检索结果-内蒙古大学图书馆

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Koch, Paul Schlüter, Marian Thill, Serge Krüger, Jörg Fraunhofer Institute for Production and System Design Technology Pascalstraße 8-9 Berlin10587 Germany Donders Institute for Brain Cognition and Behavior Radboud University Nijmegen6525 HR Netherlands Technical University Berlin Institute for Machine Tools and Factory Management Pascalstraße 8-9 Berlin10587 Germany

Recently, deep neural networks achieved state-of-the-art results in the subject of 6d object pose estimation for robot manipulation. However, those deep learning methods require expensive training data. Current methods for cost reduction use synthetic data, but rely on expert knowledge and suffer from the domain gap when shifting to the real application. Here, we present a proof of concept for a novel approach towards generating annotated training data for 6d object pose estimation. This approach is designed for learning new objects in operational environments while requiring little interaction and no expertise on the part of the user. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-Nd license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference on Manufacturing Systems 2023.

关键词： 6d object pose estimation Artificial Intelligence data Generation Robot Cognition Robotic Grasping

来源：评论

学校读者我要写书评

暂无评论

ASPP-dF-PVNet: Atrous Spatial Pyramid Pooling and distance-Filtered PVNet for occlusion resistant 6d estimation

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2021年 95卷 116268-116268页

作者： Zhu, Yazhi Wan, Lili Xu, Wanru Wang, Shenghui Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Beijing Key Lab Adv Informat Sci & Network Techno Beijing 100044 Peoples R China

detecting objects and estimating their 6d poses from a single RGB image is quite challenging under severe occlusions. Recently, vector-field based methods have shown certain robustness to occlusion and truncation. Based on the vector-field representation, applying voting strategy to localize 2d keypoints can further reduce the influence of outliers. To improve the effectiveness of vector-field based deep network and voting scheme, we propose Atrous Spatial Pyramid Pooling and distance-Filtered PVNet (ASPP-dF-PVNet), an occlusion resistant framework for 6d object pose estimation. ASPP-dF-PVNet utilizes the effective Atrous Spatial Pyramid Pooling (ASPP) module of deeplabv3 to capture multi-scale features and encode global context information, which improves the accuracy of segmentation and vector-field prediction comparing to the original PVNet, especially under severe occlusions. Considering that the distances between pixels and keypoint hypotheses will affect the voting deviations, we then present a distance-filtered voting scheme which takes the voting distances into consideration to filter out the votes with large deviations. Experiments demonstrate that our method outperforms the state-of-the-art methods by a considerable margin without using pose refinement, and obtains competitive results against the methods with refinement on the LINEMOd and Occlusion LINEMOd datasets.

关键词： 6d object pose estimation Vector fields Voting based keypoint localization Semantic segmentation ASPP

来源：评论

学校读者我要写书评

暂无评论

Graspability-Aware object pose estimation in Cluttered Scenes

引用

IEEE ROBOTICS ANd AUTOMATION LETTERS 2024年第4期9卷 3124-3130页

作者： Hoang, dinh-Cuong Nguyen, Anh-Nhat Vu, Van-duc Nguyen, Thu-Uyen Vu, duy-Quang Ngo, Phuc-Quan Hoang, Ngoc-Anh Phan, Khanh-Toan Tran, duc-Thanh Nguyen, Van-Thiep duong, Quang-Tri Ho, Ngoc-Trung Tran, Cong-Trinh duong, Van-Hiep Mai, Anh-Truong FPT Univ IT Dept Hanoi 10000 Vietnam

object recognition and pose estimation are critical components in autonomous robot manipulation systems, playing a crucial role in enabling robots to interact effectively with the environment. during actual execution, the robot must recognize the object in the current scene, estimate its pose, and then select a feasible grasp pose from the pre-defined grasp configurations. While most existing methods primarily focus on pose estimation, they often neglect the graspability and reachability aspects. This oversight can lead to inefficiencies and failures during execution. In this study, we introduce an innovative graspability-aware object pose estimation framework. Our proposed approach not only estimates the poses of multiple objects in clustered scenes but also identifies graspable areas. This enables the system to concentrate its efforts on specific points or regions of an object that are suitable for grasping. It leverages both depth and color images to extract geometric and appearance features. To effectively combine these diverse features, we have developed an adaptive fusion module. In addition, the fused features are further enhanced through a graspability-aware feature enhancement module. The key innovation of our method lies in improving the discriminability and robustness of the features used for object pose estimation. We have achieved state-of-the-art results on public datasets when compared to several baseline methods. In real robot experiments conducted on a Franka Emika robot arm equipped with an Intel Realsense camera and a two-finger gripper, we consistently achieved high success rates, even in cluttered scenes.

