检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Sukkar, Fouad Moreno, Victor Hernandez Vidal-Calleja, Teresa Deuse, Jochen UTS Robotics Institute the Centre for Advanced Manufacturing School for Mechanical and Mechatronic Engineering University of Technology Sydney UltimoNSW2007 Australia Australia

Learning from demonstration (LfD) has the potential to greatly increase the applicability of robotic manipulators in modern industrial applications. Recent progress in LfD methods have put more emphasis in learning robustness than in guiding the demonstration itself in order to improve robustness. The latter is particularly important to consider when the target system reproducing the motion is structurally different to the demonstration system, as some demonstrated motions may not be reproducible. In light of this, this paper introduces a new guided learning from demonstration paradigm where an interactive graphical user interface (GUI) guides the user during demonstration, preventing them from demonstrating non-reproducible motions. The key aspect of our approach is determining the space of reproducible motions based on a motion planning framework which finds regions in the task space where trajectories are guaranteed to be of bounded length. We evaluate our method on two different setups with a six-degree-of-freedom (DOF) UR5 as the target system. First our method is validated using a seven-DOF Sawyer as the demonstration system. Then an extensive user study is carried out where several participants are asked to demonstrate, with and without guidance, a mock weld task using a hand held tool tracked by a VICON system. With guidance users were able to always carry out the task successfully in comparison to only 44% of the time without guidance. Copyright © 2023, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

BRNES: Enabling Security and Privacy-Aware Experience Sharing in Multiagent Robotic and Autonomous Systems

BRNES: Enabling Security and Privacy-Aware Experience Sharin...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Md Tamjid Hossain Hung Manh La Shahriar Badsha Anton Netchaev The Advanced Robotics and Automation Lab Computer Science and Engineering University of Nevada Reno Nevada USA Bosch Engineering North America The U.S. Army Corps.

Although experience sharing (ES) accelerates multiagent reinforcement learning (MARL) in an advisor-advisee framework, attempts to apply ES to decentralized multiagent systems have so far relied on trusted environments and over-looked the possibility of adversarial manipulation and inference. Nevertheless, in a real-world setting, some Byzantine attackers, disguised as advisors, may provide false advice to the advisee and catastrophically degrade the overall learning performance. Also, an inference attacker, disguised as an advisee, may conduct several queries to infer the advisors' private information and make the entire ES process questionable in terms of privacy leakage. To address and tackle these issues, we propose a novel MARL framework (BRNES) that heuristically selects a dynamic neighbor zone for each advisee at each learning step and adopts a weighted experience aggregation technique to reduce Byzantine attack impact. Furthermore, to keep the agent's private information safe from adversarial inference attacks, we leverage the local differential privacy (LDP)-induced noise during the ES process. Our experiments show that our framework outperforms the state-of-the-art in terms of the steps to goal, obtained reward, and time to goal metrics. Particularly, our evaluation shows that the proposed framework is 8.32x faster than the current non-private frameworks and 1.41x faster than the private frameworks in an adversarial setting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-driven sleep structure deciphering based on cardiorespiratory signals

引用

Computer Methods and Programs in Biomedicine 2025年 267卷 108769-108769页

作者： Huang, Ming Iwata, Osuke Yokoyama, Kiyoko Tamura, Toshiyo Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Shenzhen China of Science and Technology Nara Institute of Science and Technology Ikoma Japan of Medical Sciences Nagoya City University Japan School of Data Science Nagoya City University Japan Institute for Healthcare Robotics Waseda University Japan

Background and Objective: : Cardiorespiratory signals provide a novel perspective for understanding sleep structure through the physiological mechanism of cardiopulmonary coupling. This mechanism divides the coupling spectrum into high-frequency (HF) and low-frequency (LF) bands, indicating that signal segments of 4–8 min are optimal for analysis. However, the lack of labels tailored to these signals has led to reliance on the American Academy of Sleep Medicine (AASM) definitions, which are primarily designed for electroencephalogram (EEG) and electrooculogram (EOG) data. This study aims to address the challenge of transitioning from AASM-defined labels to cardiorespiratory-oriented ones and to evaluate the feasibility of using these signals for accurate sleep structure recognition. Methods: To align with the physiological characteristics of cardiorespiratory signals, AASM labels were modified by excluding the N2 stage due to its overlap of stable and unstable non-rapid eye movement (NREM) phases, which introduces ambiguity. The modified dataset focused on the wake, N1, deep sleep (N3), and rapid eye movement (REM) stages. A physiologically-inspired deep-learning model (PIDM) was developed to extract features from cardiorespiratory time series and classify sleep stages. Post-analysis assessed the physiological validity of the model's N2 predictions by evaluating the HF-to-LF ratio and respiratory variability. Results: The pipeline, combining the modified labeling scheme with the PIDM model, achieved balanced accuracy scores of 0.83, 0.86, and 0.78 for wake, deep sleep, and REM stages, respectively in the normal group;and 0.92, 0.95, and 0.90 in the mild and moderate sleep apnea groups. Post-analysis revealed that most N2 samples were attributed to stable NREM sleep, characterized by higher HF-to-LF ratios and lower respiratory variability, aligning with physiological understanding. Conclusions: This study highlights the physiological relevance of cardiorespiratory s

