检索结果-内蒙古大学图书馆

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yongxiong Xiao Shiqiang Zhu Te Li Minhong Wan Wei Song Jason Gu Qiang Fu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Lab Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

Estimating the interference-plus-noise covariance matrix (INCM) is critical for the robustness of the minimum variance distortionless response (MVDR) beamformer. Existing INCM reconstruction methods are computationally intensive and not suitable for real-time speech separation. We propose a singular value decomposition (SVD) based INCM reconstruction method for speech separation. The spatial covariance matrix (SCM) for each source is obtained by rank-1 approximation using the nominal steering vector (SV) or the pre-measured relative transfer function (RTF). The INCM used to separate each source is reconstructed as the sum of the covariance matrices of interference and spherical isotropic noise. The proposed method is evaluated using the mixed signal received by a circular array with six microphones placed in a simulated reverberation chamber. The results show that the proposed method has comparable sound quality performance to the reference method, but requires much less computation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RFFCE: Residual Feature Fusion and Confidence Evaluation Network for 6DoF Pose Estimation

RFFCE: Residual Feature Fusion and Confidence Evaluation Net...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Qiwei Meng Shanshan Ji Shiqiang Zhu Tianlei Jin Te Li Jason Gu Wei Song Research Center for Intelligent Robotics Zhejiang Lab Research Institute of Interdisciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

In this paper, we propose a novel RGBD-based object 6DoF pose estimation network - RFFCE. It is a two-stage method that firstly leverages deep neural networks for feature extraction and object points matching, and then the geometric principles are utilized for final pose computation. Our approach consists of three primary innovations: residual feature fusion for representative RGBD feature extraction; confidence evaluation and confidence-based paired points offsets regression for self-evaluation and self-optimization respectively. Their effectiveness is verified through an ablation study, and our RFFCE achieves the SOTA performance on LineMOD, Occlusion-LineMOD and YCB-Video datasets. Additionally, we also conduct a real-world object grasping experiment for visualization and qualitative evaluation of the RFFCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models

arXiv

引用

arXiv 2024年

作者： Tang, Chao Huang, Dehao Dong, Wenlong Xu, Ruinian Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG), which refers to synthesizing grasps on an object that are configurationally compatible with the downstream manipulation task, is the first milestone towards tool manipulation. Analogous to the activation of two brain regions responsible for semantic and geometric reasoning during cognitive processes, modeling the intricate relationship between objects, tasks, and grasps necessitates rich semantic and geometric prior knowledge about these elements. Existing methods typically restrict the prior knowledge to a closed-set scope, limiting their generalization to novel objects and tasks out of the training set. To address such a limitation, we propose FoundationGrasp, a foundation model-based TOG framework that leverages the open-ended knowledge from foundation models to learn generalizable TOG skills. Extensive experiments are conducted on the contributed Language and Vision Augmented TaskGrasp (LaViA-TaskGrasp) dataset, demonstrating the superiority of FoundationGrasp over existing methods when generalizing to novel object instances, object classes, and tasks out of the training set. Furthermore, the effectiveness of FoundationGrasp is validated in real-robot grasping and manipulation experiments on a 7-DoF robotic arm. Our code, data, appendix, and video are publicly available at https://***/view/foundationgrasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

KGNet: Knowledge-Guided Networks for Category-Level 6D Object Pose and Size Estimation

KGNet: Knowledge-Guided Networks for Category-Level 6D Objec...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Qiwei Meng Jason Gu Shiqiang Zhu Jianfeng Liao Tianlei Jin Fangtai Guo Wen Wang Wei Song Zhejiang Lab Research Center for Intelligent Robotics Research Institute of Interdis-ciplinary Innovation Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

Despite the giant leap made in object 6D pose estimation and robotic grasping under structured scenarios, most approaches depend heavily on the exact CAD models of target objects beforehand, thereby limiting their wide applications. To address this, we propose a novel knowledge-guided network - KGNet to estimate the pose and size of category-level unseen objects. This network includes three primary innovations: knowledge-guided categorical model generation, pointwise deformation probability matrix and synergetic RGBD feature fusion, with the former two leveraging categorical object knowledge for unseen object reconstruction and the latter one facilitating pose-sensitive feature extraction. Exten-sive experiments on CAMERA25 and REAL275 verify their effectiveness, and KGNet achieves the SOTA performance on these two acknowledged benchmarks. Additionally, a real-world robotic grasping experiment is conducted, and its results further qualitatively prove the practicability and robustness of KGNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedded Vertexon-Graphons and Embedded GMFG Systems

