检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Biomimetics

作者： Jian Zhang Yeheng Chen Shiqiang Zhu Yuehua Li Tian Xie Jason Gu Zhejiang Laboratory Research Center for Intelligent Robotics 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

ISBN: (纸本)9781665481106

Due to communication latency with remote ground sites, automatic recognition of Mars terrain is essential for the path-planning of rovers. Currently, most vision-based terrain classification require thousands of fine-grained training samples, while the undefined terrains on Mars are difficult to be classified or fine-grained labeled. Actually, most of the terrain categories can only be coarse-grained labeled due to several limitations, such as overlapped sub-regions, blurred borders, etc. To solve this problem, CACMT (Coarse-grained Annotation-based Classification for Mars Terrain) is proposed to generate the global fine-grained classification map from the local coarse-grained data. Specifically, the complete pipeline is decomposed into (i) annotation rules with unique design, (ii) hierarchical feature fusion network for predicting sub-features of terrain (iii) and a generator for outputting dense terrain categories of Mars. Finally, the results of actual data on Mars demonstrate that the terrain sub-features can be successfully recognized and a dense terrain classification map can be generated applying only coarse-grained labeled images.

关键词： Training Image recognition Annotations Biomimetics Pipelines Generators Robots

来源：评论

学校读者我要写书评

暂无评论

Steps Toward Industry 5.0:Building“6S”Parallel Industries With Cyber-Physical-Social Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1692-1703页

作者： Xingxia Wang Jing Yang Yutong Wang Qinghai Miao Fei-Yue Wang Aijun Zhao Jian-Ling Deng Lingxi Li Xiaoxiang Na Ljubo Vlacic School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE Macao University of Science and Technology Macao 999078China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of SciencesBeijing 100098 State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China North Automatic Control Technology Institute Taiyuan 030006China China Huaneng Group Co. Ltd.Beijing 100031China Department of Electrical and Computer Engineering Indiana University-Purdue University Indianapolis(IUPUI)IndianapolisIN 46202 USA Department of Engineering University of CambridgeCambridgeCB21PZUK School of Engineering and Built Environment Griffith UniversityGold CoastQLD 4222Australia

Very recently,intensive discussions and studies on Industry 5.0 have sprung up and caused the attention of researchers,entrepreneurs,and policymakers from various sectors around the ***,there is no consensus on why and what is Industry 5.0 *** this paper,we define Industry 5.0from its philosophical and historical origin and evolution,emphasize its new thinking on virtual-real duality and human-machine interaction,and introduce its new theory and technology based on parallel intelligence(PI),artificial societies,computational experiments,and parallel execution(the ACP method),and cyber-physical-social systems(CPSS).Case studies and applications of Industry 5.0 over the last decade have been briefly summarized and analyzed with suggestions for its future *** believe that Industry 5.0 of virtual-real interactive parallel industries has great potentials and is critical for building smart *** are outlined to ensure a roadmap that would lead to a smooth transition from CPS-based Industry 4.0 to CPSS-based Industry 5.0 for a better world which is Safe in physical spaces,S ecure in cyberspaces,Sustainable in ecology,Sensitive in individual privacy and rights,Service for all,and Smartness of all.

关键词： ACP artificial intelligence CPS CPSS Industry 4.0 Industry 5.0 parallel industries parallel intelligence

来源：评论

学校读者我要写书评

暂无评论

Crashworthiness Design Optimization for an eVTOL Aircraft

Crashworthiness Design Optimization for an eVTOL Aircraft

引用

IEEE International Conference on robotics and Biomimetics

作者： Menglong Ding Anhuan Xie Shiqiang Zhu Wei Song Jiandong Cai Xufei Yan Pengyu Zhao Jason Gu Yanyan Zhang 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

ISBN: (纸本)9781665481106

The emergence of electric Vertical Takeoff and Landing (eVTOL) aircraft makes cheap, quiet and reliable short-range flights possible. As a manned aircraft, eVTOL's occupant protection capability is critical and its crashworthiness must be improved via optimization of energy absorption design for structures. This study aims to evaluate the crashworthiness of composite components and the entire eVTOL structure within the design space via the building-block approach. A variety of designs for the skid landing gear, energy absorber, structures in the cockpit and the combination of them were estimated by using the numerical method. The results show a tremendous reduction in occupant injury risk with the optimization of the skid landing gear, energy absorber and the entire eVTOL structure. This work provides a preliminary optimization design and evaluation methodology of crashworthiness for an eVTOL.

