检索结果-内蒙古大学图书馆

Computing and Machine Intelligence (ICMI), International Conference on

作者： Amanali Bekbolat M. Hassan Tanveer Ardak Kashkynbayev Md. Hazrat Ali Department of Mechanical and Aerospace Engineering SEDS Nazarbayev University Astana Kazakhstan Department of Robotics and Mechatronics Engineering Kennesaw State University Marietta GA USA Department of Mathematics SSH Nazarbayev University Astana Kazakhstan

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

As the demand for accurate vehicle attribute classification continues to grow in applications such as autonomous driving and traffic management, there is an increasing need for advanced deep-learning models capable of handling diverse and correlated attributes. This paper introduces a Multi-Head Deep Learning Model for Vehicle Attributes Classification. The multihead architecture, designed to accommodate various attributes simultaneously, addresses the limitations of traditional methods and single-head models. Leveraging a selected dataset, the model undergoes training focusing on optimizing performance. Evaluation metrics demonstrate the superiority of the proposed approach over single-head models and traditional methods. Results and insights from the experiments underscore the potential of multi-head deep learning in enhancing the accuracy and robustness of vehicle attribute classification. The paper concludes with a discussion of challenges, future directions, and the broader implications of the proposed model in real-world applications.

关键词： Deep learning Training Measurement Accuracy Computational modeling Focusing Computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility

arXiv

引用

arXiv 2024年

作者： Poddar, Prithvi Paul, Steve Chowdhury, Souma Department of Mechanical and Aerospace Engineering University at Buffalo University at Buffalo BuffaloNY14260 United States Department of Mechanical and Aerospace Engineering Center for Embodied Autonomy and Robotics University at Buffalo University at Buffalo BuffaloNY14260 United States

The advent of Urban Air Mobility (UAM) presents the scope for a transformative shift in the domain of urban transportation. However, its widespread adoption and economic viability depends in part on the ability to optimally schedule the fleet of aircraft across vertiports in a UAM network, under uncertainties attributed to airspace congestion, changing weather conditions, and varying demands. This paper presents a comprehensive optimization formulation of the fleet scheduling problem, while also identifying the need for alternate solution approaches, since directly solving the resulting integer nonlinear programming problem is computationally prohibitive for daily fleet scheduling. Previous work has shown the effectiveness of using (graph) reinforcement learning (RL) approaches to train real-time executable policy models for fleet scheduling. However, such policies can often be brittle on out-of-distribution scenarios or edge cases. Moreover, training performance also deteriorates as the complexity (e.g., number of constraints) of the problem increases. To address these issues, this paper presents an imitation learning approach where the RL-based policy exploits expert demonstrations yielded by solving the exact optimization using a Genetic Algorithm. The policy model comprises Graph Neural Network (GNN) based encoders that embed the space of vertiports and aircraft, Transformer networks to encode demand, passenger fare, and transport cost profiles, and a Multi-head attention (MHA) based decoder. Expert demonstrations are used through the Generative Adversarial Imitation Learning (GAIL) algorithm. Interfaced with a UAM simulation environment involving 8 vertiports and 40 aircrafts, in terms of the daily profits earned reward, the new imitative approach achieves better mean performance and remarkable improvement in the case of unseen worst-case scenarios, compared to pure RL results. Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Joint optimization of logistics operations and reliability-based replacement policies in a geographically distributed service parts logistic system

引用

CIRP Annals 2025年

作者： Wang, Po-Han Djurdjanovic, Dragan Graduate Program on Operations Research and Industrial Engineering The University of Texas at Austin AustinTX United States Walker Department of Mechanical Engineering The University of Texas at Austin AustinTX United States

A joint location-inventory-maintenance model is proposed for a geographically distributed Service Parts Logistics problem. The model uses a reliability-based replacement strategy and is formulated as a quadratic Mixed Integer Linear program which jointly optimizes logistic and preventive part replacement decisions. The proposed solution method employs piecewise linearization to provide a level of tractability and scalability to the method. The newly proposed joint location-inventory-maintenance model is evaluated and benchmarked against traditional local optimum-based replacement approaches. It consistently outperformed the benchmark models, with the efficiency of cost effect improvements determined by the relative prevalence of logistics factors versus asset management costs. © 2025

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Controllability Analysis and Stabilization of Untethered Tumbler Floating ROV

Controllability Analysis and Stabilization of Untethered Tum...

