检索结果-内蒙古大学图书馆

2023 International Conference on Ocean Studies, ICOS 2023

作者： Timoshenko, Aleksandr Zuev, Aleksandr Filaretov, Vladimir Institute of Marine Technology Problems Feb Ras Institute of the World Ocean Far Eastern Federal University Laboratory of Intelligent Information Sustems for Marine Robots M.D. Ageev Vladivostok Russia Institute of Marine Technology Problems Feb Ras Laboratory of Intelligent Information Sustems for Marine Robots M.D. Ageev Vladivostok Russia Institute of Automation and Control Processes Feb Ras Sevastopol State University Laboratory of Robotic Systems Vladivostok Russia

ISBN: (纸本)9798350382457

In this paper, a new approach is proposed to the construction of control systems for autonomous underwater vehicles equipped with multi-link manipulators for high-precision execution of various technological operations on underwater infrastructure objects, including those requiring force action on these objects, in fully automatic mode. The approach is based on creating a force effect on the work object using the thrusters of the underwater vehicle. In this case, all mutual influences from the manipulator moving in a viscous water space are taken into account, including nominal mutual influences between its links, the action of the added masses and moments of inertia of the liquid, as well as viscous friction. At the same time, the values of the added masses and moments of inertia of the liquid are proposed to be identified before the start of any technological operations using sliding mode observers and identification methods based on Kalman filters. Sliding mode observers allow us to estimate the values of generalized external torques acting in each actuator of the manipulator, as well as the values of rotational velocities and accelerations of their output shafts. The resulting minor displacements of the underwater vehicle during the execution of technological operations, due to errors in determining the force effect on the body of the vehicle from the operating manipulator, are compensated with the help of onboard stabilization systems of the underwater vehicle. © 2023 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Generating Manipulation Sequences using Reinforcement Learning and Behavior Trees for Peg-In-Hole Task

Generating Manipulation Sequences using Reinforcement Learni...

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Xu, Jiahua Lin, Yunhan Zhou, Haotian Min, Huasong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Reinforcement Learning (RL), a method of learning skills through trial-and-error, has been successfully used in many robotics applications in recent years. We combine manipulation primitives (MPs), behavior trees (BTs), and reinforcement learning to propose an algorithm for peg-in-hole tasks, which speeds up the convergence of the RL model and enhance the adaptability of the dynamic environment. Manipulation primitives are used as actions for RL, which can reduce the gap between control instruction and robotic actions and speed up the convergence of the RL model. Behavior trees are used as robot behavior control, which makes robots can actively adapt to the changes in the environment. In experiments, RL-BT, from the combination of RL and BT, is designed for the peg-in-hole task in the Gazebo simulation environment by using UR5 as the actuator. The experiments are conducted on a simple peg and a complex multi-hole peg by three aspects, which include convergence speed verification experiment, adaptability of dynamic environment experiment, and algorithm robustness experiment. The experiment result proves that our RL-BT can speed up the convergence and adapt to the changes in the environment. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation

arXiv

引用

arXiv 2024年

作者： Meraz, Md. Ansari, Md Afzal Javed, Mohammed Chakraborty, Pavan Center of Intelligent Robotics Lab Department of Information Technology Computer Vision & Biometrics Lab Department of Information Technology Indian Institute of Information Technology Allahabad U.P Prayagraj India

In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful feature extraction for classification tasks remains crucial. This paper presents Point-GR, a novel deep learning architecture designed explicitly to transform unordered raw point clouds into higher dimensions while preserving local geometric features. It introduces residual-based learning within the network to mitigate the point permutation issues in point cloud data. The proposed Point-GR network significantly reduced the number of network parameters in Classification and PartSegmentation compared to baseline graph-based networks. Notably, the Point-GR model achieves a state-of-the-art scene segmentation mean IoU of 73.47% on the S3DIS benchmark dataset, showcasing its effectiveness. Furthermore, the model shows competitive results in Classification and Part-Segmentation tasks. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Can transformers smell like humans? 24

Can transformers smell like humans?

