检索结果-内蒙古大学图书馆

Target Tracking control of a Biomimetic Underwater Vehicle Through Deep Reinforcement Learning

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2022年第8期33卷 3741-3752页

作者： Wang, Yu Tang, Chong Wang, Shuo Cheng, Long Wang, Rui Tan, Min Hou, Zengguang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China NUCTECH Co Ltd Beijing 100084 Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Shanghai 200031 Peoples R China

In this article, the underwater target tracking control problem of a biomimetic underwater vehicle (BUV) is addressed. Since it is difficult to build an effective mathematic model of a BUV due to the uncertainty of hydrodynamics, target tracking control is converted into the Markov decision process and is further achieved via deep reinforcement learning. The system state and reward function of underwater target tracking control are described. Based on the actor-critic reinforcement learning framework, the deep deterministic policy gradient actor-critic algorithm with supervision controller is proposed. The training tricks, including prioritized experience replay, actor network indirect supervision training, target network updating with different periods, and expansion of exploration space by applying random noise, are presented. Indirect supervision training is designed to address the issues of low stability and slow convergence of reinforcement learning in the continuous state and action space. Comparative simulations are performed to show the effectiveness of the training tricks. Finally, the proposed actor-critic reinforcement learning algorithm with supervision controller is applied to the physical BUV. Swimming pool experiments of underwater object tracking of the BUV are conducted in multiple scenarios to verify the effectiveness and robustness of the proposed method.

关键词： Reinforcement learning Target tracking Robots Sports Aerospace electronics Mobile robots Underwater vehicles Biomimetic underwater vehicle (BUV) reinforcement learning target tracking control

来源：评论

学校读者我要写书评

暂无评论

Rethinking semantic-visual alignment in zero-shot object detection via a softplus margin focal loss

引用

NEUROCOMPUTING 2021年 449卷 117-135页

作者： Li, Qianzhong Zhang, Yujia Sun, Shiying Zhao, Xiaoguang Li, Kang Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligences Beijing Peoples R China Information Sci Acad China Elect Technol Grp Corp Beijing Peoples R China

Zero-shot object detection (ZSD) aims to locate and recognize novel objects without additional training samples. Most existing methods usually map visual features to semantic space, resulting in a hubness problem, and learning an effective feature mapping between the two modalities remains a considerable challenge. In this work, we propose a novel end-to-end framework, Semantic-Visual Auto-Encoder (SVAE) network, to tackle the above issues. Distinct from previous works that utilize fully-connected layers to learn the feature mapping, we implement a 1-dimensional convolution with various shared filters to con-struct the auto-encoder, which maps semantic features to visual space to alleviate the hubness problem. Specifically, we design a novel loss function, Softplus Margin Focal Loss (SMFL), for object classification channel to align the projected semantic features in visual space and address the class imbalance problem. The SMFL improves the discrimination of projections on positive and negative categories and maintains the property of focal loss. Besides, to promote the localization performance for novel objects, we also pro -vide semantic information for object localization channel and utilize a trainable matrix to align the semantic-visual mapping, considering noises in semantic representations. We conduct extensive exper-iments on four challenging benchmarks. The experimental results show the competitive performances compared with state-of-the-art approaches. Especially, we achieve 8.39%/6.58% mean average precision (mAP) improvements for ZSD/general-ZSD on Microsoft COCO benchmark. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Zero-shot object detection Softplus margin focal loss Semantic-visual alignment Auto-encoder architecture

来源：评论

学校读者我要写书评

暂无评论

Particle filter algorithm based on geometric center and likelihood estimation

引用

AIP ADVANCES 2021年第8期11卷 1-8页

作者： Fang, Xing Luo, Yin Wang, Lei Jiang, ShuiBin Xu, Nan Zeng, Daniel Dajun Tianjin Univ Sch Management & Econ Beijing Peoples R China Wenge Technol Co Ltd Beijing Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Univ Arizona Dept Management Informat Syst Tucson AZ 85001 USA