引用

IEEE International Conference on robotics and Biomimetics

作者： Junda Huang Haiwen Wu Hanwen Cao Jianshu Zhou Yunhui Liu The Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Center for Logistics Robotics (HKCLR)

Floating ROVs have extensive applications on oceanographic research, environmental monitoring, and search and rescue operations. In this work, two levels of floating ROV stabilization is realized. First, the intrinsic stability is induced by the design of center of mass and moment of inertia based on the stability analysis, such that the ROV can always keep its upwards standing configuration. Besides, an underactuated control method for this novel untethered tumbler floating (TF) ROV is introduced for stabilization, which effectively enhances the stabilization efficiency based on the attitude controller. The model considering rigid body dynamics based on Euler equations, and nonlinear controllability with one, two, or three torques are analyzed serving for the moment of inertia design and underactuated controller. Simulation experiments are conducted to validate the efficacy of our approach, and the results demonstrate its effectiveness for stabilizing the TF-ROV.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Eclares: Energy-Aware Clarity-Driven Ergodic Search

Eclares: Energy-Aware Clarity-Driven Ergodic Search

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Kaleb Ben Naveed Devansh Agrawal Christopher Vermillion Dimitra Panagou Department of Robotics University of Michigan Ann Arbor MI USA Department of Aerospace Engineering University of Michigan Ann Arbor MI USA Department of Mechanical Engineering University of Michigan Ann Arbor MI USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Planning informative trajectories while considering the spatial distribution of the information over the environment, as well as constraints such as the robot’s limited battery capacity, makes the long-time horizon persistent coverage problem complex. Ergodic search methods consider the spatial distribution of environmental information while optimizing robot trajectories; however, current methods lack the ability to construct the target information spatial distribution for environments that vary stochastically across space and time. Moreover, current coverage methods dealing with battery capacity constraints either assume simple robot and battery models or are computationally expensive. To address these problems, we propose a framework called Eclares, in which our contribution is two-fold. 1) First, we propose a method to construct the target information spatial distribution for ergodic trajectory optimization using clarity, an information measure bounded between [0, 1]. The clarity dynamics allow us to capture information decay due to a lack of measurements and to quantify the maximum attainable information in stochastic spatiotemporal environments. 2) Second, instead of directly tracking the ergodic trajectory, we introduce the energy-aware (eware) filter, which iteratively validates the ergodic trajectory to ensure that the robot has enough energy to return to the charging station when needed. The proposed eware filter is applicable to nonlinear robot models and is computationally lightweight. We demonstrate the working of the framework through a simulation case study. [Code] a [Video] b

关键词： Graphical models Target tracking Computational modeling Stochastic processes Information filters Batteries Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing

Learning Model Predictive Control with Error Dynamics Regres...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Haoru Xue Edward L. Zhu John M. Dolan Francesco Borrelli Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Mechanical Engineering University of California Berkeley Berkeley CA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This work presents a novel Learning Model Predictive Control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/10th scale hardware, and deployed the proposed LMPC on a full-scale autonomous race car used in the Indy Autonomous Challenge (IAC) with closed loop experiments at the Putnam Park Road Course in Indiana, USA. The results show that the proposed control policy exhibits improved robustness to parameter tuning and data scarcity. Incremental and safety-aware exploration toward the limit of handling and iterative learning of the vehicle dynamics in high-speed domains is observed both in simulations and experiments.

关键词： System dynamics Roads Robustness Hardware Nonlinear dynamical systems Safety Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Using Economic Iterative Learning Control for Time-Optimal Control of a Redundant Manipulator

Using Economic Iterative Learning Control for Time-Optimal C...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Matthijs van de Vosse Tyler W. Toner Maxwell J. Wu Dawn M. Tilbury Kira L. Barton Mechanical Engineering Department Eindhoven University of Technology Eindhoven NL Department of Mechanical Engineering University of Michigan Ann Arbor MI USA Robotics Department University of Michigan Ann Arbor MI USA

Industrial manipulators are deployed for a range of repetitive tasks in cluttered environments in which the robot must rapidly execute safe trajectories. While nominal robot models exist, true dynamic models of deployed manipulators are typically unavailable. This paper addresses the problem of generating dynamically feasible, collision-free, time-optimal kinematic reference signals for redundant manipulators with unknown dynamics. A novel economic iterative learning control approach is developed to leverage repeated task executions to learn a time-optimal control signal for an uncertain robot model. Simulation results demonstrate the performance of the approach for a 7-DOF manipulator. An experimental analysis is performed to understand the impact of the initial reference trajectory on converged performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nitrogen Pretreatment of Growth Substrates for Vacancy-Saturated MoS2