引用

Proceedings of the 38th International Conference on Neural information Processing systems

作者： Farzaneh Taleb Miguel Vasco Antônio H. Ribeiro Mårten Björkman Danica Kragic Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Department of Information Technology Uppsala University Uppsala Sweden

ISBN: (纸本)9798331314385

The human brain encodes stimuli from the environment into representations that form a sensory perception of the world. Despite recent advances in understanding visual and auditory perception, olfactory perception remains an under-explored topic in the machine learning community due to the lack of large-scale datasets annotated with labels of human olfactory perception. In this work, we ask the question of whether pre-trained transformer models of chemical structures encode representations that are aligned with human olfactory perception, i.e., can transformers smell like humans? We demonstrate that representations encoded from transformers pre-trained on general chemical structures are highly aligned with human olfactory perception. We use multiple datasets and different types of perceptual representations to show that the representations encoded by transformer models are able to predict: (i) labels associated with odorants provided by experts; (ii) continuous ratings provided by human participants with respect to pre-defined descriptors; and (iii) similarity ratings between odorants provided by human participants. Finally, we evaluate the extent to which this alignment is associated with physicochemical features of odorants known to be relevant for olfactory decoding.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Photon Image-Guided Automated 3D Locating of Micropipette Tip

Two-Photon Image-Guided Automated 3D Locating of Micropipett...

引用

第43届中国控制会议

作者： Zizhen Li Jie Li Qili Zhao Xin Zhao Mingzhu Sun National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Tianjin Key Laboratory of Intelligent Robotics (tikLIR) Institute of Robotics and Automatic Information System (IRAIS) Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The 21st century has been universally recognized by the scientific community as the era of neuroscience, with the patch clamp technique serving as a key to unraveling the intricate mysteries of brain science. Due to its advantages such as reduced sample damage and enhanced penetration capability, the application of two-photon microscope in deep imaging of live animals has become prevalent, making it a preferred choice over confocal microscope. At present, there exist a few near complete automation techniques of image-guided patching in vivo, which typically start from the micropipette tip appearing in the imaging field of view. The operational workflow for the step involving the installation of the micropipette until the micropipette tip becomes visible within the field of view has regrettably not been provided. However, it is crucial information that is of utmost importance to experimental personnel. In this paper, we present a comprehensive workflow for 3D locating of micropipette tip in a self-built two-photon microscope tailored for patch clamp experiments. Moreover, by fully incorporating the distinctive features of two-photon imaging, the study applies statistical methods to achieve automated execution of the corresponding workflow. The experimental results indicate that the process of micropipette tip locating takes an average of 58.4 ***, the method is not sensitive to parameter selection, allowing experimenters to obtain suitable parameters for different systems through simple testing. The automated 3D micropipette tip locating method proposed in this paper, with its versatility, holds great potential for seamless integration into commercial two-photon microscope systems. It significantly contributes to reducing the work burden on experimenters and minimizing the time required for experimental preparation.

关键词： 3D micropipette tip locating two-photon microscope automated method

来源：评论

学校读者我要写书评

暂无评论

Integration of Partially Prior Physics and Data for Longitudinal Vehicle Dynamics Restoration 24

Integration of Partially Prior Physics and Data for Longitud...

引用

24th COTA International Conference of Transportation Professionals: Resilient, intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Wang, Yongsheng Xu, Bingrong Chu, Duanfeng Ding, Naikan Yin, Jianhua School of Information Engineering Wuhan Univ. of Technology Wuhan China School of Automation Wuhan Univ. of Technology Wuhan China Intelligent Transportation Systems Research Center Wuhan Univ. of Technology Wuhan China Chongqing Research Institute Wuhan Univ. of Technology Chongqing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

Vehicle dynamics model is critical for autonomous vehicles since it provides certain rules of motion in response to the surrounding rapidly changing environment. However, current pure physics-based models and data-driven approaches are set against each other in constructing the dynamics model. In this work, we propose a vehicle dynamics restoration approach by integrating physics principles and data based on physics-informed machine learning. The vehicle dynamics model parameters are estimated by combining data and limited prior physical knowledge. The results of a case study demonstrate that (1) the proposed methods can accurately identify the dynamics model parameters and restore the vehicle dynamics model and (2) the neural network with physical knowledge can accurately predict the state of vehicle. The proposed method has the potential to be applied in quantifying the dynamics model uncertainty due to parameter uncertainty, and stochastic motion planning and control due to uncertainty, which will be further investigated in the future. © ASCE.

