检索结果-内蒙古大学图书馆

Real-Time Path Planning and Following of a Gliding Robotic Dolphin Within a Hierarchical Framework

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2021年第4期70卷 3243-3255页

作者： Wang, Jian Wu, Zhengxing Yan, Shuaizheng Tan, Min Yu, Junzhi Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot BIC ESAT State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China

This paper proposes a novel hierarchical framework to achieve real-time path planning and following for a gliding robotic dolphin, including a learning-based path planner and an adaptive following controller. Subsequent to considering higher intelligence in unknown ocean environment, we present a novel hierarchical deep Q-network method to separately plan the collision avoidance path and the approach path, and also design different continuous-states under the kinematic constraints. Next, we adopt an improved line-of-sight method to obtain the desired points from planned path. More importantly, we derive a nonlinear control law based on backstepping technique, and specially avoid singularities in the law derivation using barrier Lyapunov function. In particular, the unknown model parameters are adaptively calculated to make the controller more robust. Finally, extensive simulation and experimental results verify the effectiveness of the proposed methods, providing a new idea to further ocean exploration.

关键词： Robots Path planning Planning Dolphins Real-time systems Training Backstepping Adaptive backstepping hierarchical deep q-network path following path planning underwater robot

来源：评论

学校读者我要写书评

暂无评论

Efficient Cooperative Structured control for a Multijoint Biomimetic Robotic Fish

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2021年第5期26卷 2506-2516页

作者： Yan, Shuaizheng Wu, Zhengxing Wang, Jian Tan, Min Yu, Junzhi Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ State Key Lab Turbulence & Complex Syst Dept Adv Mfg & Robot BIC ESATColl Engn Beijing 100871 Peoples R China

In this article, we propose an efficient locomotion control method for a two-dimensional tracking task of a biomimetic four-joint robotic fish. Regarding this issue as a comprehensive optimization procedure, we propose an optimization-based cooperative structured control framework, in which the combination of evolutionary strategy and deep deterministic policy gradient is employed to optimize the same objective function. An inconsistent optimization method is presented to further enhance the effect of parameter optimization on central pattern generator model. Moreover, for the sake of a higher reward and better robustness of controllers governed by deep reinforcement learning, we propose a linear weighted controller trained with periodic method. Extensive simulation and experimental results verify the significant energy saving of the proposed method in tracking tasks. Noticeably, the cooperative structured control can save 23.97%, 22.13%, and 38.72% energy compared with sliding mode control, active disturbance rejection control, and proportional-integral-differential control in experiments, respectively, holding a great promise for the long-term intelligent work of the biomimetic robotic fish in complex aquatic environments.

关键词： Robots Robot kinematics Optimization Biomimetics Sports Training Task analysis Deep reinforcement learning evolutionary strategy robotic fish structured control

来源：评论

学校读者我要写书评

暂无评论

Accelerating Realistic Multi-Route Traffic Flow Generation Based on Improved Simulated Annealing Algorithms 26

Accelerating Realistic Multi-Route Traffic Flow Generation B...

引用

IEEE 26th International Conference on Intelligent Transportation systems (ITSC)

作者： Chen, Hongrui Zhang, Yan Dai, Xingyuan Sun, Jiaming Cong, Fei Lu, Yanan Xu, Bingji Lv, Yisheng China Univ Geosci Beijing Sch Informat Engn Beijing 100083 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China China Telecom Digital City Technol Co Ltd Baoding 071700 Hebei Peoples R China

ISBN: (纸本)9798350399462

In the traffic simulation system, the data quality and inference speed of traffic flow generation have a direct impact on the correlation between analysis results and actual traffic conditions, as well as the efficiency of utilization. Existing traffic flow generation methods often rely on abundant sensor data and involve time-consuming generation processes. To reduce time costs, in this paper, we propose an efficient Multi-Route Traffic Flow Generator (MTFG). The generation process is divided into two parts: multi-route generation and route quantity search. In the multi-route generation, we employ a Multi-Route Generator (MRG) methodology leveraging topological road network data to generate distinct traffic routes for identical origin-destination pairs. This ensures the attainment of diversified vehicle trajectories even within a sparsely equipped detector network. Subsequently, in the route quantity search, we employ an improved simulated annealing algorithm to systematically explore the traffic route quantity based on the generated multiple routes, thereby significantly amplifying the algorithm's efficacy in route generation. We validate the effectiveness of MTFG using the Malaga open dataset on the SUMO simulation platform. Compared to the strong baseline Flow Generator Algorithm (FGA) with a training time exceeding 2.5h, MTFG achieves the target metric in just 1h under the same conditions, saving over 55% of training time.

