检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Zhijie Qiao Mingyan Zhou Zhijun Zhuang Tejas Agarwal Felix Jahncke Po-Jen Wang Jason Friedman Hongyi Lai Divyanshu Sahu Tomáš Nagy Martin Endler Jason Schlessman Rahul Mangharam School of Engineering and Applied Science University of Pennsylvania Autoware Foundation Center of Excellence for Autonomous Driving Professorship of Autonomous Vehicle Systems Technical University of Munich Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Red Hat Research

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

When academic researchers develop and validate autonomous driving algorithms, there is a challenge in balancing high-performance capabilities with the cost and complexity of the vehicle platform. Much of today’s research on autonomous vehicles (AV) is limited to experimentation on expensive commercial vehicles that require large skilled teams to retrofit the vehicles and test them in dedicated facilities. On the other hand, 1/10th-1/16th scaled-down vehicle platforms are more affordable but have limited similitude in performance and drivability. To address this issue, we present the design of a one-third-scale autonomous electric go-kart platform with open-source mechatronics design along with fully functional autonomous driving software. The platform’s multi-modal driving system is capable of manual, autonomous, and teleoperation driving modes. It also features a flexible sensing suite for the algorithm deployment across perception, localization, planning, and control. This development serves as a bridge between full-scale vehicles and reduced-scale cars while accelerating cost-effective algorithmic advancements. Our experimental results demonstrate the AV4EV platform’s capabilities and ease of use for developing new AV algorithms. All materials are available at *** to stimulate collaborative efforts within the AV and electric vehicle (EV) communities.

关键词： Location awareness Mechatronics Heuristic algorithms Software algorithms Collaboration Electric vehicles Sensors

来源：评论

学校读者我要写书评

暂无评论

TaSIL: Taylor Series Imitation Learning

arXiv

引用

arXiv 2022年

作者： Pfrommer, Daniel Zhang, Thomas T.C.K. Tu, Stephen Matni, Nikolai Department of Electrical and Systems Engineering University of Pennsylvania United States Google Brain Robotics United States Massachusetts Institute of Technology United States

We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control. TaSIL penalizes deviations in the higher-order Taylor series terms between the learned and expert policies. We show that experts satisfying a notion of incremental input-to-state stability are easy to learn, in the sense that a small TaSIL-augmented imitation loss over expert trajectories guarantees a small imitation loss over trajectories generated by the learned policy. We provide generalization bounds for TaSIL that scale as Õ(1/n) in the realizable setting, for n the number of expert demonstrations. Finally, we demonstrate experimentally the relationship between the robustness of the expert policy and the order of Taylor expansion required in TaSIL, and compare standard Behavior Cloning, DART, and DAgger with TaSIL-loss-augmented variants. In all cases, we show significant improvement over baselines across a variety of MuJoCo tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Taylor series

来源：评论

学校读者我要写书评

暂无评论

SLAM-based Joint Calibration of Multiple Asynchronous Microphone Arrays and Sound Source Localization

arXiv

引用

arXiv 2024年

作者： Wang, Jiang He, Yuanzheng Su, Daobilige Itoyama, Katsutoshi Nakadai, Kazuhiro Wu, Junfeng Huang, Shoudong Li, Youfu Kong, He The Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology No. 1088 Xueyuan Avenue Shenzhen China The College of Engineering China Agricultural University Beijing China The Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan The School of Data Science The Chinese University of Hong Kong Shenzhen China The Robotics Institute University of Technology Sydney Sydney Australia The Department of Mechanical Engineering City University of Hong Kong Hong Kong

Robot audition systems with multiple microphone arrays have many applications in practice. However, accurate calibration of multiple microphone arrays remains challenging because there are many unknown parameters to be identified, including the relative transforms (i.e., orientation, translation) and asynchronous factors (i.e., initial time offset and sampling clock difference) between microphone arrays. To tackle these challenges, in this paper, we adopt batch simultaneous localization and mapping (SLAM) for joint calibration of multiple asynchronous microphone arrays and sound source localization. Using the Fisher information matrix (FIM) approach, we first conduct the observability analysis (i.e., parameter identifiability) of the above-mentioned calibration problem and establish necessary/sufficient conditions under which the FIM and the Jacobian matrix have full column rank, which implies the identifiability of the unknown parameters. We also discover several scenarios where the unknown parameters are not uniquely identifiable. Subsequently, we propose an effective framework to initialize the unknown parameters, which is used as the initial guess in batch SLAM for multiple microphone arrays calibration, aiming to further enhance optimization accuracy and convergence. Extensive numerical simulations and real experiments have been conducted to verify the performance of the proposed method. The experiment results show that the proposed pipeline achieves higher accuracy with fast convergence in comparison to methods that use the noise-corrupted ground truth of the unknown parameters as the initial guess in the optimization and other existing frameworks. © 2024, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