The improved particle filter (PF) based on the geometric center and likelihood estimation is proposed in order to solve the problem of particle dilution and degradation. In the resampling stage, the geometric center is used to resample the particles. The particles are filtered according to the distance between the particles and the geometric center, and then the particles are resampled. The resampled particles are composed of newborn particles and non-resampled particles. The former can help alleviate the degradation problem, while the latter can keep the diversity of the particle set. In order to ensure effectiveness of the PF, the positioning error threshold of the particle filter is introduced. In the phase of particle weighting calculation, in view of the problem of low accuracy and divergence of PF state estimation caused by non-stationary and non-Gaussian noise, it adopts non-Gaussian noise parameter estimation based on likelihood to approximately estimate the measurement noise instead of the Gaussian density function. The proposed model is applied to particle weight calculation to avoid particle degradation caused by Gaussian density function approximation. The simulation results show that, after the improved algorithm, the root-mean-square error is reduced to 0.085, the variance is reduced to 0.014, and the running time is shortened by 14.8% compared with the polynomial resampling algorithm, which can effectively alleviate particle degradation and dilution in the traditional PF algorithm, and the positioning accuracy is also improved. (C) 2021 Author(s).

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Analyzing the delivery determination problem of new retail stores considering crowdsourcing under the background of blockchain

引用

RESEARCH IN TRANSPORTATION BUSINESS AND management 2024年 52卷

作者： Li, Yue Zhao, Jianyou Chen, Zenghua Changan Univ Sch Automobile Xian 710061 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 310013 Peoples R China

The parcel delivery industry is experiencing rapid growth due to the rise of new retail stores. However, the traditional self-operated delivery model often leads to idle and wasteful distribution resources due to uneven temporal and spatial distribution of delivery orders. In this study, we propose a delivery system that combines crowdsourcing and self-operated delivery for new retail stores using blockchain technology to optimize the delivery algorithm. Our proposed system solves the problem of wasted resources by introducing crowdsourcing delivery and completes the distribution task allocation on a blockchain platform to protect customer privacy and quantify the performance of crowdsourcing couriers. We present a mixed-integer nonlinear programming formulation for the 2-Echelon Winning Determination Problem, in which the delivery decision is based on the lowest total cost. The cost of crowdsourcing delivery is a dynamic cost comprising of crowdsourcing courier service errors and bid prices recorded on the tamper-evident blockchain system. We also analyzed the impact of different crowdsourcing bidding prices on the choice of delivery method and total cost. Synthetic experiments show that our proposed hybrid delivery model ensures high-quality and efficient delivery of new retail stores while saving delivery costs.

关键词： Transportation and logistics Blockchain Crowdsourcing and self-operated delivery system 2-Echelon winning determination problem Vehicle routing problem Mixed-integer linear program

来源：评论

学校读者我要写书评

暂无评论

Parallel crop planning based on price forecast

引用

INTERNATIONAL JOURNAL OF INTELLIGENT systems 2022年第8期37卷 4772-4793页

作者： Fan, Menghan Kang, Mengzhen Wang, Xiujuan Hua, Jing He, Chaoxing Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Beijing Engn Res Ctr Intelligent Syst & Technol Beijing Peoples R China Qingdao AgriTech Co Ltd Qingdao Peoples R China Chinese Acad Agr Sci Inst Vegetables & Flowers Beijing Peoples R China

Agrifood system actors operate within diverse sociocultural, economic, and biophysical settings. For growers, crop planning, usually a yearly business plan, is a key decision to make on when, what, and how many to plant. It is a challenging task as it deals with multiple constraints in volatile economic and/or climate environment. Most crop planning models have difficulty in adapting to changing situation. In this study, a parallel system of crop planning composed of the artificial system, computational experiment, and parallel execution is proposed. The farmers are described as agents, and the decision is made based on the heuristic searching of optimal plan;the adaption of plan is triggered autonomously given strong environment changes. Focus is given to economic environment, which is indicated as product price. In a case study, the economic environment of the artificial system is built based on the monthly and weekly price information for 13 products during 7 years. The computational experiment provides the initial cropping plan and harvest time, with social and ecological constraints. Result shows that the cropping plan can further adapt to price variation. This flexible cropping plan system can strengthen the capability of cooperatives serving small-scale farmers.

