检索结果-内蒙古大学图书馆

43rd Chinese control Conference, CCC 2024

作者： Chen, Si-Wen Li, Hong-Yue Hou, Hui-Rang Meng, Qing-Hao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

The emission of carbon oxides (COx), nitrogen oxides (NOx), sulfur compounds, and volatile organic compounds (VOCs) from vehicles has significantly impacted the air quality, thus posing threats to the environmental resources and human health. This work presents the development of a non-dispersive infrared (NDIR) multi-gas detection system featuring three broadband light sources, a sealed gas chamber, and three multi-channel pyroelectric detectors with a response time shorter than 32 ms. The proposed system is used for constructing an odor dataset comprising five target gases, including carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), sulfur dioxide (SO2), and propane (C3 H8). We perform odor recognition experiments using the traditional machine learning methods, as well as one-dimensional convolutional neural network (1D-CNN) and depthwise separable convolutional neural network (DS-CNN). The results show that the proposed DS-CNN model achieves an accuracy of 94.75% in recognizing different odors, thus outperforming other classification algorithms. This work demonstrates that the proposed detection system exhibits rapid response and precise recognition, thus establishing it as an effective approach for analyzing the primary components of automobile exhaust. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

E-Nose-Based Domain-Generalization Recognition of Ignitable Liquids 43

E-Nose-Based Domain-Generalization Recognition of Ignitable ...

引用

43rd Chinese control Conference, CCC 2024

作者： Song, Tian-Shu Chen, Zhen-Peng Hou, Hui-Rang Li, Hong-Yue Meng, Qing-Hao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

Detecting ignitable liquids (ILs) at the scene of a fire is crucial for fire investigation. The electronic nose (e-nose) is crucial for detecting ILs due to its affordability and rapid response time. process limitations and changes in environmental conditions can cause variations in the reactions of multiple e-noses with the same sensor array to the same input gas. This can significantly reduce the accuracy of identifying ILs when deploying a model trained on one e-nose to other e-noses. In order to tackle the issue of cross-platform identification of ILs using e-noses, we developed a feature mute gated network (FMG-Net). This network is capable of maintaining consistency in the shared components of different e-noses at the low-level feature level while effectively muting the distinct low-level features. FMG-Net is comprised of a main network and multiple branch networks that are specific to different domains. Initially, a subsidiary domain-specific convolutional neural network (SDS-CNN) is trained to learn the network parameters on various e-nose platforms with known labels. Additionally, the backbone network generates low-level features of the e-nose responses. Furthermore, the SDS-CNN incorporates random input of low-level features and generates a mask using the gradient. This mask is then used to explicitly remove the non-overlapping parts of the low-level features. At last, the low-level features are sent back to the backbone network for further training once the non-overlapping parts have been removed. Experiments were conducted to identify four types of ILs (diesel, gasoline, ethanol, and thinner) using five self-made e-nose platforms with identical sensor arrays. The results indicated that the proposed FMG-Net consistently outperforms other domain-generalization algorithms in terms of recognition accuracy and parameter sizes. FMG-Net has the ability to detect volatile gases in ILs using an e-nose, even without the need for a dataset. © 2024 Technical Committ

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Depression Level Classification Model Based on EEG and GCN Network with Domain Generalization 43

A Depression Level Classification Model Based on EEG and GCN...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Zhongyi Xu, Chenyang Jin, Licheng Hou, Huirang Meng, Qinghao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

Electroencephalography (EEG) contains a wealth of information, including neuron activity, allowing for a partial understanding of the brain's state. As a reliable tool, EEG, combined with deep neural networks, has been increasingly utilized to assist in the detection of depression and has achieved satisfactory results. However, there are still some limitations in the current models. Firstly, it is worth noting that many existing models are binary classification models. These models can determine whether a subject is depressed or not, but they lack the capability to differentiate the severity of depression. Besides, the variations in EEG signals among various individuals have not been thoroughly taken into account, leading to subpar performance when applying the trained model to new subjects. To address the aforementioned issues, we suggest implementing a multi-classification model that utilizes a graph convolutional neural network (GCN) to identify levels of depression. Additionally, to mitigate the problem of imbalanced samples in multi-classification tasks, we introduce a penalty coefficient for the smaller categories. At the same time, the issue of signal discrepancies among subjects was taken into account, leading to the introduction of the domain generalization module. Finally, the depression level identification task on the MODMA and PRED+CT dataset achieved an accuracy of 75.47% and 77.97% respectively, surpassing the performance of the state-of-the-art (SOTA) model. In addition, numerous ablation experiments were conducted to validate the efficacy of each module. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Efficient Data-Driven Force Sensing for Concentric Tube Continuum Robots using Diffeomorphic-Mapping-Based Transfer Learning