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

arXiv

引用

arXiv 2025年

作者： Li, Jinze Xu, Yixing Huang, Haiduo Yin, Xuanwu Li, Dong Ngai, Edith C.H. Barsoum, Emad Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Advanced Micro Devices Inc. Beijing China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Speculative decoding (SPD) aims to accelerate the auto-regressive token generation process of a target Large Language Model (LLM). Some approaches employ a draft model with multiple heads to predict a sequence of future tokens, where each head handles a token in the sequence. The target LLM verifies the predicted sequence and accepts aligned tokens, enabling efficient multi-token generation. However, existing methods assume that all tokens within a sequence are equally important, employing identical head structures and relying on a single-generation paradigm, either serial or parallel. To this end, we theoretically demonstrate that initial tokens in the draft sequence are more important than later ones. Building on this insight, we propose Gumiho, a hybrid model combining serial and parallel heads. Specifically, given the critical importance of early tokens, we employ a sophisticated Transformer architecture for the early draft heads in a serial configuration to improve accuracy. For later tokens, we utilize multiple lightweight MLP heads operating in parallel to enhance efficiency. By allocating more advanced model structures and longer running times to the early heads, Gumiho achieves improved overall performance. The experimental results demonstrate that our method outperforms existing approaches, fully validating its effectiveness. © 2025, CC BY.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Full State Quaternion-Based Observer Control for Multirotor Aerial Grasping

Full State Quaternion-Based Observer Control for Multirotor ...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： I. García-Mosqueda A. Tevera-Ruiz H. Abaunza P. Castillo A. Sanchez-Orta J.D. Chazot Universite de technologie de Compiegne CNRS Heudiasyc/Roberval Compiegne France Tecnologico de Monterrey School of Engineering and Sciences Jalisco Mexico CINVESTAV-Saltillo Robotics and Advanced Manufacturing Mexico

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper presents an enhanced observer control strategy for multirotor aerial grasping. Unlike previous approaches, which focused solely on translational dynamics, this method incorporates dual observers-one for the translational subsystem and another for the rotational dynamics. By lever-aging quaternions, the proposed control framework provides a singularity-free representation of orientation while naturally decoupling rotational and translational dynamics. This allows the system to be treated as fully actuated in both position and orientation, improving disturbance rejection and compensating for torques induced by offcenter or asymmetrically shaped objects during grasping. A passive, non-actuated gripper further enhances the drone's ability to interact with objects in real-world scenarios. Experimental validations confirm the robustness and adaptability of the proposed approach, demonstrating its effectiveness in handling dynamic variations in mass and torque while maintaining stable flight.

关键词： Torque Quaternions Grasping Observers Robustness Grippers Aircraft Aerospace control

来源：评论

学校读者我要写书评

暂无评论

Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning

Outram: One-shot Global Localization via Triangulated Scene ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Pengyu Yin Haozhi Cao Thien-Minh Nguyen Shenghai Yuan Shuyang Zhang Kangcheng Liu Lihua Xie Centre for Advanced Robotics Technology Innovation (CARTIN) School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong SAR China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

One-shot LiDAR localization refers to the ability to estimate the robot pose from one single point cloud, which yields significant advantages in initialization and relocalization processes. In the point cloud domain, the topic has been extensively studied as a global descriptor retrieval (i.e., loop closure detection) and pose refinement (i.e., point cloud registration) problem both in isolation or combined. However, few have explicitly considered the relationship between candidate retrieval and correspondence generation in pose estimation, leaving them brittle to substructure ambiguities. To this end, we propose a hierarchical one-shot localization algorithm called Outram that leverages substructures of 3D scene graphs for locally consistent correspondence searching and global substructure-wise outlier pruning. Such a hierarchical process couples the feature retrieval and the correspondence extraction to resolve the substructure ambiguities by conducting a local-to-global consistency refinement. We demonstrate the capability of Outram in a variety of scenarios in multiple large-scale outdoor datasets. Our implementation is open-sourced: https://***/Pamphlett/Outram.

关键词： Location awareness Point cloud compression Three-dimensional displays Laser radar Costs Pose estimation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Guided Single-Cell Encapsulation through photo-crosslinking for advanced 3D Culture

Deep Learning-Guided Single-Cell Encapsulation through photo...

