检索结果-内蒙古大学图书馆

2020 5th International Conference on Intelligent Computing and Signal Processing, ICSP 2020

作者： Wang, Junpeng Lu, Yanfeng 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 Beijing100049 China

Convolutional Neural Networks (CNN) have achieved great performance in many visual tasks. However, CNN models are sensitive to samples with large spatial variants, especially severe in fine-grained classification task. In this paper, we propose a novel CNN model called ST-BCNN to solve these problems. ST-BCNN contains two functional CNN modules: Spatial Transform Network (STN) and Bilinear CNN(BCNN). Firstly, STN module is used to select key region in input samples and get it spatially modified. Since the adoption of STN will cause an information loss phenomenon called boundary loss, we design a brand-new IOU loss method to solve it. We make a theoretical analysis of the IOU loss method. Secondly, to discover discriminative features for fine-grained classification task, BCNN module is applied. BCNN interacts CNN features from different channels to produce more discriminative bilinear features than fully connected features of CNN. ST-BCNN works by reducing irrelevant spatial states and producing fine-grained features. We evaluate our model on 3 public fine-grained classification datasets with large spatial variants: CUB200-2011, Fish100 and UAV43. Experiments show that the IOU loss method can reduce boundary loss and make STN module output spatial transformed image appropriately. Our proposed ST-BCNN model outperforms other advanced CNN models on all three datasets. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Approximate optimal control of nonlinear systems with mismatched perturbations based on asymptotically stable critic neural network 2020

Approximate optimal control of nonlinear systems with mismat...

引用

6th International Conference on Computing and Data Engineering, ICCDE 2020 and 2020 International Conference on Artificial Intelligence in Electronics Engineering, AIEE 2020

作者： Zhao, Bo Hou, Jiaxu Guo, Ping Liu, Derong Xu, Yancai School of Systems Science Beijing Normal University Beijing100875 China School of Automation Guangdong University of Technology Guangzhou510006 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781450376730

In this paper, the approximate optimal control problem for nonlinear systems with mismatched perturbations is addressed through asymptotically stable critic neural network (NN). By employing the estimated perturbation via nonlinear perturbation observer, the online updated value function is constructed to reflect the real-time perturbations, regulation and control simultaneously. In order to solve the Hamilton-Jacobi-Bellman equation, an asymptotically stable critic NN is established based on the novel nested update laws. Thus, the approximate optimal control is obtained to guarantee the closed-loop system to be uniformly ultimately bounded based on the Lyapunov's direct method. Simulation results illustrate the effectiveness of the developed control scheme. © 2020 ACM International Conference Proceeding Series. 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

Empirical policy optimization for n-player Markov games

arXiv

引用

arXiv 2021年

作者： Zhu, Yuanheng Zhao, Dongbin Zhao, Mengchen Li, Dong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Huawei Noah's Ark Lab Beijing China

In single-agent Markov decision processes, an agent can optimize its policy based on the interaction with environment. In multi-player Markov games (MGs), however, the interaction is non-stationary due to the behaviors of other players, so the agent has no fixed optimization objective. In this paper, we treat the evolution of player policies as a dynamical process and propose a novel learning scheme for Nash equilibrium. The core is to evolve one's policy according to not just its current in-game performance, but an aggregation of its performance over history. We show that for a variety of MGs, players in our learning scheme will provably converge to a point that is an approximation to Nash equilibrium. Combined with neural networks, we develop the empirical policy optimization algorithm, that is implemented in a reinforcement-learning framework and runs in a distributed way, with each player optimizing its policy based on own observations. We use two numerical examples to validate the convergence property on small-scale MGs with n ≥ 2 players, and a pong example to show the potential of our algorithm on large games. © 2021, CC BY-NC-ND.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Traffic-Condition-Awareness Ensemble Learning for Traffic Flow Prediction ⁎

引用

IFAC-PapersOnLine 2020年第5期53卷 582-587页

作者： Yuanyuan Chen Yisheng Lv Peijun Ye Fenghua Zhu State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Traffic prediction is an elemental function of Intelligent Transportation systems (ITS), and accurate and timely prediction is significant for both proactive traffic control and providing traveler information. In this paper, we focus on investigating ensemble leaning that benefits from different base models, and propose a traffic-condition-awareness ensemble approach. We apply graph convolution on the network of traffic detectors to capture the spatial patterns embedded in traffic flow. Then, the extracted features are used to formulate a weight matrix to ensemble the predictions of base models according to their performances under a certain condition. We performed a series of experiments on a real dataset to compare the proposed methods with several competitive models, including ensemble methods: Weight Regression model and Gradient Boosting Regression Tree model, and single model approach: Support Vector Regression (SVR), Long Short-term Memory (LSTM) model and Historical Average Model model. Experimental results demonstrate that our method can significantly improve the performances of traffic flow prediction.

关键词： Intelligent road transportation Urban mobility

来源：评论

学校读者我要写书评

暂无评论

Calibration of agent-based model using reinforcement learning 1

Calibration of agent-based model using reinforcement learnin...

