检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation (ICRA)

作者： Kai-Tai Song Hsiang-Hsi Chen Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of Robotics National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Robotic autonomous grasp requires the system to perform multiple functions such as gripper and robot control, making it a task with hybrid output nature. Existing methods based on closed-loop deep reinforcement learning rely on external models for termination evaluation. To achieve more effective grasp for novel objects, we propose a new autonomous grasp control scheme termed HAGrasp that considers the complete point cloud of the workspace. It integrates grasp pose estimation, end-effector pose evaluation, and motion planning of the robotic arm into a single model, enhancing the success rate while reducing computational load. We present a closed-loop grasp control system based on deep reinforcement learning. This control system can perform grasp tasks while dynamically adjusting to avoid end-effector collisions. The design of hybrid-action reinforcement learning module is trained with unified latent action space and further improve generalization, achieving real-time autonomous grasp control. Real robot experiments show that our method has 74.2% success rate for grasping 7 unseen objects. Comparative experiments show that the proposed HAGrasp outperforms open-loop baseline Contact-Graspnet in both success rate and inference time. It is demonstrated that with integrated multi-view input and sim-to-real training design, our method improves real-world applications of autonomous grasp.

关键词： Training Point cloud compression Robot control Pose estimation Deep reinforcement learning End effectors Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Power Consumption Optimization of GPU Server with Offline Reinforcement Learning

引用

IEEE Access 2025年 13卷 85826-85837页

作者： Chung, Heechan Im, Yeeun Park, Jongchan Lee, Taeho Kim, TaeYoung Kim, Hyungjun Lee, Dongwhan KT Research and Development Center AI Security Research Team Future Network Laboratory Network Group Seoul Korea Republic of KT Research and Development Center AI Perceived Quality Research Team Future Network Laboratory Network Group Seoul Korea Republic of Korea Advanced Institute of Science and Technology Robotics Program Daejeon Korea Republic of Korea Advanced Institute of Science and Technology School of Electrical Engineering Daejeon Korea Republic of

The rapid growth of artificial intelligence (AI) has led to increased reliance on power-intensive Graphics Processing Units (GPUs), which are essential for training and deploying large-scale models. However, the escalating energy demands of AI workloads pose sustainability challenges, necessitating efficient power management strategies to reduce carbon footprints. Optimizing GPU server power consumption is complex due to the interdependence of various components. Conventional methods often involve trade-offs: increasing fan speed enhances cooling but raises overall power usage, whereas lowering GPU clock frequencies conserves energy at the cost of longer computation times. To address these challenges, we propose a data-driven optimization framework based on offline reinforcement learning (RL). Our approach collects operational data from a custom-designed workload that simulates varying server loads, capturing key metrics such as power consumption, temperature, and core frequency. The reward function balances power efficiency with performance. The reinforcement learning agent learns from pre-collected server logs, enabling intelligent real-time GPU clock control decisions without costly live experiments. Additionally, periodic fan speed adjustments and pre-training of the Q-network further enhance overall efficiency. Experimental results demonstrate that our method reduces power consumption by 3.62% while improving computation time by 1.51% for synthetic workloads. For LLaMA-2 fine-tuning, power consumption decreases by 6.40% with only a minor 1.27% increase in computation time, demonstrating its practical effectiveness. Our framework was validated on the latest NVIDIA L40S GPU, demonstrating its compatibility with cutting-edge hardware. © 2013 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Task Planning and Motion Control with Temporal Logic Specifications

Task Planning and Motion Control with Temporal Logic Specifi...

