检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Wen Fan Max Yang Yifan Xing Nathan F. Lepora Dandan Zhang Department of Engineering Mathematics and Bristol Robotics Laboratory University of Bristol U.K. Department of Computer Science University of Bristol U.K.

Tactile pose estimation and tactile servoing are fundamental capabilities of robot touch. Reliable and precise pose estimation can be provided by applying deep learning models to high-resolution optical tactile sensors. Given the recent successes of Graph Neural Network (GNN) and the effectiveness of Voronoi features, we developed a Tactile Voronoi Graph Neural Network (Tac-VGNN) to achieve reliable pose-based tactile servoing relying on a biomimetic optical tactile sensor (TacTip). The GNN is well suited to modeling the distribution relationship between shear motions of the tactile markers, while the Voronoi diagram supplements this with area-based tactile features related to contact depth. The experiment results showed that the Tac-VGNN model can help enhance data interpretability during graph generation and model training efficiency significantly than CNN-based methods. It also improved pose estimation accuracy along vertical depth by 28.57% over vanilla GNN without Voronoi features and achieved better performance on the real surface following tasks with smoother robot control trajectories. For more project details, please view our website: https://***/view/tac-vgnn/home

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Hybrid Deep Learning Model for Intrusion Detection in IIoT Networks

引用

Procedia computer science 2024年 246卷 3323-3332页

作者： Safi Ullah Wadii Boulila Anis Koubaa Jawad Ahmad Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh 12435 Saudi Arabia Department of Computer Science Quaid-i-Azam University Islamabad 44000 Pakistan RIADI Laboratory National School of Computer Science University of Manouba Manouba Tunisia School of Computing Edinburgh Napier University Edinburgh EH10 5DT United Kingdom

The integration of Industrial Internet of Things (IIoT) technology into the industrial sector has produced numerous significant advantages. However, the notable concern remains the absence of robust security and privacy measures in these interconnected critical environments. To secure IIoT networks, several researchers and experts employ intrusion detection systems (IDS) for detecting cyberattacks. The current systems exhibit efficient performance when handling a few categories of attack classes, even in the presence of slight imbalances. However, these models face challenges when confronted with vast categories of attack classes and highly imbalanced data. To tackle these issues, this study introduces an attention-based hybrid deep learning (AB-HDL) model designed to monitor network traffic and predict cyberattacks within the network. The proposed model comprises an attention mechanism and a hybrid deep learning model that integrates convolutional neural networks (CNN) and an autoencoder (AE). The effectiveness of the proposed AB-HDL is assessed using publicly accessible datasets: Edge-IIoTset and X-IIoTID. To ascertain the efficacy of AB-HDL, a comparative analysis is conducted with various other machine learning (ML) and deep learning (DL) algorithms. The outcome analysis indicates that the proposed AB-HDL surpasses the performance of the other algorithms and exhibits optimal efficiency in detecting cyber attacks within IIoT networks.

关键词： Attention Mechanism Autoencoder Deep Learning Industrial Internet of Things (IIoT) Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

Robust Humanoid Walking on Compliant and Uneven Terrain with Deep Reinforcement Learning

Robust Humanoid Walking on Compliant and Uneven Terrain with...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Rohan P. Singh Mitsuharu Morisawa Mehdi Benallegue Zhaoming Xie Fumio Kanehiro CNRS-AIST JRL (Joint Robotics Laboratory) IRL National Institute of Advanced Industrial Science and Technology (AIST) Japan University of Tsukuba Ibaraki Japan Department of Computer Science Stanford University USA

