检索结果-内蒙古大学图书馆

The paralleleye dataset: Constructing large-scale artificial scenes for traffic vision research

学校读者我要写书评

暂无评论

arXiv

arXiv 2017年

作者： Li, Xuan Wang, Kunfeng Tian, Yonglin Yan, Lan Wang, Fei-Yue School of Automation Beijing Institute of Technology Beijing100081 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266000 China Department of Automation University of Science and Technology of China Hefei230027 China Research Center for Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha410073 China

Video image datasets are playing an essential role in design and evaluation of traffic vision algorithms. Nevertheless, a longstanding inconvenience concerning image datasets is that manually collecting and annotating large-scale diversified datasets from real scenes is time-consuming and prone to error. For that virtual datasets have begun to function as a proxy of real datasets. In this paper, we propose to construct large-scale artificial scenes for traffic vision research and generate a new virtual dataset called "ParallelEye". First of all, the street map data is used to build 3D scene model of Zhongguancun Area, Beijing. Then, the computer graphics, virtual reality, and rule modeling technologies are utilized to synthesize large-scale, realistic virtual urban traffic scenes, in which the fidelity and geography match the real world well. Furthermore, the Unity3D platform is used to render the artificial scenes and generate accurate ground-truth labels, e.g., semantic/instance segmentation, object bounding box, object tracking, optical flow, and depth. The environmental conditions in artificial scenes can be controlled completely. As a result, we present a viable implementation pipeline for constructing large-scale artificial scenes for traffic vision research. The experimental results demonstrate that this pipeline is able to generate photorealistic virtual datasets with low modeling time and high accuracy labeling. Copyright © 2017, The Authors. All rights reserved.

关键词： Pipelines

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Wang, Xiao Tang, Ke Dai, Xingyuan Xu, Jintao Du, Quancheng Ai, Rui Wang, Yuxiao Gu, Weihao Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei230031 China Haomo Technology Co. Ltd. Beijing100192 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266114 China The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework. Specifically, S4TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV’s planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S4TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs’ trajectories as input. With the integration of SADRF, S4TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S4TP in terms of safety and rationality. S4TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

A Learning Convolutional Neural Network Approach for Network Robustness Prediction

学校读者我要写书评

暂无评论

arXiv

arXiv 2022年

作者： Lou, Yang Wu, Ruizi Li, Junli Wang, Lin Li, Xiang Chen, Guanrong The Department of Computing and Decision Sciences Lingnan University Hong Kong The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The College of Computer Science Sichuan Normal University Chengdu610066 China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201210 China The Department of Control Science and Engineering Tongji University Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

Network robustness is critical for various societal and industrial networks again malicious attacks. In particular, connectivity robustness and controllability robustness reflect how well a networked system can maintain its connectedness and controllability against destructive attacks, which can be quantified by a sequence of values that record the remaining connectivity and controllability of the network after a sequence of node- or edge-removal attacks. Traditionally, robustness is determined by attack simulations, which are computationally very time-consuming or even practically infeasible. In this paper, an improved method for network robustness prediction is developed based on learning feature representation using convolutional neural network (LFR-CNN). In this scheme, higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction. Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors;2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability;3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations;4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures. © 2022, CC BY.

关键词： complex networks

A Blockchain-based Educational Digital Assets Management system

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2020年第5期53卷 47-52页

作者： Junqing Li Mo Lan Ying Tang Shichao Chen Fei-Yue Wang Wei Wei Shandong University of Science and Technology Qingdao China 266590 The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China 100190 Southwest University Chongqing China 400715 Beijing Achievelearn Education Technology Group Beijing China 100095 Electrical and Computer Engineering Rowan University Glassboro NJ 08003 USA Qingdao Academy of Intelligent Industries Qingdao China 266042 3E Smart Education Beijing China 100083

A variety of heterogeneous information is produced after the application of various emerging technologies in education, which is of great research value as educational assets. The traditional educational asset management system has emerged. In view of the disadvantages of traditional system centralization process, people begin to use decentralized blockchain technology for innovation. This paper proposes an educational digital asset management system architecture based on blockchain 3.0 technology system, which forms various data formed by students in and out of class learning process, courseware and experience data generated by teachers in the process of teaching into educational digital assets, and carries out the right confirmation and storage on the blockchain. The system can use a variety of heterogeneous data in digital assets to analyze the development status of school users, achieve the teaching purpose of teaching students according to their aptitude and different people.

