检索结果-内蒙古大学图书馆

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Tanin Boka M. Navid Nikkhah S. Ali A. Moosavian Dept of Mechanical Engineering K. N. Center of Excellence in Robotics and Control Advanced Robotics & Automated Systems (ARAS) Laboratory Toosi University of Technology Tehran Tehran Iran Dept of Mechanical Engineering K. N. Toosi University of Technology Tehran Tehran Iran

This paper introduces an innovative advancement in the field of wearable assistive technology by presenting a revolutionary portable soft robotic glove designed to assist individuals with hand impairments during rehabilitation exercises and daily tasks. The glove offers both active finger flexion and passive extension to aid in hand support and rehabilitative training. It achieves this by utilizing integrated soft actuators, including a variable stiffness layer and a pneumatic-driven layer, which guide specific bending, twisting, and extending movements when air pressure is applied. Notably, the variable stiffness layer takes inspiration from pangolins, whose scales are pliable during daily activities but become rigid when facing threats. To provide increased power with enhanced stiffness, a toothed pneumatic actuator is specially designed. The three-finger soft glove is manufactured by molding super-elastic material, creating the actuator mold using a 3D printer. The glove’s grasping abilities have been thoroughly tested, and experimental results demonstrate that, when compared to previously developed elastomeric-based actuators, these actuators can generate substantial force and torque to facilitate finger flexion even at lower air pressure levels. This capability allows the glove to grasp a wide range of objects, assisting individuals in their rehabilitative training. Furthermore, a control system for grasping has been developed, which includes motion processing unit sensors for collecting feedback signals aligned with the actuators, along with a closed-loop controller for regulating the pressure. In contrast to existing devices, this glove, thanks to its portable design, has the potential to significantly enhance user autonomy and independence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in D...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： Adarsh Sehga Nicholas Ward Hung Manh La Christos Papachristos Sushil Louis Advanced Robotics and Automation (ARA) Laboratory Department of Computer Science and Engineering University of Nevada Reno NV USA

ISBN: (纸本)9781665472616

Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.

关键词： Deep learning Reinforcement learning Task analysis Robots Tuning Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

GraspContrast: Self-supervised Contrastive Learning with False Negative Elimination for 6-DoF Grasp Detection

GraspContrast: Self-supervised Contrastive Learning with Fal...

引用

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

作者： Wenshuo Wang Haiyue Zhu Marcelo H. Ang Department of Mechanical Engineering National University of Singapore Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research (A*STAR) Singapore Advanced Robotics Centre National University of Singapore Singapore Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Robotic manipulation is a grand domain that primarily involves the use of robotic arms to interact with objects in the environment. While proposed methods have achieved advancements in grasping objects, they rely heavily on extensive training data that presents a significant challenge due to the labor-intensive process of human annotation. To address the issue, we propose GraspContrast, a self-supervised contrastive learning framework leveraging unlabeled RGB-D images to enhance point-wise feature representations for 6-DoF grasp detection. Our method designs a dual-branch network architecture to learn transformations that embed positive point pairs nearby, while pushing negative point pairs far apart. Specifically, we discuss a false negative elimination strategy to explicitly detect and remove the false negative samples that undesirably repel the point instances from the geometrically similar samples. Our method exhibits consistent improvements over existing learning-based grasp detection methods on both the GraspNet-1B benchmark and physical UR10e platform. These significant performance gains demonstrate the effectiveness of our proposed framework.

关键词： Point cloud compression Three-dimensional displays Annotations Pipelines Training data Contrastive learning Performance gain Network architecture Feature extraction 6-DOF

来源：评论

学校读者我要写书评

暂无评论

Mechatronic Design and Fabrication of Aerogenerator composed of Vertical Axis Wind Energy Station with Helical Blades

Mechatronic Design and Fabrication of Aerogenerator composed...

引用

IEEE Students' Conference on Electrical, Electronics and Computer Science (SCEECS)

作者： Adrian Nacarino Andre Rueda-Lopez Anderson La-Rosa Jose Cornejo Ricardo Palomares Professional School of Mechatronics Engineering Ricardo Palma University Lima Peru Universidad Tecnologica del Peru Lima Peru Research Group of Advanced Robotics and Mechatronics (GI-ROMA) Ricardo Palma University Lima Peru

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

An innovative research, supervised by the Research Group of advanced robotics and Mechatronics (GI-ROMA) and the Mechatronics engineering School at Ricardo Palma University, was conducted, which explored the development of a helical vertical axis wind energy station. The mechanical design of the helical vertical axis focused on determining the blade type to achieve a shear stress of τ=5*10 -10 , nearly negligible, to let a continuous air flow and obtain a desired voltage output of 5 V. The electrical and electronic design included developing a voltage rectification stage to obtain a regulated output of 5 V; subsequently, 6 V 4.5 Ah batteries were charged and connected in series, with a maximum voltage of 12.67 V, as determined experimentally, which was then connected to a voltage inverter which produced 220 V at 200 W, capable of powering appliances like a 5 W light bulb with a 78.50% efficiency.