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

For the deployment of legged robots in real-world environments, it is essential to develop robust locomotion control methods for challenging terrains that may exhibit unexpected deformability and irregularity. In this paper, we explore the application of sim-to-real deep reinforcement learning (RL) for the design of bipedal locomotion controllers for humanoid robots on compliant and uneven terrains. Our key contribution is to show that a simple training curriculum for exposing the RL agent to randomized terrains in simulation can achieve robust walking on a real humanoid robot using only proprioceptive feedback. We train an end-to-end bipedal locomotion policy using the proposed approach, and show extensive real-robot demonstration on the HRP-5P humanoid over several difficult terrains inside and outside the lab environment. Further, we argue that the robustness of a bipedal walking policy can be improved if the robot is allowed to exhibit aperiodic motion with variable stepping frequency. We propose a new control policy to enable modification of the observed clock signal, leading to adaptive gait frequencies depending on the terrain and command velocity. Through simulation experiments, we show the effectiveness of this policy specifically for walking over challenging terrains by controlling swing and stance durations. The code for training and evaluation is available online. https://***/rohanpsingh/LearningHumanoidWalking

关键词： Legged locomotion Training Codes Humanoid robots Propioception Deep reinforcement learning Robustness Frequency control Clocks

来源：评论

学校读者我要写书评

暂无评论

Efficient Arm Motion Planning with Reduced Viapoints for Mars Rover Operations

Efficient Arm Motion Planning with Reduced Viapoints for Mar...

引用

Space robotics (iSpaRo), International Conference on

作者： Justin Huang Valen Yamamoto Ana Warner Jet Propulsion Laboratory California Institute of Technology Pasadena CA Department of Electrical Engineering and Computer Science UC Irvine Irvine CA Department of Robotics University of Michigan Ann Arbor MI

ISBN: (数字)9798350367232

ISBN: (纸本)9798350367249

This paper describes additions and enhancements we made to the standard RRT-Connect motion planning algorithm to suit the unique needs of operating the robotic arm on the Perseverance Mars Rover. One constraint we have is to maintain a minimum distance between the terrain and any part of the arm hardware. Another goal specific to rover planning is to minimize the number of viapoints in our motion plans. These algorithms should also run efficiently so that rover planners can generate arm motion sequences in time for uplink windows. We applied the RRT-Connect algorithm to the rover’s robotic arm and tested its performance, and we found that it could be used successfully for rover planning with a few changes. First, we implemented the terrain clearance requirement using a software tool called Proximeter. Second, we simplify the paths computed by RRT-Connect to minimize the number of viapoints in a motion plan. Third, we leverage Proximeter to reduce the number of expensive terrain collision checks done by the algorithm, speeding up motion planning.

关键词： Space vehicles Mars Costs Software algorithms Manipulators Hardware Planning

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Human Simulator for Task-Oriented Multimodal Human-Robot Collaboration

An End-to-End Human Simulator for Task-Oriented Multimodal H...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Afagh Mehri Shervedani Siyu Li Natawut Monaikul Bahareh Abbasi Barbara Di Eugenio Miloš Žefran Department of Electrical and Computer Engineering Robotics Laboratory University of Illinois Chicago Chicago IL USA Department of Computer Science Natural Language Processing Laboratory University of Illinois Chicago Chicago IL USA Computer Science Department California State University Channel Islands Camarillo CA USA

This paper proposes a neural network-based user simulator that can provide a multimodal interactive environment for training Reinforcement Learning (RL) agents in collaborative tasks involving multiple modes of communication. The simulator is trained on the existing ELDERLY-AT-HOME corpus and accommodates multiple modalities such as language, pointing gestures, and haptic-ostensive actions. The paper also presents a novel multimodal data augmentation approach, which addresses the challenge of using a limited dataset due to the expensive and time-consuming nature of collecting human demonstrations. Overall, the study highlights the potential for using RL and multimodal user simulators in developing and improving domestic assistive robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Multi-dimensional Stiffness Skills Transfer for Robot Teleoperation System

Human Multi-dimensional Stiffness Skills Transfer for Robot ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Liwen Situ Zhenyu Lu Weiyong Si Chenguang Yang College of Automation Science and Engineering South China University of Technology Guangzhou China Bristol Robotics Laboratory University of the West of England Bristol UK Department of Computer Science University of Liverpool Liverpool UK