引用

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

作者： Marcos S. Pereira Luciano C. A. Pimenta Bruno V. Adorno Graduate Program in Electrical Engineering Department of Electronic Engineering Universidade Federal de Minas Gerais Belo Horizonte MG Brazil Manchester Centre for Robotics and AI The University of Manchester Manchester UK

This paper proposes a task planning and motion control framework that generates task plans for a linear temporal logic specification (LTL), which are then executed using a task-space constrained motion controller and a local task planner that overcomes local minima. We propose a new encoding for task specifications, directly in the task-space, as constraints of a mixed-integer linear program that can be used with off-the-shelf LTL linear encoding. We apply our framework to plan and execute trajectories for a free-flying robot and show that the task plan is accomplished without collisions, even in the presence of unexpected moving obstacles that are not considered in the planning phase, while control signal constraints are satisfied. To evaluate the local minima avoidance, we compare the local task planner with a sampling-based motion planner, and the results show a smoother trajectory with a faster execution and less total planning time when using our framework. Last, our framework scaled well with a longer LTL specification, as opposed to automata-based frameworks that usually suffer with the curse of the dimensionality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Renderable Street View Map-Based Localization: Leveraging 3D Gaussian Splatting for Street-Level Positioning

Renderable Street View Map-Based Localization: Leveraging 3D...

引用

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

作者： Howoong Jun Hyeonwoo Yu Songhwai Oh Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of Department of Intelligent Robotics & Mechanical Engineering Sungkyunkwan University (SKKU) Suwon-si Korea Republic of Department of Electrical and Computer Engineering (ECE) & Interdisciplinary Program in Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this paper, we introduce a new method that first utilizes 3D Gaussian splatting in street-level localization problem. Robust localization with street-level real-world images such as street view is a major issue for autonomous vehicle, augmented reality (AR) navigation, and outdoor mobile robots. The objective is to determine the position and orientation of a query image that matches a street view database composed of RGB images. However, given the limited information available in the street view images, accurately determining the location solely based on this data presents a significant challenge. To address this challenge, we propose a novel method called renderable street view map-based localization (RSM-Loc). This approach enhances the localization process by augmenting 2D street view images into a renderable 3D map using 3D Gaussian splatting, to resolve street-level localization problems. Upon receiving a query RGB image without geometry information, the proposed method renders 2D images from a pre-made renderable map and compares image pose similarities between the rendered images and the query image. Through iterations of this process, the proposed method eventually estimates the pose of the given query image. The experimental results demonstrate that RSM-Loc outperforms the baselines with neural-field-based localization. Additionally, we conduct deep analysis on the proposed method to show that our method can serve as a new concept for the street-level localization problem.

关键词： Location awareness Visualization Matched filters Three-dimensional displays Image resolution Navigation Noise measurement Mobile robots Intelligent robots Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Data Alignment Design for Robotic programming by Demonstration Based on IMU and Optical Tracker

引用

IEEE Transactions on Instrumentation and Measurement 2023年 72卷 1页

作者： Song, Kai-Tai Li, Bing-Yi Ou, Szu-Chen National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering College of Electrical and Computer Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Graduate Degree Program of Robotics Hsinchu300093 Taiwan

This study proposes a data alignment design for sensor fusion of an optical target (OT) and an inertial measurement unit (IMU) to track the trajectory of a handheld tool for robot programming by demonstration (PbD). A novel method is proposed for coordinate and temporal alignment between the OT and the IMU sensor to increase tracking accuracy. The IMU measurements are aligned with the corresponding angular velocities and accelerations derived from the OT to calibrate the IMU-OT relationship. Global and local optimizations are combined to reduce the computation time for the temporal alignment and coordinate calibration. Experimental results show that the proposed method provides improved calibration results with shorter calculation time compared with the two existing methods. The sensor fusion experiments verify the accuracy of trajectory tracking of 1.3 mm using the calibration result, an improvement from 1.4 mm of the data alignment using ruler measurement. Integrated PbD experiments using a 6-DOF manipulator were carried out to evaluate the proposed method. The manipulator imitated the hand motion of a bottle transfer task with a trajectory error of 0.66 mm. Practical robotic experiments demonstrate that the method is suitable for robot programming applications. © 1963-2012 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Optimal Vision-Based Orientation Steering Control for a 3D Printed Dexterous Snake-Like Manipulator to Assist Teleoperation

TechRxiv

引用

TechRxiv 2023年

作者： Razjigaev, Andrew Pandey, Ajay K. Howard, David Roberts, Jonathan Jaiprakash, Anjali Crawford, Ross Wu, Liao The School of Electrical Engineering and Robotics The QUT Centre for Robotics Brisbane Australia The Cyber Physical Systems Program Data61 CSIRO Australia The Department of Orthopaedic Surgery Prince Charles Hospital ChermsideQLD Australia The School of Mechanical and Manufacturing Engineering University of New South Wales Sydney Australia

