检索结果-内蒙古大学图书馆

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Saito, Daichi Kanehira, Atsushi Sasabuchi, Kazuhiro Wake, Naoki Takamatsu, Jun Koike, Hideki Ikeuchi, Katsushi Institute of Science Tokyo Department of Computer Science Tokyo Japan Applied Robotics Research Microsoft RedmondWA United States

ISBN: (纸本)9798350373578

In-hand tool manipulation is an operation that not only manipulates a tool within the hand (i.e., in-hand manipulation) but also achieves a grasp suitable for a task after the manipulation. This study aims to achieve an in-hand tool manipulation skill through deep reinforcement learning. The difficulty of learning the skill arises because this manipulation requires (A) exploring long-term contact-state changes to achieve the desired grasp and (B) highly-varied motions depending on the contact-state transition. (A) leads to a sparsity of a reward on a successful grasp, and (B) requires an RL agent to explore widely within the state-action space to learn highly-varied actions, leading to sample inefficiency. To address these issues, this study proposes Action Primitives based on Contact-state Transition (APriCoT). APriCoT decomposes the manipulation into short-term action primitives by describing the operation as a contact-state transition based on three action representations (detach, crossover, attach). In each action primitive, fingers are required to perform short-term and similar actions. By training a policy for each primitive, we can mitigate the issues from (A) and (B). This study focuses on a fundamental operation as an example of in-hand tool manipulation: rotating an elongated object grasped with a precision grasp by half a turn to achieve the initial grasp. Experimental results demonstrated that ours succeeded in both the rotation and the achievement of the desired grasp, unlike existing studies. Additionally, it was found that the policy was robust to changes in object shape. © 2024 IEEE.

关键词： Hand tools

来源：评论

学校读者我要写书评

暂无评论

Analysis of Hardware-Implemented U-Net–Like Convolutional Neural Networks 6th

Analysis of Hardware-Implemented U-Net–Like Convolutional N...

引用

6th International conference on Software Testing, Machine Learning and Complex Process Analysis, TMPA 2021

作者： Ivan, Zoev Konstantin, Maslov Nikolay, Markov Evgeniy, Mytsko School of Computer Science and Robotics Tomsk Polytechnic University 30 Lenin Avenue Tomsk634050 Russia

ISBN: (纸本)9783031504228

Two convolutional neural networks (CNNs)—modification of classic U-Net and U-Net with the use of dilated convolutions—were implemented. In order to train and test the CNNs, we utilised unmanned aerial vehicle images containing Abies sibirica trees damaged by Polygraphus proximus. The images consist five classes: four classes of the trees depending on their condition and background. The weights of the CNNs, obtained as a result of the training, were then used to implement the CNNs in the field-programmable gate array–based system on a chip platform (Xilinx Zynq 7000). The paper also presents a comparison of the hardware-implemented CNNs in terms of segmentation quality and time efficiency. © 2024, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Hardware and Software Integration of Machine Learning Vision System Based on NVIDIA Jetson Nano 1

引用

Future of Information and Communication Conference, FICC 2024

作者： Manolescu, Denis Reid, David Secco, Emanuele Lindo Robotics Lab School of Mathematics Computer Science and Engineering Liverpool Hope University Liverpool United Kingdom

ISBN: (数字)9783031540530

ISBN: (纸本)9783031540523

This study investigates the capabilities and flexibility of edge devices for real-time data processing near the source. A configurable Nvidia Jetson Nano system is used to deploy nine pre-trained computer vision models, demonstrating proficiency in local data processing, analysis and providing real-time feedback. Additionally, the system offers deployment control via a customized Graphical User Interface (GUI) and proves very low-latency inference re-stream to other local devices using the G-Streamer framework. The Machine Learning models which cover a wide range of applications, including image classification, object recognition or detection, depth estimation and semantic segmentation, show potential for IoT and industrial applications. Further, the fusion of these capabilities with AI and machine learning algorithms unveils a promising perspective for substantial industrial redevelopment. This research underscores the strategic significance of edge devices in modern computational frameworks and their potential role in future technological advancements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection 7

FlowBot++: Learning Generalized Articulated Objects Manipula...

