检索结果-内蒙古大学图书馆

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

Design and Control of Continuous Jumping Gaits for Humanoid Robots Based on Motion Function and Reinforcement Learning

引用

Procedia Computer Science 2024年 250卷 51-57页

作者： Zida Zhao Shilong Sun Haodong Huang Qingbin Gao Wenfu Xu State Key Laboratory of Robotics and System (HIT) Harbin Institute of Technology Harbin Heilongjiang China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen 518055 China

Continuous jumping of humanoid robots is a challenging problem that requires appropriate gait and force control for the robot to achieve. Reinforcement learning (RL) has been applied to the motion control of humanoid robots and has achieved significant progress. However, traditional RL control methods primarily rely on designing reward signals to generate human-like movements, and it requires developing complex reward signals for continuous jumping, resulting in limited actions and suboptimal jumping performance. To address this issue, we have designed motion functions for humanoid continuous jumping and incorporated them into the RL framework to obtain desired human-like continuous jumping actions. Furthermore, two different jumping gaits are designed to investigate the jumping effects produced by different jumping functions: bent-knee jumping (BJ) and straight-knee jumping (SJ). BJ is a typical jumping style where the legs flex during the jumping process to accumulate energy, enabling higher explosive power. SJ is more suitable for tasks requiring quick responses, as the legs remain upright during the jump, providing faster reaction speed. The performance in continuous jumping tasks has been evaluated by comparing the effects of training with different jumping functions. This research has particular guidance for improving the jumping ability of robots and enhancing the stability and efficiency of humanoid continuous jumping.

关键词： Continuous jumping gaits Humanoid robots Motion function Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantitative characterization of cell physiological state based on dynamical cell mechanics for drug efficacy indication

引用

Journal of Pharmaceutical Analysis 2023年第4期13卷 388-402页

作者： Shuang Ma Junfeng Wu Zhihua Liu Rong He Yuechao Wang Lianqing Liu Tianlu Wang Wenxue Wang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China Department of Thoracic Surgery Cancer Hospital of China Medical UniversityLiaoning Cancer Hospital and InstituteShenyang 110042China Department of Radiotherapy Cancer Hospital of China Medical UniversityLiaoning Cancer Hospital and InstituteShenyang 110042China

Cell mechanics is essential to cell development and function,and its dynamics evolution reflects the physiological state of ***,we investigate the dynamical mechanical properties of single cells under various drug conditions,and present two mathematical approaches to quantitatively characterizing the cell physiological *** is demonstrated that the cellular mechanical properties upon the drug action increase over time and tend to saturate,and can be mathematically characterized by a linear timeinvariant dynamical *** is shown that the transition matrices of dynamical cell systems significantly improve the classification accuracies of the cells under different drug ***,it is revealed that there exists a positive linear correlation between the cytoskeleton density and the cellular mechanical properties,and the physiological state of a cell in terms of its cytoskeleton density can be predicted from its mechanical properties by a linear regression *** study builds a relationship between the cellular mechanical properties and the cellular physiological state,adding information for evaluating drug efficacy.

关键词： Cellular mechanical properties Cytoskeleton Drug efficacy evaluation Cell system modelling Linear regression

来源：评论

学校读者我要写书评

暂无评论

A Genderless Docking Mechanism with Passive Locking and High Rotation Misalignment Tolerance for Modular Space Robots

A Genderless Docking Mechanism with Passive Locking and High...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Chen, Jian Wen, Xiaodong Wang, Hao Gong, Wei Deng, Zongquan Yu, Haitao Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China Tianjin Institute of Aerospace Mechanical and Electrical Equipment Tianjin Key Laboratory of Aerospace Intelligent Equipment Technology Tianjin China

ISBN: (纸本)9781665481090

Modular robots are gaining increasing attention in space services. The docking mechanism plays a critical role in performing self-healing and self-reconfiguration of modular robots. It is beneficial for the docking mechanism to operate with high efficiency, homogeneity and high misalignment tolerances. To meet these requirements, this paper presents a novel genderless docking mechanism. The construction of the docking mechanism is designed with features of passive locking and single-sided electromagnetic unlocking. To demonstrate the advantages of passive locking, the working processes of the axial and circumferential locking mechanisms are described in detail. Based on theoretical calculations and simulations, it is shown that the docking mechanism can provide fast connections or disconnections with a degree of translational and angular misalignment tolerances. This docking mechanism is intended for future applications in modular space robots or unstructured environment exploration robots. © 2022 IEEE.