关键词： Absorption Gears Force Spine computer crashes Reliability Aircraft

来源：评论

学校读者我要写书评

暂无评论

HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re-Identification Implemented on Tour-Guide Robot

HSMR: A Head-Shoulder Mask Aided ResNet to Guide Focus of Re...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zheyuan Lin Min Huang Wen Wang Mengjie Qin Te Li Minhong Wan Jason Gu Shiqiang Zhu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

For service robots, person re-identification (ReID) and multi-pedestrian tracking (MPT) are vital to get a person's location and link identities across frames. Though their accuracy keeps improving, most work lacks consideration of the application scenario, haunted by limited space, constrained power supply, and demands of the real-time response during human-robot interaction. Some ReID models learn trivial or unrelated features, inhibiting the downstream tasks. To solve these issues, the efficient and light-weighted Head-Shoulder Mask aided ResNet (HSMR) is proposed. This model applies multi-task learning to enhance the feature extraction performance in the training stage without extra computational load during inference. The auxiliary task fully uses head-shoulder information to guide the network and focuses on the head region, which contains the identity information. In experiments on the Tour-Guide Robot Data Base (TGRDB), HSMR earned results better than ResNet-18 on the ReID task and was superior to the recent two-stream method on the MPT task. On the mobile hardware, inference reaches an average of 15.2 FPS, three times faster than the two-stream method. The code is released at https://***/ZhYLin99/HSMR.

关键词： Training Service robots Computational modeling Robot vision systems Human-robot interaction Multitasking Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Acoustic Beamforming via Interference-Plus-Noise Covariance Matrix Construction for Interferences and Noise Attenuation

Acoustic Beamforming via Interference-Plus-Noise Covariance ...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yongxiong Xiao Shiqiang Zhu Wei Song Minhong Wan Jason Gu Te Li 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

ISBN: (纸本)9781665481106

The interference-plus-noise covariance matrix (INCM) is essential in improving an acoustic beamformer's interference and noise attenuation performance. In practical implementation, INCM reconstruction is required to remove the signal of interest (SOI) components from the sample covariance matrix. However, some of the interference and noise components are inevitably removed during the INCM reconstruction process to avoid distortion of the desired speech, which deteriorates the interference and noise attenuation performance of the beamformer. This paper proposes constructing an INCM with as much information on the interferences and noise as possible by adding covariance matrices of the spherically diffuse noise, background noise, and interferences. The final INCM is reconstructed by using the principal eigenvector and definition of INCM. The beamformer's weight coefficients are computed by the linearly constrained minimum variance (LCMV) formulation. The proposed method is validated by experiments using a circular microphone array mounted on a tour robot in an exhibition hall. The results show that the proposed beamformer improves the robustness of automatic speech recognition and the performance of robot audition.

关键词： Acoustic distortion Transfer functions Interference Attenuation Acoustics Robustness Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic Simulation of a Typical Multirotor e VTOL Aircraft Configuration *

Aerodynamic Simulation of a Typical Multirotor e VTOL Aircra...

引用

IEEE International Conference on robotics and Biomimetics

作者： Menglong Ding Yanyan Zhang Shiqiang Zhu Wei Song Pengyu Zhao Xufei Yan Jiandong Cai Jason Gu Anhuan Xie 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

ISBN: (纸本)9781665481106

The aerodynamic interaction among rotors is a key phenomenon that influences the performance of the electric Vertical Takeoff and Landing (eVTOL) aircraft. This study applied Lattice-Boltzmann Method (LBM) to systematically investigate the aerodynamic interaction under typical flight conditions. Simulation of a single rotor was performed to validate the reliability of LBM on rotor aerodynamics and find the maximum acceptable grid size. A numerical study on the complex unsteady flowfield caused by the sixteen rotors was also performed when considering the eVTOL is in hovering, forward flight and hovering under sidewind. Moreover, the analysis of the flowfield provides a detailed insight into the flow physics involved in such regular flight conditions.

关键词： Visualization Atmospheric modeling Rotors Aerodynamics Numerical models Reliability Aircraft

来源：评论

学校读者我要写书评

暂无评论

Robust Control of Feeding Speed for Coal Mine Tunnel Drilling Machines

Robust Control of Feeding Speed for Coal Mine Tunnel Drillin...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Xiao Liu Luefeng Chen Min Wu Weihua Cao Chengda Lu Witold Pedrycz School of Automation China University of Geosciences Wuhan China School of Automation the Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems and the Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Department of Computer Engineering Istinye University Sariyer/Istanbul Turkey

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

Changes in coal seam hardness cause fluctuations in the feed resistance at the drill bit during the drilling process, leading to unstable feeding speed. This paper proposes a robust dynamic output feedback controller to suppress disturbances caused by the variations in coal seam hardness in the feed system. Firstly, an unknown parameter measuring coal seam hardness is introduced, and an uncertain model of the feeding system is established based on the finite element model of the drill string. By designing weighted functions based on industrial field requirements and constructing a generalized plant, the controller achieves loop shaping, reducing the low-frequency impact of coal seam hardness variations on the feed system and suppressing the systems resonance peak. Simulation results demonstrate that the controller effectively suppresses parameter variations and external disturbances caused by changes in coal seam hardness, achieving stable control of the drilling speed.

