检索结果-内蒙古大学图书馆

FrontierNet: Learning Visual Cues to Explore

IEEE robotics and Automation Letters 2025年第7期10卷 6576-6583页

作者： Sun, Boyang Chen, Hanzhi Leutenegger, Stefan Cadena, Cesar Pollefeys, Marc Blum, Hermann ETH Zurich Computer Vision and Geometry Group Zurich8092 Switzerland Technical University of Munich Mobile Robotics Lab München80333 Germany ETH Zurich Mobile Robotics Lab Zurich8092 Switzerland ETH Zurich Robotic Systems Lab Zurich8092 Switzerland AI Lab Microsoft Mixed Reality Zurich8038 Switzerland University of Bonn Lamarr Institute for ML and AI Robot Perception and Learning Lab Bonn53115 Germany

Exploration of unknown environments is crucial for autonomous robots;it allows them to actively reason and decide on what new data to acquire for different tasks, such as mapping, object discovery, and environmental assessment. Existing solutions, such as frontier-based exploration approaches, rely heavily on 3D map operations, which are limited by map quality and, more critically, often overlook valuable context from visual cues. This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map. We propose a visual-only frontier-based exploration system, with FrontierNet as its core component. FrontierNet is a learning-based model that (i) proposes frontiers, and (ii) predicts their information gain, from posed RGB images enhanced by monocular depth priors. Our approach provides an alternative to existing 3D-dependent goal-extraction approaches, achieving a 15% improvement in early-stage exploration efficiency, as validated through extensive simulations and real-world experiments. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A general framework for lifelong localization and mapping in changing environment

arXiv

引用

arXiv 2021年

作者： Zhao, Min Guo, Xin Song, Le Qin, Baoxing Shi, Xuesong Lee, Gim Hee Sun, Guanghui Gaussian Robotics Shanghai China Intel Labs China Beijing China Computer Vision and Robotic Perception Lab Department of Computer Science School of Computing National University of Singapore Singapore Singapore Department of Control Science and Engineering Harbin Institute of Technology China

The environment of most real-world scenarios such as malls and supermarkets changes at all times. A prebuilt map that does not account for these changes becomes out-of-date easily. Therefore, it is necessary to have an up-todate model of the environment to facilitate long-term operation of a robot. To this end, this paper presents a general lifelong simultaneous localization and mapping (SLAM) framework. Our framework uses a multiple session map representation, and exploits an efficient map updating strategy that includes map building, pose graph refinement and sparsification. To mitigate the unbounded increase of memory usage, we propose a maptrimming method based on the Chow-Liu maximum-mutualinformation spanning tree. The proposed SLAM framework has been comprehensively validated by over a month of robot deployment in real supermarket environment. Furthermore, we release the dataset collected from the indoor and outdoor changing environment with the hope to accelerate lifelong SLAM research in the community. Our dataset is available at https://***/sanduan168/lifelong-SLAM-dataset. © 2021, CC BY.

关键词： Retail stores

来源：评论

学校读者我要写书评

暂无评论

Robust 6d object pose estimation by learning rgb-d features

arXiv

引用

arXiv 2020年

作者： Tian, Meng Pan, Liang Ang Jr, Marcelo H. Lee, Gim Hee Department of Mechanical Engineering National University of Singapore Computer Vision and Robotic Perception Lab Department of Computer Science School of Computing National University of Singapore

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of symmetric objects. In this work, we propose a novel discretecontinuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Additionally, the object location is detected by aggregating point-wise vectors pointing to the 3D center. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches. Our code is available at https://***/ mentian/object-posenet. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust 6D Object Pose Estimation by Learning RGB-D Features

Robust 6D Object Pose Estimation by Learning RGB-D Features

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Meng Tian Liang Pan Marcelo H Ang Gim Hee Lee Department of Mechanical Engineering National University of Singapore Computer Vision and Robotic Perception Lab Department of Computer Science School of Computing National University of Singapore

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of symmetric objects. In this work, we propose a novel discrete- continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Additionally, the object location is detected by aggregating point-wise vectors pointing to the 3D center. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches. Our code is available at https://***/mentian/object-posenet.