引用

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

作者： Song, Bing Xiong, Gang Yu, Songmin Ye, Peijun Dong, Xisong Lv, Yisheng 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 The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China Fraunhofer Institute for Systems and Innovation Research Breslauer Germany

ISBN: (纸本)9781665433372

In the research and application of Agent-Based Models (ABM), parameter calibration is an important content. Based on the existing state transfer equations that link the micro-parameters and macro-states of the multi-agent system, this paper further proposes to introduce Reinforcement Learning when calibrating the parameters. The state transfer of the agent after learning is used to calibrate the micro-parameters of ABM, and the interaction between each agent and multiple other agents is expressed as the parameters of the agent. The application case study of population migration demonstrates that our method can achieve high accuracy and low computational complexity. © 2021 IEEE.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

S$^{\text{4}}$TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第2期9卷 3220-3231页

作者： Xiao Wang Ke Tang Xingyuan Dai Jintao Xu Quancheng Du Rui Ai Yuxiao Wang Weihao Gu Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei China Haomo Technology Company Ltd. Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 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 (S $^{\text{4}}$ TP) framework. Specifically, S $^{\text{4}}$ TP 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. S $^{\text{4}}$ TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs' trajectories as input. With the integration of SADRF, S $^{\text{4}}$ TP 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 S $^{\text{4}}$ TP in terms of safety and rationality. S $^{\text{4}}$ TP 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%.

关键词： Trajectory Safety Vehicles Trajectory planning Autonomous vehicles Risk management Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection for Autonomous Vehicles Using Virtual-to-Real Augmentation

Pedestrian Detection for Autonomous Vehicles Using Virtual-t...

引用

Chinese automation Congress (CAC)

作者： Bo Lu Min Huang Xi Li Yunhao Nie Qinghai Miao Yisheng Lv School of Artificial Intelligence University of Chinese Academy of Sciences Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Annotated data are essential to the success of training deep neural models for autonomous driving. Practically, it is both expensive and time consuming to collect and annotate plenty of data driving cross the city. It is even harder to cover the corner cases involving rare pedestrian poses with occlusions. To tackle this problem, we propose a data augmentation method for pedestrian detection. First, we take a SMPL model to generate pedestrians with a variety of poses and textures. Second, we insert the rendered pedestrians into images with real traffic background according to vanishing point. Occlusions can also be set easily by taking use of segmentation annotations of original real dataset. We evaluated the effectiveness of the generated synthetic dataset using multiple detectors. Results of three experiments shown that detectors trained with mixture of synthetic and real data outperform those trained on only real datasets.

关键词： Training Image segmentation Urban areas Neural networks Detectors Data models Labeling

来源：评论

学校读者我要写书评

暂无评论

Visuotactile Feedback Parallel Gripper for Robotic Adaptive Grasping

Visuotactile Feedback Parallel Gripper for Robotic Adaptive ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Boyue Zhang Shaowei Cui Chaofan Zhang Jingyi Hu Shuo Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665481106

In robot grasp and dexterous manipulation tasks, tactile sensing is important for the control adjustment of the manipulator. In this paper, we present a novel low-cost parallel gripper with high-resolution tactile sensing, named the GelStereo Gripper. Furthermore, an adaptive grasp strategy is proposed to endow the gripper with tactile-feedback grasp stability-maintaining ability. We install the gripper on our robot platform and conduct various grasp experiments by utilizing proposed control methods. Experimental results verify the reliability of the GelStereo gripper and also prove the effectiveness of the proposed strategy for experimental objects with different features.

关键词： Shape Pose estimation Force Tactile sensors Grasping Robot sensing systems Sensors

来源：评论

学校读者我要写书评

暂无评论

V2X-BGN: Camera-based V2X-Collaborative 3D Object Detection with BEV Global Non-Maximum Suppression

V2X-BGN: Camera-based V2X-Collaborative 3D Object Detection ...

引用

IEEE Symposium on Intelligent Vehicle

作者： Caiji Zhang Bin Tian Shi Meng Shuangying Qi Yang Sun Yunfeng Ai Long Chen School of Artificial Intelligence University of Chinese Academy of Sciences and With the National Key Laboratory for Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Bin Tian is With the National Key Laboratory for Multi-Modal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and With the School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China National Key Laboratory for Multi-Modal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and With the School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Chongqing Iron and Steel Group Mining Co. Ltd. Chongqing China School of Mechanical and Equipment Engineering Hebei University of Engineering Handan China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Waytous Inc. Qingdao China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Waytous Ltd. Qingdao China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In recent years, research on Vehicle-to-Everything (V2X) cooperative perception algorithms mainly focuses on the fusion of intermediate features from LiDAR point clouds. Since the emergence of excellent single-vehicle visual perception models like BEVFormer, collaborative perception schemes based on camera and late-fusion have become feasible approaches. This paper proposes a V2X-collaborative 3D object detection structure in Bird's Eye View (BEV) space, based on global non-maximum suppression and late-fusion (V2X-BGN), and conducts experiments on the V2X-Set dataset. Focusing on complex road conditions with extreme occlusion, the paper compares the camera-based algorithm with the LiDAR-based algorithm, validating the effectiveness of pure visual solutions in the collaborative 3D object detection task. Additionally, this paper highlights the complementary potential of camera-based and LiDAR-based approaches and the importance of object-to-ego vehicle distance in the collaborative 3D object detection task.

关键词： Point cloud compression Visualization Three-dimensional displays Laser radar Roads Collaboration Object detection

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

Image Captioning on Fine Art Paintings via Virtual Paintings

引用

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

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

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.

关键词： Art Digital twin Conferences Machine learning Task analysis Painting

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：