关键词： Stochastic programming

来源：评论

学校读者我要写书评

暂无评论

MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation 38

MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Luo, Jialin Wang, Yuanzhi Gu, Ziqi Qiu, Yide Yao, Shuaizhen Wang, Fuyun Xu, Chunyan Zhang, Wenhua Wang, Dan Cui, Zhen PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Beijing Institute of Spacecraft System Engineering Beijing China

Recently, the diffusion-based generative paradigm has achieved impressive general image generation capabilities with text prompts due to its accurate distribution modeling and stable training process. However, generating diverse remote sensing (RS) images that are tremendously different from general images in terms of scale and perspective remains a formidable challenge due to the lack of a comprehensive remote sensing image generation dataset with various modalities, ground sample distances (GSD), and scenes. In this paper, we propose a Multi-modal, MultiGSD, Multi-scene Remote Sensing (MMM-RS) dataset and benchmark for text-to-image generation in diverse remote sensing scenarios. Specifically, we first collect nine publicly available RS datasets and conduct standardization for all samples. To bridge RS images to textual semantic information, we utilize a large-scale pretrained vision-language model to automatically output text prompts and perform hand-crafted rectification, resulting in information-rich text-image pairs (including multi-modal images). In particular, we design some methods to obtain the images with different GSD and various environments (e.g., low-light, foggy) in a single sample. With extensive manual screening and refining annotations, we ultimately obtain a MMM-RS dataset that comprises approximately 2.1 million text-image pairs. Extensive experimental results verify that our proposed MMM-RS dataset allows off-the-shelf diffusion models to generate diverse RS images across various modalities, scenes, weather conditions, and GSD. The dataset is available at https://***/ljl5261/MMM-RS. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLM-BT: Performing Robotic Adaptive Tasks based on Large Language Models and Behavior Trees

arXiv

引用

arXiv 2024年

作者： Zhou, Haotian Lin, Yunhan Yan, Longwu Zhu, Jihong Min, Huasong Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China The School of Physics Engineering and Technology University of York United Kingdom

Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Study on Vehicle Recognition Algorithm Based on Convolutional Neural Network

Study on Vehicle Recognition Algorithm Based on Convolutiona...

引用

Communications technology and Computer Science (ACCTCS), Asia-Pacific Conference on

作者： Bi Wenkai Department of Intelligent Information Systems and Technology Moscow Institute of Physics and Technology Moscow Russia

As the application of vehicles expands, the types of vehicles have also become increasingly diverse. While vehicles bring convenience to daily life, they also pose certain traffic hazards due to their different types, such as large transport vehicles entering main roads and violations in prohibited areas and dedicated lanes. Therefore, it has become important to classify and manage actual vehicles. In the field of image processing, the key to vehicle classification is to design classifiers and classify images accordingly. Against this backdrop, relevant classifier algorithms are studied, and classifier design and optimization are completed. Currently, convolutional neural networks (CNN) have been widely applied in image processing and achieved good classification results. To address the issue of actual vehicle classification, this paper selects classic convolutional models, including LeNet5, VGG16, and ResNet50, for transfer learning. The image enhancement processing and optimizer selection are conducted to achieve the final classification. After multiple parameter iterations and comparative experiments, the optimal algorithm combination of VGG16 model, cross-entropy function, and Adam optimizer is selected. The validation accuracy rate of the last iteration under this algorithm combination is 93%, and the optimal accuracy rate throughout the entire training process is 94%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of an in vitro perfusable neural interface model for sequential connection of nerve cells

Development of an in vitro perfusable neural interface model...

引用

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Menghua Liu Huaping Wang Qing Shi Yaozhen Hou Jiaxin Liu Tao Sun Qiang Huang Toshio Fukuda Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

Neural interface models based on microfluidic chips are widely used in the regeneration of neural interfaces in vitro for their low cost, simple structure and accurate simulation of complex interactions between cells and the extracellular environment. However, due to the lack of influence of the dynamic flow environment, it is difficult to realize the reduction of cell culture and the cell growth environment for a long time while forming sequential connections between cells. Here,we propose an in vitro perfusable culture chip as a neural interface for neuroblastoma cells (SH-SY5Y cells) to realize sequential cell connection under dynamic perfusion and physical guidance. A microfluidic chip with physical guidance was fabricated based on soft lithography. The microfluidic chip can realize long-term cell culture under dynamic perfusion conditions by an automatic perfusion system in vitro. The interior of the microfluidic chip is optimized to provide physical cues for SH-SY5Y cells to construct nerve conduction microunits. The microfluidic chip has great potential in the research of in vitro neural interface regeneration models in dynamic complex environments.

关键词： Soft lithography Costs Biological system modeling Neurons In vitro Extracellular Microfluidics

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：