检索结果-内蒙古大学图书馆

An Investigation into the Application of an RL-GABased Multi-Modal Motion Somatosensory Optimization Control Strategy for a Novel Rehabilitation robot

引用

IEEE robotics and Automation Letters 2025年

作者： Wu, Junyu Wang, He Zhang, Gongzi Liu, Yubin Zhao, Jie Cai, Hegao Harbin Institute of Technology State Key Laboratory - Robot Research Institute Heilongjiang Harbin150001 China Harbin Engineering University College of Intelligent Systems Science and Engineering Heilongjiang Harbin150001 China General Hospital Department of Rehabilitation Medicine Beijing100853 China

The increasing prevalence of balance disorders presents significant challenges to rehabilitation therapy, prompting the development of rehabilitation robots as effective tools for motion training. To enhance the patient experience and rehabilitation outcomes in human-robot collaborative training, a motion control strategy based on reinforcement learning and genetic algorithms (RL-GA) with somatosensory enhancement is proposed and implemented in a novel rehabilitation robot. This study introduces a mathematical model of the human sensory system to quantify somatosensory feedback related to motion and integrates the washout algorithm (WA) into the robot's control system, facilitating the reproduction of somatosensation and motion simulation. Three typical rehabilitation modes—level walking, stair climbing, and stair descending—are selected, with natural gait features extracted as predefined trajectories. The WA parameters for each mode are optimized using RL-GA in various rehabilitation scenarios. Simulation results demonstrate that the washout filtering optimization method using RL-GA reduces theoretical somatosensory error by approximately 10% to 20% across all three rehabilitation modes, compared to traditional GA optimization. The experimental results further confirm the reliability and feasibility of the proposed method. The proposed approach enhances the realism of robot-assisted motion, thereby theoretically improving training effectiveness and accelerating the rehabilitation process. © 2016 IEEE.

关键词： Collaborative robots

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Based mmWave Radar Point Cloud Enhancement Driven by Range Images

arXiv

引用

arXiv 2025年

作者： Wu, Ruixin Li, Zihan Wang, Jin Xu, Xiangyu Yu, Huan Zheng, Zhi Huang, Kaixiang Lu, Guodong The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310058 China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou310058 China Robotics Research Center of Yuyao City Ningbo315400 China State Key Laboratory of Robotics and Systems Department of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China

Millimeter-wave (mmWave) radar has attracted significant attention in robotics and autonomous driving. However, despite the perception stability in harsh environments, the point cloud generated by mmWave radar is relatively sparse while containing significant noise, which limits its further development. Traditional mmWave radar enhancement approaches often struggle to leverage the effectiveness of diffusion models in super-resolution, largely due to the unnatural range-azimuth heatmap (RAH) or bird’s eye view (BEV) representation. To overcome this limitation, we propose a novel method that pioneers the application of fusing range images with image diffusion models, achieving accurate and dense mmWave radar point clouds that are similar to LiDAR. Benefitting from the projection that aligns with human observation, the range image representation of mmWave radar is close to natural images, allowing the knowledge from pre-trained image diffusion models to be effectively transferred, significantly improving the overall performance. Extensive evaluations on both public datasets and self-constructed datasets demonstrate that our approach provides substantial improvements, establishing a new state-of-the-art performance in generating truly three-dimensional LiDAR-like point clouds via mmWave radar. Copyright © 2025, The Authors. All rights reserved.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

引用

IEEE Transactions on Image Processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

LICFM3-SLAM: LiDAR-Inertial-Camera Fusion and Multimodal Multilevel Matching for Bionic Quadruped Inspection robot Mapping

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Zhang, Haibing Li, Lin Jiang, Andong Xu, Jiajun Shen, Huan Li, Youfu Ji, Aihong Wang, Zhongyuan Nanjing University of Aeronautics and Astronautics Laboratory of Locomotion Bioinspiration and Intelligent Robots College of Mechanical and Electrical Engineering Nanjing210016 China Hefei CSG Smart Robot Technology Company Ltd Hefei230094 China City University of Hong Kong Department of Mechanical Engineering Hong Kong Nanjing University of Aeronautics and Astronautics Laboratory of Locomotion Bioinspiration and Intelligent Robots College of Mechanical and Electrical Engineering State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing210016 China Jiangsu Key Laboratory of Bionic Materials and Equipment Nanjing210016 China CSG Smart Science and Technology Company Ltd Shanghai201601 China

