检索结果-内蒙古大学图书馆

Low-Light Enhancement Visual SLAM via Deep Deformable Power Curve Estimation

IEEE Sensors Journal 2025年第10期25卷 17404-17412页

作者： Liu, Yanjie Wu, Heng Zhang, Weiwu Wang, Chao Wei, Yanlong Ren, Meixuan Harbin Institute of Technology State Key Laboratory of Robotics and System Department of Mechatronics Engineering Harbin150001 China

The unevenness and darkness of lighting in real environments are one of the main issues that affect the practical application of visual simultaneous localization and mapping (SLAM). To address this issue, we propose a visual SLAM algorithm based on low-light enhancement networks. First, we designed a lightweight low-light enhancement network based on deformable power curves, DPCE-Net, to adjust the pixels’ dynamic range of a low-light image. The curve is derived from power function, which considers the range, monotonicity, and differentiability of pixel values, and has a high dynamic range. DPCE-Net is trained and evaluated without reference images, effectively expanding the application scenarios of low-light enhancement. Then, combine the DPCE-Net with ORB-SLAM2 to construct a low-light enhancement SLAM (DPCE-SLAM). In the low-light image enhancement experiment, we compared with the state-of-the-art method, Enlighten-GAN, and Zero-DEC, achieving the good performance in structural similarity (SSIM), mean square error (mse), peak signal to noise ratio (PSNR), and natural image quality evaluator (NIQE) indicators. In state estimation evaluation, DPCE-SLAM can effectively increase the number of correctly matched feature points in dark environments, while also improving the robustness of state estimation. © 2001-2012 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

A trajectory-level robot skill learning method based on fuzzy systems

引用

Science China(Information Sciences) 2025年第5期68卷 38-52页

作者： Chao ZENG Zhen DENG Boyang TI Yongsheng GAO Department of Computer Science University of Liverpool School of Mechanical Engineering and Automation Fuzhou University State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics and System Harbin Institute of Technology

Learning from demonstration(LfD) allows for the effective transfer of human manipulation skills to a robot by building a model that represents these skills based on a limited number of demonstrated ***,a skilllearning model that can comprehensively satisfy multiple requirements,such as computational complexity,modeling accuracy,trajectory smoothness,and robustness,is still ***,this work aims to provide such a model by employing fuzzy ***,we introduce an LfD model named Takagi-Sugeno-Kang fuzzy system-based movement primitives(TSKFMPs),which exploits the advantages of the fuzzy theory for effective robotic imitation learning of human *** work formulates the TSK fuzzy system and gradient descent(GD) as imitation learning models,leveraging recent advancements in GD-based optimization for fuzzy *** study takes a two-step strategy.(ⅰ) The input-output relationships of the model are established using TSK fuzzy systems based on demonstration *** this way,the skill is encoded by the model parameter in the latent space.(ⅱ) GD is used to optimize the model parameter to increase the modeling accuracy and trajectory *** further explain how learned trajectories are adapted to new task scenarios through local *** conduct multiple tests using an open dataset to validate our method,and the results demonstrate performance comparable with those of other ***,we implement it in a real-world case study.

关键词： robot skill learning movement primitives TSK fuzzy systems gradient descent robotics

来源：评论

学校读者我要写书评

暂无评论

Online Motion Generation via Tangential Sampling-Based MPC Around Nonconvex Obstacles

引用

IEEE robotics and Automation Letters 2025年第6期10卷 5537-5544页

作者： Zhao, Guangbao Jin, Ninglong Wu, Jianhua Xiong, Zhenhua Institute of Robotics School of Mechanical Engineering State Key Laboratory of Mechanical System and Vibration Shanghai JiaoTong University Shanghai200240 China

Collision-free motion planning has a well-established research history, but the majority of studies have been centered around Euclidean space and conducted offline. The primary challenge in online motion planning lies in circumventing local minima, which become more pronounced in configuration space. We propose an online method for generating collision-free motion in configuration space that effectively avoids local minima. Our approach decomposes the optimal velocity into nominal and tangential components, with the tangential velocity optimized to facilitate escape from local minima. The tangential velocity is defined in the tangential space, with its normal direction determined by the gradient of the nearest distance between the robot and obstacles, relative to the robot's states. Direct optimization of the tangential velocity is challenging due to its dependence on varying tangent spaces. To address this, we represent the tangential velocity using the orthogonal basis of the tangent space, decoupling it from the varying tangent space. This allows explicit optimization of the tangential velocity by optimizing its components. Additionally, we introduce a warm-start operator in the tangent space to ensure the consistency and convergence. Furthermore, we propose a dynamic weight based on proximity to local minima to balance the tangential and nominal velocities, forming the optimal velocity. The effectiveness of our approach in avoiding local minima is validated through simulations and physical experiments. © 2016 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Mechanism of material removal and chip formation of alumina dispersion strengthened copper in micro-milling