End-To-End Deep Reinforcement Learning for First-Person Pedestrian Visual Navigation in Urban Environments

End-To-End Deep Reinforcement Learning for First-Person Pede...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Honghu Xue Rui Song Julian Petzold Benedikt Hein Heiko Hamann Elmar Rueckert Institute for Robotics and Cognitive Systems University of Luebeck Luebeck Institute of Computer Engineering University of Luebeck Luebeck Institute of Automation Technology Helmut Schmidt University Ham-burg Chair of Cyber-Physical-Systems Montanuniversität Leoben Leoben

ISBN: (纸本)9798350309805

We solve a pedestrian visual navigation problem with a first-person view in an urban setting via deep reinforcement learning in an end-to-end manner. The major challenges lie in severe partial observability and sparse positive experiences of reaching the goal. To address partial observability, we propose a novel 3D-temporal convolutional network to encode sequential historical visual observations, its effectiveness is verified by comparing to a commonly-used Frame-Stacking approach. For sparse positive samples, we propose an improved automatic curriculum learning algorithm NavACL + , which proposes meaningful curricula starting from easy tasks and gradually generalizing to challenging ones. NavACL + is shown to facilitate the learning process with 21% earlier convergence, to improve the task success rate on difficult tasks by 40% compared to the original NavACL algorithm [1] and to offer enhanced generalization to different initial poses compared to training from a fixed initial pose.

关键词： Training Deep learning Visualization Three-dimensional displays Navigation Urban areas Humanoid robots

来源：评论

学校读者我要写书评

暂无评论

A data acquisition system to capture extreme human driving behaviour

A data acquisition system to capture extreme human driving b...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Ines Rito Lima José Santos-Victor Department of Electrical and Computer Engineering Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal Institute for Systems and Robotics (ISR)) Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal

Assessing and encoding human driving expertise while handling challenging events, primarily during drifts, can unveil new insights regarding the professional response to extreme driving which can be integrated into Autonomous Vehicles (AVs) safety procedures. Considering the complex and dynamic data related to both human behaviour and car devices, this research area urges the inclusion of Artificial Intelligence (AI) strategies for the extraction of interdependencies and patterns that encode human driving expertise. To do so, acquiring data that comprises the pilot and vehicle performances is of utmost importance. The present work proposes a specially designed data acquisition system to collect data regarding the vehicle dynamic movement and the associated human behaviour while driving in challenging environments. Distinct sensing devices are placed across the vehicle to retrieve the vehicle position, acceleration, angular rotation, steering orientation, among others. Data was collected from professional drivers during official racing events, and initial processing results show spatial and temporal coherence with the racing performances. The preliminary analysis of the data also reveals potentially extreme events during the race.

关键词： Performance evaluation Data acquisition Robot sensing systems Encoding Sensors Safety Data mining

来源：评论

学校读者我要写书评

暂无评论

A kinematic calibration method for robots based on the PGTF error model and Levenberg-Marquardt algorithm

A kinematic calibration method for robots based on the PGTF ...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Zhi Zheng Jin Wang Jun Zhu Luan Liu Haiyun Zhang Guodong Lu State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou China Robotics Research Center of Yuyao City Ningbo China Robotics Institute of Zhejiang University Hangzhou China School of Robotics Ningbo University of Technology Ningbo China Zhejiang Qiantang Robot and Intelligent Equipment Research Co. LTD Hangzhou China

Robots use motors for power output and realize joint motion through reducers and mechanical transmissions, which affect the absolute positioning accuracy. In view of this problem, an error model based on Preprocessing-Geometric-Transmission-Flexibility (PGTF) is proposed and solved by Levenberg-Marquardt algorithm. First, the theoretical kinematic model is established by MD-H model method. Second, the data was pre-processed in dimension upgrade and the robot error identification model was established for geometric error, transmission error and flexible error. Third, Levenberg-Marquardt algorithm was used to find the global convergence solution to realize the identification of error parameters, and the actual robot kinematic model was compensated. Finally, the experiment is carried out on the real robot machine. Through theoretical analysis and verification of real machine data, the average error of kenbei-5kg robot is reduced from 6.8787 mm to 0.1267 mm, the positioning accuracy is improved by 98.16%, the accuracy compensation algorithm is accurate, and the compensation effect is remarkable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bringing sensation to prosthetic hands-chronic assessment of implanted thin-film electrodes in humans