关键词： blockchain blockchain system digital assets educational technology decentralized systems

Uv-Ozone Treated Ti3c2tx-Mxene Nanosheets as Hole Injection Layer for Organic Light-Emitting Diodes

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Lu, Qiqing Wang, Jingkun Miao, Yanqin Guo, Yuanyuan Wang, Guoliang Dong, Jianhua Zhao, Min Wang, Hua Key Laboratory of Interface Science and Engineering in Advanced Materials Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanxi-Zheda Institute of Advanced Materials and Chemical Engineering Taiyuan030024 China Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China College of Textile Engineering Taiyuan University of Technology Jinzhong030600 China

In this work, we successfully synthesized Ti3C2Tx-MXene nanosheets with a lateral dimension of 1~2 um by using wet-chemical etchant and sonication-assisted liquid-phase exfoliation method. After UV-ozone treatment, the work function for Ti3C2Tx-MXene nanosheets was adjusted to 5.14 eV well matching to indium tin oxide (ITO) anode (4.80 eV). Using Ti3C2Tx-MXene nanosheets as hole injection layer (HIL), Ir(ppy)3-based green organic light-emitting diodes (OLEDs) were fabricated, and the resulting devices exhibit a low turn-on voltage of 3.0 V and the high current efficiency, power efficiency and external quantum efficiency of 72.79 cd/A, 54.44 lm/W and 20.34%, which are obviously better than these of 67.38 cd/A, 50.38 lm/W and 18.65% for PEDOT:PSS-based reference device. Further, FIrpic- and Ir(pq)2acac-based blue and red OLEDs with Ti3C2Tx-MXene nanosheets HIL were demonstrated, which also show the significantly improved device efficiency of 44.56 cd/A, 32.44 lm/W and 22.07% for blue device and 39.17 cd/A, 38.54 lm/W and 21.90% for red device than these for corresponding PEDOT:PSS-based devices, proving the universal applicability of Ti3C2Tx-MXene nanosheets as HIL in OLEDs. The higher performance for Ti3C2Tx-MXene nanosheets-based devices can be attributed to the appropriate work function, high transmittance, high carrier mobility and good film forming property for Ti3C2Tx-MXene nanosheets. This is the first report about the MXene using as HIL in OLEDs, which opens up a new way to develop high-performance holes injection materials for solution-processed OLEDs. © 2022, The Authors. All rights reserved.

关键词： Organic light emitting diodes (OLED)

Rapid Response and Recovery Performance of NO2 Gas Sensor Based on Gan Hexagonal Pits at Room Temperature

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Han, Xiaomei Han, Dan Liu, Xiaoru Chen, Yi Liu, Lulu Liu, Zhihua Li, Donghui Sang, Shengbo Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System The Ministry of Education Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Interface Science and Engineering in Advanced Materials Taiyuan University of Technology Ministry of Education Taiyuan030024 China

Although fantastic milestones of Gallium nitride (GaN)-based materials in optoelectronic devices had been reached, the focus on the optimization of their geometrical structure for gas-sensing applications was relatively scarce. In this work, we demonstrated NO2 gas sensor based on p-type GaN hexagonal pits (GaN-HP) with high surface-to-volume ratio by wet etching method. The fabricated NO2 gas sensor had high sensitivity, high selectivity, fast response/recovery times. The response of p-type GaN-HP with etching time for 10 min to 2 ppm NO2 gas was 6.2%, which also have quick response and recovery time at room temperature. UV light drastically enhanced the response of p-type GaN-HP sensor by 1.3 times to 100 ppm NO2 . The gas sensing mechanism of p-type GaN-HP gas sensor was explored, which provided a theoretical and experimental basis for further research and development of high-performance gas sensors based on GaN material. © 2022, The Authors. All rights reserved.

关键词： Gallium nitride

Stochastic resonance in an ensemble of bistable systems under stable distribution noises and nonhomogeneous coupling

学校读者我要写书评

暂无评论

Physical Review E 2012年第4期85卷 046207-046207页

作者： Yang Tang Wei Zou Jianquan Lu Jürgen Kurths Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin 150080 China Institute of Physics Humboldt University Berlin Berlin D-12489 Germany Potsdam Institute for Climate Impact Research Telegraphenberg Potsdam D-14415 Germany School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan 430074 China Department of Mathematics Southeast University Nanjing 210096 China Institute for Complex systems and Mathematical Biology University of Aberdeen Aberdeen AB24 3FX United Kingdom

