Bingyao
Zhu, Zheng
Zhou, Jie
Lu, Jiwen
author_facet Xu, Xiuwei
Ma, Angyuan
Li, Hankun
Yu, Bingyao
Zhu, Zheng
Zhou, Jie
Lu, Jiwen
contents Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To achieve this, substantial human demonstrations need to be collected to cover different spatial configurations for training a generalized visuomotor policy via imitation learning. Prior works explore a promising direction that leverages data generation to acquire abundant spatially diverse data from minimal source demonstrations. However, most approaches face significant sim-to-real gap and are often limited to constrained settings, such as fixed-base scenarios and predefined camera viewpoints. In this paper, we propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data. R2RGen is simulator- and rendering-free, thus being efficient and plug-and-play. Specifically, we propose a unified three-stage framework, which (1) pre-processes source demonstrations under different camera setups in a shared 3D space with scene / trajectory parsing; (2) augments objects and robot's position with a group-wise backtracking strategy; (3) aligns the distribution of generated data with real-world 3D sensor using camera-aware post-processing. Empirically, R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08547
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation
Xu, Xiuwei
Ma, Angyuan
Li, Hankun
Yu, Bingyao
Zhu, Zheng
Zhou, Jie
Lu, Jiwen
Robotics
Computer Vision and Pattern Recognition
Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To achieve this, substantial human demonstrations need to be collected to cover different spatial configurations for training a generalized visuomotor policy via imitation learning. Prior works explore a promising direction that leverages data generation to acquire abundant spatially diverse data from minimal source demonstrations. However, most approaches face significant sim-to-real gap and are often limited to constrained settings, such as fixed-base scenarios and predefined camera viewpoints. In this paper, we propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data. R2RGen is simulator- and rendering-free, thus being efficient and plug-and-play. Specifically, we propose a unified three-stage framework, which (1) pre-processes source demonstrations under different camera setups in a shared 3D space with scene / trajectory parsing; (2) augments objects and robot's position with a group-wise backtracking strategy; (3) aligns the distribution of generated data with real-world 3D sensor using camera-aware post-processing. Empirically, R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.
title R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.08547