关键词： pose estimation Feature extraction Robots Three-dimensional displays Solid modeling Point cloud compression Geometry 6d object pose estimation grasp detection robot manipulation

来源：评论

学校读者我要写书评

暂无评论

Enhancing object pose estimation for RGB images in cluttered scenes

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-15页

作者： Al-Selwi, Metwalli Ning, Huang Gao, Yin Chao, Yan Li, Qiming Li, Jun Chinese Acad Sci Fujian Inst Res Struct Matter Fuzhou Fujian Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci Quanzhou Inst Equipment Mfg Haixi Inst Quanzhou Fujian Peoples R China Univ Chinese Acad Sci Fujian Coll Fuzhou Fujian Peoples R China

Estimating the 6d pose of objects is crucial for robots to interact with the environment. 6d object pose estimation from RGB images in a cluttered scene and heavy occlusions is a critical issue. Most existing methods use two stages to estimate object pose: First, extract the object features, and then use the PnP/RANSAC method to estimate object pose. However, most of these techniques merely localize a group of key-points by regressing their coordinates, which are vulnerable to occlusion and have poor performance for multi-object pose estimation. These methods cannot directly regress the 6d pose estimation from a loss during training. In this paper, we propose a framework based on convolutional neural network (CNN) and self-attention mechanism as an end-to-end method for single and multi-object 6d pose estimation using RGB images with low computational cost. Our method utilizes feature fusion to extract local features and combines multi-head self-attention (MHSA) with iterative refinement to improve pose estimation performance. Furthermore, our method can be scaled according to computational resources. Our experiments illustrate that our method performs in benchmark datasets the Linemod and Occlusion Linemod and achieves 97.45% and 84.84% in terms of the Add(-S) metric in both datasets, respectively.

关键词： 6d object pose estimation Heavy occlusion Cluttered scenes Convolutional neural networks Self-attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

Towards Robot-Assisted data Generation with Minimal User Interaction for Autonomously Training 6d pose estimation in Operational Environments

引用

Procedia CIRP 2023年 120卷 249-254页

作者： Paul Koch Marian Schlüter Serge Thill Jörg Krüger Fraunhofer Institute for Production and System Design Technology Pascalstraße 8-9 10587 Berlin Germany Donders Institute for Brain Cognition and Behavior Radboud University 6525 HR Nijmegen Netherlands Technical University Berlin Institute for Machine Tools and Factory Management Pascalstraße 8-9 10587 Berlin Germany

关键词： 6d object pose estimation Artificial Intelligence data Generation Robotic Grasping Robot Cognition

来源：评论

学校读者我要写书评

暂无评论

MRC-Net: 6-doF pose estimation with MultiScale Residual Correlation

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Corr...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Yuelong Mao, Yafei Bala, Raja Hadap, Sunil Amazon Inc Seattle WA 98109 USA

ISBN: (纸本)9798350353006

We propose a single-shot approach to determining 6-doF pose of an object with available 3d computer-aided design (CAd) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3d object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between the input image and rendering from first stage. MRC-Net employs a Siamese network with shared weights between both stages to learn embeddings for input and rendered images. To mitigate ambiguity when predicting discrete pose class labels on symmetric objects, we use soft probabilistic labels to define pose class in the first stage. We demonstrate state-of-the-art accuracy, outperforming all competing RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O, YCB-V, and ITOdd. Our method is non-iterative and requires no complex post-processing. Our code and pretrained models are available at https://***/amzn/mrc-net-6d-pose.