Endoscopic cameras attached to miniaturised snakelike continuum robotic arms can improve dexterity, accessibility, and visibility in minimally invasive surgical tasks. This steerable camera can expand the field of view and enhance the surgical experience with additional degrees of freedom. However, it also creates more control options that complicate human-machine interaction. This challenge presents an opportunity to develop novel human-machine control strategies using visual sensing to complement the dexterous actuation of a steerable surgical manipulator. This study presents a semi-autonomous controller to assist teleoperation by steering a camera such that it keeps an arbitrary target in the centre of the field of view, thus assisting in surveying different orientations about the target with image-based information. Two controllers are proposed using classical image-based visual servoing techniques and optimal visual predictive control techniques. These techniques are simulated and validated on our robot SnakeRaven: a 3D-printed patient-specific end-effector attached to the RAVEN II surgical platform. Both systems, most notably the visual predictive approach, operated successfully with robustness to a lack of information about the target. A video demonstrating the main results of this paper can be found via https://***/fiUM9qYdl1U © 2023, CC BY.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Design of Volumetric Magnetic Induction Tomography (VMIT) System Using COMSOL Simulation

Design of Volumetric Magnetic Induction Tomography (VMIT) Sy...

引用

International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET)

作者： Muhammad Nurul Puji Prawito Prajitno Warsito Purwo Taruno Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Electronic and Instrumentation Physics of The Department of Physics Universitas Indonesia Depok Indonesia C-TECH LABS Edwar Technology Tangerang Indonesia

ISBN: (数字)9798350389920

ISBN: (纸本)9798350389937

Magnetic Induction Tomography (MIT) is a low-resolution imaging technique used to reconstruct the magnetic permeability distribution of an object. COMSOL Simulation of VMIT (Volumetric Magnetic Induction Tomography) system has been developed by using 8 coils as transmitter and 8 coils as receiver. The existence of sine excitation signal in the transmitter coil cause magnetic field changing, it causing emf at the receiver coil. The magnitude of the magnetic field induction is also influenced by the permeability of the medium between the transmitter and receiver coils. COMSOL and MATLAB simulation of VMIT 8 coil systems indicate that, by using ILBP algorithms, ball-shaped object with ferromagnetic materials (iron) can be reconstructed to produce a similar image. The sensitivity matrix significantly influences image reconstruction in MIT, leading to distorted elliptical images of objects, particularly when positioned at the top center, as the matrix shows homogeneity mainly in the middle area.

关键词： Coils Microwave antennas Transmitters Magnetic resonance imaging Receivers Tomography Radar antennas Permeability Magnetic fields Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Material informatics-driven insights into brain cancer nanocarriers: A bibliometric comparison of PLGA vs. liposomes

引用

OpenNano 2025年 21卷

作者： Makalew, Brilly Andro Abrori, Syauqi Abdurrahman Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta 11480 Indonesia

This study explores a comparative analysis of PLGA nanoparticles and liposomes as potential carriers for brain cancer drug delivery, with a special focus on how material informatics enhances their design, biocompatibility, and drug release profiles to improve treatment efficacy and contribute to sustainable health outcomes. The investigation employed a bibliometric analysis using Scopus and VOSviewer to uncover the role of material informatics in optimizing these nanocarriers. The analysis revealed that material informatics, particularly through the application of machine learning and molecular dynamics simulations, significantly optimizes the performance of both PLGA nanoparticles and liposomes. The results highlighted distinct strengths of each nanocarrier: PLGA nanoparticles excel in biodegradability, while liposomes offer superior drug encapsulation capabilities. However, material informatics techniques bridged these enhancing drug release kinetics, stability, and biocompatibility. These improvements are crucial for effective delivery across the blood-brain barrier, a major challenge in brain cancer treatment. The integration of computational modelling, machine learning, and high-throughput screening enabled by material informatics is shown to be a key factor in advancing the design and optimization of these nanocarriers. By leveraging these tools, researchers can develop more personalized and efficient drug delivery systems tailored to address the specific challenges of glioblastoma therapy, ultimately contributing to sustainable health outcomes © 2024 The Author(s)

