检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yu, Yi Yao, Shengyue Wang, Fei-Yue Li, Juanjuan Lin, Yilun Urban Computing Lab Shanghai AI Laboratory Shanghai China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Macau Institute of Systems Engineering Macau University of Science and Technology China

Data trading has been hindered by privacy concerns associated with user-owned data and the infinite reproducibility of data, making it challenging for data owners to retain exclusive rights over their data once it has been disclosed. Traditional data pricing models relied on uniform pricing or subscription-based models. However, with the development of Privacy-Preserving Computing techniques, the market can now protect the privacy and complete transactions using progressively disclosed information, which creates a technical foundation for generating greater social welfare through data usage. In this study, we propose a novel approach to modeling multi-round data trading with progressively disclosed information using a matchmaking-based Markov Decision Process (MDP) and introduce a Social Welfare-optimized Data Pricing Mechanism (SWDPM) to find optimal pricing strategies. To the best of our knowledge, this is the first study to model multi-round data trading with progressively disclosed information. Numerical experiments demonstrate that the SWDPM can increase social welfare 3 times by up to 54% in trading feasibility, 43% in trading efficiency, and 25% in trading fairness by encouraging better matching of demand and price negotiation among traders. Copyright © 2023, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A New Constrained Cost Value Iteration for Optimal control of Discrete-Time Nonlinear systems

A New Constrained Cost Value Iteration for Optimal Control o...

引用

2021 China Automation Congress, CAC 2021

作者： Li, Tao Wei, Qinglai The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426473

In this paper, a new constrained cost value iteration (CCVI) adaptive dynamic programming (ADP) algorithm is developed to solve optimal control problems with constrained cost function. The CCVI algorithm is initialized by a feasible control law, and the cost function of this initial feasible control constitutes the constraint condition in the policy update step. The convergence and optimality of the CCVI are analyzed. Furthermore, the feasibility of any iterative control law and the on-line evolving control law are proven. It is emphasized that the feasibility of any iterative control law and the on-line evolving control law guarantee that the CCVI algorithm can be used in situations where the cost function constraint is extremely important. Finally, a simulation example is given to verify the effect of the developed algorithm. © 2021 IEEE

关键词： control theory

来源：评论

学校读者我要写书评

暂无评论

Image captioning on fine art paintings via virtual paintings 1

Image captioning on fine art paintings via virtual paintings

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Lu, Yue Guo, Chao Dai, Xingyuan Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665433372

Machine learning in fine art paintings is attracting increasing attention recently. Image captioning of paintings is of great importance for painting analysis, but it is rarely studied. The paintings have abstract expressions and lack annotated datasets, leading to the data-hungry problem in painting captioning. Thus, painting captioning has more significant challenges than photographic image captioning. This paper makes a novel attempt at generating content descriptions of paintings. We generate virtual paintings using the style transfer technique to deal with the data-hungry problem, then train the painting captioning model via a two-step manner. We evaluate our method on an annotated small-scale painting captioning dataset and demonstrate our improvements. © 2021 IEEE.

关键词： Painting

来源：评论

学校读者我要写书评

暂无评论

An Efficient Learning control Framework with Sim-to-Real for String-Type Artificial Muscle-Driven Robotic systems

arXiv

引用

arXiv 2024年

作者： Tao, Jiyue Zhang, Yunsong Rajendran, Sunil Kumar Zhang, Feitian The Robotics and Control Laboratory Department of Advanced Manufacturing and Robotics College of Engineering the State Key Laboratory of Turbulence and Complex Systems Peking University Beijing100871 China The BSS Technologies Inc. Takoma ParkMD20912 United States