关键词： Modular robots

来源：评论

学校读者我要写书评

暂无评论

Dynamic Object Removal of Static 3D Point-Cloud Map Building in Casualty Collection Point

Dynamic Object Removal of Static 3D Point-Cloud Map Building...

引用

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Haidong Wang Wanlei Li Yijie Dai Xiaogang Xiong Yunjiang Lou State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology ShenZhen Shenzhen China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

Understanding the environment is crucial for the autonomous navigation of vehicles. Accurately identifying and removing dynamic objects that cause occlusions and noisy pose issues is crucial to the task. The casualty collection point (CCP) is a designated location for treating casualties during disasters. These sites are commonly located in open fields to ensure that the injured receive timely and appropriate care. Therefore, the construction of a 3D map in CCP may encounter additional challenges. In this paper, we introduces a novel algorithm that integrates a learning-based multi-object detection network with a Kalman Filter tracking framework to remove dynamic object traces from the 3D map building, particularly in CCP scenarios, and it redirects attention on the velocity attribute of dynamic objects at the object-level scale. Additionally, we contribute a new dataset specifically designed for the CCP scenario. Comparative experiments conducted on the SemanticKITTI dataset and CCP dataset show that our proposed method achieves the state-of-the-art performance in removing traces of dynamic objects on 3D Map. Dataset is available at https://***/haidongwang96/ccp_dataset.

关键词： Point cloud compression Three-dimensional displays Simultaneous localization and mapping Heuristic algorithms Buildings Object detection Kalman filters Object recognition Noise measurement Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based model for automated STN localization using local field potentials in Parkinson’s disease

引用

Soft Computing 2025年第4期29卷 2343-2362页

作者： Hosny, Mohamed Naeem, Mohamed A. Zhu, Minwei Gao, Wenpeng Elshenhab, Ahmed M. Fu, Yili Department of Electrical Engineering Benha Faculty of Engineering Benha University Benha Egypt State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150080 China Department of Mechatronics and Robotics Engineering Faculty of Engineering South Valley University Qena Egypt First Affiliated Hospital Harbin Medical University Harbin150001 China School of Life Science and Technology Harbin Institute of Technology Harbin150080 China Department of Mathematics Faculty of Science Mansoura University Mansoura35516 Egypt

Accurate identification of the subthalamic nucleus (STN) borders is time-consuming, relying heavily on the neurosurgeon expertise in manually interpreting the electrophysiological signals. Local field potentials (LFPs) have garnered imperative attention due to their strong correlation with the STN. However, existing detection models often face challenges with high computational complexity, hyperparameter optimization and lack of explainability, making them unreliable for clinicians. Therefore, this study introduces an explanatory framework using convolutional neural networks (CNN) for detecting the STN region from LFPs. Continuous wavelet transform is employed to convert LFPs signals into scalogram images, which are then processed by sixteen CNN models. We evaluated our framework by examining the impact of various limiting factors on the classification performance, including model size, learning rate (LR), optimizers and data scaling. Deep features are extracted from the top-performing CNN architectures to capture rich representations of the scalograms. These features are then fused and classified using k-nearest neighbour algorithm. Gradient-weighted class activation mapping is used to explain the decisions made by the proposed model. Our approach achieved an accuracy of 99.61%, outperforming individual CNN models for STN localization. The experimental results revealed that CNN models, embedded with additional hyperparameters and layers, generally outperformed smaller models. Besides, low LR significantly enhanced the performance compared to high LR. Moreover, features extracted from untuned networks produced lower performance than tuned networks. The proposed system could revolutionize deep brain stimulation surgery by increasing efficiency and reducing reliance on clinician expertise for STN detection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Review of Multi-Robot Collaborative Simultaneous Localization and Mapping

A Review of Multi-Robot Collaborative Simultaneous Localizat...

引用

2023 IEEE International Conference on Unmanned systems, ICUS 2023

作者： Zhao, Xianzhe Shao, Shiliang Wang, Ting Fang, Chuxi Zhang, Jin Zhao, Hai School of Computer Science and Engineering Northeastern University Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350316308

Collaborative Simultaneous Localization and Mapping (C-SLAM), commonly known as multi-robot SLAM, is a prefatory technology that allows multiple robots to efficiently traverse large and intricate areas. This is possible due to the merging of maps and the recognition of shared spaces. Despite its many benefits, multi-robot systems encounter various challenges, such as communication barriers, co-localization issues, and joint optimization problems. This paper reviews the sensors and back-end optimization methods used for SLAM. Then, it summarizes existing collaborative SLAM frameworks and some novel solutions. Finally, it discusses trends and promising research directions for collaborative SLAM. © 2023 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Lidar-Visual-Inertial Odometry with Online Extrinsic Calibration

