Query：
学者姓名：吴海彬
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
针对机器人示教编程过程中使用高斯混合模型(GMM)规划运动轨迹时存在的高斯分布个数难以选择、复现轨迹精度较低等问题,提出了一种复合的机器人运动轨迹学习策略.该策略包含动态时间规整(DTW)算法、高斯混合模型与道格拉斯-普克(DP)算法.首先,针对示教过程中采集的多条轨迹在时间长度上存在差异的问题,采用DTW 算法来统一示教轨迹在时域上的变化.其次,使用 GMM 算法对示教轨迹的特征进行提取,并利用高斯混合回归(GMR)算法将其重构为复现轨迹.在这个过程中采用DP算法来预估GMM算法的关键参数高斯分布的数量,与传统方法相比,能够简单直观地得到相对准确的参数值.利用 DP 算法对复现轨迹的数据点进行稀疏化并优化,不仅确保了机器人最终运动轨迹的精度,而且大幅减少了最终轨迹数据点的数量.最后,进行了不同形状的模拟焊接轨迹学习规划实验.结果表明:经由 DTW 对齐后的示教轨迹具有更加明显的运动特征,经过 GMM-GMR 学习输出的复现轨迹具有良好的表征结果;在使用GMM-GMR算法学习示教轨迹的过程中,采用DP算法可以有效预估高斯分布个数;经过DP算法稀疏化并优化的最终轨迹的平均位置误差均在 0.500 mm以内,其最大误差可以控制在0.800 mm以内,可以满足焊接轨迹规划的精度要求,验证了该策略的有效性和优越性.
Keyword ：
动态时间规整 动态时间规整 工业机器人 工业机器人 示教编程 示教编程 轨迹复现 轨迹复现 道格拉斯-普克算法 道格拉斯-普克算法 高斯混合模型 高斯混合模型
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 肖洒 , 陈旭阳 , 叶锦华 et al. 一种基于DTW-DP-GMM的工业机器人轨迹学习策略 [J]. | 天津大学学报（自然科学与工程技术版） , 2025 , 58 (1) : 68-80 . |
| MLA | 肖洒 et al. "一种基于DTW-DP-GMM的工业机器人轨迹学习策略" . | 天津大学学报（自然科学与工程技术版） 58 . 1 (2025) : 68-80 . |
| APA | 肖洒 , 陈旭阳 , 叶锦华 , 吴海彬 . 一种基于DTW-DP-GMM的工业机器人轨迹学习策略 . | 天津大学学报（自然科学与工程技术版） , 2025 , 58 (1) , 68-80 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对随机采样一致性(random sample consensus,RANSAC)算法对含有噪声的点云数据进行平面拟合时效果不佳和容易产生误识别的问题,对算法进行改进.通过基于密度的噪声应用空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法改变RANSAC算法初始点集合的选择策略,并使用主成分分析法(principal component analysis,PCA)计算点云各点法向量,以点到平面距离以及点的法向量与平面法向量夹角两个约束条件同时作为RANSAC算法平面拟合模型内点判定的准则.采用无噪声与分别含有300个噪声点和500个噪声点的点云仿真数据进行测试,本文算法拟合结果均接近理论值且内点距离标准差分别为1.007×10-8、0.003、0.007,优于RANSAC算法.采用实际工件点云数据在两种工况场景下进行测试,本文算法拟合平面内点比率相对于传统RANSAC算法分别提高24.7%和24.6%,平面提取完整度及准确率同样优于RANSAC算法.仿真模拟及实例分析证明了本文算法的有效性.
