检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Liu, Ziyi Li, Zongyuan Cao, Qianqian Wan, Yuan Guo, Xian NanKai University Inst. of Robotics and Automat. Info. System and the Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China Wuhan University of Technology Department of Mathematical WuHan430070 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Deep reinforcement learning algorithms can enable agents to learn policies for complex tasks without expert knowledge. However, the learned policies are typically specialized to one specific task and can not generalize to new tasks. While meta-reinforcement learning (meta-RL) algorithms can enable agents to solve new tasks based on prior experience, most of them build on on-policy reinforcement learning algorithms which require large amounts of samples during meta-Training and do not consider task-specific features across different tasks and thus make it very difficult to train an agent with high performance. To address these challenges, in this paper, we propose an off-policy meta-RL algorithm abbreviated as CRL (Celebrating Robustness Learning) that disentangles task-specific policy parameters by an adapter network to shared low-level parameters, learns a probabilistic latent space to extract universal information across different tasks and perform temporal-extended exploration. Our approach outperforms baseline methods both in sample efficiency and asymptotic performance on several meta-RL benchmarks. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of normal force of wheel-sand interaction for planetary rovers with active suspension*

Analysis of normal force of wheel-sand interaction for plane...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zhengyin Wang Huaiguang Yang Liang Ding Qingning Lan Haibo Gao Zdravko Terze Zongquan Deng State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Faculty of Mechanical Engineering and Naval Architecture University of Zagreb Zagreb Croatia

The planetary rover with active suspension can climb steeper slopes and cross bigger obstacles in a wheel-step motion mode, which enables the planetary rover to perform more complex exploration tasks. However, wheel-step motion requires coordinated movement of the suspension and the wheels: the suspension can determine the wheel's sinkage depth and translation speed. Matching up with the wheel rotation speed can actively construct the slip ratio. The forces exerted on the wheels by sand during this process are a key index for motion control. This poses new challenges to existing wheel-sand interaction models. In this paper, dynamic normal force tests are carried out. The dynamic variation of wheel normal force with slip ratio is investigated at different sinkage depths. It is found that the normal force exerted on the wheel increases firstly and then decreases with the slip ratio, and reaches the maximum value near s=0. The distributed stresses of the wheel were analysed by discrete element method (DEM) simulation, and the phenomenon of the distribution stress reconstruction of the wheel is found. Further, by analyzing the local particles in contact with the wheel, it is found that the particle movement direction and morphology vary with slip ratio. The analysis of the wheel’s normal force and the granular material variation with slip ratio provides the basis for establishing a physics-based wheel-sand interaction model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of Integrated Air Transportation Cooperative Information SoS Based on Complex Network Theory

Modeling and Analysis of Integrated Air Transportation Coope...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Li, Song Wu, Zhenfeng Jong, Hans De State Key Laboratory of Air Traffic Management System and Technology Nanjing China DFS Aviation Services GmbH Beijing China

ISBN: (纸本)9781665465335

In this paper, a system of systems (SoS) modeling and evaluation method based on complex network theory is proposed for the Integrated Air Transportation Cooperative Information SoS (IATCI-SoS). In the proposed method, the target SoS is abstracted into a network model composed of multiple types of nodes and their interconnections, so as to facilitate its standardized description and quantitative evaluation. On this basis, SoS evaluation indicators in the aspects of flexibility, robustness, and efficiency are designed and applied to the case simulation of the 'Belt and Road Initiative' air transportation collaborative information environment. By simulating the network model of the current SoS and the target IATCI-SoS, both of them are evaluated and analyzed. Simulation results show the advantages and disadvantages of the target IATCI-SoS, and validate that the proposed method can provide theoretical support for the top-level architecture construction of the future IATCI-SoS. © 2022 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Diverse Gaussian Sampling for Human Motion Prediction 16th

Diverse Gaussian Sampling for Human Motion Prediction

引用

16th International Conference on Social robotics, ICSR + InnoBiz 2024

作者： Luo, Jiefu Wang, Jiansheng Liu, Zhenfei Cheng, Jun Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong Department of Pediatric Orthopedics Shenzhen Children’s Hospital Guangdong Shenzhen518000 China

ISBN: (纸本)9789819611508

In many industrial applications, it is necessary to obtain accurate human motion prediction. The prediction of human movement based on a 3D skeleton, which forecasts future postures using the human skeletal structure, significantly aids in enabling machines to understand human behavior and react more intelligently. Additionally, by predicting human actions, potential dangers can be perceived, especially in safety-related issues, necessitating a broader range of predictions. In this paper, considering the greater diversity generated by Variational Autoencoders (VAEs), we employ VAEs for prediction. In contrast to other studies, our primary focus is on obtaining more diverse samples. Extensive experiments demonstrate that our proposed model performs well on the Human 3.6M [35] and HumanEva-I [36] datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Phase-Only Beamforming for Dual-Polarization Array Radar Based on Manifold Optimization

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Dongwei, Lu Jiazhi, Ma Zhanling, Wang Longfei, Shi National University of Defense Technology State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System Changsha410073 China

The phase-only beamforming (POB) technique manipulates the weighted phases of array antenna elements to create a desired radiation pattern, thereby reducing the hardware and power costs associated with large phased arrays. However, two significant challenges currently hinder the practical implementation of POB. First, the beam gain generated by POB can be severely distorted when a main lobe interference is present. Second, the POB method struggles to suppress interferences whose positions change within the spatial domain. To address these challenges, this letter proposes a novel POB method for dual-polarization array radar. This method incorporates polarization constraints on a Riemannian manifold under the condition of null broadening. By doing so, it generates robust nulls that can effectively suppress moving interferences in the main lobe and side lobes while preserving the beam gain. Numerical simulations demonstrate that this method exhibits excellent anti-interference performance. © 2025 IEEE.

关键词： Antenna lobes

来源：评论

学校读者我要写书评

暂无评论

Robust Tracking for Electromagnetic-Actuated Microrobot Via Sliding Mode Control 49

Robust Tracking for Electromagnetic-Actuated Microrobot Via ...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Wu, Yihang Qu, Ziyao Chang, Xiaocong Hu, Zhijian Yang, Rongni Ma, Renjie Harbin Institute of Technology State Key Laboratory of Robotics and Systems Harbin China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Control Science and Engineering Shandong University Jinan China

ISBN: (纸本)9798350331820

Microrobots can work in small, enclosed spaces and complete complex tasks. It has potential applications in the field of biomedical and life sciences. This paper focuses on investigating robust dynamic tracking for electromagnetic-actuated microrobot via sliding mode control. First, we generalize the planar motion to the case of spatial trajectory tracking and then establish the three-dimensional tracking error model of microrobot. Then, we deploy a novel sliding control strategy and ensure the stability of sliding mode dynamics, once the robotic state reaches the sliding surface and sustains there in the sequel. Finally, the numerical simulation is conducted, compared to the traditional proportion-integration-differentiation control strategy, to verify the effectiveness and advantages of our proposed control scheme. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Enlarging grain sizes for efficient perovskite solar cells by methylamine chloride assisted recrystallization

引用

Journal of Energy Chemistry 2022年第2期31卷 55-61页

作者： Gao Wu Molang Cai Yujia Cao Zhuoxin Li Zhongyan Zhang Weng Yang Xianggang Chen Dongxu Ren Yaqi Mo Miao Yang Xuepeng Liu Songyuan Dai State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China Beijing Key Laboratory of Novel Thin-Film Solar Cells North China Electric Power UniversityBeijing 102206China Jiangsu Shunfeng Photovoltaic Technology Co.Ltd. Changzhou 213164JiangsuChina

The quality of MAPbI3 film prepared by solvent engineering process highly depends on environment and antisolvent ***,we provided a simple methylamine chloride(MACl)solution treatment using a two-step process to enlarge the perovskite crystal grain sizes to more than 1 *** than treatment on the film surface,the MACl solution diffuses into the MAPbI_(3) films to assist the recrystallization of small crystal at the bottom of perovskite *** imitative contact between perovskite and substrate is ***,the enlargement of grain size and ten times enhancement of crystalline reduce trap-assisted recombination of perovskite ***,the significant improvement of cell efficiency of 20.89%as well as device stability is obtained with the MACl treatment.

关键词： Perovskite solar cells Methylamine chloride Large grain size High efficiency

来源：评论

学校读者我要写书评

暂无评论

FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer

arXiv

引用

arXiv 2023年

作者： Zhang, Xinyu Wang, Li Jiang, Zhiqiang Dai, Kun Xie, Tao Yang, Lei Yu, Wenhao Shen, Yang Li, Jun The School of Vehicle and Mobility Tsinghua University Beijing100084 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China

Local Feature Matching, an essential component of several computer vision tasks (e.g., structure from motion and visual localization), has been effectively settled by Transformer-based methods. However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy. In addition, these methods utilize a conventional handcrafted encoding approach to integrate the positional information of keypoints into the visual descriptors, which limits the capability of the network to extract reliable positional encoding message. In this study, we propose Feature Matching with Reconciliatory Transformer (FMRT), a novel Transformer-based detector-free method that reconciles different features with multiple receptive fields adaptively and utilizes parallel networks to realize reliable positional encoding. Specifically, FMRT proposes a dedicated Reconciliatory Transformer (RecFormer) that consists of a Global Perception Attention Layer (GPAL) to extract visual descriptors with different receptive fields and integrate global context information under various scales, Perception Weight Layer (PWL) to measure the importance of various receptive fields adaptively, and Local Perception Feed-forward Network (LPFFN) to extract deep aggregated multi-scale local feature representation. Besides, we introduce a novel Axis-Wise Position Encoder (AWPE) that perceives positional encoding as two independent keypoints encoding tasks along the row and column dimensions and utilizes two parallel network branches to decouple the X- and Y -coordinate information of keypoints, so that boosting the capability of the network to model position information for different images. Extensive experiments demonstrate that FMRT yields extraordinary performance on multiple benchmarks, including pos

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Small-Object Detection with Super Resolution Embedding 1

引用

3rd International Conference on Artificial Intelligence, 2022

作者： Tang, Wenyi Xu, Qiucheng Ding, Hui Wu, Lianghao Shi, Yanyang State Key Laboratory of Air Traffic Management System and Technology Nanjing Research Institute of Electronic Engineering Nanjing210007 China

ISBN: (数字)9789811694233

ISBN: (纸本)9789811694226

The detection performance of ground vehicles on the airport surface in video-sensor based air traffic control surveillance has not been satisfactory compared to larger planes, especially in panoramic images of remote tower applications. Inspired by the success of GAN-based super resolution and oversampling augmentation methods, we apply a new super-resolution network to resize cropped small samples and augment each of those images by resize-and-pasting small objects many times. It allows us to trade off the quantity of the detector on large objects with that on small objects. We propose an architecture with two components: ESRGAN and Detection network. We use residual dense blocks for ESRGAN, and for the detector network, we use one state-of-the-art detector (YOLOv3). Extensive experiments on a public (car overhead with context) dataset and another self-assembled airport surface dataset show superior performance of our method compared to the standalone state-of-the-art object detectors. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Passive ISAR Jamming Method Based on Time-Modulated Corner Reflectors Under Asynchronous Control

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Gan, Lin Wu, Zehao Li, Jianbing National University of Defense Technology State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System Changsha410073 China

The time-modulated corner reflector (TMCR) is an improvement of the traditional corner reflector utilizing time-modulated metasurfaces, which demonstrates superior capability in dynamically modulating characteristics of electromagnetic waves in real-time. Despite its potential, the application of TMCRs in radar imaging remains underexplored. This paper presents a passive ISAR modulation method through the asynchronous control of TMCRs, which can directly disrupt the ISAR imaging mechanism. Through the joint inter-pulse and intra-pulse periodic modulation, multiple TMCRs are alternately switched between strong and weak reflection states asynchronously, which can interfere with the alignment process of range profiles and further causing errors in initial phase compensation. The intra-pulse modulation model is constructed firstly, and the influence of TMCR and modulation parameters on the envelope correlation is investigated quantitatively. On this basis, the optimization model of inter-pulse modulation is developed, which is calculated through Genetic Algorithm (GA). Then the effectiveness of the method is systematically analyzed under varying application parameters, with corresponding applicable boundaries subsequently determined. Finally, experiments are conducted based on the electromagnetic simulation data and measured data of the UAV, which verifies that the proposed method can effectively interfere with the envelop alignment and phase compensation processes, thereby making the ISAR image blurred. © 1965-2011 IEEE.

关键词： Inverse synthetic aperture radar

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：