引用

npj Flexible Electronics 2023年第1期7卷 32-45页

作者： PaulČvančara Giacomo Valle Matthias Müller Inga Bartels Thomas Guiho Arthur Hiairrassary Francesco Petrini Stanisa Raspopovic Ivo Strauss Giuseppe Granata Eduardo Fernandez Paolo M.Rossini Massimo Barbaro Ken Yoshida Winnie Jensen Jean-Louis Divoux David Guiraud Silvestro Micera Thomas Stieglitz Laboratory for Biomedical Microtechnology Department of Microsystems Engineering-IMTEKAlbert-Ludwig-University FreiburgFreiburgGermany Center for Neuroprosthetics and Institute of Bioengineering School of EngineeringÉcole Polytechnique Fédérale de Lausanne(EPFL)LausanneSwitzerland The Biorobotics Institute Scuola Superiore Sant’AnnaPisaItaly Camin Team INRIAUniversity of MontpellierMontpellierFrance Institute of Neurology Catholic University of the Sacred HeartRomaItaly Institute of Neurosurgery Catholic University of the Sacred HeartRomaItaly Department of Neuroscience&Neurorehabilitation IRCCS San Raffaele Roma00166 RomeItaly Department of Electrical and Electronic Engineering University of CagliariCagliariItaly Biomedical Engineering Department Indiana University-Purdue UniversityIndianapolisINUSA SMI Dept.Health Science and TechnologyAalborg UniversityAalborgDenmark AXONIC/Groupe MXM VallaurisFrance BrainLinks-BrainTools Albert-Ludwig-University FreiburgFreiburgGermany Bernstein Center Freiburg Albert-Ludwig-University FreiburgFreiburgGermany Present address:Laboratory for Neuroengineering Department of Health Sciences and TechnologyInstitute for Robotics and Intelligent SystemsETH ZürichZürichSwitzerland

Direct stimulation of peripheral nerves with implantable electrodes successfully provided sensory feedback to amputees while using hand *** of the electrodes is key to success,which we have improved for the polyimide-based transverse intrafascicular multichannel electrode(TIME).The TIMEs were implanted in the median and ulnar nerves of three trans-radial amputees for up to six *** present a comprehensive assessment of the electrical properties of the thin-film metallization as well as material status post *** TIMEs stayed within the electrochemical safe limits while enabling consistent and precise amplitude *** lead to a reliable performance in terms of eliciting *** signs of corrosion or morphological change to the thin-film metallization of the probes was observed by means of electrochemical and optical *** presented longevity demonstrates that thin-film electrodes are applicable in permanent implant systems.

关键词： film electrodes sensation

来源：评论

学校读者我要写书评

暂无评论

Multi-Quadrotor Cooperative Encirclement and Capture Approach in Obstacle Environments

Multi-Quadrotor Cooperative Encirclement and Capture Approac...

引用

International Conference on Mechatronics (ICM)

作者： Zhenyu Li Ruixin Wu Jin Wang Chuanqi Hu Zhi Zheng Jun Meng Guodong Lu School of Mechanical Engineering Zhejiang University Hangzhou China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou China Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Zhejiang University Hangzhou China Robotics Research Center of Yuyao City Ningbo China Polytechnic Institute Zhejiang University Hangzhou China College of Electrical Engineering Zhejiang University Hangzhou China Center for Data Mining and Systems Biology College of Electrical Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798331533892

ISBN: (纸本)9798331533908

This article proposes an algorithm designed for autonomous quadrotors to capture target quadrotors in complex obstacle environments, enabling multiple pursuers to perform distributed capture while simultaneously avoiding obstacles and collisions. We first introduce a 3D obstacle space representation method based on safety-priority reachable region (SPRR) and implement real-time construction for general point cloud maps. Subsequently, leveraging SPRR, we employ an area minimization approach to ensure the effective capture of the evader within a limited time. The outcomes are then integrated into a MINCO-based trajectory planning framework to ensure their practical execution by real quadrotors. Relying on SPRR, the optimization problem is simplified and the solution efficiency is improved. In the scenario of simulating the dynamics of real quadrotors, we compare the proposed algorithm with state-of-the-art evasion and pursuit methods, validating its effectiveness and advancements. This work presents a practical solution for multi-quadrotor collaborative capture.

