检索结果-内蒙古大学图书馆

A Game Approach for EV Brands' Investment Planning of Battery Swapping Stations

A Game Approach for EV Brands' Investment Planning of Batter...

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

作者： Ren, Heyu Sun, Chenxi Tang, Xiaoying Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (数字)9781665432542

ISBN: (纸本)9781665432542

In the current market of energy supply for electric vehicles (EVs), charging stations (CSs) have a definitely high market share, while the battery swapping stations (BSSs) are rapidly developed in recent years due to their potential to save users' waiting time by replacing a depleted battery with a fully-charged one. In order to assess the benefits of battery swapping, an economic model is needed to analyze the market, and different EV brands need to determine the optimal investment plans of BSSs in order to maximize their individual revenues. This paper proposes a Stackelberg game to characterize the interactions between different EV brands, CSs, BSSs, and EV consumers. By analyzing the Nash Equilibrium of the Stackelberg game, a pricing scheme for BSSs is proposed and EV brands' specific profit model from BSSs is formulated to analyze the optimal investment plan of BSSs. Experimental results show that our model and strategy improve EV brands' profits, especially for brands with moderate battery capacity, moderate car price and large sales volume. © 2022 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Dynamic Movement Primitives Based Robot Skills Learning

引用

Machine intelligence Research 2023年第3期20卷 396-407页

作者： Ling-Huan Kong Wei He Wen-Shi Chen Hui Zhang Yao-Nan Wang School of Intelligence Science and Technology University of Science and Technology BeijingBeijing 100083China Institute of Artificial Intelligence University of Science and Technology BeijingBeijing 100083China School of Robotics and the National Engineering Laboratory of Robot Visual Perception and Control Technology Hunan UniversityChangsha 410082China

In this article,a robot skills learning framework is developed,which considers both motion modeling and *** order to enable the robot to learn skills from demonstrations,a learning method called dynamic movement primitives(DMPs)is introduced to model motion.A staged teaching strategy is integrated into DMPs frameworks to enhance the generality such that the complicated tasks can be also performed for multi-joint *** DMP connection method is used to make an accurate and smooth transition in position and velocity space to connect complex motion *** addition,motions are categorized into different goals and *** is worth mentioning that an adaptive neural networks(NNs)control method is proposed to achieve highly accurate trajectory tracking and to ensure the performance of action execution,which is beneficial to the improvement of reliability of the skills learning *** experiment test on the Baxter robot verifies the effectiveness of the proposed method.

关键词： Dynamic movement primitives(DMPs) trajectory tracking control robot learning from demonstrations neural networks(NNs) adaptive control

来源：评论

学校读者我要写书评

暂无评论

Semantic-aware knowledge distillation with parameter-free feature uniformization

引用

Visual intelligence 2023年第1期1卷 1-12页

作者： Guo, Guangyu Han, Longfei Wang, Le Zhang, Dingwen Han, Junwei Brain and Artificial Intelligence Laboratory School of Automation Northwestern Polytechnical University Xi’an China Beijing Technology and Business University Beijing China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an China Xijing Hospital The Fourth Military Medical University Xi’an China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China

Knowledge distillation aims to distill knowledge from teacher networks to train student networks. Distilling intermediate features has attracted much attention in recent years as it can be flexibly applied in various fields such as image classification, object detection and semantic segmentation. A critical obstacle of feature-based knowledge distillation is the dimension gap between the intermediate features of teacher and student, and plenty of methods have been proposed to resolve this problem. However, these works usually implement feature uniformization in an unsupervised way, lacking guidance to help the student network learn meaningful mapping functions in the uniformization process. Moreover, the dimension uniformization process of the student and teacher network is usually not equivalent as the mapping functions are different. To this end, some factors of the feature are discarded during parametric feature alignment, or some factors are blended in some non-parametric operations. In this paper, we propose a novel semantic-aware knowledge distillation scheme to solve these problems. We build a standalone feature-based classification branch to extract semantic-aware knowledge for better guiding the learning process of the student network. In addition, to avoid the inequivalence of feature uniformization between teacher and student, we design a novel parameter-free self-attention operation that can convert features of different dimensions into vectors of the same length. Experimental results show that the proposed knowledge distillation scheme outperforms existing feature-based distillation methods on the widely used CIFAR-100 and CINIC-10 datasets. © The Author(s) 2023.

