检索结果-内蒙古大学图书馆

第三十九届中国控制会议

作者： Zi-Zhen Yang Tao Jing Qing-Hao Meng Institute of Robotics and Autonomous System Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University

A single unmanned-aerial-vehicle(UAV) based odor source localization(OSL) method for outdoor multi-building environments was proposed. The simulated annealing(SA) algorithm was introduced in this problem in consideration of the difficulties of relatively large search space, turbulent airflow in the building environment, and local concentration extrema near the building walls. To avoid the effect of rotating UAV rotors on airflow, a tunable diode laser absorption spectroscopy(TDLAS) rather than the contact gas sensor was used to collect odor information remotely. Moreover, a three-mode(plume finding, tracking, and escaping local extremum) searching framework was designed in the SA-based OSL method to equip the UAV with abilities of traversing the searching area and escaping local extrema rapidly. Simulation results on a robot active olfaction simulator show that, the UAV could effectively escape the local extremum, track the plume and localize the odor source in the area of 30×30×10 m with an average time of about 119 steps and an average error of 1.56 m.

关键词： Odor source localization active olfaction UAV multi-building environments simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Teleoperation with Tactile Feedback based on a Capacitive Proximity Sensor Array

Teleoperation with Tactile Feedback based on a Capacitive Pr...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Hosam Alagi Stefan Escaida Navarro Jan Hergenhan Selma Musić Björn Hein Institute for Anthropomatics and Robotics - Intelligent Process Control and Robotics Lab (IAR-IPR) Karlsruhe Institute of Technology Defrost at Inria Lille-Nord Europe IAR-IPR Chair of Information-oriented Control Technical University of Munich Munich Germany

ISBN: (数字)9781728144603

ISBN: (纸本)9781728144610

In this paper, we show our novel teleoperation system that mediates proximity perception at the slave system as tactile information to the user. We have equipped a robot's end-effector with a capacitive proximity sensor array. Based on the proximity information, tactile feedback is generated for the user via a tactile display. Thus, the user can feel some of an object's features through his fingers, without the need for establishing contact between the slave system and the object. In our setting, the proximity sensing-based feedback complements the visual feedback provided by a workspace camera and a robot tool camera. Both the sensor array and the tactile display, have a spatial resolution of 4×4. To evaluate the impact, we conducted a user study covering scenarios with visual occlusion and distortion in pre-touch and pre-manipulation phases. The study revealed an improvement in the accuracy of positioning of the end-effector when the visual and the tactile feedback were both provided to the user. The study also showed high acceptance of the new modality by the users.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Odor Evaluation of Vehicle Interior Materials Based on Portable E-nose

Odor Evaluation of Vehicle Interior Materials Based on Porta...

引用

第三十九届中国控制会议

作者： Zhe-Hua Sun Ke-Xian Liu Xue-Han Xu Qing-Hao Meng Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University

The evaluation of the odor emitted by the interior materials is of great significance to the air quality control in the vehicle. This paper focuses on the multi-label classification problem of the odor type(i.e. the type of material from which the odor is released) and the grade evaluation in the vehicle. Two multi-label classifiers based on binary relevance(BR) and classification chain(CC) were designed to distinguish odor types and grades simultaneously and to distinguish odor types first and then grades, respectively. Based on the self-designed portable E-nose, six grades of odors released from six types of common interior materials were detected and classified. Experimental results showed that both the multi-label classifiers achieved better recognition accuracy, but the CC had an average recognition rate of 88.17% slightly better than the BR. It is preliminarily verified that the portable E-nose based multi-label classifiers could be used to evaluate the odor of automotive interior materials.

关键词： E-nose vehicle interior materials multi-label classifier Odor evaluation

来源：评论

学校读者我要写书评

暂无评论

Attitude Adjustment of a Multi-joint AUV Using an Improved LADRC

Attitude Adjustment of a Multi-joint AUV Using an Improved L...