Embedded Vertexon-Graphons and Embedded GMFG Systems

引用

IEEE Conference on Decision and Control

作者： Peter E. Caines Department of Electrical and Computer Engineering and the Center for Intelligent Machines McGill University and GERAD Montreal Canada

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

An (embedded) vertexon in a connected compact set M in R m is defined to be the vertex set of a graph together with an asymptotically dense partition hierarchy of M. It is shown that sequences of vertexons have subsequential vertexon limits measures in M independent of the particular partition hierarchy employed within a large class of hierarchies. Consequently, the differentiation of functions on vertexon limits with open support is well defined. Further, along these sequences the associated sequence of graphs have subsequential graph edge limits termed embedded graphons; the resulting embedded vertexon-graphon limit (measure) pair permits the definition of critical nodes and other features involving differentiation with respect to node location. This is significant for the analysis of Nash value functions for Embedded Graphon Mean Field Game (EGMFG) systems, that is to say, GMFG systems with nodes lying in a limiting vertexon in M ⊂ R m with open support and associated embedded graphons defined on M 2 . A further feature of vertexon limits is that they provide a form of node population density which extends the local agent population aspect of embedded GMFG systems.

关键词： Weight measurement Limiting Density measurement Sociology Games Aerospace electronics Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Real-time Architecture for Audio-Visual Active Speaker Detection

Real-time Architecture for Audio-Visual Active Speaker Detec...

引用

IEEE International Conference on robotics and Biomimetics

作者： Min Huang Wen Wang Zheyuan Lin Fiseha B. Tesema Shanshan Ji Jason Gu Minhong Wan Wei Song Te Li Shiqiang Zhu Intelligent Robotics Research Center Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical And Computer Engineering Dalhousie University Canada

ISBN: (纸本)9781665481106

Continuously measuring the speaking state of users with robot in a human-robot Interaction(HRI) system improves metrics of interaction quality. Meanwhile, mainstream active speaker detection (ASD) algorithms emphasize achieving high AUCs at frame level in the AVA-Active Speaker dataset and pay less attention to get real-time performance in robotic systems. In this paper, we propose a model named FSDNet to keep a high AUC score in the AVA-Active Speaker dataset while reducing time cost, our model increase AUC score by 0.1% compared with the State-Of-The-Art and need only 75% running time. Furthermore, we put forward an architecture with a time-related prediction function to make our algorithm more effective and generative in interactive robotic systems. The code is released at https://***/huangmin9966/FSDNet_RealTimeArch.

关键词： Measurement Visualization Costs Codes Biological system modeling Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

TGRMPT: A Head-Shoulder Aided Multi-Person Tracker and a New Large-Scale Dataset for Tour-Guide Robot

TGRMPT: A Head-Shoulder Aided Multi-Person Tracker and a New...

引用

IEEE International Conference on robotics and Biomimetics

作者： Wen Wang Zheyuan Lin Min Huang Shunda Hu Tianlei Jin Te Li Minhong Wan Jason Gu Shiqiang Zhu Research Center for Intelligent Robotics Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Canada

ISBN: (纸本)9781665481106

A service robot serving safely and politely needs to track the surrounding people robustly, especially for Tour-Guide Robot (TGR). However, existing multi-object tracking (MOT) or multi-person tracking (MPT) methods are not applicable to TGR for the following reasons: 1. lacking relevant large-scale datasets; 2. lacking applicable metrics to evaluate trackers. In this work, we target the visual perceptual tasks for TGR and present the TGRDB dataset, a novel large-scale multi-person tracking dataset containing roughly 5.6 hours of annotated videos and over 450 long-term trajectories. Besides, we propose a more applicable metric to evaluate trackers using our dataset. As part of our work, we present TGRMPT, a novel MPT system that incorporates information from head shoulder and whole body, and achieves state-of-the-art performance. We have released our codes and dataset in https://***/wenwenzju/TGRMPT.

关键词： Measurement Visualization Target tracking Codes Service robots Biomimetics Trajectory

来源：评论

学校读者我要写书评

暂无评论

Enhancing UAV Autonomous Navigation in Indoor Environments Using Reinforcement Learning and Convolutional Neural Networks 22

Enhancing UAV Autonomous Navigation in Indoor Environments U...

