检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liang, Mingjian Hu, Junjie Bao, Chenyu Feng, Hua Deng, Fuqin Lam, Tin Lun Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

Recently, RGB-Thermal based perception has shown significant advances. Thermal information provides useful clues when visual cameras suffer from poor lighting conditions, such as low light and fog. However, how to effectively fuse RGB images and thermal data remains an open challenge. Previous works involve naive fusion strategies such as merging them at the input, concatenating multi-modality features inside models, or applying attention to each data modality. These fusion strategies are straightforward yet insufficient. In this paper, we propose a novel fusion method named Explicit Attention-Enhanced Fusion (EAEF) that fully takes advantage of each type of data. Specifically, we consider the following cases: i) both RGB data and thermal data, ii) only one of the types of data, and iii) none of them generate discriminative features. EAEF uses one branch to enhance feature extraction for i) and iii) and the other branch to remedy insufficient representations for ii). The outputs of two branches are fused to form complementary features. As a result, the proposed fusion method outperforms state-of-the-art by 1.6% in mIoU on semantic segmentation, 3.1% in MAE on salient object detection, 2.3% in mAP on object detection, and 8.1% in MAE on crowd counting. The code is available at https://***/Freeformrobotics/EAEFNet. © 2023, CC BY.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Pricing and Charging Scheduling for Cooperative Electric Vehicle Charging Stations via Deep Reinforcement Learning

Pricing and Charging Scheduling for Cooperative Electric Veh...

引用

2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2022

作者： Liu, Jie Wang, Shuoyao Tang, Xiaoying Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Shenzhen University Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China Guangdong Provincial Key Laboratory of Future Networks of Intelligence China

ISBN: (数字)9781665432542

ISBN: (纸本)9781665432542

The rapid adoption of electric vehicles (EVs) stimulates the proliferation of charging stations (CSs), motivating the cooperative management of growing CSs. However, cooperative CS management still remains an open problem, due to the uncertain user behavior and heterogeneous service capabilities. To capture the CS dynamics caused by uncertain user behavior, we propose a deep reinforcement learning (DRL)-based cooperative method for multiple CSs, towards maximizing the total profit. The proposed method determines pricing and charging scheduling decisions for CSs, considering stochastic CSs selection and its impact on CSs energy supply. In order to reduce the computational burden of dimensions caused by the time-varying decisions, we design a discretization strategy for action space, based on the current market rule of tiered pricing and CS types. The simulations using real data demonstrate that our proposed method can obtain higher profit than the independent operation and benchmark cooperative algorithms such as Q-learning. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An enhanced hybrid ensemble deep learning approach for forecasting daily PM_(2.5)

引用

Journal of Central South University 2022年第6期29卷 2074-2083页

作者： LIU Hui DENG Da-hua Institute of Artificial Intelligence&Robotics(IAIR) Key Laboratory for Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China

PM_(2.5) forecasting technology can provide a scientific and effective way to assist environmental governance and protect public *** forecast PM_(2.5),an enhanced hybrid ensemble deep learning model is proposed in this *** whole framework of the proposed model can be generalized as follows:the original PM_(2.5) series is decomposed into 8 sub-series with different frequency characteristics by variational mode decomposition(VMD);the long short-term memory(LSTM)network,echo state network(ESN),and temporal convolutional network(TCN)are applied for parallel forecasting for 8 different frequency PM_(2.5) sub-series;the gradient boosting decision tree(GBDT)is applied to assemble and reconstruct the forecasting results of LSTM,ESN and *** comparing the forecasting data of the models over 3 PM_(2.5) series collected from Shenyang,Changsha and Shenzhen,the conclusions can be drawn that GBDT is a more effective method to integrate the forecasting result than traditional heuristic algorithms;MAE values of the proposed model on 3 PM_(2.5) series are 1.587,1.718 and 1.327μg/m3,respectively and the proposed model achieves more accurate results for all experiments than sixteen alternative forecasting models which contain three state-of-the-art models.

关键词： PM_(2.5)forecasting variational mode decomposition deep neural network ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments

arXiv

引用

arXiv 2022年

作者： Alt, Benjamin Katic, Darko Jäkel, Rainer Beetz, Michael ArtiMinds Robotics Karlsruhe Germany Institute for Artificial Intelligence University of Bremen Germany

In both industrial and service domains, a central benefit of the use of robots is their ability to quickly and reliably execute repetitive tasks. However, even relatively simple peg-in-hole tasks are typically subject to stochastic variations, requiring search motions to find relevant features such as holes. While search improves robustness, it comes at the cost of increased runtime: More exhaustive search will maximize the probability of successfully executing a given task, but will significantly delay any downstream tasks. This trade-off is typically resolved by human experts according to simple heuristics, which are rarely optimal. This paper introduces an automatic, data-driven and heuristic-free approach to optimize robot search strategies. By training a neural model of the search strategy on a large set of simulated stochastic environments, conditioning it on few real-world examples and inverting the model, we can infer search strategies which adapt to the time-variant characteristics of the underlying probability distributions, while requiring very few real-world measurements. We evaluate our approach on two different industrial robots in the context of spiral and probe search for THT electronics assembly.*MSC Codes 68T40 © 2022, CC BY.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Highly Dynamic Locomotion Control of Biped Robot with Swing Arms