引用

Frontiers of Mechanical engineering 2025年第1期20卷 27-43页

作者： Chang LIU Chunya WU Xiguang LI Bo HOU Jiahao WU Ruijiang SUN Mingjun CHEN School of Mechatronics Engineering Harbin Institute of TechnologyHarbin 150001China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Alumina dispersion-strengthened copper (ADSC), as a representative particle-reinforced metal matrix composite (PRMMC), exhibits superior wear resistance and high strength. However, challenges arise in their processability because of the non-uniform material properties of biphasic materials. In particular, limited research has been conducted on the reinforcement mechanism and behavior of particles during material cutting deformation of PRMMC with nanoscale particles. In this study, a cutting simulation model for ADSC was established, separating the nanoscale reinforcement particles from the matrix. This model was utilized to analyze the interactions among particles, matrix, and tool during the cutting process, providing insights into chip formation and fracture. Particles with high strength and hardness are more prone to storing stress concentrations, anchoring themselves at grain boundaries to resist grain fibration, thereby influencing the stress distribution in the cutting deformation zone. Stress concentration around the particles leads to the formation of discontinuous chips, indicating that ADSC with high-volume fractions of particle (VFP) exhibits low cutting continuity, which is consistent with the results of cutting experiments. The tool tip that is in contact with particles experiences stress concentration, thereby accelerating tool wear. Cutting ADSC with 1.1% VFP results in tool blunting, which increases the radius of cutting edge from 0.5 to 1.9 μm, accompanied with remarkable coating delamination and wear. Simulation results indicate that the minimum uncut chip thickness increases from 0.04 to 0.07 μm as VFP increases from 0.3% to 1.1%. In conjunction with scratch experiments, MUCT increases with the augmentation of VFP. Computational analysis of the specific cutting force indicates that particles contribute to the material’s size effect. The results of this study provide theoretical guidance for practical engineering machining of ADSC, indicating its g

关键词： alumina dispersion-strengthened copper particle-reinforced metal matrix composites material removal mechanism micro-milling chip formation minimum uncut chip thickness

来源：评论

学校读者我要写书评

暂无评论

Hybrid Tension and Configuration Control of Cable-Driven Hyper-Redundant Robots for High Accuracy and Stability

引用

IEEE robotics and Automation Letters 2025年第6期10卷 5601-5608页

作者： Zhu, Zhenpu Li, Ziqing Peng, Zhanxuan Liu, Chao Gu, Guoying Shanghai Jiao Tong University State Key Laboratory of Mechanical System and Vibration Robotics Institute School of Mechanical Engineering Shanghai200240 China

Due to the advantages of dexterity and adaptability, cable-driven hyper-redundant robots (CDHRRs) are promising for detection in confined spaces like narrow internal cavities. However, due to redundant degrees of freedom (DoFs), CDHRRs are susceptible to the singular configuration, which aggravates the difficulty of high-accuracy control and high-stable motion. To solve these problems, this work proposes hybrid tension and configuration control to improve motion accuracy and stability. Firstly, a CDHRR model with structural optimization and friction reduction is developed. The quasi-static and cable-hole length estimation models are obtained, including cable-hole friction, cable-hole interval, and cable deformation. Subsequently, single and multi-segment controllers are designed. The controller can distribute tension in the expected range with the above design while featuring high accuracy, responsiveness, and stability. The control algorithm optimizes configuration with an average error under 1.00°. Moreover, the controller reaches the target with controllable forces in 1.0 s and flattens the fluctuations within 0.3 s. The controller can be implemented into automatic zeroing and tip loading. Experimental results demonstrate that the proposed controller features speedy automatic zeroing (in 4 mins) and low angle tracking errors (less than 1.50°) under various tip loads. © 2016 IEEE.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

Leader-follower:Human-centered intention-guided controller for novel SuperLimb with application to load-carrying scenarios

