检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wenbo Wang Hsuan-I Ho Chen Guo Boxiang Rong Artur Grigorev Jie Song Juan Jose Zarate Otmar Hilliges Department of Computer Science ETH Zürich Max Planck Institute for Intelligent Systems Tübingen

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The studies of human clothing for digital avatars have predominantly relied on synthetic datasets. While easy to collect, synthetic data often fall short in realism and fail to capture authentic clothing dynamics. Addressing this gap, we introduce 4D-DRESS, the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes. 4D-DRESS captures 64 outfits in 520 human motion sequences, amounting to 78k textured scans. Creating a real-world clothing dataset is challenging, particularly in annotating and segmenting the extensive and complex 4D human scans. To address this, we develop a semi-automatic 4D human parsing pipeline. We efficiently combine a human-in-the-loop process with automation to accurately label 4D scans in diverse garments and body movements. Leveraging precise annotations and high-quality garment meshes, we establish several benchmarks for clothing simulation and reconstruction. 4D-DRESS offers realistic and challenging data that complements synthetic sources, paving the way for advancements in research of lifelike human clothing.

关键词： computer vision Annotations Motion segmentation Clothing Semantics Pipelines Dynamics

来源：评论

学校读者我要写书评

暂无评论

Start State Selection for Control Policy Learning from Optimal Trajectories

Start State Selection for Control Policy Learning from Optim...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Christoph Zelch Jan Peters Oskar von Stryk Department of Computer Science TU Darmstadt Simulation Systems Optimization and Robotics Group Darmstadt Germany Department of Computer Science Intelligent Autonomous Systems Group TU Darmstadt Darmstadt Germany

Combination of optimal control methods and machine learning approaches allows to profit from complementary benefits of each field in control of robotic systems. Data from optimal trajectories provides valuable information that can be used to learn a near-optimal state-dependent feedback control policy. To obtain high-quality learning data, careful selection of optimal trajectories, determined by a set of start states, is essential to achieve a good learning performance. In this paper, we extend previous work with new comple-menting strategies to generate start points. These methods complement the existing approach, as they introduce new criteria to identify relevant regions in joint state space that need coverage by new trajectories. It is demonstrated that the extensions significantly improve the overall performance of the previous method in simulation on full nonlinear dynamics model of the industrial Manutec r3 robot arm. Further, it is demonstrated that it suffices to learn a policy that reaches the proximity of the goal state, from where a PI controller can be used for stable control reaching the final system state.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-stage Objective Function Optimized Hand-Eye Self-calibration of Robot in Autonomous Environment 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Liu, Kaibo Zheng, Wangli Min, Huasong Lin, Yunhan School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Hubei Wuhan430065 China State Grid Electric Power Research Institute Jiangsu Nanjing211106 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Hubei Wuhan430081 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

In the application scenario of robot autonomous tasks, the robot needs to be able to complete calibration online and automatically to achieve self-maintenance, which differs from traditional robot hand-eye calibration in that the traditional robot hand-eye calibration requires a dedicated calibration board to assist offline completion. Aiming at the problem that the existing self-calibration methods cannot be optimized as a whole, which leads to low accuracy and instability of the solution, a multi-stage objective function optimization self-calibration algorithm is proposed, which describes the solution of hand-eye self-calibration as a minimization objective function problem involving multiple stages. An optimization method based on the minimization of re-projection error is designed to compensate for the results, which uses an efficient Oriented fast and rotated brief (ORB) feature extraction algorithm and introduces a scoring mechanism to retain more correct matching points in the feature matching stage. Two different types of experiments were designed to validate our method. One is a single camera dataset experiment, which shows that our method is more accurate and robust than the existing self-calibration method;the other is an application platform experiment, which verifies the feasibility and availability of our method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

Causal action influence aware counterfactual data augmentation 24

Causal action influence aware counterfactual data augmentati...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Núria Armengol Urpí Marco Bagatella Marin Vlastelica Georg Martius Department of Computer Science ETH Zurich Zurich Switzerland and Max Planck Institute for Intelligent Systems Tübingen Germany Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science University of Tübingen Tübingen Germany and Max Planck Institute for Intelligent Systems Tübingen Germany

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online environment interactions. By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping action-unaffected parts of the state-space between independent trajectories in the dataset. We empirically show that this leads to a substantial increase in robustness of offline learning algorithms against distributional shift. Videos, code and data are available at https://***/view/caiac.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ArsenicSkinNet: A Deep Learning Approach for Arsenicosis Skin Lesion Classification 17th

ArsenicSkinNet: A Deep Learning Approach for Arsenicosis Sk...

引用

17th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2024

作者： Aakash, Abhinav O’Halloran, Tony Obaido, George Mienye, Ibomoiye Domor Mienye, Ebikella Ogunruku, Oyindamola Omolara Aliyu, Mikail Department of Computer Science KIIT University Bhubaneswar India Department of Computer Science National University of Ireland Galway Ireland Center for Human-Compatible Artificial Intelligence Berkeley Institute for Data Science University of California BerkeleyCA United States Institute of Intelligent Systems University of Johannesburg Johannesburg South Africa Department of Decision Sciences Western Illinois University MacombIL61455 United States School of Public Health University of California BerkeleyCA United States