引用

第三十九届中国控制会议

作者： Lin Yu Ke-Xian Liu Qing-Hao Meng Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and ControlSchool of Electrical and Information Engineering Tianjin University

To achieve vertical profile exploration of deep-sea hybrid structures, a multi-joint autonomous underwater vehicle(MJ-AUV) with the orthogonal joints structure was designed, and its virtual prototype was built using Automatic Dynamic Analysis of Mechanical Systems(ADAMS). This paper focuses on the attitude control of the designed MJ-AUV which is a nonlinear system with strong coupling, big hysteresis, large inertia, and time-varying disturbance. According to the special structure of the MJ-AUV, an error based variable gain linear active disturbance rejection controller(EVG-LADRC) was proposed and compared with the traditional proportional-integral-derivative(PID) controller and LADRC. Simulation results demonstrated that EVG-LADRC outperformed the PID and LADRC in terms of rapidity, anti-interference, and accuracy.

关键词： MJ-AUV virtual prototype attitude control EVG-LADRC

来源：评论

学校读者我要写书评

暂无评论

Heatmap-based vanishing point boosts lane detection

arXiv

引用

arXiv 2020年

作者： Liu, Yin-Bo Zeng, Ming Meng, Qing-Hao Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University China

Vision-based lane detection (LD) is a key part of autonomous driving technology, and it is also a challenging problem. As one of the important constraints of scene composition, vanishing point (VP) may provide a useful clue for lane detection. In this paper, we proposed a new multi-task fusion network architecture for high-precision lane detection. Firstly, the ERFNet was used as the backbone to extract the hierarchical features of the road image. Then, the lanes were detected using image segmentation. Finally, combining the output of lane detection and the hierarchical features extracted by the backbone, the lane VP was predicted using heatmap regression. The proposed fusion strategy was tested using the public CULane dataset. The experimental results suggest that the lane detection accuracy of our method outperforms those of state-of-the-art (SOTA) *** Codes 68T45 (Primary) 68T07 (Secondary) Copyright © 2020, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual SLAM based on VGG Feature Point Extraction

Monocular Visual SLAM based on VGG Feature Point Extraction

引用

Chinese control Conference (CCC)

作者： Xu-Yang Dai Qing-Hao Meng Wen-Jian Zheng Shao-Kai Zhu Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

Significant progress has been made in the field of visual SLAM (Simultaneous Localization and Mapping). However, the localization accuracy of visual SLAM can be significantly reduced in low-texture and illumination-changing environments. To solve these problems, an enhanced visual SLAM algorithm based on VGG (Visual Geometry Group) network was proposed in this paper. Firstly, the VGG network for feature point extraction was incorporated into the visual odometry (VO) to achieve robust camera pose estimation. Secondly, an automatic corner annotation method was adopted to set up the training database, which could reduce the workload of data annotation. Thirdly, to make the backend optimization more suitable for the VGG based VO, the BA (bundle adjustment) optimization process was improved. Experimental results showed that, the proposed visual SLAM method outperformed the mainstream ORB-SLAM (Oriented FAST and Rotated BRIEF SLAM) method, in terms of the number of effective feature points, the robustness of feature matching process to light changes, and the accuracy of robot pose estimation.

关键词： Feature extraction Simultaneous localization and mapping Cameras Visualization Optimization Training Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

A Novel E-Nose Chamber Design for VOCs Detection in Automobiles

A Novel E-Nose Chamber Design for VOCs Detection in Automobi...