引用

Science China(Technological Sciences) 2025年第1期68卷 321-334页

作者： Qinghua ZHANG Xianglong LI Hongwei JING Kerui SUN Yuancheng LI Sikai ZHAO Lele LI Haotian JU Ziqi WANG Rui WU Tianjiao ZHENG Jie ZHAO Yanhe ZHU The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China The Learning Algorithms and Systems Laboratory School of EngineeringÉcole Polytechnique Fédérale de LausanneLausanne CH 101510587Switzerland

Supernumerary robotic arms(SuperLimb)are a new type of wearable robot that works closely with humans as a third hand to augment human operation *** conveyance of wearers'intentions,allocation of roles,and humancentered interaction considerations are the key points in the process of human-SuperLimb *** paper proposes a human-centered intention-guided leader-follower controller that relies on the dynamic modeling of SuperLimb with application to load-carrying *** proposed leader-follower controller takes the human as the leader and the SuperLimb as the follower,achieving effective information communication,autonomous coordination,and good force compliance between SuperLimb,humans,and the environment under human safety ***,the human-SuperLimb dynamic system is modeled to achieve force interaction with the environment and ***,to achieve the precise intention extraction of humans,pose data from five visual odometry sensors are fused to capture the human state,the generalized position,the velocity of hands,and the surface electromyography signals from two myoelectric bracelets sensors are processed to recognize the natural hand gestures during load-carrying scenarios by a designed Swin transformer ***,based on the real-time distance detection between human and mechanical limbs,the security assurance and force-compliant interaction of the human-SuperLimb system are ***,the human hand muscle intention recognition,human-robot safety strategy verification,and comparative load-carrying experiments with and without the proposed method are conducted on the SuperLimb *** showed that the task parameters are well estimated to produce more reasonable planning trajectories,and SuperLimb could well understand the wearer's intentions to switch different SuperLimb *** proposed sensor-based human-robot communication framework motivates future studies of other collaboration scenes fo

关键词： SuperLimb leader-follower human intention estimation human-robot safety human-robot communication

来源：评论

学校读者我要写书评

暂无评论

High-precision trajectory calibration for robot surface machining by meta-heuristic search algorithm from local error in machining area

引用

International Journal of Advanced Manufacturing Technology 2025年第5期138卷 2281-2295页

作者： Bi, Guangde Lu, Lei Zhang, Lei Fan, Cheng Sun, Lining School of Mechanical and Electric Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou215123 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Industrial robots used in complex surface machining are gradually increasing because of their high flexibility and large workspace. However, due to their low geometric accuracy, their application in high-precision surface machining is hindered. In order to improve the machining accuracy, a high-precision robot trajectory calibration method for complex surface machining is proposed. In the machining process, the machining trajectory is usually only within a certain machining area. In the method, high-precision standard balls are set at the boundary of the machining area. Based on the precise position information of these standard balls, the trajectory of the robot in the machining area is calibrated. Compared with the global robot calibration method, the proposed method can calibrate the robot trajectory in the machining area through standard parts, which will improve the trajectory accuracy of the machining robot to the level of repeated positioning accuracy. In this method, a large amount of standard ball data is obtained by the in-place measuring device before the machining process. Then, based on these data, a meta-heuristic search algorithm is used to calibrate the kinematic deviation of the robot measurement and the machining system. The trajectory of the machining robot is adjusted by the kinematic deviation after calibration, and it is applied to the motion control of the machining process to improve the positioning accuracy of the machining trajectory. In the end, to verify the accuracy and practicability of the machining trajectory obtained by this method, measurement and machining experiments are carried out. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Modeling tactile perceived intensity for vibration from a coin eccentric rotating mass motor

引用

Science China(Technological Sciences) 2025年第2期68卷 125-135页

作者： Yun FANG Jingchen HUANG Yujun WU Jiaqi DONG Weichao GUO Xinjun SHENG State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Meta Robotics Institute Shanghai Jiao Tong UniversityShanghai 200240China

Establishing the relationship between vibrotactile parameters and perceived intensity(PI)is of great significance in the regulation of desired sensations,which contribute to haptic interfaces in practical *** eccentric rotating mass(ERM)motors are routinely utilized due to their lightweight design and efficient ability to evoke strong tactile *** adjusting input voltages,ERMs can yield different stimuli,but the effects of their physical properties on PI remain ***,we developed the physical model of the ERM-skin system and optimized the parameters affecting ***,the relationship between stimulus and perception was derived based on Fechner's *** experiments were conducted on fifteen subjects(ten males and five females,aged 24.40±2.87 years)to identify the vibration parameters and corresponding PI to verify the proposed PI *** in this study were attached to phantom skin/forearm with slim adhesive tape to minimize the *** 1 performed vibration calibration with ERM attached to the skin phantom to simulate the actual ***,the relative and absolute PI of subjects on specific stimuli were acquired in Experiments 2 and *** fitting reliability of the proposed PI model was evaluated on fifteen subjects with R^(2) of 0.73±0.07 and root mean squared error(RMSE)of 1.35±***,the proposed PI model established the quantitative relationship between stimulus parameters(vibration parameters and physical parameters)and subjective PI,which provided theoretical support for ERM optimization and vibrotactile modulation.