Keyword ：
主成分分析 主成分分析 噪声 噪声 密度聚类 密度聚类 点云平面拟合 点云平面拟合 随机采样一致性 随机采样一致性
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 叶锦华 , 林旭敏 , 吴海彬 . 基于DBSCAN的改进RANSAC点云平面拟合算法 [J]. | 湖南大学学报（自然科学版） , 2025 , 52 (2) : 76-87 . |
| MLA | 叶锦华 et al. "基于DBSCAN的改进RANSAC点云平面拟合算法" . | 湖南大学学报（自然科学版） 52 . 2 (2025) : 76-87 . |
| APA | 叶锦华 , 林旭敏 , 吴海彬 . 基于DBSCAN的改进RANSAC点云平面拟合算法 . | 湖南大学学报（自然科学版） , 2025 , 52 (2) , 76-87 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The accurate detection and identification of collision states in industrial robot environments is a critically important and challenging task. Deep learning-based methods have been widely applied to collision detection; however, these methods primarily rely on dynamic models and dynamic threshold settings, which are subject to modeling errors and threshold adjustment latency. To address this issue, we propose MomentumNet-CD, a novel collision detection method for industrial robots that leverages backpropagation (BP) neural networks. MomentumNet-CD extracts collision state features through a momentum observer and constructs an observation model using Mahalanobis distance. These features are then processed by an optimized three-layer BP neural network for accurate collision identification. The network is trained using a modified Levenberg-Marquardt algorithm by introducing regularization terms and continuous probability outputs. Furthermore, we developed a comprehensive acquisition system based on the Q8-USB data acquisition card and the QUARC 2.7 real-time control environment. The system integrates key hardware components including a MR-J2S-70A servo driver, ATI six-dimensional force/torque (F/T) sensor, and ISO-U2-P1-F8 isolation transmitter, and the corresponding software module is developed through MATLAB/Simulink R2022b, which achieves the high-frequency real-time acquisition of critical robot joint states. The experimental results show that the MomentumNet-CD method achieves an overall accuracy of 93.65% under five different speed conditions, and the detection delay is only 12.16 ms. Compared with the existing methods, the method shows obvious advantages in terms of the accuracy and response speed of collision detection.
Keyword ：
BP neural network BP neural network industrial robot industrial robot Levenberg-Marquardt algorithm Levenberg-Marquardt algorithm Mahalanobis distance Mahalanobis distance momentum observer momentum observer
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Jinhua , Fan, Yechen , Kang, Quanjie et al. MomentumNet-CD: Real-Time Collision Detection for Industrial Robots Based on Momentum Observer with Optimized BP Neural Network [J]. | MACHINES , 2025 , 13 (4) . |
| MLA | Ye, Jinhua et al. "MomentumNet-CD: Real-Time Collision Detection for Industrial Robots Based on Momentum Observer with Optimized BP Neural Network" . | MACHINES 13 . 4 (2025) . |
| APA | Ye, Jinhua , Fan, Yechen , Kang, Quanjie , Liu, Xiaohan , Wu, Haibin , Zheng, Gengfeng . MomentumNet-CD: Real-Time Collision Detection for Industrial Robots Based on Momentum Observer with Optimized BP Neural Network . | MACHINES , 2025 , 13 (4) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Technology is nudging robot into automation and intelligence field, making dynamic collision avoidance indispensable in robotics. Aiming at safety control of mobile manipulator in human-robot coexistence environment, a novel artificial potential field based on danger index (DIAPF) approach is proposed. Firstly, hinged on the kinematic and dynamic model of mobile manipulators, a danger index system is established to take precautions against accident during the operation. We further improve the repulsion field and velocity repulsive field to promote dynamic obstacle avoidance in the human-robot coexistence environments. Feasibility and effectiveness of the proposed method are verified in simulation environment. © 2025 Acta Press. All rights reserved.
Keyword ：
Accident prevention Accident prevention Accidents Accidents Industrial robots Industrial robots Intelligent robots Intelligent robots Mobile robots Mobile robots Social robots Social robots
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Jinhua , Hong, Linxin , Wu, Haibin et al. AN IMPROVED APF METHOD FOR SAFETY CONTROL OF MOBILE MANIPULATOR IN HUMAN-ROBOT COEXISTENCE ENVIRONMENT [J]. | International Journal of Robotics and Automation , 2025 , 40 (3) : 184-193 . |
| MLA | Ye, Jinhua et al. "AN IMPROVED APF METHOD FOR SAFETY CONTROL OF MOBILE MANIPULATOR IN HUMAN-ROBOT COEXISTENCE ENVIRONMENT" . | International Journal of Robotics and Automation 40 . 3 (2025) : 184-193 . |
| APA | Ye, Jinhua , Hong, Linxin , Wu, Haibin , Zheng, Gengfeng . AN IMPROVED APF METHOD FOR SAFETY CONTROL OF MOBILE MANIPULATOR IN HUMAN-ROBOT COEXISTENCE ENVIRONMENT . | International Journal of Robotics and Automation , 2025 , 40 (3) , 184-193 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this letter, we propose the B-GHF framework, an end-to-end collision state inference method based on a Bayesian framework that does not rely on external force/torque (F/T) sensors in the human-robot collaboration (HRC) environment. This method integrates GMM for probabilistic object position and error analysis, HMP for temporal collision state evolution, and BNN for observational uncertainties. Dynamic collision state assessment and decision uses multi-joint state-weighted integration and recursive Bayesian updates. The experimental results show that B-GHF achieves a detection success rate of 98.36% and an average detection time of 8.34 ms, significantly outperforming both a state-of-the-art (SOTA) learning-based method (MCD-CNN) and a classic model-based approach (MO-ID) in terms of accuracy, speed, and robustness.