引用

Chinese control Conference (CCC)

作者： Lu Cheng Yin-Bo Liu Qing-Hao Meng Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

To detect parts per billion (ppb)-level volatile organic compounds (VOCs) in automobiles, a pre-concentrator is generally needed for electronic noses (e-noses), which can enrich ppb-level concentration to parts per million (ppm) level. However, the current e-nose chamber structure could dilute the pre-concentrated gases and then the detection performance is reduced. To solve this problem, a novel chamber design was proposed in this paper. The core design idea was to reduce the space for the gas flow in the chamber, taking into account the shape and size of the gas sensors. Specially, for the pin-type gas sensors, a series of cylindrical structure design was adopted, and for the micro-electro-mechanical system (MEMS) patch-type sensors, the headspace was compressed. The results of computational fluid dynamics (CFD) based simulation showed that the concentration of pre-concentrated gases in the novel chamber was higher than that of the traditional chamber. The designed chambers were manufactured using polylactic acid (PLA) material by 3D printing. Experimental gases were prepared from polyurethane (PU) leather and polyvinyl chloride (PVC) leather to verify the performance of the chambers, and the results demonstrated that the proposed new e-nose chamber was superior to the traditional one in terms of the pre-concentration effect, repeatability and classification performance.

关键词： Gas detectors Sensor arrays Micromechanical devices Fluid flow Gases Automobiles

来源：评论

学校读者我要写书评

暂无评论

Indoor Layout Estimation by Fusing Monocular RGB Image Features Extracted with HRNet

Indoor Layout Estimation by Fusing Monocular RGB Image Featu...

引用

Chinese control Conference (CCC)

作者： Rong-Ze Huang Yin-Bo Liu Meh Jabeen Qing-Hao Meng Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

Indoor layout estimation (ILE) is a challenging research that segments the natural indoor scene image into floor, walls and ceiling, and it has a wide range of application prospects in the fields such as scene understanding, reconstruction, robot positioning, and virtual reality. An ILE method by merging multiple features from a monocular red-green-blue (RGB) image was proposed. Firstly, the High-resolution networks (HRNet) was used to extract the features of indoor corner keypoints (CKs) and informative edges (IEs) in the form of heatmaps. Secondly, the extracted features were then selected through a room type (RT) classification network. Finally, a feature fusion algorithm was proposed, which obtained the initial layout hypothesis through CK features and then continuously optimized the layout hypothesis with IE features. The proposed ILE method was validated on the large scene understanding challenge (LSUN) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

D-VPnet: A Network for Real-time Dominant Vanishing Point Detection in Natural Scenes

arXiv

引用

arXiv 2020年

作者： Bo Liu, Yin Ming, Zeng Meng, Qing-Hao Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin University Tianjin300072 China

As an important part of linear perspective, vanishing points (VPs) provide useful clues for mapping objects from 2D photos to 3D space. Existing methods are mainly focused on extracting structural features such as lines or contours and then clustering these features to detect VPs. However, these techniques suffer from ambiguous information due to the large number of line segments and contours detected in outdoor environments. In this paper, we present a new convolutional neural network (CNN) to detect dominant VPs in natural scenes, i.e., the Dominant Vanishing Point detection Network (D-VPnet). The key component of our method is the feature line-segment proposal unit (FLPU), which can be directly utilized to predict the location of the dominant VP. Moreover, the model also uses the two main parallel lines as an assistant to determine the position of the dominant VP. The proposed method was tested using a public dataset and a Parallel Line based Vanishing Point (PLVP) dataset. The experimental results suggest that the detection accuracy of our approach outperforms those of state-of-the-art methods under various conditions in real-time, achieving rates of 115fps. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unstructured Road Vanishing Point Detection Using the Convolutional Neural Network and Heatmap Regression

arXiv

引用

arXiv 2020年

Unstructured road vanishing point (VP) detection is a challenging problem, especially in the field of autonomous driving. In this paper, we proposed a novel solution combining the convolutional neural network (CNN) and heatmap regression to detect unstructured road VP. The proposed algorithm firstly adopts a lightweight backbone, i.e., depthwise convolution modified HRNet, to extract hierarchical features of the unstructured road image. Then, three advanced strategies, i.e., multi-scale supervised learning, heatmap super-resolution, and coordinate regression techniques are utilized to achieve fast and high-precision unstructured road VP detection. The empirical results on Kong’s dataset show that our proposed approach enjoys the highest detection accuracy compared with state-of-the-art methods under various conditions in real-time, achieving the highest speed of 33 fps. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：