Efficient Data-Driven Force Sensing for Concentric Tube Cont...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Heiko Donat Jochen Steil Aziza Ben Halima The Institute of Robotics and Process Control - IRP Technische Universität Braunschweig Germany

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

Data-driven techniques show promising results in force estimation for Concentric Tube Continuum Robots, but often require extensive datasets, which are difficult to acquire. This work introduces a mapping-based transfer learning approach to improve the efficiency of data-driven methods for contact force estimation, by proposing a diffeomorphic mapping-based algorithm that reduces data requirements, enabling more practical application of these methods. By transforming data from pre-curved tubes into the feature space of non-curved tubes, our method allows a pre-trained neural network to estimate forces efficiently across various tube configurations, eliminating the need for additional data for changing tube configurations and retraining of the network. Simulation tests show high accuracy for curvatures up to $\kappa = 7\frac{1}{m}$, significantly reducing the need to create large datasets for each new robot configuration.

关键词： Accuracy Force Transfer learning Estimation Soft robotics Robot sensing systems Sensors Continuum robots Noise measurement Testing

来源：评论

学校读者我要写书评

暂无评论

Efficient Data-Driven Force Sensing for Concentric Tube Continuum Robots using Diffeomorphic-Mapping-Based Transfer Learning 8

Efficient Data-Driven Force Sensing for Concentric Tube Cont...

引用

8th IEEE International Conference on Soft robotics, RoboSoft 2025

作者： Donat, Heiko Steil, Jochen Halima, Aziza Ben Technische Universität Braunschweig The Institute of Robotics and Process Control-IRP Germany

ISBN: (纸本)9798331520205

Data-driven techniques show promising results in force estimation for Concentric Tube Continuum Robots, but often require extensive datasets, which are difficult to acquire. This work introduces a mapping-based transfer learning approach to improve the efficiency of data-driven methods for contact force estimation, by proposing a diffeomorphic mapping-based algorithm that reduces data requirements, enabling more practical application of these methods. By transforming data from pre-curved tubes into the feature space of non-curved tubes, our method allows a pre-trained neural network to estimate forces efficiently across various tube configurations, eliminating the need for additional data for changing tube configurations and retraining of the network. Simulation tests show high accuracy for curvatures up to κ = 71m, significantly reducing the need to create large datasets for each new robot configuration. © 2025 IEEE.

关键词： Tubes (components)

来源：评论

学校读者我要写书评

暂无评论

Systematic Testing of Exoskeletons with Robots: Challenges and Opportunities 54

Systematic Testing of Exoskeletons with Robots: Challenges a...

引用

54th International Symposium on robotics, ISR Europe 2022

作者： Wehrle, Theresa Barut, Sinan Klankers, Kilian Mohammadi, Pouya Steil, Jochen The Institute of Robotics and Process Control Technische Universität Braunschweig Mühlenpfordtstraße 23 Braunschweig38106 Germany

ISBN: (纸本)9783800758920

Due to the change of industrial processes and demographic shift in many countries, an increase in the use and application of exoskeletons is expected. However, design, development and deployment of exoskeletons requires testing. The standard way of testing novel interactive technologies by user studies suffers from a number of limitations, namely low repeatability between and within subjects, high resource demands, and technical and logistical issues. In this paper, we therefore promote the idea to use robots for more systematic and effective testing of exoskeletons. We suggest a threefold methodology that (i) employs models and simulation to investigate essential mechanisms of the human’s or the robot’s interaction with the exoskeleton, (ii) relies on capturing human motion and using machine learning to model it, and (iii) develops a dedicated platform to deploy the learned human-like motion models on the testing robot. In particular, we argue for a robot design that is specifically tailored to this testing task and can exhibit human-like motion. In this paper we discuss our methodology and its steps towards design and development of such a dedicated test platform. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

E-Nose-Based Cross-Domain Recognition of Combustion-Supporting Agents via M-BFFNet 42

E-Nose-Based Cross-Domain Recognition of Combustion-Supporti...