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Neuroscience research has demonstrated the sig-nificance of modulating stiffness during human task performance. Similarly, endowing robots with such capability is expected. However, existing methods for robot teleoperation require operators to simultaneously control position and stiffness, resulting in high workload and task inefficiency. On the other hand, learning from demonstration (LfD) offers a feasible approach for autonomously generating stiffness. Therefore, this paper proposes a robot teleoperation system that combines the advantages of teleoperation and LfD. Teleoperation enables precise positioning guided by human operators, while LfD can transfer human stiffness skills to robots. A teleoperation-oriented stiffness-adaptive Gaussian Mixture Model/Gaussian Mixture Regression method is proposed to learn human multi-dimensional stiffness and reproduce robot stiffness on a Riemannian manifold. To enhance generalization and cooperate with teleoperation, reference points and position-driven output are introduced. Furthermore, a teleoperation strategy for both the single-leader-single-follower configuration and the single-leader-dual-follower configuration are designed, which allows operators to control either one or two robot arms with a single leader device. Finally, the effectiveness of our method is verified through a plugging-in task and a continuous flipping task, demonstrating that the proposed system is capable of performing tasks that demand high positioning accuracy and stiffness adjustment. A supplementary video for this paper is available in GitHub**https://***/setowenGit/TOSA-GMM-GMR-Video.

关键词： Manifolds Performance evaluation Hands Accuracy Neuroscience Sockets Manipulators Robots Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Path Integral Control of I2RIS Robot Using RBF Identifier and Extended Kalman Filter

arXiv

引用

arXiv 2025年

作者： Esfandiari, Mojtaba Du, Pengyuan Wei, Haochen Gehlbach, Peter Munawar, Adnan Kazanzides, Peter Iordachita, Iulian Department of Mechanical Engineering Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Department of Computer Science Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Wilmer Eye Institute Johns Hopkins Hospital BaltimoreMD21287 United States

Modeling and controlling cable-driven snake robots is a challenging problem due to nonlinear mechanical properties such as hysteresis, variable stiffness, and unknown friction between the actuation cables and the robot body. This challenge is more significant for snake robots in ophthalmic surgery applications, such as the Improved Integrated Robotic Intraocular Snake (I2RIS), given its small size and lack of embedded sensory feedback. Data-driven models take advantage of global function approximations, reducing complicated analytical models’ challenge and computational costs. However, their performance might deteriorate in case of new data unseen in the training phase. Therefore, adding an adaptation mechanism might improve these models’ performance during snake robots’ interactions with unknown environments. In this work, we applied a model predictive path integral (MPPI) controller on a data-driven model of the I2RIS based on the Gaussian mixture model (GMM) and Gaussian mixture regression (GMR). To analyze the performance of the MPPI in unseen robot-tissue interaction situations, unknown external disturbances and environmental loads are simulated and added to the GMM-GMR model. These uncertainties of the robot model are then identified online using a radial basis function (RBF) whose weights are updated using an extended Kalman filter (EKF). Simulation results demonstrated the robustness of the optimal control solutions of the MPPI algorithm and its computational superiority over a conventional model predictive control (MPC) algorithm. © 2025, CC BY.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

CLEAR-Net: A Cascaded Local and External Attention Network for Enhanced Dehazing of Remote Sensing Images

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Ali, Anas M. El-Rabaie, El-Sayed M. Ramadan, Khalil F. El-Samie, Fathi E. Abd El-Shafai, Walid Prince Sultan University Robotics and Internet-of-Things Laboratory Riyadh12435 Saudi Arabia Faculty of Electronic Engineering Menoufia University Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Computer Science Department Riyadh11586 Saudi Arabia