关键词： Point cloud compression Visualization Three-dimensional displays Trajectory planning Heuristic algorithms Collaboration Real-time systems Safety Optimization Quadrotors

来源：评论

学校读者我要写书评

暂无评论

Learning to Turn: Deformation Control of a Novel Flexible Fishtail Actuated by Artificial Muscles

Learning to Turn: Deformation Control of a Novel Flexible Fi...

引用

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Junwen Gu Yukai Feng Zhengxing Wu Jian Wang Junzhi Yu Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Advanced Manufacturing and Robotics State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China

ISBN: (数字)9798350388039

ISBN: (纸本)9798350388046

Achieving agile, fish-like turning remains a critical challenge in the development of robotic fish. The flexible deformation of a fish’s body significantly contributes to its turning ability. Consequently, researchers have devoted substantial efforts to enhancing the compliance and agility of robotic fish. This paper presents a novel flexible fishtail, inspired by the musculoskeletal structure of real fish, which can control the deformation of its flexible components during turns, improving the turning performance of robotic fish. The fishtail primarily consists of a carbon fiber plate with attached artificial muscles. These muscles can contract and stretch, causing the carbon fiber tail to bend and deform. To enable precise deformation control, a dynamic model of the fishtail is established based on Hamilton’s principle. Subsequently, deep reinforcement learning methods such as deep deterministic policy gradient and soft actor-critic are employed to develop a deformation controller under joint deflection. Cross-validation ensures the controller’s accuracy and robustness. The experimental results demonstrate that this controller facilitates the deformation control of the flexible tail across various turning amplitudes and speeds, allowing the fishtail to exhibit adjustable compliance or resistance to fluids during turning motion. Consequently, this enhances the agility of the robotic fish.

关键词： Artificial muscles Deformation Tail Learning (artificial intelligence) Muscles Turning Fish Robustness Carbon Robots

来源：评论

学校读者我要写书评

暂无评论

Electrolyte Effect on Photoetching of Gallium Nitride

引用

Nanomanufacturing and Metrology 2024年第1期7卷 61-74页

作者： Huiqiang Liang Zhenghao Wei Jiongchong Fang Yanming Li Changli Li Zhirun Xie Yun Hau Ng Guosong Zeng Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Southern University of Science and TechnologyShenzhen 518055People’s Republic of China Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhen 518055People’s Republic of China School of Materials Sun Yat-Sen UniversityGuangzhou 510275People’s Republic of China School of Energy and Environment City University of Hong KongKowloon 999077Hong Kong SARPeople’s Republic of China City University of Hong Kong Shenzhen Research Institute Shenzhen Hi-Tech Industrial ParkNanshan DistrictShenzhen 518000People’s Republic of China SUSTech Energy Institute for Carbon Neutrality Southern University of Science and TechnologyShenzhen 518055People’s Republic of China

The limited material removal rate of conventional chemical mechanical polishing(CMP)significantly hinders the fabrica-tion efficiency and surface quality,thereby preventing the development of gallium nitride(GaN)-based ***,the incorporation of photoelectrochemistry in CMP has garnered increasing attention because of its potential to enhance the quality and efficiency of the GaN ***,a considerable gap still exists in the comprehensive understanding of the specific photoelectrochemical(PEC)behavior of ***,we report the influence of the electrolyte on the PEC etching of *** acids and bases were tested,with their pH being carefully *** concentrations of the cations and anions were also *** results showed that photocorrosion/photoetching was more pronounced in sulfuric acid,phosphoric acid,and nitric acid environments than in alkaline environments,but it was less pronounced in hydrochloric ***,the effects of pH and anion concentration on photoetching were investigated,and the results revealed that pho-toetching in acidic environments weakened with increasing pH levels and diminished with increasing sulfate *** underlying reasons contributing to this observation were *** findings provide ideas for improving the pho-toetching efficiency of GaN,thereby enriching the photoelectrochemical mechanical polishing(PECMP)technology of GaN.

关键词： GaN Photoelectrochemistry Photoetching pH

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：