关键词： 3d from single image 6d object pose estimation direct pose estimation Geometric deep learning

来源：评论

学校读者我要写书评

暂无评论

GenFlow: Generalizable Recurrent Flow for 6d pose Refinement of Novel objects

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Moon, Sungphill Son, Hyeontae Hur, dongcheol Kim, Sangwook NAVER LABS Meylan France

ISBN: (纸本)9798350353006

despite the progress of learning-based methods for 6d object pose estimation, the trade-off between accuracy and scalability for novel objects still exists. Specifically, previous methods for novel objects do not make good use of the target object's 3d shape information since they focus on generalization by processing the shape indirectly, making them less effective. We present GenFlow, an approach that enables both accuracy and generalization to novel objects with the guidance of the target object's shape. Our method predicts optical flow between the rendered image and the observed image and refines the 6d pose iteratively. It boosts the performance by a constraint of the 3d shape and the generalizable geometric knowledge learned from an end-to-end differentiable system. We further improve our model by designing a cascade network architecture to exploit the multi-scale correlations and coarse-to-fine refinement. GenFlow ranked first on the unseen object pose estimation benchmarks in both the RGB and RGB-d cases. It also achieves performance competitive with existing state-of-the-art methods for the seen object pose estimation with-out any fine-tuning.

关键词： 6d object pose estimation generalization optical flow

来源：评论

学校读者我要写书评

暂无评论

deepIM: deep Iterative Matching for 6d pose estimation

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2020年第3期128卷 657-678页

作者： Li, Yi Wang, Gu Ji, Xiangyang Xiang, Yu Fox, dieter Univ Washington Seattle WA 98195 USA Tsinghua Univ Beijing Peoples R China BNRist Beijing Peoples R China NVIDIA Seattle WA USA

Estimating 6d poses of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the input image can produce accurate results. In this work, we propose a novel deep neural network for 6d pose matching named deepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using a disentangled representation of 3d location and 3d orientation and an iterative training process. Experiments on two commonly used benchmarks for 6d pose estimation demonstrate that deepIM achieves large improvements over state-of-the-art methods. We furthermore show that deepIM is able to match previously unseen objects.

关键词： 3d object recognition 6d object pose estimation object tracking

来源：评论

学校读者我要写书评

暂无评论

Robot-based object pose Auto-annotation System for dexterous Manipulation 14

Robot-based Object Pose Auto-annotation System for Dexterous...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Park, Sunme Kim, Yujin Lee, Seungwon Jung, Mingi Park, Jongbum Korea Electronics Technology Institute Intelligent Robotics Research Center Bucheon Korea Republic of

ISBN: (纸本)9798350313277

To effectively employ robots in real-life scenarios, comprehending information about the surrounding objects is crucial for achieving dexterous manipulations. Since vision-based recognition relies on reliable high-quality annotated data, we present a 6d object pose auto-annotation method based on robot kinematics. This system directly measures object orientation and position through real-world robot operations by applying coordinate transformations among the robot, camera, and object. Leveraging robots enables automatic and precise object pose measurement while minimizing human effort. depending on the robot's posture, capturing various facets of the object becomes straightforward. Furthermore, we account for occlusion caused by various robot hand grip styles to collect a diverse range of visible object portions while maintaining precise poses. The visualization code and data examples are publicly available at https://***/SunmePark/robot-based_annotation." © 2023 IEEE.

关键词： 6d object pose estimation object pose annotation system Occlusion Robot-based auto annotation

来源：评论

学校读者我要写书评

暂无评论

NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Hands 6

NeuralGrasps: Learning Implicit Representations for Grasps o...

引用

6th Conference on Robot Learning (CoRL)

作者： Khargonkar, Ninad Song, Neil Xu, Zesheng Prabhakaran, Balakrishnan Xiang, Yu Univ Texas Dallas Richardson TX 75083 USA St Marks Sch Texas Dallas TX USA

We introduce a neural implicit representation for grasps of objects from multiple robotic hands. different grasps across multiple robotic hands are encoded into a shared latent space. Each latent vector is learned to decode to the 3d shape of an object and the 3d shape of a robotic hand in a grasping pose in terms of the signed distance functions of the two 3d shapes. In addition, the distance metric in the latent space is learned to preserve the similarity between grasps across different robotic hands, where the similarity of grasps is defined according to contact regions of the robotic hands. This property enables our method to transfer grasps between different grippers including a human hand, and grasp transfer has the potential to share grasping skills between robots and enable robots to learn grasping skills from humans. Furthermore, the encoded signed distance functions of objects and grasps in our implicit representation can be used for 6d object pose estimation with grasping contact optimization from partial point clouds, which enables robotic grasping in the real world (1).

关键词： Robot Grasping Neural Implicit Representations Grasp Transfer Grasping Contact Modeling 6d object pose estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：