关键词： Feature extraction Pose estimation Three-dimensional displays Robustness Uncertainty Image segmentation Robots

来源：评论

学校读者我要写书评

暂无评论

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Poi...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Liang Pan Chee-Meng Chew Gim Hee Lee Advanced Robotics Centre National University of Singapore Department of Mechanical Engineering National University of Singapore Computer Vision and Robotic Perception (CVRP) Lab National University of Singapore

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge features in point clouds. Our PAG is constructed by several novel modules, such as Point Atrous Convolution (PAC), Edgepreserved Pooling (EP) and Edge-preserved Unpooling (EU). Similar with atrous convolution, our PAC can effectively enlarge receptive fields of filters and thus densely learn multi-scale point features. Following the idea of non-overlapping maxpooling operations, we propose our EP to preserve critical edge features during subsampling. Correspondingly, our EU modules gradually recover spatial information for edge features. In addition, we introduce chained skip subsampling/upsampling modules that directly propagate edge features to the final stage. Particularly, our proposed auxiliary loss functions can further improve our performance. Experimental results show that our PAG outperform previous state-of-the-art methods on various 3D semantic perception applications.

关键词： Three-dimensional displays Picture archiving and communication systems Convolution Semantics Image edge detection Task analysis Decoding

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning of structure-aware fully convolutional networks for landmark localization

arXiv

引用

arXiv 2017年

作者： Chen, Yu Shen, Chunhua Chen, Hao Wei, Xiu-Shen Liu, Lingqiao Yang, Jian Key Lab of Intelligent Perception and Systems High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology School of Computer Science University of Adelaide Australian Centre for Robotic Vision Department of Computer Science and Technology Nanjing University

Landmark/pose estimation in single monocular images has received much effort in computer vision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator G generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D human pose estimation, 2D facial landmark estimation and 3D human pose estimation. The proposed approach significantly outperforms several state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Task-based grasp adaptation on a humanoid robot

Task-based grasp adaptation on a humanoid robot

引用

10th IFAC Symposium on Robot Control, SYROCO 2012

作者： Bohg, Jeannette Welke, Kai León, Beatriz Do, Martin Song, Dan Wohlkinger, Walter Madry, Marianna Aldóma, Aitor Przybylski, Markus Asfour, Tamim Martí, Higinio Kragic, Danica Morales, Antonio Vincze, Markus Humanoids and Intelligence Systems Lab. Institute for Anthropomatics KIT Germany Autonomous Motion Lab. MPI for Intelligent Systems Germany Robotic Intelligence Laboratory Department of Computer Science and Engineering UJI Spain Computer Vision and Active Perception Lab. KTH Sweden Automation and Control Institute TUW Austria

ISBN: (纸本)9783902823113

In this paper, we present an approach towards autonomous grasping of objects according to their category and a given task. Recent advances in the field of object segmentation and categorization as well as task-based grasp inference have been leveraged by integrating them into one pipeline. This allows us to transfer task-specific grasp experience between objects of the same category. The effectiveness of the approach is demonstrated on the humanoid robot ARMAR-IIIa. © 2012 IFAC.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Task-based Grasp Adaptation on a Humanoid Robot

引用

IFAC Proceedings Volumes 2012年第22期45卷 779-786页

作者： Jeannette Bohg Kai Welke Beatriz León Martin Do Dan Song Walter Wohlkinger Marianna Madry Aitor Aldóma Markus Przybylski Tamim Asfour Higinio Martí Danica Kragic Antonio Morales Markus Vincze Humanoids and Intelligence Systems Lab Institute for Anthropomatics KIT DE Autonomous Motion Lab MPI for Intelligent Systems DE Robotic Intelligence Laboratory Department of Computer Science and Engineering UJI ES Computer Vision and Active Perception lab KTH SE Automation and Control Institute TUW AT

关键词： robotic Grasping and Manipulation Task-based Grasp Synthesis Visual Servoing Attention Segmentation Object categorization System Integration

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：