Atmospheric haze degrades remote sensing images by obscuring critical details, diminishing data interpretation accuracy. This paper presents CLEAR-Net: Cascaded Local and External Attention Resource Network, a novel dehazing framework designed to enhance clarity and detail in remote sensing images. CLEAR-Net employs a two-block cascaded architecture to address both global and local haze effects. The first block utilizes an Outer Global Attention (OGA) mechanism, processing global features via a U-Net Inner Attention (UIA) module to mitigate widespread haze. The second block focuses on Outer Local Attention (OLA), refining local image features through reintegration with the UIA module. An ensemble method selects the most effective model weights based on perceptual quality metrics, and a composite loss function emphasizes the preservation of high-frequency details to maintain textural and edge fidelity. CLEAR-Net's efficacy is evaluated on the SateHaze1k and RICE datasets, outperforming existing state-of-theart dehazing techniques. On SateHaze1k, CLEAR-Net achieves an average PSNR of 27.876 dB, surpassing the next best model by approximately 4.81%;under moderate fog, it attains a PSNR of 30.824 dB, about 9.8% higher than existing methods. On the RICE dataset, which includes challenging cloud cover, CLEARNet achieves PSNRs of 36.873 dB on RICE1 and 34.624 dB on RICE2, improving over next-best models by approximately 18.2% and 12%, respectively, and attains the lowest LPIPS values, indicating superior perceptual quality. © 2008-2012 IEEE.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Surgical robotics Environment in NVIDIA Isaac Sim for Robot-Assisted Suturing

Surgical Robotics Environment in NVIDIA Isaac Sim for Robot-...

引用

International Symposium on Medical robotics (ISMR)

作者： Tae Wan Kim Haoying Zhou Juan Antonio Barragan Hisashi Ishida Peter Kazanzides Adnan Munawar Department of Computer Science Johns Hopkins University Baltimore MD USA Department of Biomedical Engineering Johns Hopkins University Baltimore MD USA Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798331599003

ISBN: (纸本)9798331599010

Virtual simulations have served as important tools to design and test robotic frameworks in a variety of domains. Increasingly, they have been used to train and experiment on surgical robotics applications. Having seen the success of an open simulation environment for robot-assisted surgical suturing in the Asynchronous Multi-Body Framework (AMBF), we sought to reproduce the surgical suturing environment from AMBF in NVIDIA Isaac Sim, a new simulator with impressive visual fidelity and GPU-accelerated computation capabilities. We present a virtual scene for robotic suturing comprising two robotic manipulators, an endoscope, two surgical phantoms, and a needle attached to a thread. The thread is modeled using three different techniques. This work also provides interactive manipulation of the virtual scene via haptic input devices using the Robot Operating System interface. We measured performance speeds, ranging between 13 to 60 frames per second depending on the task, and approximately 0.5 seconds of delay between a haptic input device and the simulator. In this environment, we hope to provide a descriptive overview of the capabilities and limitations of NVIDIA Isaac Sim for surgical simulation applications.

关键词： Performance evaluation Visualization Medical robotics Instruction sets Computational modeling Operating systems Input devices Phantoms Needles Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

Adaptive Stiffness Control of Series Elastic Actuator Manipulators Based on Dynamic System

Adaptive Stiffness Control of Series Elastic Actuator Manipu...

引用

IEEE International Conference on Automation science and Engineering (CASE)

作者： Kunlin Guo Chao Zeng Weiyong Si Ning Wang Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control School of Automation Science and Engineering South China University of Technology Guangzhou China Department of Computer Science University of Liverpool Liverpool UK School of Computer Science and Electronic Engineering University of Essex Colchester Bristol Robotics Laboratory University of the West of England Bristol UK

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In traditional control methods, Series Elastic Actuator (SEA) joint manipulators are limited by their hardware and can only perform simple tasks with low stiffness. To address this issue, we propose a stiffness adjustment control strategy for SEA manipulators based on Dynamic Systems (DS) with good generalization performance. By enhancing the generalization capability of DS in complex tasks and combining posture control, the SEA manipulators can autonomously adjust control gains and postures according to task requirements to achieve higher stiffness at the end-effector. Experimental results involving the activation of air switches with different stiffness levels and installation angles have demonstrated the effectiveness of our proposed method. The results indicate that compared to traditional methods of adjusting the control gain and retraining DS for similar tasks, our approach exhibits superior generalization performance while maintaining end-effector stiffness during interactions.

关键词： Actuators computer aided software engineering Automation Adaptive systems Control systems End effectors Hardware Dynamical systems Manipulator dynamics

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：