检索结果-内蒙古大学图书馆

2024 International conference on Intelligent robots and Systems

作者： Wang, Junbo Liu, Wenhai Yu, Qiaojun You, Yang Liu, Liu Wang, Weiming Lu, Cewu Shanghai Jiao Tong Univ Shanghai Peoples R China Stanford Univ Stanford CA 94305 USA Hefei Univ Technol Hefei Anhui Peoples R China

ISBN: (纸本)9798350377712;9798350377705

Articulated objects are commonly found in daily life. It is essential that robots can exhibit robust perception and manipulation skills for articulated objects in real-world robotic applications. However, existing methods for articulated objects insufficiently address noise in point clouds and struggle to bridge the gap between simulation and reality, thus limiting the practical deployment in real-world scenarios. To tackle these challenges, we propose a framework towards Robust Perception and Manipulation for Articulated Objects (RPMArt), which learns to estimate the articulation parameters and manipulate the articulation part from the noisy point cloud. Our primary contribution is a Robust Articulation Network (RoArtNet) that is able to predict both joint parameters and affordable points robustly by local feature learning and point tuple voting. Moreover, we introduce an articulation-aware classification scheme to enhance its ability for sim-to-real transfer. Finally, with the estimated affordable point and articulation joint constraint, the robot can generate robust actions to manipulate articulated objects. After learning only from synthetic data, RPMArt is able to transfer zero-shot to real-world articulated objects. Experimental results confirm our approach's effectiveness, with our framework achieving state-of-the-art performance in both noise-added simulation and real-world environments. Code, data and more results can be found on the project website at https://***.

关键词： robot applications

来源：评论

学校读者我要写书评

暂无评论

Software Framework of Autonomous Mobile robots on Isaac Sim and ROS 11

Software Framework of Autonomous Mobile Robots on Isaac Sim ...

引用

11th International conference on Control, Mechatronics and Automation (ICCMA)

作者： Jiono, Mahfud Lin, Hsien-I Natl Taipei Univ Technol Coll Mech & Elect Engn Taipei 10608 Taiwan Natl Yang Ming Chiao Tung Univ Inst Elect & Control Engn Hsinchu 30010 Taiwan

ISBN: (纸本)9798350315684

The purpose of this research is to address the increasing significance of autonomous mobile robots (AMR) in military applications. Several researchers have made significant investments in AMR development, recognizing the urgency of enhancing their capabilities in preparation for potential threats in factory environments. The research aims to integrate key technologies essential for polishing robots in the factory using Isaac Sim and the ROS framework. This includes the use of AI and sensor fusion technology for robot movement, as well as for detecting and tracking obstacles, target objects, and the formation control of the AMR itself. The outcomes of our experiments have been promising. We have effectively defined and executed a sequence of arm robot positions. The robots start from the initial position, proceed to the predetermined second point, and subsequently advance to the position goal point before returning to their starting point. Concerning mobile robot movement control, we have established target positions to demonstrate the robot's capabilities.

关键词： AMR robot robot formation control Isaac Sim simulation ROS framework

来源：评论

学校读者我要写书评

暂无评论

Reusable Architecture Growth for Continual Stereo Matching

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第9期46卷 6167-6184页

作者： Zhang, Chenghao Meng, Gaofeng Fan, Bin Tian, Kun Zhang, Zhaoxiang Xiang, Shiming Pan, Chunhong Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci HK Inst Sci & Innovat Ctr Artificial Intelligence & Robot Beijing 100190 Peoples R China Univ Sci & Technol Beijing Sch Intelligence Sci & Technol Beijing 100083 Peoples R China Univ Sci & Technol Beijing Inst Artificial Intelligence Beijing 100083 Peoples R China

The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogeneous scenes at deployment time. However, training samples are typically acquired continuously in practical applications, making the capability to learn new scenes continually even more crucial. For this purpose, we propose to perform continual stereo matching where a model is tasked to 1) continually learn new scenes, 2) overcome forgetting previously learned scenes, and 3) continuously predict disparities at inference. We achieve this goal by introducing a Reusable Architecture Growth (RAG) framework. RAG leverages task-specific neural unit search and architecture growth to learn new scenes continually in both supervised and self-supervised manners. It can maintain high reusability during growth by reusing previous units while obtaining good performance. Additionally, we present a Scene Router module to adaptively select the scene-specific architecture path at inference. Comprehensive experiments on numerous datasets show that our framework performs impressively in various weather, road, and city circumstances and surpasses the state-of-the-art methods in more challenging cross-dataset settings. Further experiments also demonstrate the adaptability of our method to unseen scenes, which can facilitate end-to-end stereo architecture learning and practical deployment.

关键词： Task analysis Adaptation models Costs Training Clouds Three-dimensional displays Sensors Architecture growth continual learning deep learning domain adaptation stereo matching

来源：评论

学校读者我要写书评

暂无评论

Robust Facial Emotion Detection in Low-Light Conditions: A Novel Approach Using Real-Time WebSocket Data Transfer 6

Robust Facial Emotion Detection in Low-Light Conditions: A N...