引用

7th Conference on Robot Learning, CoRL 2023

作者： Zhang, Harry Eisner, Ben Held, David Robotics Institute School of Computer Science Carnegie Mellon University United States

Understanding and manipulating articulated objects, such as doors and drawers, is crucial for robots operating in human environments. We wish to develop a system that can learn to articulate novel objects with no prior interaction, after training on other articulated objects. Previous approaches for articulated object manipulation rely on either modular methods which are brittle or end-to-end methods, which lack generalizability. This paper presents FlowBot++, a deep 3D vision-based robotic system that predicts dense per-point motion and dense articulation parameters of articulated objects to assist in downstream manipulation tasks. FlowBot++ introduces a novel per-point representation of the articulated motion and articulation parameters that are combined to produce a more accurate estimate than either method on their own. Simulated experiments on the PartNet-Mobility dataset validate the performance of our system in articulating a wide range of objects, while real-world experiments on real objects' point clouds and a Sawyer robot demonstrate the generalizability and feasibility of our system in real-world scenarios. Videos are available on our anonymized website here. © 2023 Proceedings of Machine Learning Research. All Rights Reserved.

关键词： 3D Learning Articulated Objects Manipulation

来源：评论

学校读者我要写书评

暂无评论

Person Segmentation and Action Classification for Multi-Channel Hemisphere Field of View LiDAR Sensors

Person Segmentation and Action Classification for Multi-Chan...

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Seliunina, Svetlana Otelepko, Artem Memmesheimer, Raphael Behnke, Sven University of Bonn Autonomous Intelligent Systems Group Computer Science Institute VI - Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Center for Robotics Germany

ISBN: (纸本)9798331531614

Robots need to perceive persons in their surroundings for safety and to interact with them. In this paper, we present a person segmentation and action classification approach that operates on 3D scans of hemisphere field of view LiDAR sensors. We recorded a data set with an Ouster OSDome-64 sensor consisting of scenes where persons perform three different actions and annotated it. We propose a method based on a MaskDINO model to detect and segment persons and to recognize their actions from combined spherical projected multi-channel representations of the LiDAR data with an additional positional encoding. Our approach demonstrates good performance for the person segmentation task and further performs well for the estimation of the person action states walking, waving, and sitting. An ablation study provides insights about the individual channel contributions for the person segmentation task. The trained models, code and dataset are made publicly available. © 2025 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Fusion of Feature Ranking Methods for an Effective Intrusion Detection System

引用

computers, Materials & Continua 2023年第8期76卷 1721-1744页

作者： Seshu Bhavani Mallampati Seetha Hari School of Computer Science and Engineering VIT-AP UniversityAndhra PradeshIndia Center of Excellence AIand RoboticsVIT-AP UniversityAndhra PradeshIndia

Expanding internet-connected services has increased cyberattacks,many of which have grave and disastrous *** Intrusion Detection System(IDS)plays an essential role in network security since it helps to protect the network from vulnerabilities and *** extensive research was reported in IDS,detecting novel intrusions with optimal features and reducing false alarm rates are still ***,we developed a novel fusion-based feature importance method to reduce the high dimensional feature space,which helps to identify attacks accurately with less false alarm ***,to improve training data quality,various preprocessing techniques are *** Adaptive Synthetic oversampling technique generates synthetic samples for minority *** the proposed fusion-based feature importance,we use different approaches from the filter,wrapper,and embedded methods like mutual information,random forest importance,permutation importance,Shapley Additive exPlanations(SHAP)-based feature importance,and statistical feature importance methods like the difference of mean and median and standard deviation to rank each feature according to its *** by simple plurality voting,the most optimal features are *** the optimal features are fed to various models like Extra Tree(ET),Logistic Regression(LR),Support vector Machine(SVM),Decision Tree(DT),and Extreme Gradient Boosting Machine(XGBM).Then the hyperparameters of classification models are tuned with Halving Random Search cross-validation to enhance the *** experiments were carried out on the original imbalanced data and balanced *** outcomes demonstrate that the balanced data scenario knocked out the imbalanced ***,the experimental analysis proved that our proposed fusionbased feature importance performed well with XGBM giving an accuracy of 99.86%,99.68%,and 92.4%,with 9,7 and 8 features by training time of 1.5,4.5 and 5.5 s on Network Security Laborat

关键词： Cyber security feature ranking imbalance preprocessing IDS SHAP

来源：评论

学校读者我要写书评

暂无评论

Collaborate and Explain on the Fly: Nonmonotonic Logical Reasoning and Incremental Learning for Ad Hoc Teamwork 21

Collaborate and Explain on the Fly: Nonmonotonic Logical Rea...