Keyword ：
Accuracy Accuracy Bayesian neural network Bayesian neural network Bayes methods Bayes methods Collision avoidance Collision avoidance Covariance matrices Covariance matrices Gaussian mixture model Gaussian mixture model hidden Markov process hidden Markov process Human-robot collaboration Human-robot collaboration Probability distribution Probability distribution Robots Robots Robot sensing systems Robot sensing systems Sensors Sensors Uncertainty Uncertainty Vectors Vectors
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Jinhua , Fan, Yechen , Wu, Haibin et al. A Bayesian Framework Based on Gaussian Mixture Model and Hidden Markov Process for Collision Detection in Cobots [J]. | IEEE ROBOTICS AND AUTOMATION LETTERS , 2025 , 10 (10) : 10554-10561 . |
| MLA | Ye, Jinhua et al. "A Bayesian Framework Based on Gaussian Mixture Model and Hidden Markov Process for Collision Detection in Cobots" . | IEEE ROBOTICS AND AUTOMATION LETTERS 10 . 10 (2025) : 10554-10561 . |
| APA | Ye, Jinhua , Fan, Yechen , Wu, Haibin , Zhang, Xin , Zhao, Jianghao , Zhang, Xinjie et al. A Bayesian Framework Based on Gaussian Mixture Model and Hidden Markov Process for Collision Detection in Cobots . | IEEE ROBOTICS AND AUTOMATION LETTERS , 2025 , 10 (10) , 10554-10561 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The users often encounter issues such as difficulty in selecting the appropriate number of Gaussian distributions and low accuracy in reproducing trajectories when using Gaussian mixture model(GMM)to plan robot trajectories during programming by demonstration. To address these concerns，a composite strategy is proposed，which integrates dynamic time warping(DTW)algorithm，GMM and the Douglas-Peucker(DP)algorithm. First，to address the issue of varying time lengths in multiple trajectories，the DTW algorithm is used to align the variation of the demonstrated trajectories in the time domain. Second，the motion features are learned from the aligned demonstrated trajectories using GMM，which can subsequently be reconstructed into a reproduced trajectory using Gaussian mixture regression(GMR). In this process，the number of Gaussian distributions，a key parameter of GMM，is estimated by DP algorithm，which can derive a relatively precise parameter value simply and intuitively compared with the traditional method. Furthermore，the DP algorithm is employed to sparsify and optimize the data points in the reproduced trajectory，ensuring that the final trajectory maintains high precision while drastically reducing the number of data points in the final trajectory. Finally，experiments conducted on simulated welding trajectories of different shapes are carried out. The experimental results show that the demonstrated trajectories aligned by DTW exhibit more pronounced motion features，and the reproduced trajectory generated using GMM-GMR has great representation result；moreover，the DP algorithm effectively estimates the necessary number of Gaussian distributions for GMM-GMR learning. The average positional errors in final trajectories sparsified by the DP algorithm are within 0.500 mm，and the maximum errors can be controlled within 0.800 mm，meeting the precision requirements of welding trajectory planning. It verifies the effectiveness and the superiority of the proposed strategy. © 2025 Tianjin University. All rights reserved.