关键词： Feature uniformization Feature-based Knowledge distillation Parameter-free Self-attention Semantic-aware

来源：评论

学校读者我要写书评

暂无评论

VLSI Design for High-Precision Three-Dimensional Depth Perception Chip

引用

Chinese Journal of Electronics 2021年第3期30卷 556-560页

作者： GE Chenyang YAO Huimin ZHOU Yanhui DENG Pengchao Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Institute of electromagnetic and information technology Xi'an Jiaotong University

This paper presents a Very large scale integration(VLSI) design method for Three-dimensional(3 D) depth perception chip based on infrared coding structure light. The primary sub-modules on the chip contain the speckle pattern preprocessing module, blockmatching disparity estimation, depth mapping and postprocessing. The chip employs pipelining technology,and after Application specific integrated circuit(ASIC)verification, it proves that our chip has more advantages in performance of depth precision(12 bits, 1 mm @ 1 m),image resolution(1280×960), time delay(less than 17 ms),range limit(0.4～6 m). It also can generate more stable and smooth depth map in real-time, which can be used in 3 D recognition, motion capture or scene perception.

关键词： stable depth map image motion analysis depth precision high-precision Three-dimensional depth perception chip infrared coding structure light word length 12.0 bit VLSI design smooth depth map primary sub-modules application specific integrated circuits time 17.0 ms stereo image processing size 1.0 mm speckle pattern motion capture range limit image resolution depth mapping scale integration design method VLSI size 0.4 m to 6.0 m block-matching disparity estimation Application specific integrated circuit verification image matching

来源：评论

学校读者我要写书评

暂无评论

Modeling and Linear Active Disturbance Rejection Control of a New Morphing Quadrotor

Modeling and Linear Active Disturbance Rejection Control of ...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Sun, Haosheng He, Chunhui Wu, Qingxiang Chen, He Sun, Ning Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China School of Artificial Intelligence Hebei University of Technology Tianjin300401 China

ISBN: (纸本)9789811966125

In many practical applications like rescues, the morphing quadrotors perform better than conventional quadrotors in complex and variable environments, such as traveling through narrow gaps. However, their dynamic properties are more complicated. In this paper, a new morphing quadrotor with foldable arms is presented. Then, the dynamic model of the morphing quadrotor is established. Moreover, the linear active disturbance rejection control (LADRC) method is used to achieve stable flight during morphing, and its performance is compared with the PID method with the simulations. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

An Auto-tuned Motion Scaling Method Based on Visual Recognition∗

An Auto-tuned Motion Scaling Method Based on Visual Recognit...

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Wang, Xinyu Ji, Xiaoqiang Sun, Zhenglong The Chinese University of HongKong School of Science and Engineering Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong China

ISBN: (纸本)9798350327182

Motion scaling is an effective technique in teleoperation systems. Changing the scaling factor makes it possible for delicate operations in a certain area. However, manually tuning the scaling factor is complex for the operator and leads to a new problem: When the master device finishes the work and returns to its original place, the slave device can't return to its original place, which brings a bad feeling experience to the operator. Therefore, adaptive methods were introduced to tune the scaling factor autonomously according to the distance between the end effector of the slave robot and the object. The Distance Based Scaling method is introduced firstly to handle the scaling problem, then the Original Point Based Scaling method, built on the Distance Based Scaling method, was designed with three kinds of scaling factors for different scenarios to solve the problem described above during the scaling process. Visual recognition system using an RGB-D camera was also established for the purpose of obtaining the position data of the object. Experiments designed in the Matlab and chai3d environment are conducted for performance evaluation, and the visual recognition system is also tested. © 2023 IEEE.

关键词： Slave robots

来源：评论

学校读者我要写书评

暂无评论

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

Socially-Compatible Motion Planning of Autonomous Vehicles with Verification on Real Human Data 27

Socially-Compatible Motion Planning of Autonomous Vehicles w...