关键词： Renewable energy sources Mechatronics Wind energy Blades Inverters Wind turbines Voltage control Sustainable development Stress Robots

来源：评论

学校读者我要写书评

暂无评论

Contacts from Motion: Learning Discrete Features for Automatic Contact Detection and Estimation from Human Movements *

Contacts from Motion: Learning Discrete Features for Automat...

引用

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

作者： Hibiki Miyake Ko Ayusawa Ryusuke Sagawa Eiichi Yoshida Department of Medical and Robotic Engineering Design Faculty of Advanced Engineering Tokyo University of Science Tokyo Japan Human Augmented Research Center (Kashiwa Chiba) CNRS-AIST JRL (Joint Robotics Laboratory) IRL Artificial Intelligence Research Center (Tsukuba Ibaraki) National Institute of Advanced Industrial Science and Technology (AIST) Japan

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper presents a novel method for detecting and estimating contact forces only from human motions using machine learning techniques. Knowing the location of the contacts with the environment and the magnitude of the exerted force is critical for dynamic human motion analysis. However, their annotation is usually made manually from captured motion data especially in case of multiple contacts even if the data includes force measurement. Moreover, most existing human motion datasets do not include contact force. To overcome these bottlenecks, we introduce a network that leverages vector-quantized variational autoencoder (VQ-VAE) and self-attention that learns a small set of discrete feature values representing various contact states. These feature values, called contact codes, allow human motions to be converted to contact states and resulting forces. By applying an optimization for contact estimation with a reduced set of manual annotations, the existence of contacts can be automatically determined, which is essential information for dynamic analysis. We validated the effectiveness and potential usefulness of the proposed method with a human walking gait dataset, by converting the human motions into contact sequences and forces and applying the estimated contacts to dynamic motion analysis.

关键词： Legged locomotion Codes Annotations Force Dynamics Estimation Manuals Feature extraction Motion analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Real Time Humanoid Footstep Planning With Foot Angle Difference Consideration for Cost-To-Go Heuristic

Real Time Humanoid Footstep Planning With Foot Angle Differe...

引用

International Conference on Ubiquitous Robots (UR)

作者： Joon-Ha Kim Young-Ha Shin Hyobin Jeong Jun-Ho Oh Hae-Won Park Department of Mechanical Engineering Humanoid Research Center School of Mechanical Aerospace & Systems Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea Rainbow Robotics Company Daejeon Republic of Korea

This paper proposes a real-time footstep planning framework based on the A* footstep planning algorithm. The proposed footstep planner utilizes an energy consumption-based cost function to generate energy efficient navigation plan. To increase the computational efficiency, the cost-to-go heuristic function, which approximates the remaining cost to reach the goal, is modeled more precisely by considering the angle difference between the robot and the goal position. Furthermore, an efficient dual-level feasibility check is done to avoid occlusion with the environment while stepping over small objects if possible. Finally, the proposed footstep planning algorithm is integrated with the mapping algorithm and the walking controller to solve the humanoid navigation problem and validated in simulation and real-world experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Environmental Exploration and Target Tracking Control for Unmanned Surface Vehicles in Uncertain Environment

Autonomous Environmental Exploration and Target Tracking Con...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Kaiwei Zhu Shihan Kong Fang Wu Jinan Sun Junzhi Yu Department of Advanced Manufacturing and Robotics State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China SPIC Nuclear Energy Co. Ltd. China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

In this paper, a set of methods of autonomous obstacle exploration, avoiding, and target-tracking control in the uncertain environment is proposed. First, a secure and reliable obstacle exploration framework via multi-sensors information fusion is developed for USV to autonomously perceive obstacles in unknown environments. Second, a modified dynamic artificial potential field-based path planning method is proposed to dynamically generate a safe and feasible path even without complete prior obstacle position information. Third, a robust sliding mode control law with extended state observer is designed to track expectational target in the dynamical and uncertain environment. Finally, the target-tracking control law has been validated through the simulation experiments. Besides, the proposed methods of obstacle exploration, path planning, and target-tracking control are comprehensively evaluated through the simulation experiments in WEBOTS software, which is closer to the real world.