Keyword ：
Gaussian distribution Gaussian distribution Industrial robots Industrial robots Robot programming Robot programming
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiao, Sa , Chen, Xuyang , Ye, Jinhua et al. A Strategy for Industrial Robot Trajectory Learning Based on DTW-DP-GMM [J]. | Journal of Tianjin University Science and Technology , 2025 , 58 (1) : 68-80 . |
| MLA | Xiao, Sa et al. "A Strategy for Industrial Robot Trajectory Learning Based on DTW-DP-GMM" . | Journal of Tianjin University Science and Technology 58 . 1 (2025) : 68-80 . |
| APA | Xiao, Sa , Chen, Xuyang , Ye, Jinhua , Wu, Haibin . A Strategy for Industrial Robot Trajectory Learning Based on DTW-DP-GMM . | Journal of Tianjin University Science and Technology , 2025 , 58 (1) , 68-80 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
PurposeThis study aims to address the issue that existing methods for limb action recognition typically assume a fixed wearing orientation of inertial sensors, which is not the case in real-world human-robot interaction due to variations in how operators wear it, installation errors, and sensor movement during operation.Design/methodology/approachTo address the resulting decrease in recognition accuracy, this paper introduced a data transformation algorithm that integrated the Euclidean norm with singular value decomposition. This algorithm effectively mitigates the impact of orientation errors on data collected by inertial sensors. To further enhance recognition accuracy, this paper proposed a method for extracting features that incorporate both time-domain and time-frequency domain features, markedly improving the algorithm's robustness. This paper used five classifiers to conduct comparative experiments on action recognition. Finally, this paper built an experimental human-robot interaction platform.FindingsThe experimental results demonstrate that the proposed method achieved an average action recognition accuracy of 96.4%, conclusively proving its effectiveness. This approach allows for the recognition of data from sensors placed in any orientation, using only training samples conducted at an orientation.Originality/valueThis study addresses the challenge of reduced accuracy in limb action recognition caused by sensor misorientation. The human-robot interaction system developed in this paper was experimentally verified to effectively and efficiently guide the industrial robot to perform tasks based on the operator's limb actions.
Keyword ：
Euclidean norm Euclidean norm Heuristic algorithm Heuristic algorithm Human-robot interaction Human-robot interaction Inertial sensor Inertial sensor Limb action recognition Limb action recognition
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Song, Chenyang , Wu, Jianxuan , Wu, Haibin . Orientation - invariant limb action recognition method for human-robot interaction [J]. | SENSOR REVIEW , 2025 , 45 (2) : 286-295 . |
| MLA | Song, Chenyang et al. "Orientation - invariant limb action recognition method for human-robot interaction" . | SENSOR REVIEW 45 . 2 (2025) : 286-295 . |
| APA | Song, Chenyang , Wu, Jianxuan , Wu, Haibin . Orientation - invariant limb action recognition method for human-robot interaction . | SENSOR REVIEW , 2025 , 45 (2) , 286-295 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Traditional flexible tactile sensors usually have high hysteresis and creep due to the use of viscoelastic materials such as Polydimethylsiloxane, rubber, etc., which brings about the low data accuracy and high unreliability in dynamic and static loading applications. Herein, a capacitive tactile sensor based on airbag-structured electrode (ASE) is proposed, which has low hysteresis and creep. The feasibility of ASE in reducing the hysteresis and creep of sensors is determined by theoretical derivation and finite element analysis and confirmed through experimental data. Based on the ASE, the proposed sensor has low hysteresis of 2.94% and low creep of 3.11%. In addition, the sensor also has key characteristics such as good sensitivity, wide linear sensing range, low detection limit, high durability, and good repeatability. These features enable the sensor to perform well in dynamic and static loading applications and show a promising potential for other applications in human-machine interaction.