In comparison to wheeled robots, the locomotion of bionic quadruped robots is more vigorous. Mapping systems should maintain satisfactory robustness and accuracy in various complex real-world scenarios, even when the robot’s body experiences intense shaking. To address these challenges, this study proposes a simultaneous localization and mapping (SLAM) system based on LiDAR-inertial-camera fusion and a multimodal multilayer matching algorithm (LICFM3-SLAM). First, a tightly coupled strategy is utilized to fuse LiDAR, inertial, and camera information, introducing a visual-inertial odometry (VIO) subsystem based on adaptive graph inference;thus, high-precision and robust robot state estimation is achieved. Second, inspired by human spatial cognition, the study proposes a multimodal multilayer matching algorithm and utilizes observation data obtained from the camera and LiDAR, thereby achieving accurate and robust data association. Finally, incremental poses are optimized using factor graph optimization methods;thus, a globally consistent 3-D point cloud map is constructed. The proposed system is tested on a public benchmark dataset and applied to a bionic quadruped inspection robot (BQIR), and experiments are conducted in various challenging indoor and outdoor large-scale scenarios. The results reveal that LICFM3-SLAM exhibits high robustness and mapping accuracy while meeting real-time requirements. © 1963-2012 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Integrating kinematic and dynamic factors with generative design for high-performance additive manufacturing structures

引用

Virtual and Physical Prototyping 2025年第1期20卷

作者： Zong, Huaizhi Lou, Bin Yuan, Haihui Wang, Dandan Zhang, Yicha Ai, Jikun Zhang, Junhui Xu, Bing State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou China Robot Control Department Wuba Intelligent Technology Co. Ltd China Design & Mechanical Engineering Department Université de Technologie Belfort-Montbéliard Sevenans France

Mechanical structures often operate under dynamic loads and complex kinematic conditions, but current design methods primarily adopt static or simplified boundary conditions, leading to inaccuracy in defining the design space and the resulting solutions. To address these limitations, this paper presents a novel generative design framework that integrates kinematic and dynamic factors to establish more precise design inputs. To accurately capture the real-world mechanical states of structures, extensive kinematic and dynamic data are extracted through virtual prototyping technology. A novel design domain determination method is proposed based on kinematic relationships, while a load condition extraction approach is formulated based on material deformation theory, collectively ensuring a more realistic representation of design inputs in generative design. Furthermore, a design for additive manufacturing strategy is incorporated to refine and optimise the generative design outcomes, enhancing the structural manufacturability. The proposed method is applied to a challenging case study: designing a hydraulically actuated quadruped robot leg with complex kinematic relationships and varying dynamic load conditions. Experiment results indicate that the proposed method greatly improves structural efficiency and performance, demonstrating its potential in designing complex mechanical structures. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Design for manufacturability

来源：评论

学校读者我要写书评

暂无评论

Bridging VLM and KMP: Enabling Fine-grained robotic manipulation via Semantic keypoints Representation

arXiv

引用

arXiv 2025年

作者： Zhu, Junjie Liu, Huayu Wang, Jin Wen, Bangrong Huang, Kaixiang Li, Xiaofei Zhang, Haiyun Lu, Guodong The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310058 China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou310058 China School of Robotics Ningbo University of Technology Ningbo315211 China Robotics Research Center of Yuyao City Ningbo315400 China

From early Movement Primitive (MP) techniques to modern Vision-Language Models (VLMs), autonomous manipulation has remained a pivotal topic in robotics. As two extremes, VLM-based methods emphasize zero-shot and adaptive manipulation but struggle with fine-grained planning. In contrast, MP-based approaches excel in precise trajectory generalization but lack decision-making ability. To leverage the strengths of the two frameworks, we propose VL-MP, which integrates VLM with Kernelized Movement Primitives (KMP) via a low-distortion decision information transfer bridge, enabling fine-grained robotic manipulation under ambiguous situations. One key of VL-MP is the accurate representation of task decision parameters through semantic keypoints constraints, leading to more precise task parameter generation. Additionally, we introduce a local trajectory feature-enhanced KMP to support VL-MP, thereby achieving shape preservation for complex trajectories. Extensive experiments conducted in complex real-world environments validate the effectiveness of VL-MP for adaptive and fine-grained manipulation. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Predefined-Time Neural Adaptive Quantized Self-Triggered Control with Appointed Performance for a 2-DOF Helicopter System

引用

IEEE Transactions on Vehicular technology 2025年

作者： Song, Xiaona Chu, Longbo Zhao, Zhijia Song, Shuai Hong, Keum-Shik Henan University of Science and Technology School of Information Engineering Luoyang471000 China Henan University of Science and Technology. Henan Key Laboratory of Robot and Intelligent Systems China Guangzhou University School of Mechanical and Electrical Engineering 510006 China Pusan National University School of Mechanical Engineering 2 Busandaehak-ro Guemjeong-gu Busan46241 Korea Republic of