引用

ACS Applied Materials and Interfaces 2023年第36期15卷 42746-42752页

作者： Yao, Yu-Chi Wu, Bo-Yi Chin, Hao-Ting Yen, Zhi-Long Ting, Chu-Chi Hofmann, Mario Hsieh, Ya-Ping Institute of Atomic and Molecular Sciences Academia Sinica Taipei10617 Taiwan Department of Physics National Taiwan University Taipei10617 Taiwan Graduate Institute of Opto-Mechatronics Department of Mechanical Engineering National Chung Cheng University Chia-Yi62102 Taiwan International Graduate Program of Molecular Science and Technology National Taiwan University Taipei10617 Taiwan Molecular Science and Technology Program Taiwan International Graduate Program Academia Sinica Taipei10617 Taiwan

Two-dimensional transition-metal dichalcogenides (2D TMDCs) are considered promising materials for optoelectronics due to their unique optical and electric properties. However, their potential has been limited by the occurrence of atomic vacancies during synthesis. While post-treatment processes have demonstrated the passivation of such vacancies, they increase process complexity and affect the TMDC’s quality. We here introduce the concept of pretreatment as a facile and powerful route to solve the problem of vacancies in MoS2. Low-temperature nitridation of the sapphire substrate prior to growth provides a nondestructive method to MoS2 modification without introducing new processing steps or increasing the thermal budget. Spectroscopic characterization and atomic-resolution microscopy reveal the incorporation of nitrogen from the sapphire surface layer into chalcogen vacancies. The resulting MoS2 with nitrogen-saturated defects shows a decrease in midgap states and more intrinsic doping as confirmed by ab initio calculations and optoelectronic measurements. The demonstrated pretreatment method opens up new routes toward future, high-performance 2D electronics, as evidenced by a 3-fold reduction in contact resistance and a 10-fold improved performance of 2D photodetectors. © 2023 American Chemical Society

关键词： Molybdenum compounds

来源：评论

学校读者我要写书评

暂无评论

Flexible organic solar cells for biomedical devices

引用

Nano Research 2021年第9期14卷 2891-2903页

作者： Bin Kan Faheem Ershad Zhoulyu Rao Cunjiang Yu Department of Mechanical Engineering University of HoustonHoustonTX 77204USA Department of Biomedical Engineering University of HoustonHoustonTX 77204USA Materials Science and Engineering Program University of HoustonHoustonTX 77204USA Department of Electrical and Computer Engineering University of HoustonHoustonTX 77204USA Texas Center for Superconductivity University of HoustonHoustonTX 77204USA

Organic solar cells(OSCs),particularly made based on solution processing methods,have made significant progress over the past decades through the concurrent evolution of organic photovoltaic materials and device ***,high power conversion efficiencies around 18%and over 16%have been demonstrated in both rigid and flexible OSCs,*** most of the OSC research has centered on efficiency and cost,their emerging and potential usages in many critical applications,particularly in biomedical fields have been *** this mini-review,we will briefly discuss the high-performance organic photovoltaic materials and the representative flexible OSCs to give a scope on the recent rapid development of ***,we will review some progress on the applications of OSCs in biomedical devices and integrated *** potential challenges associated with integrating OSCs for biomedical devices will be put forward.

关键词： organic solar cells photovoltaic flexible biomedical bioelectronics

来源：评论

学校读者我要写书评

暂无评论

Development of the Physical Simulation Platform for Catenary Cantilever

Development of the Physical Simulation Platform for Catenary...

引用

IEEE International Conference on Mechatronics and Automation

作者： Jinjiao Xie Chuxiong Hu Zhenhua Li Mingli Liu Department of Mechanical Engineering Tsinghua University Beijing China Department of Research and Design THTC Robotics (Tianjin) Co. Ltd. Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Regarding to the problem of deviations in the cantilever pre-assembling, a physical simulation platform for cantilevers has been developed. This platform simulates the actual operating conditions of the high-speed rail pantograph-catenary and conducts simulated inspections and calculations to the pre-assembling cantilever before installation, obtaining stagger value data and predicting whether the cantilever is qualified or not. This allows for timely adjustments or re-manufacturing of the cantilever, thereby effectively reducing construction risks.

关键词： Laser theory Mechatronics Automation Measurement by laser beam User interfaces Inspection Rail transportation

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：