关键词： Drilling Robust control Uncertainty Robust stability Simulation Coal Resonance

来源：评论

学校读者我要写书评

暂无评论

Quantum Calculus-Based Two-Dimensional Least Mean Square Algorithm

Quantum Calculus-Based Two-Dimensional Least Mean Square Alg...

引用

Asilomar Conference on Signals, systems & computers

作者： Muhammad Moinuddin Azzedine Zerguine Ubaid M. Al-Saggaf Muhammad Arif Electrical and Computer Engineering Department and the Centre of Excellence in Intelligent Engineering Systems King Abdulaziz University Jeddah Saudi Arabia Electrical Engineering Department and the Interdisciplinary Research Center for Communication Systems and Sensing KFUPM Dhahran Saudi Arabia Institute of Networked and Embedded Systems University of Klagenfurt and the Ubiquitous Sensing Systems Lab University of Klagenfurt-Silicon Austria Labs Klagenfurt Austria

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Recent work of the one-dimensional q-LMS algorithm give insight that the Quantum Calculus based gradient called the q-gradient is capable of improving the convergence behavior in contrast to the standard LMS algorithm. The reason for this is the fact that the q-derivative takes larger steps in minimizing a cost function as it evaluates the secant in contrast to the tangent of the cost function. Motivated by this, we propose a two-dimensional version of the q-LMS algorithm. More precisely, we employ Quantum Calculus based q-gradient in steepest descent optimization of mean-square-error (MSE) cost function in 2D adaptive filtering scenario to obtain two-dimensional q-LMS (2D q-LMS) algorithm. A thorough analytical investigation of the proposed 2D q-LMS algorithm in both mean and mean-square sense is provided. Both the transient and steady-state convergence behaviours are examined. Consequently, excess MSE (EMSE) learning curve and its steady-state expression are evaluated in closed form. Simulation results are presented for the application of noise cancelation in images to show the superiority of the proposed 2D q-LMS algorithm.

关键词： Filtering Two-dimensional displays Simulation Cost function Calculus Steady-state Performance analysis Transient analysis Standards Convergence

来源：评论

学校读者我要写书评

暂无评论

Distance Protection Application for 33kV Traction Network

Distance Protection Application for 33kV Traction Network

引用

Power engineering Conference (SAUPEC), Southern African Universities

作者： Luthando Nkalitshana Senthil Krishnamurthy Haltor Mataifa Department of Electrical Electronics and Computer Engineering Centre for Substation Automation and Energy Management Systems (CSAEMS) Center for Intelligent Systems and Emerging Technologies (CSIET) Cape Peninsula University of Technology Bellville South Africa

ISBN: (数字)9798331535162

ISBN: (纸本)9798331535179

The research investigates the laboratory-scale setup and functional testing of distance protection techniques for the Transnet traction system. The Transnet network, which powers South Africa's railway system, requires a strong protection mechanism to assure the safety and dependability of the electrical systems that power locomotives. Distance protection, essential in securing high-voltage transmission networks, is critical to detecting faults, isolating affected portions, and minimizing system interruptions. In this study, a simulation environment was created to simulate the features of the Transnet traction system, including traction substations, overhead power lines, and associated equipment. A lab-scale model was developed utilizing protection functional simulation to simulate real-time fault situations and evaluate the distance protection relay's response under different fault conditions. The performance and efficacy of the protection mechanism were assessed by varying key factors such as fault impedance, fault location, and fault types.

关键词： Rails Substations Simulation Reliability engineering Stability analysis Software Real-time systems Protection Load flow Testing

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving

Risk-Aware Reward Shaping of Reinforcement Learning Agents f...

引用

Annual Conference of Industrial Electronics Society

作者： Lin-Chi Wu Zengjie Zhang Sofie Haesaert Zhiqiang Ma Zhiyong Sun Department of Electrical Engineering Eindhoven University of Technology Netherlands Research Center for Intelligent Robotics School of Astronautics Northwestern Polytechnical University Xi'an China

Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, the reward function for an RL agent, which is significant to its performance, is challenging to determine. The conventional work mainly focuses on rewarding safe driving states but does not incorporate the awareness of risky driving behaviors of the vehicles. In this paper, we investigate how to use risk-aware reward shaping to leverage the training and test performance of RL agents in autonomous driving. Based on the essential requirements that prescribe the safety specifications for general autonomous driving in practice, we propose additional reshaped reward terms that encourage exploration and penalize risky driving behaviors. A simulation study in OpenAI Gym indicates the advantage of risk-aware reward shaping for various RL agents. Also, we point out that proximal policy optimization (PPO) is likely to be the best RL method that works with risk-aware reward shaping.

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：