检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kruzhkov, Evgenii Savinykh, Alena Behnke, Sven Autonomous Intelligent Systems Computer Science Institute VI University of Bonn Bonn Germany Autonomous Intelligent Systems Computer Science Institute VI – Intelligent Systems and Robotics Center for Robotics Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Bonn Germany

Robotic applications require a comprehensive understanding of the scene. In recent years, neural fields-based approaches that parameterize the entire environment have become popular. These approaches are promising due to their continuous nature and their ability to learn scene priors. However, the use of neural fields in robotics becomes challenging when dealing with unknown sensor poses and sequential measurements. This paper focuses on the problem of sensor pose estimation for large-scale neural implicit SLAM. We investigate implicit mapping from a probabilistic perspective and propose hierarchical pose estimation with a corresponding neural network architecture. Our method is well-suited for large-scale implicit map representations. The proposed approach operates on consecutive outdoor LiDAR scans and achieves accurate pose estimation, while maintaining stable mapping quality for both short and long trajectories. We built our method on a structured and sparse implicit representation suitable for large-scale reconstruction and evaluated it using the KITTI and MaiCity datasets. Our approach outperforms the baseline in terms of mapping with unknown poses and achieves state-of-the-art localization accuracy. © 2024, CC BY-NC-ND.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

DEALING WITH NON-STATIONARITY IN MARL VIA TRUST-REGION DECOMPOSITION 10

DEALING WITH NON-STATIONARITY IN MARL VIA TRUST-REGION DECOM...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Li, Wenhao Wang, Xiangfeng Jin, Bo Sheng, Junjie Zha, Hongyuan School of Computer Science and Technology East China Normal University Shanghai China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning (MARL). One of the reasons is the policy changes of agents during the learning process. Some existing works have discussed various consequences caused by non-stationarity with several kinds of measurement indicators. This makes the objectives or goals of existing algorithms are inevitably inconsistent and disparate. In this paper, we introduce a novel notion, the δ-stationarity measurement, to explicitly measure the non-stationarity of a policy sequence, which can be further proved to be bounded by the KL-divergence of consecutive joint policies. A straightforward but highly non-trivial way is to control the joint policies' divergence, which is difficult to estimate accurately by imposing the trust-region constraint on the joint policy. Although it has lower computational complexity to decompose the joint policy and impose trust-region constraints on the factorized policies, simple policy factorization like mean-field approximation will lead to more considerable policy divergence, which can be considered as the trust-region decomposition dilemma. We model the joint policy as a pairwise Markov random field and propose a trust-region decomposition network (TRD-Net) based on message passing to estimate the joint policy divergence more accurately. The Multi-Agent Mirror descent policy algorithm with Trust region decomposition, called MAMT, is established by adjusting the trust-region of the local policies adaptively in an end-to-end manner. MAMT can approximately constrain the consecutive joint policies' divergence to satisfy δ-stationarity and alleviate the non-stationarity problem. Our method can bring noticeable and stable performance improvement compared with baselines in cooperative tasks of different complexity. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

SEPL-Net: A Semantics-Enhanced Pseudo Labeling Network for Semi-Supervised Image Analysis

SEPL-Net: A Semantics-Enhanced Pseudo Labeling Network for S...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Xiao, Wenjing Hwang, Kai Chen, Min Li, Xianzhi School of Computer Science and Technology Huazhong University of Science and Technology China School of Data Science Chinese University of Hong Kong Hong Kong The Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

As the mainstream solution for semi-supervised learning (SSL), pseudo-labeling-based approaches have achieved re-markable success. However, an obvious drawback of existing methods is that the valuable semantic relationships among categories are often ignored, thus leading to suboptimal encoded embeddings. To address this, we present a novel Semantics-Enhanced Pseudo Labeling Network, called SEPL-Net, for image analysis in a semi-supervised manner. SEPL-Net explores the prior knowledge of visual similarity between different classes to improve the quality of pseudo label decision making. Particularly, we encode semantic labels combined with the one-hot label to jointly train our network by exploiting their disagreement. To alleviate the difficulty of labeling unlabeled images due to the introduction of semantic labels, we further design different classifiers with differentiated strong augmentation modes to enable cooperative pseudo labeling. Extensive experimental results show that our SEPL-Net outperforms existing SSL methods with the averaged 1.84% accuracy improvement on image classification task. Code is available at https://***/sweetvicky/***. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Surface Defects Detection of Cylindrical High-Precision Industrial Parts Based on Deep Learning Algorithms: A Review