Robotic systems driven by artificial muscles present unique challenges due to the nonlinear dynamics of actuators and the complex designs of mechanical structures. Traditional model-based controllers often struggle to achieve desired control performance in such systems. Deep reinforcement learning (DRL), a trending machine learning technique widely adopted in robot control, offers a promising alternative. However, integrating DRL into these robotic systems faces significant challenges, including the requirement for large amounts of training data and the inevitable sim-to-real gap when deployed to real-world robots. This paper proposes an efficient reinforcement learning control framework with sim-to-real transfer to address these challenges. Bootstrap and augmentation enhancements are designed to improve the data efficiency of baseline DRL algorithms, while a sim-to-real transfer technique, namely randomization of muscle dynamics, is adopted to bridge the gap between simulation and real-world deployment. Extensive experiments and ablation studies are conducted utilizing two string-type artificial muscle-driven robotic systems including a two degree-of-freedom robotic eye and a parallel robotic wrist, the results of which demonstrate the effectiveness of the proposed learning control strategy. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Call for V&VIV: Verification and Validation of Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2022年第3期7卷 401-406页

作者： Fei-Yue Wang Javier Ibanez-Guzman Yisheng Lv State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Expert Autonomous Systems Artificial Intelligence Renault S.A. SIVALab CNRS Common Laboratory Chateau Renault France

Presents a summary of articles included in this issue of the publication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DriveRP: RAG and Prompt Engineering Embodied Parallel Driving in Cyber-Physical-Social Spaces

DriveRP: RAG and Prompt Engineering Embodied Parallel Drivin...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Jun Huang Hao Ma Tengchao Zhang Fei Lin Siji Ma Xiao Wang Fei-Yue Wang Faculty of Innovation Engineering Macau University of Science and Technology Macau China School of Artificial Intelligence Anhui University Hefei China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

In recent years, numerous technological advancements in Artificial Generative Intelligences (AGIs) have demonstrated significant potential to transform the intelligence acquisition mechanisms in connected autonomous vehicles (CAVs). Integrating technologies like ChatGPT into CAVs can enhance human-machine interactions. However, the emergence of such new traffic entities may introduce unforeseen hallucinations and complex risks that surpass our current understanding. To address these challenges, Retrieval-Augmented Generation (RAG) and prompt engineering technologies are being explored to enhance the reliability and safety of autonomous driving systems. RAG retrieves relevant contextual information, such as driving experiences and real-time road network status, from external databases to ensure that foundation models have access to accurate and timely data for informed decision-making. Prompt engineering optimizes the performance of large language models in autonomous driving systems by designing and refining prompts that guide the models’ responses, thereby improving their relevance and accuracy in various driving scenarios. Together, these technologies enhance the robustness and trustworthiness of autonomous driving systems. This paper proposes DriveRP, a framework that integrates RAG and prompt engineering within the Descriptive-Predictive-Prescriptive Intelligence framework of Parallel Driving theory. DriveRP aims to enhance the safety and interpretability of autonomous vehicle trajectory planning, decision-making, and motion control, ultimately achieving the "6S" goals. Grounded in Digital Twins and Metaverse-embodied parallel driving theory, DriveRP provides the infrastructure and foundational intelligence for parallel driving with Multi-modal Large Lange Models(MLLMs). Additionally, the paper discusses future trends and potential research directions, focusing on the "6S" goals of parallel driving: Smart, Safe, Secure, Sensitive, Sustainable, and Serviceable.

关键词： Accuracy Trajectory planning Decision making Transportation Transforms Safety Digital twins Prompt engineering Motion control Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Valuing Equity-Linked Guaranteed Minimum Death Benefits with European-Style Asian Payoffs Under the Regime-Switching Diffusion Process with Jump

SSRN

引用

SSRN 2022年

作者： Wang, Yayun Liu, Shengda Key Laboratory of Intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications Chongqing400065 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

In this paper, we consider a novel and efficient method to price equity-linked guaranteed minimumdeath benefits (GMDB) with European-style geometric Asian and arithmetic Asian payoffs. In thesituation of continuous transition of market economy, we assume that the underlying asset price processfollows regime-switching Ĺevy model and use complex Fourier series (CFS) expansion method to derivethe approximate value of GMDB products. The error analysis shows an exponential convergence rateunder geometric Asian and arithmetic Asian payoffs. Furthermore, the CFS approach is comparedwith other Fourier transform methods and Monte Carlo simulation, the numerical experiment resultsillustrate our method has a distinct advantage over other methods in both efficiency and accuracy. © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered Environments using Sliding Primitives