引用

42nd Chinese control Conference, CCC 2023

作者： Wang, De-Xiu Meng, Qing-Hao Han, Rui-Xue Li, Hong-Yue Hou, Hui-Rang Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China Tianjin Navigation Instruments Research Institute Tianjin300131 China

ISBN: (纸本)9789887581543

Identification of the type of combustion-supporting agents (CSAs) by an electronic nose (e-nose) is severely limited due to the absence of untested gas concentration in the e-nose training set. In order to solve this problem, this study designs an e-nose for classifying four CSAs (Diesel, Gasoline, Ethanol and Thinner), and builds cross-concentrations data set. This study uses Gramian Angular Field method that converts one-dimensional time series data to two-dimensional data, and proposes an algorithm named the Multi-Branch Feature Fusion Network (M-BFFNet). This algorithm passes the one-dimensional and two-dimensional data through two different networks and obtains two types of features. First, the algorithm can strength the one-dimensional raw data, integrate the advantages of different networks, and fuse the characteristics of different networks. Second, it can learn the characteristics of volatile gas with specific concentrations to identify the unknown concentrations. Last, a feature fusion module is designed to improve the algorithm ability of learning odor fingerprint. In order to verify the superiority of the algorithm, this study tests the recognition performance of the e-nose based systems and compares the proposed M-BFFNet with traditional algorithms. The results show that the proposed M-BFFNet improves the identification accuracy compared to other algorithms. According to the analysis of this work, the M-BFFNet can be used to identify CSAs with unknown concentrations. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Electronic nose

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Estimation of Forces Along the Backbone of Concentric Tube Continuum Robots

Data-Driven Estimation of Forces Along the Backbone of Conce...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Heiko Donat Pouya Mohammadi Jochen Steil The Institute of Robotics and Process Control - IRP Technische Universität Braunschweig Germany

Concentric tube continuum robots (CTCRs) belong to the family of continuum robots with applications in minimally invasive surgeries. Because of this application domain, measuring the external forces along the body of the robot is paramount. CTCRs are made up of thin elastic rods and are intended to be applied inside the human body, where conventional sensor-based measurements are not feasible. Consequently, research is resorting to estimate the forces through geometric, numeric, or optimization methods. However, these methods often suffer from slow convergence. In this paper, we introduce a novel data-driven approach for estimating contact forces along the body of a CTCR that offers an estimation precision comparable to the current state-of-the-art optimization-based approaches, but exhibits nearly two orders of magnitude faster convergence. The proposed method is scalable and exhibits a significant performance in response to a wide range of external forces. The approach was evaluated in simulations and on a real 2-tube CTCR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Domain Generalization Method for E-nose Cross-platform Identification of Ignitable Liquids

引用

IEEE Sensors Journal 2025年第13期25卷 25829-25839页

作者： Song, Tian-Shu Hou, Hui-Rang Chen, Zhen-Peng Ding, Hui-Hang Meng, Qing-Hao Tianjin University Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control School of Electrical and Information Engineering Tianjin300072 China

Electronic nose (e-nose) can carry out odor fingerprinting and identification, exhibiting several advantages such as speed, low cost and portability. The e-nose technology allows objective, accurate and real-time detection and recognition of ignitable liquids (ILs), which provide technical support for fire cause determination and fire scene reproduction. Metal oxide semiconductor (MOS) gas sensors have certain technical limitations, and multiple e-nose platforms assembled using the same sensor array will produce different output responses when sampling the same gas. Manual data labeling and repetitive training of models involve a huge workload. This study proposes a novel domain generalization method to mitigate this problem. During the training process, we assign pseudo-domain labels iteratively for the e-nose response signals obtained from multiple source domains by clustering. This approach avoids the situation where multiple potential domains can exist for the same e-nose. The highlights of our approach are as follows: 1) The training paradigm of traditional domain generalization methods that require domain labels is not used;2) Pseudo-domain labels are generated for the samples according to each cycle iteration during training;3) The feature extractor is trained to learn domain-invariant features by adversarial learning based on pseudo-domain labels;4) The statistics of each hidden layer of the neural network are used to cluster the e-nose signals and generate pseudo-domain labels from them. Five e-noses, each with 16 identical sensor channels, are used to recognize four types of ILs. Our method achieves an average cross-platform recognition accuracy of 85.2%. © 2001-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Panda's Elbow Motion in Null Space and a Combined Analytical-Numerical IK with Intuitive Redundancy Resolution

Analysis of Panda's Elbow Motion in Null Space and a Combine...

引用

International Conference on Advanced robotics (ICAR)

作者： Sven Tittel Institute of Robotics and Process Control (IRP) Technische Universität Braunschweig Braunschweig Germany

The kinematic structure of Franka Emika's redundant cobot Panda features two translational offsets that prevent three of the six pairs of adjacent joints from intersecting each other. These offsets make Panda's elbow motion in null space hard to predict with respect to existing redundancy parameters. The null space motion analysis of Panda's elbow presented in this work leads to the definition of a redundancy parameter that can be used intuitively. The semi-analytical approach applied in this work induces a fast inverse kinematics algorithm that offers a redundancy resolution which does not affect the reachability of the given end effector pose. Even libfranka, Franka Emika's supplied library, does not offer such a Cartesian approach of keeping control of Panda's secondary motion while fulfilling primary manipulation tasks.

关键词：

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

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

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：