引用

22nd IEEE International Symposium on intelligent Systems and Informatics, SISY 2024

作者： Safarpour Motealegh Mahalegi, Homayoun Farhadi, Amirfarhad Molnar, Gyorgy Nagy, Eniko Obuda University Institute of Mechatronics and Vehicle Engineering Budapest Hungary Islamic Azad University Department of Computer Engineering Science and Research Branch Tehran Iran Obuda University Hungary Szechenyi University Apaczai Csere János Faculty of Humanities Education and Social Sciences Kando Kalman Faculty of Electrical Engineering Budapest Gyor Hungary Obuda University Antal Bejczy Center for Intelligent Robotics John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350385601

In recent years, the number of unmanned aerial vehicle (UAV) applications has increased. However, navigating them indoors is still tricky because no GPS signals are available, and the obstacles constantly change. This study exploits the collaboration between convolutional neural networks (CNNs) and reinforcement learning (RL) to overcome these challenges, improving the level of independence of UAVs in indoor settings. We present a new technique known as potential-based reward shaping, which directly incorporates expert knowledge into the reinforcement learning framework. This technique efficiently addresses the problem of sparse rewards that often hinder learning in conventional RL configurations. In addition, we have created a reflective reinforcement learning agent that systematically assesses its actions to prioritize those that result in the most substantial enhancements. We have extensively evaluated the performance of our method with the High-Definition Indoor Navigation (HDIN) dataset to show that our method continuously outperformed current non-introspective RL techniques in terms of decision-making speed and navigation accuracy in this evaluation. The results show that this new CNN-RL combination is feasible and suggests a scalable method for complex indoor navigation problems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Study of Helicopter Optimal Autorotation Landing Procedure in Tail Rotor Drive Failure

Study of Helicopter Optimal Autorotation Landing Procedure i...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Yan, Xufei Chen, Renliang Zhu, Shiqiang Xie, Anhuan Gu, Jason Research Center for Intelligent Robotics Zhejiang Lab Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China National Key Laboratory of Science and Technology on Rotorcraft Aeromechanics College of Aeronautics Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

This paper investigates the optimal landing trajectory and control procedure when a helicopter undergoes autorotation due to tail rotor drive failure (TRDF), in which an optimal control methodology is proposed. First, a helicopter flight dynamics model with TRDF was developed. Then, the autorotation in TRDF was converted to be a nonlinear optimal control problem, solved by direct node collocation method and sequential quadratic programming algorithm. Finally, a model helicopter (Z11) with single main rotor and tail rotor was used to demonstrate the proposed approach. An optimal autorotation landing procedure in TRDF was determined accordingly. Results indicate that the airframe will immediately respond to the excess torque generated by the main rotor via yawing, sideslip and rolling when TRDF occurs. The pilot is recommended to shut down the engine and perform a series of critical operations to stabilize the violent yaw and roll movements. In addition, flight test data were used to validate the numerical simulations of autorotation landing. The proposed optimal control approach provides a useful tool to investigate helicopter TRDF autorotation landing procedure. © 2022 IEEE.

关键词： Helicopters

来源：评论

学校读者我要写书评

暂无评论

Optimal Landing of Tilt-rotor Aircraft after Engine Failure Considering Pilot Inherent Limitations

Optimal Landing of Tilt-rotor Aircraft after Engine Failure ...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Yan, Xufei Chen, Renliang Zhu, Shiqiang Xie, Anhuan Gu, Jason Research Center for Intelligent Robotics Zhejiang Lab Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China College of Aeronautics Nanjing University of Aeronautics and Astronautics National Key Laboratory of Science and Technology on Rotorcraft Aeromechanics Jiangsu Nanjing China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

An augmented longitudinal rigid-body model is developed with a set of algebra equations describing the controls in the cockpit and the differential equations describing the pilot inherent limitations. The landing procedure after one engine failure is formulated into a nonlinear optimal control problem. XV-15 tilt-rotor aircraft is taken as the sample for the demonstration of landing in one engine failure during short takeoff. The results show that the total power required, thrust coefficient, longitudinal flapping angle and optimal controls are more relatively gentle than the solutions without considering the pilot inherent limitations. Compared with the basic longitudinal rigid-body model, the optimal solutions involve more control information. © 2022 IEEE.

关键词： Differential equations

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：