引用

Operations Research Forum 2024年第3期5卷 58页

作者： Wei, Li Solihin, Mahmud Iwan Saruchi, Sarah ‘Atifah Astuti, Winda Hong, Lim Wei Kit, Ang Chun School of Computer Science and Technology (School of Software) Guangxi University of Science and Technology Guangxi 545006 China Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur 56000 Malaysia Faculty of Manufacturing and Mechatronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Computer Engineering Department Automotive and Robotics Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

High-precision cylindrical parts are critical components across various industries including aerospace, automotive, and manufacturing. Since these parts play a pivotal role in the performance and safety of the systems they are integrated into, they are often subject to stringent quality control measures. Defects on the interior and exterior wall surfaces of these cylindrical parts can severely undermine their function, leading to degraded performance, increased wear, and even catastrophic failures in extreme cases. This article aims to comprehensively summarize the task definition, challenges, mainstream methods, public datasets, evaluation metrics, and other aspects of surface defect detection for high-precision cylindrical parts, in order to help researchers quickly grasp this field. Specifically, the background and characteristics of industrial defect detection are first introduced. Owing to the unique geometric features of cylindrical part surfaces, algorithms and equipment for image data acquisition used in surface defect detection are elaborated in detail. This article presents an extensive overview of state-of-the-art surface defect detection techniques designed for high-precision cylindrical components, all rooted in deep learning. The methods are systematically classified into three main categories: fully supervised, unsupervised, and alternative approaches, based on their data labeling strategies. Additionally, the paper conducts a comprehensive analysis within each category, shedding light on their unique strengths, limitations, and practical use cases. Concluding the discussion, the paper provides insights into future development trends and potential research directions in this field that will lead to manufacturing innovation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection computer vision Deep learning Defect detection High-precision cylindrical parts Image processing Optical illumination

来源：评论

学校读者我要写书评

暂无评论

Onboard Perception-Assisted High Fidelity Simulation Framework for Autonomous Planetary Soft-Landing

Onboard Perception-Assisted High Fidelity Simulation Framewo...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Alibekov, Ulugbek Banerjee, Avijit Satpute, Sumeet Gajanan Nikolakopoulos, George ERASMUS MUNDUS JOINT MASTER in Intelligent Field Robotic Systems Faculty of Informatics Eötvös Loránd University Budapest Hungary Robotics and AI research group Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This article presents an onboard perception-assisted high-fidelity simulation framework for autonomous planetary soft-landing, enabling visual information processing tightly integrated with advanced onboard guidance system in a realistic simulation environments. Utilizing the open source Unity game engine, a physics-based simulation toolbox integrated with the Robotic Operating System (ROS2), we effectively emulate the motion of spacecraft approaching planetary terrain. The simulation environment features a realistic 3D terrain model and a lander spacecraft equipped with onboard camera to effectively capture detailed local terrain images. The simulation engine accurately captures the spacecraft’s 6-degrees of freedom motion, seamlessly integrating space craft orientation with the associated camera feed while incorporating various illumination conditions using a light source representing the Sun. To demonstrate the efficacy of the framework, we implement a recently developed attitude-constrained minimum jerk guidance algorithm to emulate spacecraft motion. Concurrently, the visual feed from the onboard RGB camera is processed through a gradient extraction-based perception system, providing the visual odometer. This system identifies provably safe landing sites, effectively avoiding potential risks of landing on uneven terrain. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Planetary landers

来源：评论

学校读者我要写书评

暂无评论

Modal Synthesis of Interval Systems with Aperiodic Transients

Modal Synthesis of Interval Systems with Aperiodic Transient...

引用

International Conference on Computation, Automation and Knowledge Management (ICCAKM)

作者： Tatiana Ezangina Sergey Gayvoronskiy Alexander Sobol School of computer Science & Robotics National Research Tomsk Polytechnic University Tomsk Russia

ISBN: (数字)9798350393248

ISBN: (纸本)9798350393255

The system of automatic control of an object with interval parameters is considered. Its model is represented by a characteristic polynomial with interval coefficients, which linearly include adjustable controller parameters. The problem of determining their values for which the system has an aperiodic transient process is solved. The decision is based on the desired location of the segment of the dominant real pole of the system in accordance with the principle of dominant poles.

关键词： Uncertainty Automation Transfer functions Process control Control systems Stability analysis Knowledge management

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Bengali Visual Question Answering System 25

A Deep Learning-Based Bengali Visual Question Answering Syst...