引用

IEEE International Conference on Mechatronics and Automation

作者： Yanfeng Zhao Kaijun Lin Haotian Yang Xinyi Dong Tao Sun Qing Shi Qiang Huang Huaping Wang Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institude of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Encapsulating single cells in hydrogels provides them with a relatively autonomous and controllable three-dimensional extracellular environment. This environment can facilitate cell interaction and proliferation, making it highly valuable in fields such as tissue engineering and single-cell research. However, traditional methods of single-cell encapsulation encounter limitations in terms of single-cell encapsulation rate and topography control, which hinder of the progress of single-cell encapsulation research. In this paper, we propose a novel method for printing microgel-encapsulated single cells using deep learning-guided DLP printing. By leveraging deep learning algorithms, we accurately capture and translate the real-time positional data of single cells into the printing system’s coordinate framework. Based on the single-cell positional information, a virtual digital mask is created via the OpenCV algorithm, which is then input into the digital microscope to complete the single-cell encapsulation. The single-cell encapsulation rate achieved by this method is 86.3%, which is about 2.87 times higher than that of the traditional method. Experimental results show that our method achieves high accuracy in single-cell encapsulation and the fabrication of microgels with arbitrary shapes, which hold significant importance for biological and medical applications.

关键词： Encapsulation Printing Fabrication Deep learning Three-dimensional displays Shape Hydrogels

来源：评论

学校读者我要写书评

暂无评论

Modeling a Sensorized Soft Layer for Adding Compliance to the Environment in Robotic Manipulation

Modeling a Sensorized Soft Layer for Adding Compliance to th...

引用

作者： Pozzi, Maria Gaudeni, Chiara Iqbal, Zubair Prattichizzo, Domenico Malvezzi, Monica Department of Information Engineering and Mathematics University of Siena Siena Italy Department of Advanced Robotics Istituto Italiano di Tecnologia Genoa Italy

Soft robots are spreading quickly and widely thanks to their adaptability, tolerance to uncertainties, reliability, and intrinsic safety. To predict their behaviour and optimize their design, it is fundamental to devise models that account for the fact that they are made of highly non-linear materials and can be subjected to large, continuous deformations. In this work, we focus on modelling a soft robotic device developed to provide controllable compliance and sensing capabilities to the environment. Different models for non-linear materials in FEM static simulations are tested to evaluate which type of representation is more convenient in terms of accuracy. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

3D Localization of Objects Buried within Granular Material Using a Distributed 3-Axis Tactile Sensor

3D Localization of Objects Buried within Granular Material U...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Zhengqi Chen Elisabetta Versace Lorenzo Jamone ARQ (Advanced Robotics at Queen Mary) School of Engineering and Materials Science Queen Mary University of London UK Department of Biological and Experimental Psychology Queen Mary University of London UK

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

While visual sensing is often the predominant modality for a robot to localize objects in the environment, tactile and force sensing become crucial when objects are occluded, poorly visible, or buried. However, existing works on locating buried objects rely solely on force measurements at a single contact point on the robot end-effector, making 3D localization very challenging. This paper presents an alternative approach using a tactile sensor that measures both normal and shear forces (i.e. 3-axis) on distributed points; three Long Short-Term Memory (LSTM) models are trained with real-world data to perform real-time 3D localization (i.e. distance, direction and depth) of an object buried within a granular material. Our experimental results suggest that measuring both normal and shear forces (instead of just normal) on distributed contact points (instead of only one point) is essential for the accurate 3D localization of buried objects.

关键词： Location awareness Visualization Solid modeling Three-dimensional displays Force measurement Force Tactile sensors Sensors Buried object detection Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Fast Spatial Reasoning of Implicit 3D Maps through Explicit Near-Far Sampling Range Prediction

Fast Spatial Reasoning of Implicit 3D Maps through Explicit ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Chaerin Min Sehyun Cha Changhee Won Jongwoo Lim Department of Computer Science Brown University Advanced Robotics Lab. CTO Division LG Electronics MultiplEYE Co. Ltd Department of Mechanical Engineering Seoul National University

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

3D mapping is critical for many robotics applications, such as autonomous navigation and object manipulation. Recently, deep implicit mapping approaches have received much attention for their compactness and ability to represent fine-grained details. However, without explicit guidance, such implicit representations are often cumbersome for searching the full range on the rays to find the object surfaces. As a result, several approaches, including hierarchical sampling, occupancy grids, and zero-level set baking, have been proposed to improve sampling where costly forward passes of the neural network should be performed. However, hierarchical sampling is still suboptimal in that it requires uniform coarse samples. Discrete occupancy grids of Instant NGP and zero-level sets of various baking methods are less suitable for large and noisy real *** this paper, we present a novel framework for adaptively predicting the near-far range for sampling the query positions of the deep implicit map. For this purpose, the truncated signed distance grid for the map is pre-constructed and used to provide hints for near-far prediction during rendering. In addition, our recovery algorithm automatically detects failed near-far predictions and recovers only those rays by directly using the implicit map. We conduct extensive experiments on a synthetic dataset, a public real dataset, and a real dataset captured by our multi-camera robot system. The experimental results show that our algorithm achieves the same rendering quality with surprisingly fewer samples compared to the existing methods, which means that the robot can reason about the image and depth properties of the scene much faster. Finally, a thorough analysis of the sample distribution along the rays is provided to give a better understanding of our method’s strong efficiency, adaptability, and robustness. https://***/TSDF-sampling/

关键词： Three-dimensional displays Neural networks Rendering (computer graphics) Prediction algorithms Search problems Robustness Cognition Noise measurement Intelligent robots Synthetic data

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：