In this paper, stochastic resonance of an ensemble of coupled bistable systems driven by noise having an α-stable distribution and nonhomogeneous coupling is investigated. The α-stable distribution considered here is characterized by four intrinsic parameters: α∈(0,2] is called the stability parameter for describing the asymptotic behavior of stable densities; β∈[−1,1] is a skewness parameter for measuring asymmetry; γ∈(0,∞) is a scale parameter for measuring the width of the distribution; and δ∈(−∞,∞) is a location parameter for representing the mean value. It is demonstrated that the resonant behavior is optimized by an intermediate value of the diversity in coupling strengths. We show that the stability parameter α and the scale parameter γ can be well selected to generate resonant effects in response to external signals. In addition, the interplay between the skewness parameter β and the location parameter δ on the resonance effects is also studied. We further show that the asymmetry of a Lévy α-stable distribution resulting from the skewness parameter β and the location parameter δ can enhance the resonance effects. Both theoretical analysis and simulation are presented to verify the results of this paper.

关键词： STOCHASTIC resonance BISTABLE devices PARAMETER estimation SIMULATION methods & models DISTRIBUTION (Probability theory) SYMMETRY (Physics) NOISE

Black Phosphorus-Organic Framework-Derived Pei/Peg Nanohybrid Prepared by a One-Pot Method for a Wide Detection Range Co2 Gas Sensor

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Lulu Sang, Shengbo Han, Dan Liu, Zhihua Han, Xiaomei Li, Donghui Chen, Yi Liu, Dongming Liu, Xiaoru Zhuo, Kai Cheng, Yongqiang Yang, Kun Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Interface Science and Engineering in Advanced Materials Taiyuan University of Technology Ministry of Education Taiyuan030024 China

In this paper, we report a hybrid PEI/PEG-BP sensor (composite material of black phosphorus-organic framework-derived PEI/PEG nanohybrid) prepared by a one-pot method, in which the existence of PEI/PEG onto BP was confirmed by SEM, EDS, XPS and UPS. The gas sensing properties of the PEI/PEG-BP sensor, including the sensor response, response/recovery times, repeatability, selectivity, and effects of humidity on the sensor, were studied by exposure to several CO 2 gas concentrations ranging from 200 ppm to 300,000 ppm at room temperature (25 ℃). The results show that the PEI/PEG-BP sensor had an extremely wide detection range, with lower and upper detection limits of 200 ppm and 160,000 ppm, respectively. The response of the PEI/PEG-BP sensor to 200 ppm, and 160,000 ppm CO 2 gas at room temperature ( RT ) was 4.48%, and 254.02%, respectively, showing fast response/recovery time, excellent repeatability and high selectivity. The gas-sensing properties of the PEI/PEG-BP sensor are better than BP, PEI, PEG, PEI-BP and PEG-BP sensors. The superior properties of the PEI/PEG-BP sensor can be attributed to the BP framework, porous structure, electron doping, and surface reactive groups such as -NH 2 and -OH. The PEI/PEG-BP sensor, with its excellent gas-sensing performance will help us to further explore the changes of CO 2 concentration in microbial growth systems, natural environments, industrial production and so on. © 2022, The Authors. All rights reserved.

关键词： Carbon dioxide

The Path Planning Algorithm for Uuv Based on the Fusion of Grid Obstacles of Artificial Potential Field

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Sun, Mingxiao Xiao, Xiaotian Luan, Tiantian Zhang, Xiaoshuang Wu, Baoqi Zhen, Liqiang School of Automation Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Jiangsu Automation Research Institution No. 18 Shenghu Road Haizhou District Jiangsu Province Lianyungang City222000 China

The artificial potential field approach (APFA) has the advantages of short computation time and easy implementation, widely used in path planning. The problems of local oscillation and susceptibility to local minima for APFA are considered in three dimensions (3D) path planning application of unmanned underwater vehicle (UUV), and the artificial potential field grid method (APFG) is proposed. Firstly, the obstacles are rasterized in 3D map. The repulsive points are attached to the surface of the raster to change the repulsive influence range. This method can compensate for the long planning path caused by the idealization of traditional APFA modeling. At the same time, the repulsion function on the grid surface is changed so that the potential field on the grid surface is parallel to the grid surface, which will solve the local oscillation problem in the path planning of UUV. Then, virtual target points are introduced to avoid the UUV falling into local optimization. The simulations show that APFG effectively overcomes the shortcomings of local oscillations and the tendency to fall into local minima for UUV in 3D path planning, and the path planning is smooth and efficient. © 2024, The Authors. All rights reserved.

关键词： Motion planning