引用

6th International conference on Intelligent Computing in Data Sciences, ICDS 2024

作者： Patel, Dhruv Qurashi, Abdul Wahab Johnson, Anju P. School of Computing and Engineering University of Huddersfield Huddersfield United Kingdom Advanced Manufacturing Research Centre University of Sheffield Sheffield United Kingdom

ISBN: (纸本)9798350351200

Facial emotion detection plays a crucial role in human-computer interaction and psychological research. However, existing methods often falter in low-light environments, limiting their real-world applicability. This paper presents a novel approach to enhance the robustness of facial emotion detection systems in low-light conditions using a standard camera and real-Time data transfer via WebSocket. Our method employs advanced computer vision techniques, including adaptive histogram equalization and deep learning-based feature extraction, to ensure robust facial feature detection and emotion classification across varied lighting conditions. We will integrate our system with a TurtleBot 4 mobile platform to demonstrate its practical applications in assistive technologies and interactive systems. Experimental results show that our approach achieves 85.2% accuracy in low-light conditions, a significant improvement over baseline models. This research contributes to the development of more versatile and reliable emotion recognition systems for real-world applications. © 2024 ieee.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Real-time Trajectory-based Social Group Detection

Real-time Trajectory-based Social Group Detection

引用

ieee/RSJ International conference on Intelligent robots and Systems (IROS)

作者： Jahangard, Simindokht Hayat, Munawar Rezatofighi, Hamid Monash Univ Fac Informat Technol Clayton Vic Australia

ISBN: (纸本)9781665491907

Social group detection is a crucial aspect of various robotic applications, including robot navigation and human-robot interactions. To date, a range of model-based techniques have been employed to address this challenge, such as the F-formation and trajectory similarity frameworks. However, these approaches often fail to provide reliable results in crowded and dynamic scenarios. Recent advancements in this area have mainly focused on learning-based methods, such as deep neural networks that use visual content or human pose. Although visual content based methods have demonstrated promising performance on large-scale datasets, their computational complexity poses a significant barrier to their practical use in real-time applications. To address these issues, we propose a simple and efficient framework for social group detection. Our approach explores the impact of motion trajectory on social grouping and utilizes a novel, reliable, and fast data-driven method. We formulate the individuals in a scene as a graph, where the nodes are represented by LSTM-encoded trajectories and the edges are defined by the distances between each pair of tracks. Our framework employs a modified graph transformer module and graph clustering losses to detect social groups. Our experiments on the popular JRDB-Act dataset reveal noticeable improvements in performance, with relative improvements ranging from 2% to 11%. Furthermore, our framework is significantly faster, with up to 12x faster inference times compared to state-of-the-art methods under the same computation resources. These results demonstrate that our proposed method is suitable for real-time robotic applications.

关键词： Social grouping Graph transformers Motion behaviour robot perception

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Ceiling robot Assisted Intelligent Warehouse Management System 2

Cloud-Based Ceiling Robot Assisted Intelligent Warehouse Man...

引用

2nd International conference on Power, Electrical, Electronics and Industrial applications, PEEIACON 2024

作者： Oyon, Md. Shihab Sharar Arafat, Eyasir Uddin, Mohammad Nasir American International University-Bangladesh Dept. of Eee Dhaka Bangladesh

ISBN: (纸本)9798331517984

Driven by the surge in online shopping, warehouses are expanding and evolving, but often grapple with limited storage and inefficient use of space due to flawed layouts and outdated technologies. It was seen that heavier products take more time to deliver. To address these challenges, a new research proposes a cloud-based, ceiling-mounted robot. This innovative system dispatches from the ceiling, swiftly picking and delivering products in an average of 30.11 seconds. Thanks to its unique eight-wheel mechanism, the robot boasts auto-steering capabilities, exceptional stability, and impressive load capacity (170 grams) while maintaining low power consumption (2 Watts). Operated wirelessly via the web or app, the system empowers users to control stocking and delivery, enhancing adaptability and efficiency in modern warehouses. The proposed solution addresses the issues of inefficient product delivery times and space utilization, significantly improving warehouse operations. © 2024 ieee.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Intelligent Control System for Line Follower robot: From Theory to Implementation on the Mechatronics Field

Intelligent Control System for Line Follower Robot: From The...

引用

2023 ieee International conference on Dependable, Autonomic and Secure Computing, 2023 International conference on Pervasive Intelligence and Computing, 2023 International conference on Cloud and Big Data Computing, 2023 International conference on Cyber Science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Pavon, Wilson Campana, Justin Santamaria, Paolo Iza, Christian Zapata, Ricardo Universidad Politécnica Salesiana Engineering Department Quito Ecuador Universidad Politécnica Salesiana Mechatronic Department Quito Ecuador

ISBN: (纸本)9798350304602

In this paper, it is investigated the design and implementation of a line follower robot. The research aims to create a durable and efficient chassis that is both lightweight and reliable. To achieve this, the methodology has developed a simple and streamlined electronic circuit printed on a circuit board and an advanced control system that enhances the robot's autonomy and adaptability. We aim to bridge the gap between theoretical concepts and practical applications in the field of mechatronics, and this line-follower robot will prove to be a valuable contribution to the field. © 2023 ieee.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Dynamic Throwing with robotic Material Handling Machines

Dynamic Throwing with Robotic Material Handling Machines

引用

2024 International conference on Intelligent robots and Systems

作者： