检索结果-内蒙古大学图书馆

GNN-Assisted BiG-AMP: Joint Channel Estimation and Data Detection for Massive MIMO Receiver

IEEE Transactions on Wireless Communications 2025年第6期24卷 4631-4646页

作者： Liu, Zishen Wu, Nan He, Dongxuan Yuan, Weijie Li, Yonghui Quek, Tony Q. S. School of Information and Electronics Beijing Institute of Technology Beijing100081 China School of System Design and Intelligent Manufacturing Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2008 Australia Singapore University of Technology and Design 487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of

In this paper, we develop a graph neural network (GNN)-assisted bilinear inference approach to enhance the receiver performance of the MIMO system through message passing-based joint channel estimation and data detection (JCD). Specifically, based on the bilinear generalized approximate message passing (BiG-AMP) framework and conditional correlation of signal, we propose a GNN-assisted BiG-AMP (GNN-BiGAMP) approach, which integrates a GNN module into the data-detection-loop to compensate the inaccurate marginal likelihood approximation. By leveraging the coupling between the channel and received symbols, a bilinear GNN-assisted BiG-AMP (BiGNN-BiGAMP) JCD receiver is further proposed. This method incorporates two GNNs with similar graph representation into the bilinear posterior estimation loops, which not only compensates for approximation errors but also alleviates performance loss due to premature variance convergence, thereby enhancing the receiver performance significantly. To fully exploit the supervised information from channel estimation and data detection, we propose a multitask learning based training scheme, which coordinates GNNs with different tasks in two loops. Simulation results show that our proposed GNN-assisted JCD receivers significantly outperform other JCD counterparts in terms of both channel estimation and data detection. © 2025 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Imaginary filtered hindsight experience replay for UAV tracking dynamic targets in large-scale unknown environments

引用

Chinese Journal of Aeronautics 2023年第5期36卷 377-391页

作者： Zijian HU Xiaoguang GAO Kaifang WAN Neretin EVGENY Jinliang LI School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710129China School of Robotic and Intelligent Systems Moscow Aviation Institute(National Research University)Moscow 125993Russia Electromagnetic Space Operations and Applications Laboratory The 29th Research Institute of China Electronics Technology Group CorporationChengdu 610036China

As an advanced combat weapon,Unmanned Aerial Vehicles(UAVs)have been widely used in military *** this paper,we formulated the Autonomous Navigation Control(ANC)problem of UAVs as a Markov Decision Process(MDP)and proposed a novel Deep Reinforcement Learning(DRL)method to allow UAVs to perform dynamic target tracking tasks in large-scale unknown *** solve the problem of limited training experience,the proposed Imaginary Filtered Hindsight Experience Replay(IFHER)generates successful episodes by reasonably imagining the target trajectory in the failed episode to augment the *** welldesigned goal,episode,and quality filtering strategies ensure that only high-quality augmented experiences can be stored,while the sampling filtering strategy of IFHER ensures that these stored augmented experiences can be fully learned according to their high *** training in a complex environment constructed based on the parameters of a real UAV,the proposed IFHER algorithm improves the convergence speed by 28.99%and the convergence result by 11.57%compared to the state-of-the-art Twin Delayed Deep Deterministic Policy Gradient(TD3)*** testing experiments carried out in environments with different complexities demonstrate the strong robustness and generalization ability of the IFHER ***,the flight trajectory of the IFHER agent shows the superiority of the learned policy and the practical application value of the algorithm.

关键词： Artificial intelligence Autonomous navigation control Deep reinforcement learning Hindsight experience replay UAV

来源：评论

学校读者我要写书评

暂无评论

Achieving Adaptive Tasks from Human Instructions for Robots Using Large Language Models and Behavior Trees

SSRN

引用

SSRN 2024年

作者： Zhou, Haotian Lin, Yunhan Yan, Longwu Min, Huasong Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

Large Language Models (LLMs) are widely used to generate control commands from human instructions. By monitoring the execution of control commands, slight disturbances can be effectively addressed by re-executing these commands, such as re-picking an object when it drops. However, in situations where an obstacle suddenly impedes the planned trajectory, considered a heavy disturbance, the robot needs to perform re-planning, which is time-consuming. Therefore, if the robot has a reaction mechanism that can respond to disturbances and partially modify its plan, it will significantly improve its task efficiency. Behavior Trees (BTs) are a good solution that can achieve the reactivity and modularity of the plan through a logical tree structure. In this paper, we combine LLMs with BTs to propose a framework called LLM-BT, enabling robots to achieve adaptive tasks from human instructions. Different from other LLMs-based system, LLM-BT outputs variable BTs. As reactive goal-directed policies, they can modify the task plan partially and dynamically, thus handling slight and heavy disturbances without re-planning. Simulation and real-world experiments validate the advantages of our method. © 2024, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Optimized Design and Experimental Study of Shank Structure of Biped Robot

Optimized Design and Experimental Study of Shank Structure o...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Qin, Meijuan Kong, Lingyu Nie, Daming Jiang, Hongjian Zhang, Yu Fu, Yili Intelligent Robot Research Center Zhejiang Laboratory Hangzhou311100 China The National Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9798350325706

Lightweight design can improve the energy efficiency of biped robots, which is significant in the field of biped robot. Topology optimization has been widely used in the field of robot. However, the existing optimization is limited to the structural space based on traditional empirical design, and the potential of topology optimization is not fully utilized. Moreover, the finite element model is too simplified, which leads to a large optimization deviation. In this paper, a method of structural innovation design for the shank structure of biped robot is proposed. In the initial stage of conceptual design, the design space of optimization object is effectively maximized. Then, the load transmission characteristics of bearings are simulated by link10 element, and the topology optimization method of multiple load cases is carried out to obtain the optimized shank structure, which reduces the weight by 14.09 % compared with the existing shank. Finally, finite element extreme strength check and experiment test are both used to verify the feasibility and availability of the structure. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Map Construction of UAV Autonomous Landing in Unknown Environment

Semantic Map Construction of UAV Autonomous Landing in Unkno...

引用

Chinese Control and Decision Conference, CCDC

作者： Jiagang Wu Zheng Zhang Weihua Huang Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Aiming at the problems of environment identification and dynamic target information detection in the process of autonomous landing map construction of quadrotor UAVs in unknown environments, a method of autonomous landing semantic map construction of UAVs in unknown environments is proposed. Firstly, an improved Deeplabv3+ model is proposed. The image collected by UAV is restored based on the Lucy Richardson algorithm. On this basis, the information after fusion processing of the collected original image features and restored image features is input into the semantic segmentation model. Shufflenetv2 is used as the backbone network of Deeplabv3+ and the CBAM attention mechanism is introduced to improve the accuracy of the semantic segmentation model. Secondly, to improve the accuracy of dynamic target detection, a dynamic target detection method based on optical flow and semantics is designed. The environmental semantic information is introduced into the Lucas Kanade algorithm to estimate the motion displacement of the airborne camera to determine the optical flow threshold of the dynamic target. Then, a semantic grid map is established to model the environment, define the measurement index of the safe landing sites, and design the selection strategy of the safe landing sites. The ICG Drone Dataset is used for experiments, and the results show that the image segmentation accuracy of the designed method is improved by 4.3% on average compared with the traditional DeeplabV3+ model, and the detection rate of the dynamic targets reaches 93.8% correctly. The measured results show that the drone can accurately detect the dynamic targets in an unknown environment and autonomously select the safe area as the landing site.

关键词： Accuracy Semantic segmentation Motion segmentation Semantics Dynamics Object detection Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

SDSLP-YOLO: An End-to-End Model for Simultaneously Detecting Strawberry and Locating Picking Point

SDSLP-YOLO: An End-to-End Model for Simultaneously Detecting...

引用

Chinese Automation Congress (CAC)

作者： Xueyi Du Wenhui Huang Huasong Min Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurately identifying strawberries and locating picking points are prerequisites for harvesting robots. To address the issues of multiple detections, missed detections, and false detections, as well as inaccurate picking point localization caused by large differences in fruit shape, complex backgrounds, and occlusions during the picking process, this paper proposes a method based on the YOLOv8-pose model. First, a dual-path feature extraction backbone network (LGFBNet) that combines convolution and Transformer is proposed. This module enhances the richness and expressiveness of features by coupling global and local features, effectively solving the issue of multiple detections caused by large differences in fruit shape. Secondly, CBAM is introduced into the neck of the network, allowing the network to focus more on the distinguishing features between the strawberries and the background, effectively addressing the missed and false detections caused by complex backgrounds. Finally, the NWD-CIoU weighted loss function is introduced, where the scale-balancing property of NWD compensates for the sensitivity of CIoU to positional shifts, reducing the additional missed detection rate caused by severe occlusions. Experimental results show that the proposed method achieves an average precision (mAP-obj) of 88.3% for strawberry detection and an average precision (mAP-kp) of 74.2% for keypoint detection, which are 1.7% and 3% higher than YOLOv8-pose, respectively. In summary, this method has significant theoretical and practical implications for tasks such as strawberry recognition and picking point localization in complex environments.

关键词： Location awareness Performance evaluation Sensitivity Shape Pipelines Feature extraction Transformers Neck Spatial resolution Robots

来源：评论

学校读者我要写书评

暂无评论

A Fruit Detection Model in Complex Environments Based on Attention Mechanism and Feature Fusion

A Fruit Detection Model in Complex Environments Based on Att...

引用

Chinese Automation Congress (CAC)

作者： Qian Nan Wenhui Huang Huasong Min Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

In complex orchard environments, harvesting robots face significant challenges in identifying fruits accurately due to fruits of various sizes, varying degrees of sunlight intensity, and occlusion. To resolve this issue, we propose a fruit detection model in this paper, which is called AMMFF-YOLO and based on the YOLOv8s architecture. Firstly, a small target detection layer is introduced to enhance the model's ability to identify small-sized fruits. Secondly, a light-adaptive module is proposed, which increases spatial dimension information without reducing the channel dimension, enriching the model's perception ability under different sunlight intensities. This module is named C2f-CS, which stands for C2f module based on channel and spatial (CS) attention mechanisms. Furthermore, a context information enhancement module (CIEM) is proposed, which employs dilated convolutions and skip connections to fuse feature information from multiple scales, enlarges the receptive field, and improves the model's ability to recognize target fruits and backgrounds under occlusion. Lastly, the Inner-MPDIoU Loss is used as a bounding box regression loss function to improve the mod-el's localization ability and detection accuracy. In the detection experiments of strawberries, apples, and citrus in complex orchard environments, the detection accuracy of the proposed model is higher than the detection accuracy of other state-of-art models 0.4 % ~ 8.8 %. The experimental results validate the effectiveness of AMMFF-YOLO in fruit detection under complex orchard environments.

关键词： Accuracy Attention mechanisms Fuses Target recognition Lighting Object detection Feature extraction Robustness Spatial resolution Robots

来源：评论

学校读者我要写书评

暂无评论

YOLOv5-LF: An Optimized YOLOv5 Algorithm for Real-Time Automatic Tracking

YOLOv5-LF: An Optimized YOLOv5 Algorithm for Real-Time Autom...

引用

Chinese Automation Congress (CAC)

作者： Jicheng Luo Lei Cheng Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Recent research has concentrated on enhancing robot visual tracking in dynamic settings. To boost real-time tracking capabilities, we introduce an optimized robot visual tracking control system that employs an advanced lightweight YOLOv5 algorithm. This system integrates the LCNet-a lightweight CPU-based Convolutional Neural Network-and a PConv-driven FasterNet module, both of which significantly enhance the detection of object features. Our experimental setup, which uses an industrial camera to acquire target pose data, demonstrates that after implementing the optimized model, the system efficiently detects and tracks moving objects in real-time from video streams. The gimbal's positioning is dynamically adjusted in response to the moving target's image displacement. The YOLOv5-LF network model, quantified with OpenVINO, has demonstrated a detection accuracy of 95.23% and a recognition rate of 90 frames per second (FPS) on Intel's NUC. This not only ensures seamless real-time system management but also enhances the precision of object detection. The refined detection algorithm notably outperforms the original network in terms of visual tracking efficacy on our experimental platform.

关键词： YOLO Visualization Target tracking Accuracy Quantization (signal) Heuristic algorithms Computational modeling Termination of employment Real-time systems Robots

来源：评论

学校读者我要写书评

暂无评论

3D Source Tracking Using a Position-Unknown AOA Sensor with Measurement Drift and UAV Moving Direction Optimization

3D Source Tracking Using a Position-Unknown AOA Sensor with ...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Xu, Rongrong Xu, Sheng Cao, Kaimin Li, Xianliang Wang, Jialiang Cao, Wujing Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China China Nanhu Academy of Electronics and Information Technology Robotics Laboratory 314051 China University of Chinese Academy of Sciences Beijing101408 China

ISBN: (纸本)9798350372601

This work solves the angle-of-arrival (AOA) source tracking problem in 3-dimensional (3D) space utilizing a position-unknown unmanned aerial vehicle (UAV). An AOA sensor is carried by a mobile UAV, and the conventional self-positioning module, such as the global positioning system (GPS), is not allowed due to environmental limitations. Thus, to guarantee the feasibility of this source tracking problem, at least two position-known landmarks are required. Firstly, the detailed problem formulation is provided with the consideration of measurement drift caused by sensor-vehicle installation errors. Secondly, all the unknown states are estimated using a proposed extended Kalman filter (EKF). Thirdly, a UAV moving direction optimization algorithm is developed to promote the estimation accuracies of the source, UAV and measurement drift. Finally, simulation examples demonstrate the characteristics of the proposed method. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

DNGF-LS: A Dynamic Non-Ground Points Filtering LiDAR SLAM Based on Sparse 4DCNN

DNGF-LS: A Dynamic Non-Ground Points Filtering LiDAR SLAM Ba...

引用

Chinese Automation Congress (CAC)

作者： Tingtian Chen Qi Wang Huasong Min Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Achieving precise localization and high-quality static map construction in unfamiliar environments is fundamental for mobile robots. However, in environments like urban roads, dynamic objects such as pedestrians and vehicles can cause LiDAR SLAM odometry drift, leaving ghostings in the constructed map, which can lead to the failure of subsequent tasks such as path planning based on prior maps. Therefore, performing dynamic points filtering on point clouds is crucial for mobile robots, this paper introduces a novel Dynamic Non-Ground points Filtering LiDAR SLAM(DNGF-LS). Firstly, employing a Coarse-to-Fine Concentric Zone Model(C-F-CZM) to represent point clouds and perform ground segmentation addresses the sparsity issue caused by distant points in ground plane fitting, yielding accurate non-ground point clouds. Subsequently, converting the current frame's previous ten frames of point clouds to 4D point clouds with the same viewpoint, utilizing sparse voxel grids to represent 4D point clouds, and inputting them into a sparse 4D Convolutional Neural Network(CNN) for dynamic points filtering. Finally, retaining static points for pose estimation and mapping using LiDAR Odometry And Mapping(LOAM). Experimental results on highly dynamic datasets demonstrate that DNGF-LS can construct high-quality static maps and achieve superior localization accuracy compared to LIO-SEGMOT and SUMA++.

关键词： Point cloud compression Location awareness Laser radar Accuracy Simultaneous localization and mapping Filtering Heuristic algorithms Object segmentation Odometry Vehicle dynamics

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：