关键词： agent-based modeling crop planning parallel agricultural management price prediction

来源：评论

学校读者我要写书评

暂无评论

An Optimal control Based Trajectory Planning Method for Cooperative Merging Maneuvers

An Optimal Control Based Trajectory Planning Method for Coop...

引用

Intelligent Robotics and systems (ISoIRS), International Symposium on

作者： Qi Wang Hao Ge Xuting Duan Jianshan Zhou State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control State Key Laboratory of Air Traffic Management System and Technology School of Transportation Science and Engineering Beihang University Beijing China State Key Laboratory of Air Traffic Management System and Technology Nanjing Research Institute of Electronic Engineering Nanjing China State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing China

Due to the prediction errors and diverse driving styles of surrounding vehicles, traffic congestion and even accidents can occur in the traffic bottleneck area where vehicles merge into the main road. To ensure that connected and automated vehicles (CAVs) can quickly and efficiently merge into the main road, this paper proposes a cooperative trajectory planning method based on optimal control for vehicle cut-in scenarios. A optimal control model is constructed, and a quintic polynomial is used to generate the initial solution of the optimal control problem to accelerate the solution process and improve the success rate. Finally, The obtained merging trajectory is then synchronized with the movement of vehicles on the main road to optimize their actions and ensure a safe merging process. Joint simulation with Robot Operating System (ROS) and RVIZ is utilized, and the results show that the proposed algorithm can quickly obtain cooperative results, the locally successful merging trajectory meets the requirements of smoothness and safety, and if the solution does not allow merging, the merging vehicle is instructed to terminate the execution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Consensus control of Leader-Following Multi-Agent systems in Directed Topology With Heterogeneous Disturbances

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 423-431页

作者： Qinglai Wei Xin Wang Xiangnan Zhong Naiqi Wu the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049and also with Qingdao Academy of Intelligent IndustriesQingdao 266109China the Department of Computer and Electrical Engineering and Computer Science Florida Atlantic UniversityBoca Raton FL33431 USA the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and TechnologyMacao 999078China

This paper investigates the consensus problem for linear multi-agent systems with the heterogeneous disturbances generated by the Brown *** main contribution is that a control scheme is designed to achieve the dynamic consensus for the multi-agent systems in directed topology interfered by stochastic *** traditional ways,the coupling weights depending on the communication structure are static.A new distributed controller is designed based on Riccati inequalities,while updating the coupling weights associated with the gain matrix by state errors between adjacent *** introducing time-varying coupling weights into this novel control law,the state errors between leader and followers asymptotically converge to the minimum value utilizing the local *** the Lyapunov directed method and It?formula,the stability of the closed-loop system with the proposed control law is *** simulation results conducted by the new and traditional schemes are presented to demonstrate the effectiveness and advantage of the developed control method.

关键词： Consensus control directed topology external disturbance multi-agent(MA)systems

来源：评论

学校读者我要写书评

暂无评论

A Constant-Force End-Effector With Online Force Adjustment for Robotic Ultrasonography

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2547-2554页

作者： Bao, X. Wang, S. Housden, R. Hajnal, J. Rhode, K. Kings Coll London Kings Hlth Partners St Thomas Hosp Sch Biomed Engn & Imaging Sci London SE1 7EH England Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this letter, we propose a novel constant-force end-effector (CFEE) to address current limitations in robotic ultrasonography. The CFEE uses a parallel, motor-spring-based solution to precisely generate constant operating forces over a wide range and enable the ultrasound (US) probe to adapt to the abdominal contours autonomously. A displacement measurement unit was developed to realize the acquisition of probe position and precise control of the operating force. Moreover, the operating force can be adjusted online to maintain safety and continuity of operation. Simulations and experiments were carried out to evaluate the performance. Results show that the proposed CFEE can provide constant forces of 4-12 N with displacements of 0-8 mm. The maximum relative error of force generation is 8.28%, and the accuracy and precision for displacement measurement are 0.29 mm and +/- 0.16 mm, respectively. Various operating forces can be adjusted online during the same operation. Ultrasound images acquired by the proposed CFEE are of equally good quality compared to a manual sonographer scan. The proposed CFEE would have potential further medical applications.