关键词： Traffic flow SUMO Simulated annealing algorithm

来源：评论

学校读者我要写书评

暂无评论

Scene Coordinate Regression Network With Global Context-Guided Spatial Feature Transformation for Visual Relocalization

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 5737-5744页

作者： Guan, Peiyu Cao, Zhiqiang Yu, Junzhi Zhou, Chao Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Dept Adv Mfg & Robot Coll Engn State Key Lab Turbulence & Complex SystBIC ESAT Beijing 100871 Peoples R China

Among visual relocalization from a single RGB image, the scene coordinate regression (SCoRe) based on convolutional neural network (CNN) becomes prevailing, however, it is insufficient to extract invariant features under different viewpoints due to fixed geometric structures of CNN. In this letter, we propose a global context-guided spatial feature transformation (SFT) network to learn invariant feature representation for robustness against viewpoint changes. Specifically, global feature extracted from source feature map is regarded as a dynamic convolutional kernel, which is convolved with source feature map for the prediction of transformation parameters. The predicted parameters are used to transform features of multiple viewpoints to a canonical space with the constraint of maximum likelihood-derived loss, and thus viewpoint invariance is achieved. CoordConv is also employed to further improve the discrimination of features on texture-less or repetitive zones. The proposed SFT network can be easily incorporated into the general SCoRe network. To our best knowledge, features are first decoupled from viewpoints explicitly in SCoRe network by the spatial feature transformation network, which achieves a stable and accurate visual relocalization. The experimental results demonstrate the effectiveness of the proposed method in terms of accuracy and efficiency.

关键词： Scene coordinate regression network global context spatial feature transformation visual relocalization

来源：评论

学校读者我要写书评

暂无评论

Inspection of Welding Defect Based on Multi-feature Fusion and a Convolutional Network

引用

JOURNAL OF NONDESTRUCTIVE EVALUATION 2021年第4期40卷 1-11页

作者： Yang, Lei Fan, Junfeng Huo, Benyan Liu, Yanhong Zhengzhou Univ Sch Elect Engn Zhengzhou 450001 Peoples R China Robot Percept & Control Engn Lab Henan Prov Zhengzhou 450001 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Robot welding is a basic but indispensable technology for many industries in modern manufacturing. However, many welding parameters affect welding quality. During the real welding process, welding defects are inevitably generated that affect the structural strengths and comprehensive performances of different welding products. Therefore, an accurate welding defect recognition algorithm is necessary for automatic robot welding to assess the effects of defects on structural properties and system maintenance. Much work has been devoted to welding defect recognition. It can be mainly divided into two categories: feature-based and deep learning-based methods. The detection performances of feature-based methods rely on effective image features and strong classifiers. However, faced with weak-textured and weak-contrast welding images, the realization of strong image feature expression still faces a certain challenge. Deep learning-based methods can provide end-to-end detection schemes for welding robots. Nevertheless, an effective deep network model relies on much training data that are not easily collected during real manufacturing. To address the above issues regarding defect detection, a novel welding defect recognition algorithm is proposed based on multi-feature fusion for accurate defect detection based on X-ray images. To improve network training, an effective data augmentation process is proposed to construct the dataset. Combined with transfer learning, the multi-scale features of welding images are acquired for effective feature expression with the pre-trained AlexNet network. On this basis, based on multi-feature fusion, a welding defect recognition algorithm fused to a support vector machine with Dempster-Shafer evidence theory is proposed for multi-scale defect detection. Experiments show that the proposed method achieves a better recognition performance in terms of detecting welding defects than those of other related recognition algorithms.

关键词： Welding defect X-ray detection Transfer learning Multi-feature fusion Dempster-Shafer evidence theory

来源：评论

学校读者我要写书评

暂无评论

Chat With ChatGPT on Interactive Engines for Intelligent Driving

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第3期8卷 2034-2036页

作者： Gao, Yubing Tong, Wei Wu, Edmond Q. Q. Chen, Wei Zhu, GuangYu Wang, Fei-Yue Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Nanjing Univ Sci & Technol Nanjing 210094 Peoples R China Zhejiang Univ State Key Lab CAD & CG Hangzhou 310058 Peoples R China Beijing Jiaotong Univ Sch Traff & Transportat Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Res Ctr Urban Traff Informat Sensing & Ser Beijing 100044 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

ChatGPT, a chatbot launched by OpenAI, is making waves across the internet recently. Its potential capabilities and how it can impact various industries have been widely discussed. In the field of smart vehicles, integrating human-machine interaction systems with ChatGPT can be a game changer. For example, Jidu Auto, the electric vehicle arm of Baidu, announced in February 2023 that they will integrate ERNIE Bot (Sun et al., 2021), Baidu's ChatGPT-like service, into their cars. While ChatGPT has boosted the development of intelligent interaction, some limitations still exist that hinder its practical application. In this article, we discuss its potential applications in intelligent vehicles and analyze the challenges it faces.

