GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qian, Quanhao, Zhao, Guoyang, Zhang, Gongjie, Wang, Jiuniu, Xu, Ran, Gao, Junlong, Zhao, Deli
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909797608062976
author Qian, Quanhao
Zhao, Guoyang
Zhang, Gongjie
Wang, Jiuniu
Xu, Ran
Gao, Junlong
Zhao, Deli
author_facet Qian, Quanhao
Zhao, Guoyang
Zhang, Gongjie
Wang, Jiuniu
Xu, Ran
Gao, Junlong
Zhao, Deli
contents Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D geometry-aware robotic manipulation policy that leverages multi-view input. GP3 employs a spatial encoder to infer dense spatial features from RGB observations, which enable the estimation of depth and camera parameters, leading to a compact yet expressive 3D scene representation tailored for manipulation. This representation is fused with language instructions and translated into continuous actions via a lightweight policy head. Comprehensive experiments demonstrate that GP3 consistently outperforms state-of-the-art methods on simulated benchmarks. Furthermore, GP3 transfers effectively to real-world robots without depth sensors or pre-mapped environments, requiring only minimal fine-tuning. These results highlight GP3 as a practical, sensor-agnostic solution for geometry-aware robotic manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation
Qian, Quanhao
Zhao, Guoyang
Zhang, Gongjie
Wang, Jiuniu
Xu, Ran
Gao, Junlong
Zhao, Deli
Robotics
Artificial Intelligence
Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D geometry-aware robotic manipulation policy that leverages multi-view input. GP3 employs a spatial encoder to infer dense spatial features from RGB observations, which enable the estimation of depth and camera parameters, leading to a compact yet expressive 3D scene representation tailored for manipulation. This representation is fused with language instructions and translated into continuous actions via a lightweight policy head. Comprehensive experiments demonstrate that GP3 consistently outperforms state-of-the-art methods on simulated benchmarks. Furthermore, GP3 transfers effectively to real-world robots without depth sensors or pre-mapped environments, requiring only minimal fine-tuning. These results highlight GP3 as a practical, sensor-agnostic solution for geometry-aware robotic manipulation.
title GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2509.15733