关键词： Robotic ultrasonography online force adjustment constant force end-effector

来源：评论

学校读者我要写书评

暂无评论

Digital twins and artificial intelligence in transportation infrastructure: Classification, application, and future research directions

引用

COMPUTERS & ELECTRICAL ENGINEERING 2022年 101卷

作者： Wu, Jingyi Wang, Xiao Dang, Yukun Lv, Zhihan Qingdao Univ Coll Comp Sci & Technol 308 Ningxia Rd Qingdao 266071 Peoples R China State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Artificial Intelligence (AI) technology is extensively applied in all walks of life with continuous acceleration of the construction of smart cities. The current research status of intelligent development of transportation infrastructure is classified and predicted oriented to smart cities, which is mainly based on space type, function type, and facility use. The classification is mainly between residents and vehicles, between and vehicles, and between vehicles and transportation systems. The related scholars analyzed that Digital Twins (DTs) technology and AI technology show significant advantages in the classification of transportation infrastructure and the management of transportation spatial information network. The intelligent development of transportation infrastructure is analyzed, and it is predicted in functional design, intelligent development, and effective integration with new media, aiming to provide a reference for the subsequent intelligent development and construction of transportation infrastructure in smart cities.

关键词： Transport infrastructure Artificial intelligence Digital twins Damage detection Traffic spatial information network

来源：评论

学校读者我要写书评

暂无评论

Dissecting and Mitigating Semantic Discrepancy in Stable Diffusion for Image-to-Image Translation

引用

IEEE-CAA JOURNAL OF AUTOMATICA SINICA 2025年第4期12卷 705-718页

作者： Yuan, Yifan Yang, Guanqun Wang, James Z. Zhang, Hui Shan, Hongming Wang, Fei-Yue Zhang, Junping Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Fuxi Team NetEase Corp Hangzhou Peoples R China Penn State Univ Coll Informat Sci & Technol University Pk PA 16802 USA Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100098 Peoples R China Fudan Univ Inst Sci & Technol Brain inspired Intelligence Shanghai 200433 Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai 200433 Peoples R China Shanghai Ctr Brain Sci & Brain inspired Technol Shanghai 200031 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Peoples R China

Finding suitable initial noise that retains the original image's information is crucial for image-to-image (I2I) translation using text-to-image (T2I) diffusion models. A common approach is to add random noise directly to the original image, as in SDEdit. However, we have observed that this can result in "semantic discrepancy" issues, wherein T2I diffusion models mis-interpret the semantic relationships and generate content not present in the original image. We identify that the noise introduced by SDEdit disrupts the semantic integrity of the image, leading to unintended associations between unrelated regions after U-Net upsampling. Building on the widely-used latent diffusion model, Stable Diffusion, we propose a training-free, plug-and-play method to alleviate semantic discrepancy and enhance the fidelity of the translated image. By leveraging the deterministic nature of denoising diffusion implicit models (DDIMs) inversion, we correct the erroneous features and correlations from the original generative process with accurate ones from DDIM inversion. This approach alleviates semantic discrepancy and surpasses recent DDIM-inversion-based methods such as PnP with fewer priors, achieving a speedup of 11.2 times in experiments conducted on COCO, ImageNet, and ImageNet-R datasets across multiple I2I translation tasks.

关键词： Translation Correlation Codes Image edge detection Semantics Noise Noise reduction Text to image Diffusion models Erosion DDIM inversion diffusion model image-to-image translation semantic discrepancy stable diffusion

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：