关键词： Bibliometric analysis Brain cancer Drug delivery Liposomes Material informatics Nanocarriers PLGA nanoparticles VOSviewer

来源：评论

学校读者我要写书评

暂无评论

uSkin Pillow: Tactile-Sensor-Based Non-Invasive Approach to Sleep Analysis

uSkin Pillow: Tactile-Sensor-Based Non-Invasive Approach to ...

引用

Cyber Science and Technology Congress (CyberSciTech), IEEE

作者： Riya Mahajan Yegang Du Alexander Schmitz Gabriele Trovato Yasuyuki Taki Shigeki Sugano Future Robotics Organization Waseda University Tokyo Japan Smart Ageing International Research Center Tohoku University Sendai Japan College of Engineering Innovative Global Program Shibaura Institute of Technology Tokyo Japan

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

Sleep analysis is pivotal in maintaining physical and mental health, as well as enhancing the quality of life, particularly for the elderly. Despite significant advancements in wearable sleep analysis devices in recent years, their intrusive nature often causes discomfort and reduces their acceptability among older adults. This study introduces a non-invasive method for sleep analysis utilizing tactile sensors, termed the uSkin pillow. By integrating uSkin sensors into a standard pillow, we collected data on the user's movements during sleep. This data was processed using a Savitzky-Golay digital filter and algorithmic analysis, resulting in comprehensive sleep-related information, including movement, sleep duration, respiratory rate, and sleep positions. The study also conducted experiments to evaluate both the satisfaction of elderly users with the uSkin pillow and the accuracy of its sleep analysis capabilities. The findings confirmed that the uSkin pillow is not only user-friendly but also capable of delivering sleep analysis results that are comparable to those obtained from commercially available smart bracelets. This suggests that the uSkin pillow holds significant potential as a comfortable and effective alternative for non-invasive sleep monitoring, particularly suited for the elderly population.

关键词： Accuracy Tactile sensors Mental health Sensors Older adults Digital filters Biomedical monitoring Standards Monitoring

来源：评论

学校读者我要写书评

暂无评论

Automatic Anti-Swing Gantry Crane Based on Gradient Descent Optimization Proportional Integrated Derivative (PID): A Comparison Simulation and Real Experiment

Automatic Anti-Swing Gantry Crane Based on Gradient Descent ...

引用

International Conference on Electrical engineering and Informatics, ICEEI

作者： Munzir Qadri Danang Karuna Harjanto Jonathan Miharja Winda Astuti Yosica Mariana Sofyan Tan Mahmud Iwan Solihin Mechanical Engineering Department Engineering Faculty University of Muhammadiyah Jakarta Jakarta Indonesia Computer Engineering Department Automotive and Robotics Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Industrial Engineering Department Product Design program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Departement of Mechanical & Mechatronics Engineering UCSI University Kuala Lumpur Malaysia

Transporting payload with precise swing angles and transfer times poses a challenging task in building construction, which is why gantry crane systems are extensively utilized. Various control strategies, including open-loop and closed-loop systems, have been proposed to tackle this issue. However, most of these controllers rely on a model and parameters specific to the crane system, making the process of modeling and parameter identification complex and time-consuming. To address this challenge, this work presents a practical and simulation control method for automatic gantry cranes, which is evaluated simulation and experimentally. The lab-scale Gantry crane is developed in this work, which consists of mechanical and electrical parts. Proportional Integral and Derivative (PID) and Proportional Derivative (PD) controllers which applied optimization method are implemented in the electrical part of the system. The PID and PD controller applied in controlled the position and swing angle, respectively. The Gradient Decent optimization method is the best optimization method in determining the parameter of the controller, since it has the best simulation performance in the output of the system. The experimental result is developed and compared between simulation and lab-scale Gantry crane hardware implementation part. The performance of experimental results is shown appropriately approaching the performance of the simulation result, with the approximately settling time.

关键词：

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：