Highly Dynamic Locomotion Control of Biped Robot with Swing ...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Weijie Wang Song Liu Qinfeng Shan Lihao Jia Research Center for Brain-inspired Intelligence Institute of Automation Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

The swinging motion of the arms plays a crucial role in improving the dynamic movement of humans by expanding their ability to control angular momentum, as viewed through the lens of biomechanics. However, biped robot with human morphological structures rarely take full advantage of the swing arms, since there is no effective locomotion control strategy combining swing arms modeling and control reasonably suitable. In this paper, a control strategy is proposed for bipedal robots that incorporates swing arms in the process of achieving jumping motion. The strategy involves modeling, planning trajectories, and tracking movements to enhance the overall performance and stability of the robot. In this process, in order to extract characteristics of swing arms, biped robot is modeled as a flywheel-spring loaded inverted pendulum (F-SLIP), and whole-body controller (WBC) is chosen as the method of trajectory tracking to bring these characteristics into play. Simulation of jumping motion is implemented on a kind of biped robot Purple V1.0 designed for high explosive locomotion, and an well-established evaluation method of biped robot's highly dynamic locomotion is proposed which includes three aspects of agility, stability and energy consumption. Experiment results show this control strategy's effectiveness: agility is increased by a maximum of 6 %, stability is enhanced by an average of 30%, and energy consumption is reduced by an average of 15 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Trusted Multi-view Classification Framework with Hierarchical Opinion Aggregation

arXiv

引用

arXiv 2024年

作者： Shi, Long Tang, Chuanqing Deng, Huangyi Xu, Cai Xing, Lei Chen, Badong The School of Computing and Artificial Intelligence China The Financial Intelligence and Financial Engineering Key Laboratory of Sichuan Province Southwestern University of Finance and Economics Chengdu611130 China School of Computer Science and Technology Xidian University China The Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

Recently, multi-view learning has witnessed a considerable interest on the research of trusted decision-making. Previous methods are mainly inspired from an important paper published by Han et al. in 2021, which formulates a Trusted Multi-view Classification (TMC) framework that aggregates evidence from different views based on Dempster’s combination rule. All these methods only consider inter-view aggregation, yet lacking exploitation of intra-view information. In this paper, we propose a generalized trusted multi-view classification framework with hierarchical opinion aggregation. This hierarchical framework includes a two-phase aggregation process: the intra-view and inter-view aggregation hierarchies. In the intra aggregation, we assume that each view is comprised of common information shared with other views, as well as its specific information. We then aggregate both the common and specific information. This aggregation phase is useful to eliminate the feature noise inherent to view itself, thereby improving the view quality. In the inter-view aggregation, we design an attention mechanism at the evidence level to facilitate opinion aggregation from different views. To the best of our knowledge, this is one of the pioneering efforts to formulate a hierarchical aggregation framework in the trusted multi-view learning domain. Extensive experiments show that our model outperforms some state-of-art trust-related baselines. One can access the source code on https://***/lshi91/GTMC-HOA. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimization Design of Energy Management System for Based on Microservice Architecture and Reinforcement Learning

Optimization Design of Energy Management System for Based on...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Ye Wang Changqing Xia Chuanzhi Zang Xi Jin Chi Xu School of Artificial Intelligence Shenyang University of Technology Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automaton Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

As software architecture continues to evolve and system scales expand, microservices architecture has gradually become the mainstream paradigm in software development, particularly well-suited for addressing increasingly complex business logic and the need for rapid feature iteration. The scalability, flexibility, and fault tolerance of microservices provide new solutions for traditional Energy Management Systems (EMS) in handling complex energy demands and supply management. However, challenges persist in areas such as resource scheduling in dynamic and complex environments, load balancing, and fault recovery mechanisms, making it difficult to meet the requirements of distributed energy and rapidly changing market conditions. To address these issues, this paper proposes an EMS architecture optimization design based on a combination of microservices architecture and reinforcement learning techniques. By decoupling the system through microservices, the scalability and flexibility of the EMS are enhanced. Furthermore, leveraging the advantages of reinforcement learning algorithms in complex decision-making and adaptability to dynamic environments, the proposed system achieves intelligent decision-making and control. Based on this approach, a web-based microservice EMS for process industries has been developed. Experimental results demonstrate that the proposed method significantly improves system performance and exhibits strong adaptability to complex business demands.