关键词： Chatbots Vehicles Autonomous vehicles Training Automobiles Safety Solid modeling Human-vehicle systems intelligent vehicles intelligent transportation systems natural language processing

来源：评论

学校读者我要写书评

暂无评论

BiN-Flow: Bidirectional Normalizing Flow for Robust Image Dehazing

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 6635-6648页

作者： Wu, Yiqiang Tao, Dapeng Zhan, Yibing Zhang, Chenyang Yunnan Univ Sch Informat Sci & Engn FIST Lab Kunming 650500 Yunnan Peoples R China Yunnan Key Lab Intelligent Syst & Comp Kunming 650500 Yunnan Peoples R China Yunnan United Vis Technol Co Ltd Kunming 650500 Yunnan Peoples R China JD Explore Acad Beijing 100000 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Image dehazing aims to remove haze in images to improve their image quality. However, most image dehazing methods heavily depend on strict prior knowledge and paired training strategy, which would hinder generalization and performance when dealing with unseen scenes. In this paper, to address the above problem, we propose Bidirectional Normalizing Flow (BiN-Flow), which exploits no prior knowledge and constructs a neural network through weakly-paired training with better generalization for image dehazing. Specifically, BiN-Flow designs 1) Feature Frequency Decoupling (FFD) for mining the various texture details through multi-scale residual blocks and 2) Bidirectional Propagation Flow (BPF) for exploiting the one-to-many relationships between hazy and haze-free images using a sequence of invertible Flow. In addition, BiN-Flow constructs a reference mechanism (RM) that uses a small number of paired hazy and haze-free images and a large number of haze-free reference images for weakly-paired training. Essentially, the mutual relationships between hazy and haze-free images could be effectively learned to further improve the generalization and performance for image dehazing. We conduct extensive experiments on five commonly-used datasets to validate the BiN-Flow. The experimental results that BiN-Flow outperforms all state-of-the-art competitors demonstrate the capability and generalization of our BiN-Flow. Besides, our BiN-Flow could produce diverse dehazing images for the same image by considering restoration diversity.

关键词： Training Image restoration Image color analysis Band-pass filters Convolutional neural networks Atmospheric modeling Noise measurement Image dehazing bidirectional normalizing flow weakly-paired training and restoration diversity

来源：评论

学校读者我要写书评

暂无评论

Scenario Engineering for Autonomous Transportation: A New Stage in Open-Pit Mines

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2024年第3期9卷 4394-4404页

作者： Teng, Siyu Li, Xuan Li, Yuchen Li, Lingxi Zhe, Xuanyuan Ai, Yunfeng Chen, Long Hong Kong Baptist Univ Kowloon Hong Kong 999077 Peoples R China BNU HKBU UIC Zhuhai 519085 Peoples R China Peng Cheng Lab Dept Math & Theories Shenzhen 518000 Peoples R China Purdue Univ Indianapolis IUPUI Purdue Sch Engn & Technol Indianapolis IN 46202 USA BNU HKBU UIC Guangdong Prov Key Lab IRADS Zhuhai 519087 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China WAYTOUS Inc Beijing 100083 Peoples R China Guangdong Lab Artificial Intelligence & Digital Ec Shenzhen 518107 Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Peoples R China

In recent years, open-pit mining has seen significant advancement, the cooperative operation of various specialized machinery substantially enhancing the efficiency of mineral extraction. However, the harsh environment and complex conditions in open-pit mines present substantial challenges for the implementation of autonomous transportation systems. This research introduces a novel paradigm that integrates Scenario Engineering (SE) with autonomous transportation systems to significantly improve the trustworthiness, robustness, and efficiency in open-pit mines by incorporating the four key components of SE, including Scenario Feature Extractor, Intelligence and Index, Calibration and Certification, and Verification and Validation. This paradigm has been validated in two famous open-pit mines, the experiment results demonstrate marked improvements in robustness, trustworthiness, and efficiency. By enhancing the capacity, scalability, and diversity of autonomous transportation, this paradigm fosters the integration of SE and parallel driving and finally propels the achievement of the '6S' objectives.