ISBN: (纸本)9789819606917

In many low-resource settings, the debilitating effects of arsenicosis remain a critical public health concern. This condition leads to serious health problems, including skin lesions, skin cancer, cardiovascular disease, and neurological impairment. Visual inspection is the standard practice for diagnosing arsenicosis;however, it is often subjective and can lead to variability in diagnosis. To address the urgent need for efficient arsenicosis skin detection, we propose ArsenicSkinNet, adapted from the EfficientNet architecture for the automatic classification of arsenicosis skin disease. ArsenicSkinNet is a state-of-the-art technique based on the EfficientNet neural network architecture and transfer learning, known for achieving high performance with fewer computational resources compared to traditional models. Our results show that ArsenicSkinNet achieved a classification accuracy of 99.61% on the arsenicosis skin lesion dataset. Our study demonstrates that deep learning could significantly improve the capacity for early detection and management of arsenicosis, thereby mitigating its impact on affected populations in low-resource settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous Door Opening with a Rescue Robot

Autonomous Door Opening with a Rescue Robot

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Renat Abdulganeev Roman Lavrenov Alexandra Dobrokvashina Yang Bai Evgeni Magid Intelligent Robotics Department Laboratory of Intelligent Robotic Systems (LIRS) Institute of Information Technology and Intelligent Systems Kazan Federal University Kazan Russia Graduated School of Information Science and Technology Osaka University Osaka Japan

ISBN: (数字)9798350394245

ISBN: (纸本)9798350394252

Autonomy of a mobile robot can only be achieved if it independently deals with obstacles. This article discusses an experience of autonomously opening doors by the Russian crawler rescue robot Servosila Engineer. A door and handle detection is based on the YOLO v3 algorithm. The robot motion and stopping at a predefined distance are guided by a laser range finder. After gripping the door handle, the door could be opened using either a pulling or pushing method. Recommended optimal distance to the door, an angle at which the robot turns towards the door and a stopping point for the robot were experimentally set and evaluated in an indoor office environment.

关键词： Robot motion YOLO Visualization Lasers Crawlers Robot sensing systems Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Communicating Intent as Behaviour Trees for Decentralised Multi-Robot Coordination

Communicating Intent as Behaviour Trees for Decentralised Mu...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Rhett Hull Diluka Moratuwage Emily Scheide Robert Fitch Graeme Best Robotics Institute University of Technology Sydney NSW Australia Department of Defence Defence Science and Technology Group Australia Collaborative Robotics and Intelligent Systems (CoRIS) Institute Oregon State University USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We propose a decentralised multi-robot coordination algorithm that features a rich representation for encoding and communicating each robot’s intent. This representation for “intent messages” enables improved coordination behaviour and communication efficiency in difficult scenarios, such as those where there are unknown points of contention that require negotiation between robots. Each intent message is an adaptive policy that conditions on identified points of contention that conflict with the intentions of other robots. These policies are concisely expressed as behaviour trees via algebraic logic simplification, and are interpretable by robot teammates and human operators. We propose this intent representation in the context of the Dec-MCTS online planning algorithm for decentralised coordination. We present results for a generalised multi-robot orienteering domain that show improved plan convergence and coordination performance over standard Dec-MCTS enabled by the intent representation’s ability to encode and facilitate negotiation over points of contention.

关键词： Robot kinematics Encoding Planning Logic Standards Convergence

来源：评论

学校读者我要写书评

暂无评论

Subjective weight determination methods in multi-criteria decision-making: a systematic review 28th

Subjective weight determination methods in multi-criteria de...

引用

28th International Conference on Knowledge Based and intelligent information and Engineering systems, KES 2024

作者： Kizielewicz, Bartlomiej Tomczyk, Tomasz Gandor, Michal Salabun, Wojciech National Institute of Telecommunications National Research Institute ul. Szachowa 1 Warsaw04-894 Poland Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland

The determination of weights is a critical step in Multi-Criteria Decision-Making (MCDM) processes, and subjective methods play a significant role in this area. This paper provides a comprehensive review of subjective weight determination methodologies, focusing primarily on sources from the Scopus database. Through a systematic literature review, this study analyzes 33,434 publications related to subjective weight determination, providing insights into the trends, advancements, and applications of these methodologies. The review underscores the importance of expert knowledge in contemporary decision-making and suggests potential areas for future research, including the integration of subjective methods with emerging technologies and the development of more robust and consistent weighting frameworks. This paper aims to serve as a valuable resource for researchers and practitioners in the field of MCDM, offering a detailed overview of the current state of subjective weight determination methods and their practical implications. © 2024 The Authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems

arXiv

引用

arXiv 2024年

作者： Sidrane, Chelsea Tumova, Jana The Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden

Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show that the system is generally functioning as desired, but a formal tool like reachability analysis can provide a guarantee of correctness. For linear systems, reachability analysis is straightforward and fast, but as more complex components are added to the control system such as nonlinear dynamics or a neural network controller, reachability analysis may slow down or become overly conservative. To address these challenges, much literature has focused on spatial refinement, e.g., tuning the discretization of the input sets and intermediate reachable sets. However, this paper addresses a different dimension: temporal refinement. The basic idea of temporal refinement is to automatically choose when along the horizon of the reachability problem to execute slow symbolic queries which incur less approximation error versus fast concrete queries which incur more approximation error. Temporal refinement can be combined with other refinement approaches and offers an additional "tuning knob" with which to trade off tractability and tightness in approximate reachable set computation. Here, we introduce an automatic framework for performing temporal refinement and we demonstrate the effectiveness of this technique on computing approximate reachable sets for nonlinear systems with neural network control policies. We demonstrate the calculation of reachable sets of varying approximation error under varying computational budget and show that our algorithm is able to generate approximate reachable sets with a similar amount of error to the baseline approach in 20-70% less time. © 2024, CC BY.

关键词： Linear systems

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：