引用

21st International Workshop on Non-Monotonic Reasoning, NMR 2023

作者： Dodampegama, Hasra Sridharan, Mohan Intelligent Robotics Lab School of Computer Science University of Birmingham United Kingdom

This paper describes an architecture for ad hoc teamwork, i.e., to enable an agent to collaborate with other agents "on the fly". State of the art frameworks for ad hoc teamwork often pursue a data-driven approach, using a large labeled dataset of prior observations to model the behavior of other agents and to determine the ad hoc agent’s behavior. These models are computationally expensive to learn, lack transparency, and make it difficult to recognize and adapt to previously unseen changes. In a departure from existing work, we introduce an architecture for ad hoc teamwork that performs non-monotonic logical reasoning with prior commonsense domain knowledge and models that are learned and revised rapidly from limited examples to predict the behavior of other agents. In addition, the architecture enables the agent to provide relational descriptions as on-demand explanations of its decisions and beliefs in response to different types of questions. We evaluate the architecture’s capabilities in two benchmark multiagent collaboration domains: Fort Attack and Half field Offense, in comparison with data-driven and knowledge-driven baselines. © 2023 Copyright for this paper by its authors.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Cognitive Architecture for Integrated Robot Systems

A Cognitive Architecture for Integrated Robot Systems

引用

2023 International Workshop on Cognitive AI, CogAI 2023

作者： Sridharan, Mohan Intelligent Robotics Lab School of Computer Science University of Birmingham United Kingdom

This paper describes an integrated architecture for robots that combines knowledge-based and data-driven methods for transparent reasoning, control, and learning. Specifically, the architecture builds on the principle of step-wise iterative refinement to support non-monotonic logical reasoning and probabilistic reasoning with tightly-coupled transition diagrams of the domain at different resolutions. Reasoning with prior domain knowledge and heuristic methods guide the interactive learning and revision of knowledge in the form of axioms governing change, predictive models controlling the robot's movement, and predictive models of the behavior of other agents. Furthermore, the interplay between these components is used to embed the principles of explainable agency, enabling a robot to provide on-demand relational descriptions of its decisions and beliefs in response to different types of questions. © 2023 Copyright for this paper by its authors.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

A study on Automated railway level crossing control system using FMCW radar for accident prevention 28

A study on Automated railway level crossing control system u...

引用

28th International Conference on Applied Electronics, AE 2023

作者： Greitans, Kristaps Maris Institute of Electronics and Computer Science Robotics and Machine Perceptions Laboratory Riga Latvia

ISBN: (纸本)9798350335538

This study paper explores the implementation of Intelligent Transportation Systems (ITS) in railway transportation, with a focus on level crossings, which have been a significant issue in railway safety. The paper discusses the limitations of current technologies such as laser technology and video surveillance and presents a novel solution utilizing a 79GHz Frequency Modulated Continuous Wave (FMCW) radar in combination with a CCTV camera for a dual sensor module. The FMCW radar is shown to be more accurate and cost-effective than previous technologies and can detect both large and small objects in the defined area at level crossings and difficult weather situations. The paper also presents a system architecture that takes into account vehicle detection time, which is crucial in reducing the risk of accidents and improving the safety of level crossings. This study aimed to compare the performance of different object detection modules under varying weather conditions. Three object detection methods were tested: a camera with the object detection algorithm Yolov5, FMCW radar with a built-in tracker, and manual observation. Four measurement sessions were conducted, each with a different combination of weather and time of day. The results showed that all modules performed similarly well under clear weather conditions, with the camera and radar modules detecting all vehicles approaching. However, under rainy and dark conditions, the radar module outperformed the camera, detecting 5 more objects. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Dynamic Inversion-based Motion Planning of a Floating Satellite Platform

Nonlinear Dynamic Inversion-based Motion Planning of a Float...

引用

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

作者： Banerjee, Avijit Tevetzidis, Ilias Satpute, Sumeet Gajanan Nikolakopoulos, George 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 a nonlinear dynamic inversion-based motion plan for a levitating robotic satellite emulation platform. The frictionless motion of such a levitating platform has dynamic equivalency with a satellite’s realistic movement in space, thus evolving as an efficient demonstration tool as a hardware-in-loop satellite motion simulator. A brief design description of the emulation platform unified with various sensor and actuator units is presented, and an associated nonlinear mathematical model representing its coupled dynamic motion is described. The proposed control design architecture manipulates the associated nonlinear dynamics, which appear due to the coupling of translational and rotational movement of the robotic platform, thereby establishing an efficient trajectory tracking capability for various operating regions without the additional requirement of gain scheduling. In order to realize the control requirement through a set of ON-OFF thruster-based actuation units, which closely resembles the reaction control system of realistic satellite design, an optimal thrust allocation logic is proposed that accounts for various physical limitations of thrusters such as thrusters as its magnitude constraint and minimum on time. The efficacy of the proposed modelling and control scheme is experimentally validated in different realistic motion planning scenarios, such as point-to-point manoeuvres with terminal objectives and a superior path-following capability. The experimental studies are supported with related results. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Motion planning

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：