关键词： Target tracking Observers Path planning Software Real-time systems Reliability Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Object Detection and Tracking for Autonomous Vehicles using Deep Learning Technique- YOLO

Object Detection and Tracking for Autonomous Vehicles using ...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Nilesh Parmanand Motwani Soumya S Upasna Singh School of Robotics Defence Institute of Advanced Technology Pune India School of Computer Engineering and Mathematical Sciences Defence Institute of Advanced Technology Pune India

For self-driving cars, Optical Perception is the most important factor. By accurately detecting road signs, foottravelers and vehicles, it could help and guide auto driven vehicles to drive as safely as human beings. In recent times, several CNN (Convolutional Neural Network) centered classification- after-localization methods have increased detection results under various situations. It is not possible for the two-stage methods to be used in real-time situations as it has very slow recognition speed. In recent times, (YOLO) You Only Look Once, was anticipated, can straight forwardly degenerate to object class positions and scores from input image. This model has single network structure and has greater detection precision than present-day real-time methods. This model handles images at 45 frames per second on PASCAL VOC 2007 dataset. In this detailed study and research, YOLO model is implemented to verify its general applicability, on three unlike datasets. This helped to completely scrutinized its behavior from several features on KITTI dataset which is specifically dedicated for self-directed driving. KITTI is my key dataset. In addition, for pre-training, ImageNet dataset is used and rest three datasets are implemented for other class domains are FDDB (Face Detection Dataset & Benchmarks), Road Signs, Pascal VOC-2007/2012

关键词： Deep learning Roads Optical computing Object detection Benchmark testing Optical imaging Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Influence of melanopic illuminance on spatial brightness in interior spaces: A controlled-variable study with comparison spectra

引用

Building and Environment 2025年 281卷

作者： Hu, Zhiguo Li, Jiuhui Zhang, Mingdao Dai, Qi Institute of Future Lighting Academy for Engineering & Technology Fudan University Shanghai China School of Intelligent Robotics and Advanced Manufacturing Fudan University Shanghai China Zhongshan - Fudan Joint Innovation Center Guangdong Zhongshan China

Spatial brightness, a visual perception related to the magnitude of overall ambient lighting, has become a key aspect of indoor lighting quality. Traditional lighting measures, however, cannot accurately assess spatial brightness across different lighting spectra as the spectral sensitivity of spatial brightness differs from the V(λ) function, particularly in the short-wavelength range. Previous studies have reported that intrinsically photosensitive retinal ganglion cells (ipRGCs) may contribute to spatial brightness, but conclusive evidence is lacking, as potential interference from other photoreceptors and spectral attributes has not been excluded. This study aims to investigate the direct impact of ipRGCs on spatial brightness of interior spaces, with other influencing spectral attributes strictly controlled. A color-mixing lighting system with nine spectral channels was used to generate five comparison spectra, covering a wide tuning range of ipRGC-related melanopic illuminance at fixed levels of photopic illuminance, cyanopic illuminance, chromaticity coordinates, gamut index (Rg), while maintaining color fidelity (Rf) values greater than 70. Human-factor studies were conducted to compare spatial brightness across these comparison spectra with controlled variables. The results indicated that increasing melanopic illuminance alone leads to a small but clear increase in spatial brightness when other spectral factors are held constant, proving the positive contribution of ipRGCs to spatial brightness. Additionally, this contribution is influenced by the corneal illuminance levels: when corneal illuminance is between 50 and 150 lx, ipRGCs have a clear positive impact on spatial brightness;however, when the corneal illuminance is outside of this range, changing ipRGC stimulation alone does not affect spatial brightness. © 2025 Elsevier Ltd

关键词： Color vision

来源：评论

学校读者我要写书评

暂无评论

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke Patient During Walking

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke ...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Shang, Wenze Huang, Ruisen Liao, Wei-Hsin Wu, Xinyu Gao, Fei Southern University of Science and Technology Shenzhen518005 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong999077 Hong Kong

ISBN: (纸本)9781665481090

SEMG signal is widely used and explored in control strategies of powered assistive human-robot interaction systems due to its non-invasive nature and ability to estimate motion intention well. However, prolonged use of the sEMG-based systems leads to muscle fatigue, contributing to unstable sEMG signals and regarding the performance of sEMG-based control strategies. In this study, three subjects, including two healthy subjects and one stroke subject, participated in our experiment, and the time domain, frequency domain, and complex features extracted from their sEMG signals were utilized to evaluate muscle fatigue. The results indicate that sEMG from the stroke side of the stroke subject contains more non-linear and chaotic parts, and the statistical differences between different trials are more significant, indicating that stroke has a more significant impact on the stroke side of the stroke subject. This study suggests that RMS in the stroke side of stroke subjects is less than that in others, whereas FuzzyEn in the stroke side of stroke subjects is greater than that in others, indicating that stroke leads to different motion patterns and more susceptibility to muscle fatigue. © 2024 IEEE.

关键词： Human robot interaction

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：