Keyword ：
Airbag-structured electrodes Airbag-structured electrodes Creep Creep Human-machine interaction Human-machine interaction Hysteresis Hysteresis Tactile sensor Tactile sensor
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Hao , He, Zuen , Yea, Jinhua et al. Capacitive tactile sensors with airbag-structured electrodes for low hysteresis and creep [J]. | SENSORS AND ACTUATORS A-PHYSICAL , 2025 , 393 . |
| MLA | Chen, Hao et al. "Capacitive tactile sensors with airbag-structured electrodes for low hysteresis and creep" . | SENSORS AND ACTUATORS A-PHYSICAL 393 (2025) . |
| APA | Chen, Hao , He, Zuen , Yea, Jinhua , Wu, Haibin . Capacitive tactile sensors with airbag-structured electrodes for low hysteresis and creep . | SENSORS AND ACTUATORS A-PHYSICAL , 2025 , 393 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
PurposeImitation learning is a powerful tool for planning the trajectory of robotic end-effectors in Cartesian space. Present methods can adapt the trajectory to the obstacle; however, the solutions may not always satisfy users, whereas it is hard for a nonexpert user to teach the robot to avoid obstacles in time as he/she wishes through demonstrations. This paper aims to address the above problem by proposing an approach that combines human supervision with the kernelized movement primitives (KMP) model.Design/methodology/approachThis approach first extracts the reference database used to train KMP from demonstrations by using Gaussian mixture model and Gaussian mixture regression. Subsequently, KMP is used to modulate the trajectory of robotic end-effectors in real time based on feedback from its interaction with humans to avoid obstacles, which benefits from a novel reference database update strategy. The user can test different obstacle avoidance trajectories in the current task until a satisfactory solution is found.FindingsExperiments performed with the KUKA cobot for obstacle avoidance show that this approach can adapt the trajectories of the robotic end-effector to the user's wishes in real time, including trajectories that the robot has already passed and has not yet passed. Simulation comparisons also show that it exhibits better performance than KMP with the original reference database update strategy.Originality/valueAn interactive learning approach based on KMP is proposed and verified, which not only enables users to plan the trajectory of robotic end-effectors for obstacle avoidance more conveniently and efficiently but also provides an effective idea for accomplishing interactive learning tasks under constraints.
Keyword ：
Kernelized movement primitives (KMP) Kernelized movement primitives (KMP) Obstacle avoidance Obstacle avoidance Physical human-robot interaction Physical human-robot interaction Trajectory adaptation Trajectory adaptation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiao, Sa , Chen, Xuyang , Lu, Yuankai et al. A KMP-based interactive learning approach for robot trajectory adaptation with obstacle avoidance [J]. | INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION , 2024 , 51 (2) : 326-339 . |
| MLA | Xiao, Sa et al. "A KMP-based interactive learning approach for robot trajectory adaptation with obstacle avoidance" . | INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION 51 . 2 (2024) : 326-339 . |
| APA | Xiao, Sa , Chen, Xuyang , Lu, Yuankai , Ye, Jinhua , Wu, Haibin . A KMP-based interactive learning approach for robot trajectory adaptation with obstacle avoidance . | INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION , 2024 , 51 (2) , 326-339 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
工业机器人在制造业已得到广泛应用,快速、准确、自动获得目标运动点位和轨迹可以大幅提升工业机器人编程与作业效率,并可应对变化的作业环境.以自动化制造常见的平面类工件角接结合缝自动识别与跟踪为应用场景,提出基于3D点云的工件特征识别与工业机器人运动跟踪系统.通过结构光相机获得3D点云,对点云数据进行预处理、滤波、工件平面拟合、平面交叉获得结合缝点云,以及对结合缝点云进行必要的插值和顺滑处理,最终获得结合缝空间分布轨迹.再把该轨迹信息经过坐标变换和姿态补齐后,提供给工业机器人实现轨迹跟踪.实验结果表明,系统可以实现结合缝作为工件特征的自动识别与工业机器人自动运动跟踪功能.结合缝识别的路径点与实际结合缝轨迹平均误差不超过1.62 mm.目标特征的自动识别与跟踪可以大幅提升工业机器人适应多品种小批量生产的能力.
Keyword ：
工业机器人 工业机器人 点云数据处理 点云数据处理 特征识别 特征识别 轨迹规划 轨迹规划
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 王凤伟 , 虞增益 , 薛坤斌 et al. 工件3D点云特征识别与工业机器人运动跟踪 [J]. | 制造业自动化 , 2024 , 46 (10) : 205-212 . |
| MLA | 王凤伟 et al. "工件3D点云特征识别与工业机器人运动跟踪" . | 制造业自动化 46 . 10 (2024) : 205-212 . |
| APA | 王凤伟 , 虞增益 , 薛坤斌 , 吴海彬 . 工件3D点云特征识别与工业机器人运动跟踪 . | 制造业自动化 , 2024 , 46 (10) , 205-212 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