Learning Pre-Grasp Manipulation of Flat Objects in Cluttered...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiaxi Wu Haoran Wu Shanlin Zhong Quqin Sun Yinlin Li State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China Department of Automation University of Science and Technology of China Heifei China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science Beijing China Science and Technology on Thermal Energy and Power Laboratory Wuhan China

Flat objects with negligible thicknesses like books and disks are challenging to be grasped by the robot because of the width limit of the robot's gripper, especially when they are in cluttered environments. Pre-grasp manipulation is conducive to rearranging objects on the table and moving the flat objects to the table edge, making them graspable. In this paper, we formulate this task as Parameterized Action Markov Decision Process, and a novel method based on deep reinforcement learning is proposed to address this problem by introducing sliding primitives as actions. A weight-sharing policy network is utilized to predict the sliding primitive's parameters for each object, and a Q-network is adopted to select the acted object among all the candidates on the table. Meanwhile, via integrating a curriculum learning scheme, our method can be scaled to cluttered environments with more objects. In both simulation and real-world experiments, our method surpasses the existing methods and achieves pre-grasp manipulation with higher task success rates and fewer action steps. Without fine-tuning, it can be generalized to novel shapes and household objects with more than 85% success rates in the real world. Videos and supplementary materials are available at https://***/view/pre-grasp-sliding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FIT: Frequency-based Image Translation for Domain Adaptive Object Detection

arXiv

引用

arXiv 2023年

作者： Zhang, Siqi Zhang, Lu Liu, Zhiyong Feng, Hangtao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attention since it can alleviate performance degradation due to the large shift of data distributions in the wild. To align distributions between domains, adversarial learning is widely used in existing DAOD methods. However, the decision boundary for the adversarial domain discriminator may be inaccurate, causing the model biased towards the source domain. To alleviate this bias, we propose a novel Frequency-based Image Translation (FIT) framework for DAOD. First, by keeping domain-invariant frequency components and swapping domain-specific ones, we conduct image translation to reduce domain shift at the input level. Second, hierarchical adversarial feature learning is utilized to further mitigate the domain gap at the feature level. Finally, we design a joint loss to train the entire network in an end-to-end manner without extra training to obtain translated images. Extensive experiments on three challenging DAOD benchmarks demonstrate the effectiveness of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Planning-inspired Hierarchical Trajectory Prediction for Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Li, Ding Zhang, Qichao Xia, Zhongpu Zhang, Kuan Yi, Menglong Jin, Wenda Zhao, Dongbin School of Artificial Intelligence University of Chinese Academy of Sciences China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China Baidu Inc. China

Recently, anchor-based trajectory prediction methods have shown promising performance, which directly selects a final set of anchors as future intents in the spatio-temporal coupled space. However, such methods typically neglect a deeper semantic interpretation of path intents and suffer from inferior performance under the imperfect High-Definition (HD) map. To address this challenge, we propose a novel Planning-inspired Hierarchical (PiH) trajectory prediction framework that selects path and speed intents through a hierarchical lateral and longitudinal decomposition. Especially, a hybrid lateral predictor is presented to select a set of fixed-distance lateral paths from map-based road-following and cluster-based free-move path candidates. Then, the subsequent longitudinal predictor selects plausible goals sampled from a set of lateral paths as speed intents. Finally, a trajectory decoder is given to generate future trajectories conditioned on a categorical distribution over lateral-longitudinal intents. Experiments demonstrate that PiH achieves competitive and more balanced results against state-of-the-art methods on the Argoverse motion forecasting benchmark and has the strongest robustness under the imperfect HD map. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

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：