关键词： coin ERM vibrotactile perceived intensity vibration

来源：评论

学校读者我要写书评

暂无评论

A High-Power Wave Energy Harvester with Mag-Boost Mechanism 5th

A High-Power Wave Energy Harvester with Mag-Boost Mechanism

引用

5th International Conference on Vibration and Energy Harvesting Applications, VEH 2024

作者： Tang, Tianyi Li, Yunfei Sun, Lining Liu, Huicong State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China School of Mechanical and Electrical Engineering Jiangsu Provincial Key Laboratory of Advanced Robotics Soochow University Suzhou China

ISBN: (纸本)9789819611904

Ocean wave energy is a widely anticipated new type of renewable energy. However, due to the ultra-low-frequency and random motion characteristics of ocean waves, effectively harnessing it presents a significant challenge. This paper proposes a Mag-Boost mechanism based on the phenomenon that the magnetic torque undergoes a sudden change when the magnetic poles of two magnets are orthogonal. This innovative mechanism, requiring just a trigger below 1 Hz, can stimulate a power-magnet to generate high-frequency oscillation without direct contact. Utilizing this mechanism, a high-power wave energy harvester (WEH) with ultra-low-frequency response capabilities has been developed. Tested on a six-degree-of-freedom platform, the WEH demonstrated a high-output power of 1.44W and a power density of 1.2 kW/m3 at a frequency of 1 Hz and an inclination angle of 30°. The peak open-circuit voltage of the WEH reached 5 V, ensuring a completely independent and stable power supply for wireless temperature and humidity sensors. Furthermore, the Mag-Boost mechanism also shows considerable potential for harvesting other forms of low-frequency environmental energy, including wind, vibration, and human kinetic energy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Water waves

来源：评论

学校读者我要写书评

暂无评论

FWAF-VID: A Flapping-Wing Aggressive Flight Benchmark Dataset for Visual-Inertial Localization

引用

IEEE robotics and Automation Letters 2025年第6期10卷 6328-6335页

作者： Jiang, Jizhou Pan, Erzhen Xu, Wenfu Sun, Wei Ye, Jingyang Harbin Institute of Technology School of Robotics and Advanced Manufacture Shenzhen518055 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen518055 China Guangdong Biomimetic Intelligent Unmanned System Engineering Technology Research Center Shenzhen518052 China

Accurate state estimation of micro aerial vehicles (MAVs) in high-speed and dynamic environments poses a significant challenge for visual-inertial odometry (VIO) algorithms. Flapping-wing aerial vehicles (FWAVs), as an emerging flight platform, have attracted significant attention for stealth capabilities and efficient flight characteristics. Despite the availability of numerous MAV visual-inertial datasets for six-degree-of-freedom (6-DoF) state estimation, these datasets are not applicable for FWAVs with pronounced vibrations and agile maneuverability. To address this gap, we propose a large-scale flapping-wing aggressive flight visual-inertial dataset FWAF-VID. It contains diverse integrations of synchronized onboard cameras and IMU sensors. A total of 28 sequences include static flapping, calibration, and real-world flights collected in outdoor and indoor environments. The 17 flight sequences feature variations in illuminations, speeds, trajectories, camera perspectives, and flight modalities. We provide precisely aligned ground truth RTK and UWB measurements for algorithm evaluation. Furthermore, a comprehensive benchmark comparison is conducted, qualitatively and quantitatively evaluating the positioning accuracy of state-of-the-art VIO algorithms. The experimental results indicate that despite the degradation in localization accuracy in high-dynamic environments, FWAF-VID can effectively support the further development of VIO algorithms for FWAVs. To the best of our knowledge, this is the first onboard benchmark dataset tailored for aggressive flight in flapping-wing airborne platforms. © 2025 IEEE.

关键词： Micro air vehicle (MAV)

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：