引用

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

作者： Zhang, Chenxi Chen, Shitao Shi, Jiamin Xin, Jingmin Zheng, Nanning 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'an710049 China

ISBN: (纸本)9798331505929

One of the fundamental challenges for autonomous vehicles in complex dynamic scenarios is planning human-like trajectories in a socially acceptable manner. Existing methods, focused solely on self-interest and implicitly modeling a singular driving style, prove inadequate for the deployment of autonomous vehicles in mixed traffic environments while maintaining social acceptability. This paper presents the Socially-Compatible Motion Planning (SCMP) framework, which dynamically captures the spatiotemporal interaction characteristics of traffic participants for various driving tasks and adaptively adjusts the driving style of autonomous vehicles. Guided by driving style, the motion planning module considers vehicle physical constraints, safety constraints and comfort constraints, thereby generating human-like trajectories that incorporate multiple driving styles. The proposed method was rigorously validated and evaluated using the real-world dataset nuPlan, where it demonstrated exceptional performance in various driving scenarios and tasks. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Reward-Based Energy-Aware Routing Protocols in Wireless Sensor Networks

Reward-Based Energy-Aware Routing Protocols in Wireless Sens...

引用

International Conference on Smart Applications and Sustainability in the artificial intelligence of Things, SAS-AIoT 2024

作者： Salama, Ramiz Alturjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Cyprus Artificial Intelligence Software and Information Systems Engineering Departments AI and Robotics Institute Near East University Nicosia Cyprus

ISBN: (纸本)9783031782756

Smart cities, industrial automation, healthcare, and environmental monitoring are just a few of the industries that have seen revolutionary changes as a result of Wireless Sensor Networks’ (WSNs) explosive growth. WSNs are significantly hampered by the limited energy resources of their sensor nodes, which are usually battery-powered and placed in inaccessible locations, despite their wide-ranging applications. As a result, energy efficiency is now a crucial component of these networks’ operation and design. Though these protocols frequently fail to adjust to the dynamic and unpredictable nature of WSNs, traditional energy-aware routing methods have been created to decrease energy consumption by choosing the best paths for data transfer. By allowing sensor nodes to learn from their surroundings and make wise routing decisions, the machine learning field of reinforcement learning (RL) provides a viable answer to these problems. In contrast to conventional techniques, RL-based protocols provide continuous energy optimization by dynamically modifying their routing strategies in response to real-time feedback. This paper investigates how to include RL methods—specifically, Q-learning and SARSA—into WSN energy-aware routing protocols. The suggested method creates a more distributed and scalable solution by enabling each node to independently learn and modify its routing choices. The effectiveness of RL-based routing protocols is compared to traditional methods through comprehensive simulations. The findings show that by slowing down the rate at which energy is being used up by each node, RL not only increases energy efficiency but also lengthens the network's operational life. In particular, Q-learning demonstrates a notable improvement in sustaining data delivery rates and network connectivity under various circumstances. Although a little more computationally demanding, the SARSA algorithm offers greater flexibility in situations where network topology changes often. Th

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

MDRAE: An Attention Mechanism-Based Autoencoder for Missing Data Recovery in Smart Grids 7

MDRAE: An Attention Mechanism-Based Autoencoder for Missing ...

引用

7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023

作者： Liu, Guolong Bai, Yan Liu, Jinjie Zhao, Huan Liang, Gaoqi Zhao, Junhua Shenzhen Institute of Artificial Intelligence and Robotics For Society The Chinese University of Hong Kong Shenzhen Shenzhen China School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Shenzhen Institute of Artificial Intelligence and Robotics For Society School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics For Society School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen China

ISBN: (纸本)9798350345094

Smart grids have rapidly developed in recent years, and a large amount of data has been collected and become the basis for decision-making of power grid operation. To ensure the safe and stable operation of the power grid, how to improve the data quality of the collected data has become an important research topic. Therefore, an attention mechanism-based autoencoder is proposed in this paper for missing data recovery to improve data quality in smart grids. The proposed method named missing data recovery autoencoder (MDRAE) contains two parts of an encoder and a decoder, and the attention mechanism is integrated into the encoder part to better extract the key information of the data. The effectiveness of the proposed method is verified by conducting experiments on two datasets including industrial load data and residential load data. The experimental results show that the model performance of the proposed method is better than that of the two benchmarks, and the proposed method can recover the missing data accurately. © 2023 IEEE.

关键词： Smart power grids

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：