关键词： Heuristic algorithms Scalability Fault tolerant systems Microservice architectures Reinforcement learning Computer architecture Dynamic scheduling Energy management Energy management systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Numerical Analysis of Flat Panel Composite Material for Two-Bay Crack Arrest Competency with Fractured Central Longeron

引用

Journal of The Institution of Engineers (India): Series D 2024年 1-12页

作者： S, Suresh Kumar G, Veeresha Matur, Mahantesh S. R, Aprameya C. Bavan, Saravana Prem Chand, R. B, Manjunatha L, Kumar P. Manjunath, C.J. Department of Mechanical Engineering RV Institute of Technology and Management Karnataka Bengaluru India Department of Mechanical Engineering New Horizon College of Engineering Karnataka Bengaluru India Department of Mechanical Engineering Ramaiah Institute of Technology Karnataka Bengaluru India Department of Mechanical Engineering Government Polytechnic College Karnataka Ballari583101 India Department of Mechanical Engineering Dayananda Sagar University Karnataka Bengaluru560078 India Department of Robotics & amp Artificial Intelligence Bangalore Institute of Technology Karnataka Bengaluru India Department of Mechanical Engineering Bangalore Institute of Technology Karnataka Bengaluru India Department of Mechanical Engineering Atria Institute of Technology Karnataka Bengaluru India

A phenomenon that might cause a structure to collapse catastrophically is the propagation of cracks inside composite materials or at the interface of composite joints. Fail-safe design becomes essential when a structure's integrity is compromised by the element of safety because it has measures that limit failure. This work summarises the research that has been done on these types of crack-arresting features, or CAFs, for metal, composite, and composite laminate joints. Large fatigue cracks are intended to be tolerated in wide-bodied aircraft, and the general damage tolerance design includes two-bay crack arrest capability. In these aircrafts, longeron failure at fuselage crown leads to development of circumferential cracks in the pressurised cabin. The longeron’s capacity to accept load transfer from the cracked skin is what causes these skin cracks to be arrested for two-bay long crack. In direction to create effective damage-tolerant configuration, several parametric studies were carried out, with the longeron being crucial to the safety of circumferential cracks. Using finite element method (FEM) & analysis method, the geometry for longeron was assessed, and it was discovered that Z-Stiffener with larger cross section was more successful in stopping cracks. © The Institution of Engineers (India) 2024.

关键词： Cracks

来源：评论

学校读者我要写书评

暂无评论

Refinement of Sparsely Tagged Ground Truth Paths Using PDR and Particle Filter Smoothing

Refinement of Sparsely Tagged Ground Truth Paths Using PDR a...

引用

International Conference on Indoor Positioning and Indoor Navigation (IPIN)

作者： Steffen Kastner Markus Bullmann Markus Ebner Toni Fetzer Frank Deinzer Marcin Grzegorzek Center for Artificial Intelligence and Robotics Technical University of Applied Sciences Würzburg-Schweinfurt Würzburg Germany cronn GmbH Bonn Germany Institute of Medical Informatics University of Lübeck German Research Center for Artificial Intelligence Lübeck Germany

ISBN: (数字)9798350366402

ISBN: (纸本)9798350366419

Acquiring accurate ground truth or fingerprint data for indoor localization typically demands specialized hardware and considerable effort. This paper introduces three post-processing methods to simplify the recording of such data within certain limitations. The methods can be categorized into fixed-interval smoothing where the complete recording data is available for the optimal state estimation and there is no live processing requirement. Our methods are based on a particle filter system, employing the CONDENSATION algorithm to estimate the hidden state. Particles represent positions and headings in 3D space. They are moved and evaluated using pedestrian dead reckoning based on IMU measurements and a map of the building only. The development and application of these methods is presented in this paper, demonstrating their effectiveness in reducing the effort required for accurate ground truth and fingerprint data recording.

关键词： Accuracy Smoothing methods Fluctuations Error analysis Buildings Fingerprint recognition Tagging Particle filters Hardware Recording

来源：评论

学校读者我要写书评

暂无评论

Generating Realistic VRU-AV Scenarios via Social Force-Based Gradient Optimization 27

Generating Realistic VRU-AV Scenarios via Social Force-Based...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Long, Tingting Zong, Mengru Zhang, Chi Liu, Yuehu Ma, Shuangxun Li, Li National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Shaanxi Xi'an China School of Electrical Engineering Xi' An Jiaotong University Shaanxi Xi'an China School of Future Transportation Changan University Xi'an710064 China BNRist Tsinghua University Department of Automation Beijing100084 China

ISBN: (纸本)9798331505929

Validating safe and reliable interaction with vulnerable road users (VRUs) is imperative for autonomous vehicles, especially in simulation testing procedures before on-road applications. However, existing VRU agents are either with predefined routes or with collision-oriented behaviors, which limits the fidelity and diversity of scenarios. Bridging the gap between the simulated world and reality requires realistic VRU behaviors. In this paper, we apply social force to capture natural human behavior, considering how individuals are influenced by their surroundings and adhere to real-world rules. To this end, we propose HybridSFM, an improved social force model designed for characterizing human-vehicle interacting behavior. Specifically, the steering and acceleration of the VRUs are parameterized and integrated with social norms to forecast trajectories. Based on this, we further implement a gradient optimization framework for generating VRU-AV safety-critical scenarios. Firstly, VRUs are positioned randomly around the ego-agent. Differentiable simulation updates states and unrolls trajectories while backpropagation optimizes the actions of VRUs. The modified scenario is further optimized in the subsequent time step until a collision happens. The experiments demonstrate that our approach can enhance realistic safety-critical scenarios at intersection scenarios, facilitating the testing of interaction capabilities for autonomous vehicles. © 2024 IEEE.

关键词： Autonomous vehicles

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：