引用

Journal of Shanghai Jiaotong university(Science) 2023年第1期28卷 70-76页

作者：茅天阳赵文韬王景川陈卫东 Department of Automation Institute of Medical RoboticsShanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China

To achieve precise localization,autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile *** is a time-consuming process,and mechanical distortion will cause extrinsic calibration ***,we propose a lidar-visual-inertial odometry,which is combined with an adapted sliding window mechanism and allows for online nonlinear optimization and extrinsic *** the adapted sliding window mechanism,spatial-temporal alignment is performed to manage measurements arriving at different *** nonlinear optimization with online calibration,visual features,cloud features,and inertial measurement unit(IMU)measurements are used to estimate the ego-motion and perform extrinsic *** experiments were carried out on both public datasets and real-world *** indicate that the proposed system outperforms state-of-the-art open-source methods when facing challenging sensor-degenerating conditions.

关键词： autonomous vehicles multi-sensor fusion online calibration

来源：评论

学校读者我要写书评

暂无评论

基于细胞内应变评估的卵母细胞去核方法及在机器人化克隆中的应用

引用

Engineering 2023年第5期24卷 73-83,I0002页

作者： Ming-Zhu Sun Yao-Wei Liu Mao-Sheng Cui Qi-Li Zhao Xiang-Fei Zhao Yi-Di Zhang Jing-Jing Huang Gui-Zhang Lu Xin Zhao Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent RoboticsNankai UniversityTianjin 300071China Tianjin Animal Science and Veterinary Research Institute Tianjin 300201China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai UniversityShenzhen 518063China

自1996年第一只克隆羊诞生,克隆技术就由于其在动物育种方面的巨大潜力而得到了大量关注。体细胞核移植技术是动物克隆的核心,其操作过程非常复杂,不可避免地造成细胞内损伤。通常来说,只有不到1%的重构胚胎能够发育成克隆动物,克隆的... 详细信息

自1996年第一只克隆羊诞生,克隆技术就由于其在动物育种方面的巨大潜力而得到了大量关注。体细胞核移植技术是动物克隆的核心,其操作过程非常复杂,不可避免地造成细胞内损伤。通常来说,只有不到1%的重构胚胎能够发育成克隆动物,克隆的低成功率是制约其广泛应用的主要原因之一。为此,本文提出了一种基于细胞内应变评估的卵母细胞去核方法,来减少体细胞核移植中的潜在细胞内损伤,从而提高克隆成功率。首先,论文根据细胞内速度场计算细胞内应变,进而将内应变作为评价标准来优化去核操作;在此基础上,开发了一套机器人批量体细胞核移植系统,用于实现机器人化克隆。实验结果表明,本文方法将体细胞核移植后的胚胎囊胚率从10.0%提高到20.8%,并成功获得17头克隆小猪,这是世界首批由机器人完成克隆操作获得的克隆动物。对比手动核移植操作,本文将克隆成功率从平均0.73%提升到了2.50%,大幅提升了克隆效率。与此同时,基于细胞内应变的去核方法有望应用于其他生物操作,并建立一种通用的减少细胞内损伤的细胞操作规范。

关键词：动物育种去核方法体细胞核移植克隆动物卵母细胞机器人化动物克隆克隆技术

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Evaluation of WLR-III

Design and Experimental Evaluation of WLR-III

引用

IEEE International Conference on robotics and Biomimetics

作者： Xu Li Yili Fu State Key Laboratory of Robotics and System Harbin Institute of Technology and State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Intelligent Robot Research Center Zhejiang Laboratory and State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

This paper introduces the design and experimental evaluation of WLR-III, which stands for the third-generation hydraulic wheel-legged robot. WLR-III is expected to be applied to disaster scenarios where the mobility, adaptability and manipulation capability are required. Based on the development of the previous two generations of wheel-legged robots, this work continuously optimizes the design to achieve higher mobility and stronger adaptability by reducing weight & inertia. The hydraulic power transmission system adopts a hose-less design method to ensure the robustness of the system. What's more prominent is that the successful development of hydraulic power unit (HPU) enables WLR-III to realize hydraulic power autonomy. In addition, to accomplish all kinds of operational tasks in the rescue scene, the electro-hydraulic hybrid drives anthropomorphic arms with heavy load grippers were developed. Finally, the effectiveness and reliability of design optimization have been evaluated through a series of experiments, including grassland movement, load bearing, obstacle-stepping and tool-operating. To the authors' best knowledge, this is the first time that a hydraulic powered autonomous wheel-legged humanoid robot with the ability to operate simple tools has been developed.

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：