引用

25th International Conference on computer and Information Technology, ICCIT 2022

作者： Rafi, Mahamudul Hasan Islam, Shifat Hasan Imtiaz Labib, S.M. Hasan, Sm Sajid Shah, Faisal Muhammad Ahmed, Sifat Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Engineering and Technology Department of Computer Science and Engineering Dhaka Bangladesh Robotics & Artificial Intelligence Environmental Intelligence & Innovation Co. Ltd. Tokyo Japan

ISBN: (纸本)9798350346022

Visual Question Answering (VQA) is a challenging task in Artificial Intelligence (AI), where an AI agent answers questions regarding visual content based on images provided. Therefore, to implement a VQA system, a computer system requires complex reasoning over visual aspects of images and textual parts of the questions to anticipate the correct answer. Although there is a good deal of VQA research in English, Bengali still needs to thoroughly explore this area of artificial intelligence. To address this, we have constructed a Bengali VQA dataset by preparing human-annotated question-answers using a small portion of the images from the VQA v2.0 dataset. To overcome high linguistic priors that hide the importance of precise visual information in visual question answering, we have used real-life scenarios to construct a balanced Bengali VQA dataset. This is the first human-annotated dataset of this kind in Bengali. We have proposed a Top-Down Attention-based approach in this study and conducted several studies to assess our model's performance. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service robotics

arXiv

引用

arXiv 2024年

作者： Bode, Jonas Pätzold, Bastian Memmesheimer, Raphael Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI – Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics University of Bonn Germany

Recent advances in Large Language Models (LLMs) have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLMs to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models. We make our code, including all prompts, available at https://***/AIS-Bonn/Prompt_Engineering. Copyright © 2024, The Authors. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Human Multi-dimensional Stiffness Skills Transfer for Robot Teleoperation System

Human Multi-dimensional Stiffness Skills Transfer for Robot ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Situ, Liwen Lu, Zhenyu Si, Weiyong Yang, Chenguang College of Automation Science and Engineering South China University of Technology Guangzhou510640 China University of the West of England Bristol Robotics Laboratory BristolBS161QY United Kingdom University of Liverpool Department of Computer Science LiverpoolL69 3BX United Kingdom

ISBN: (纸本)9781665410205

Neuroscience research has demonstrated the sig-nificance of modulating stiffness during human task performance. Similarly, endowing robots with such capability is expected. However, existing methods for robot teleoperation require operators to simultaneously control position and stiffness, resulting in high workload and task inefficiency. On the other hand, learning from demonstration (LfD) offers a feasible approach for autonomously generating stiffness. Therefore, this paper proposes a robot teleoperation system that combines the advantages of teleoperation and LfD. Teleoperation enables precise positioning guided by human operators, while LfD can transfer human stiffness skills to robots. A teleoperation-oriented stiffness-adaptive Gaussian Mixture Model/Gaussian Mixture Regression method is proposed to learn human multi-dimensional stiffness and reproduce robot stiffness on a Riemannian manifold. To enhance generalization and cooperate with teleoperation, reference points and position-driven output are introduced. Furthermore, a teleoperation strategy for both the single-leader-single-follower configuration and the single-leader-dual-follower configuration are designed, which allows operators to control either one or two robot arms with a single leader device. Finally, the effectiveness of our method is verified through a plugging-in task and a continuous flipping task, demonstrating that the proposed system is capable of performing tasks that demand high positioning accuracy and stiffness adjustment. A supplementary video for this paper is available in GitHub∗∗https://***/setowenGit/TOSA-GMM-GMR-Video. © 2024 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Self-Centering 3-DoF Feet Controller for Hands-Free Locomotion Control in Telepresence and Virtual Reality

arXiv

引用

arXiv 2024年

作者： Memmesheimer, Raphael Lenz, Christian Schwarz, Max Schreiber, Michael Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI - Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics University of Bonn Germany

We present a novel seated feet controller for handling 3 Degree of Freedom (DoF) aimed to control locomotion for telepresence robotics and virtual reality environments. Tilting the feet on two axes yields in forward, backward and sideways motion. In addition, a separate rotary joint allows for rotation around the vertical axis. Attached springs on all joints self-center the controller. The HTC Vive tracker is used to translate the trackers' orientation into locomotion commands. The proposed self-centering feet controller was used successfully for the ANA Avatar XPRIZE competition, where a naive operator traversed the robot through a longer distance, surpassing obstacles while solving various interaction and manipulation tasks in between. We publicly provide the models of the mostly 3D-printed feet controller for reproduction. Copyright © 2024, The Authors. All rights reserved.

关键词： Biped locomotion

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：