logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Language-Embedded 6D Pose Estimation for Tool Manipulation

delete2025-09-01
delete0
PRE
AI
Y
Yuyang Tu
Y
Yunlong Wang
H
Hui Zhang
W
Wenkai Chen
张
张建伟 (Jianwei Zhang)
DOI：10.1109/LRA.2025.3587559delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
机器人工具操作需要在视觉挑战条件下（如形状变化和遮挡）理解任务相关的语义。本文提出了一种新颖的语言嵌入语义6D位姿估计框架，该框架将自然语言指令与3D点云数据相结合，以实现工具功能部件的类别级6D位姿估计。通过嵌入来自大型语言模型（LLMs）的语义信息并利用基于扩散的位姿估计器，本方法实现了跨多种工具类别的鲁棒泛化。我们介绍了一个全面的合成数据集，该数据集针对工具操作场景进行了设计，并标注了功能部件的6D位姿。在合成数据集和真实机器人上进行的广泛实验表明，本系统能够解释自然语言命令、预测功能部件的位姿，并在操作任务中表现出显著提高的准确性和泛化能力。
Keyword:
6D Pose estimation
dataset generation
large language model (LLM)
robotic manipulation

期刊

I
IEEE Robotics and Automation Letters
IF:
5.3
论文数:
1.9K
被引数:
3.9W

机构

U
university of hamburg
学者数:
3.7W
论文数: 2.9W
被引数: 30
引用论文

引用论文

Semantic Pose Using Deep Networks Trained on Synthetic RGB-D
err2015 IEEE International Conference on Computer Vision (ICCV)
IF0
err2015-12-01
err0
errOAAI
errJeremie Papon; Markus Schoeler
err分享
err收藏
A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators
errIMAGE AND VISION COMPUTING
IF4.2
err2020-04-01
err75
errOAAI
errSahin, Caner; Garcia-Hernando, Guillermo; Sock, Juil; Kim, Tae-Kyun
err分享
err收藏
Category-Level Articulated Object Pose Estimation
err2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2020-06-01
err0
errOAAI
errXiaolong Li; He Wang; Li Yi; Leonidas J. Guibas; A. Lynn Abbott; Shuran Song
err分享
err收藏
Gradient Response Maps for Real-Time Detection of Textureless Objects
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2012-05-01
err0
errOAAI
errS. Hinterstoisser; C. Cagniart; S. Ilic; P. Sturm; N. Navab; P. Fua; V. Lepetit
err分享
err收藏
On the Continuity of Rotation Representations in Neural Networks关于神经网络中旋转表示的连续性
err2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2019-06-01
err0
PREAI
errYi Zhou; Connelly Barnes; Jingwan Lu; Jimei Yang; Hao Li
err分享
err收藏
GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable PartsGAPartNet：通过通用且可执行部件实现跨类别、领域泛化的物体感知与操作
err2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2023-06-01
err0
errOAAI
errHaoran Geng; Helin Xu; Chengyang Zhao; Chao Xu; Li Yi; Siyuan Huang; He Wang
err分享
err收藏
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
errRobotics: Science and Systems XIV
IF0
err2018-06-26
err0
errOAAI
errYu Xiang; Tanner Schmidt; Venkatraman Narayanan; Dieter Fox
err分享
err收藏
RobotGPT: Robot Manipulation Learning From ChatGPT
errIEEE Robotics and Automation Letters
IF0
err2024-03-01
err0
errOAAI
errYixiang Jin; Dingzhe Li; Yong A; Jun Shi; Peng Hao; Fuchun Sun; Jianwei Zhang; Bin Fang
err分享
err收藏
SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation
err2021 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2021-10-01
err0
PREAI
errKai Chen; Qi Dou
err分享
err收藏
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errWei Chen; Xi Jia; Hyung Jin Chang; Jinming Duan; Linlin Shen; Ales Leonardis
err分享
err收藏
学者 查看更多内容