This article investigates the predefined-time neural adaptive self-triggered quantized control design for a two-degree of freedom (2-DOF) helicopter system with appointed tracking performance. To begin with, a fixed-time performance function is integrated into the predefined-time dynamic surface control (PTDSC) framework, and the transient fluctuations of the tracking error can be effectively constrained by the performance function. Then, a neural adaptive self-triggered quantized resilient controller is designed, where the self-triggered mechanism and input quantization are incorporated into to recursive control design to reduce the bandwidth consumption. Furthermore, the obtained stability results have proved that the designed controller ensures all the signals in the closed-loop system are practical predefined-time bounded (PPTB), and the tracking errors can be strictly confined to a region with preset transient and steady-state performance, even under limited communication resources. Finally, the simulation results demonstrate the effectiveness of the proposed control scheme. © 1967-2012 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Electric Field Manipulation of Rydberg States for Very Low Frequency Fields Detection

arXiv

引用

arXiv 2025年

作者： Chen, Minze Feng, Haonan Gao, Ge Zhu, Zhiao Li, Zhongxiang Wu, Zhonghuai Xiao, Wei Dai, Weidong Peng, Peng Zheng, Dezhi State Key Laboratory of Environment Characteristics and Effects for Near-Space Beijing Institute of Technology Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China State Key Laboratory of Explosion Science and Safety Protection Beijing Institute of Technology Beijing100081 China Jiaxing314019 China Zhuhai519088 China Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing100081 China Taizhou Meteorological Bureau Taizhou318000 China Chongqing Caeri Robot Technology Co. Ltd. Chongqing400722 China

The very low frequency(VLF) band is widely used in submarine communication and geophysical exploration for its strong penetration and long-distance propagation. This paper theoretically and experimentally investigates Rydberg EIT in 133Cs vapor under VLF and DC fields. A model is established to describe the EIT spectral response under dual-field conditions, with theoretical predictions showing agreement with experimental results. We propose a novel calibration-free method to measure VLF electric fields, bypassing traditional Stark shift measurements. This method detects additional splitting intervals of Stark sublevels, separated from the degenerate energy level under a DC field. This phenomenon arises from the averaging effect of sublevel sinusoidal oscillations in the spectrum induced by the VLF field. The splitting interval is proportionally dependent on the VLF field amplitude. The VLF electric field sensor is enhanced by increasing the strength of the DC field, extending the traceable measurement limit for weak VLF electric fields by more than an order of magnitude. This work highlights the potential for precise VLF electric field measurements, significantly advancing the calibration-free detection capabilities of Rydberg atom sensors for low-frequency applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Rydberg states

来源：评论

学校读者我要写书评

暂无评论

Decoupled Prototype Learning for Reliable Test-Time Adaptation

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui South China University of Technology School of Electronic and Information Engineering 381 Wushan Road Tianhe District Guangzhou510000 China Pazhou Lab Guangzhou510330 China South China University of Technology School of Future Technology 381 Wushan Road Tianhe District Guangzhou510000 China South China University of Technology School of Software Engineering Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL's robustness for the small batch sizes often encountered in TTA. We update each class's pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. © 1999-2012 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Battery Swapping Service Management System Reliability-Based Design Concerning Station Information Delay

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Xinyu Cao, Yue Hu, Ziyi Zhang, Xu Liu, Zhi Lei, Xinhai Wuhan University School of Cyber Science and Engineering Wuhan430073 China Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan430250 China School of Computing Sciences Norwich United Kingdom University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan Wuhan Public Resources Trading Center Wuhan China

Since the long duration associated with traditional plug-in charging modes inevitably causes range anxiety to electric vehicle (EV) drivers, the battery swapping technology has emerged as a promising alternative. It thus becomes imperative to develop a reliable battery swapping service system, efficiently managing the large-scale energy replenishing demands from EVs. Firstly, this paper considers drivers' trip destination to minimize total trip duration, and the expense paid for battery swapping service to save users' service cost. By optimizing the requirement of battery swapping service during peak-price period, the expenditure for energy supplement can be reduced. Secondly, concerning in practice that the transmission delay is a crucial factor impacting the overall network and system reliability, this paper further investigates the impact of station information delay between the global controller and battery swapping stations (BSSs). By characterizing the delay into two types, namely, low and large delays, the scenario based on a known delay type are investigated. Thirdly, delay cases with multiple BSSs are also taken into account and a mixed decision-making method is developed. Finally, simulation results indicate the desirable performance of proposed scheme in satisfying user demand and alleviating impact of station information delay. © 1975-2011 IEEE.

关键词： Decision making

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：