关键词： Transportation Feature extraction Robustness Machinery Minerals Pipelines Artificial intelligence Autonomous transportation intelligent transportation system parallel mining parallel system theory

来源：评论

学校读者我要写书评

暂无评论

Investigating the neural activity of various 3D visual fatigue degrees using depth-related visual evoked potentials

引用

JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY 2021年第3期29卷 196-206页

作者： Yue, Kang Wang, Danli Chinese Acad Sci Inst Automat Beijing Peoples R China State Key Lab Management & Control Complex Syst Beijing Peoples R China Beijing Inst Technol Sch Opt & Photon Beijing Peoples R China

Severe visual fatigue symptoms occur while users view three-dimensional (3D) content. These symptoms adversely affect the user experience and hinder the widespread application of 3D media. Existing studies mainly used electroencephalography (EEG) power (based on frequency domain analysis) to evaluate 3D visual fatigue (3DVF), but their results were often contradictory and confusing. To address this problem, we investigated the relationship between EEG features and visual fatigue from the perspective of both time and time-frequency domain. Random-dot stereograms (RDS) with various disparities were employed to elicit depth-related visual evoked potentials (VEPs). The experiment lasted about 27 min for each subject to induce fatigue, and the EEG was recorded synchronously. VEPs of different fatigue levels were processed to extract both time (such as P-120 and N-170 components in VEPs) and time-frequency (like event-related spectral perturbation [ERSP]) domain characteristics. A significant increase in P-120 amplitude was observed in the parietal region, and time-frequency analysis also revealed a significant ERSP decrease of theta bands in the central-frontal region with a latency of 200 to 300 ms when subjects suffered fatigue. Our results confirm the hypothesis that activity of theta decreased with 3DVF level, or rather, we found ERSPs of theta bands on FC4 and Cz in the 200- to 300-ms window decreased significantly across four fatigue levels. Furthermore, we first reported the relationship between P-120 amplitude and 3DVF, which implied this feature could be considered as a feature of 3DVF evaluation. In summary, our studies could provide a new insight for 3DVF evaluation using EEG.

关键词： 3D EEG visual fatigue

来源：评论

学校读者我要写书评

暂无评论

Deep patch learning algorithms with high interpretability for regression problems

引用

INTERNATIONAL JOURNAL OF INTELLIGENT systems 2022年第11期37卷 8239-8276页

作者： Huang, Yunhu Chen, Dewang Zhao, Wendi Lv, Yisheng Wang, Shiping Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China FuJian Univ Technol Sch Transportat Fuzhou 350118 Peoples R China Fujian Univ Technol Intelligent Transportat Syst Res Ctr Fuzhou Peoples R China Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing Peoples R China Fujian Prov Key Lab Network Comp & Intelligent In Fuzhou Peoples R China

Improving the performance of machine learning algorithms to overcome the curse of dimensionality while maintaining interpretability is still a challenging issue for researchers in artificial intelligence. Patch learning (PL), based on the improved adaptive network-based fuzzy inference system (ANFIS) and continuous local optimization for the input domain, is characterized by high accuracy. However, PL can only handle low-dimensional data set regression. Based on the parallel and serial ensembles, two deep patch learning algorithms with embedded adaptive fuzzy systems (DPLFSs) are proposed in this paper. First, using the maximum information coefficient (MIC) and Pearson's correlation coefficients for feature selection, the variables with the least relationship (linear or nonlinear) are excluded. Second, principal component analysis is used to reduce the complexity further of DPLFSs. Meanwhile, fuzzy C-means clustering is used to enhance the interpretability of DPLFSs. Then, an improved PL method is put forward for the training of each sub-fuzzy system in a fashion of bottom-up layer-by-layer, and finally, the structure optimization is performed to significantly improve the interpretability of DPLFSs. Experiments on several benchmark data sets show the advantages of a DPLFS: (1) it can handle medium-scale data sets;(2) it can overcome the curse of dimensionality faced by PL;(3) its precision and generalization are greatly improved;and (4) it can overcome the poor interpretability of deep learning networks. Compared with shallow and deep learning algorithms, DPLFSs have the advantages of interpretability, self-learning, and high precision. DPLFS1 is superior for medium-scale data;DPLFS2 is more efficient and effective for high-dimensional problems, has a faster convergence, and is more interpretable.

关键词： deep learning deep patch learning fuzzy system fuzzy C-means clustering interpretability maximum information coefficient (MIC) Pearson's correlation coefficients (PCC)

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：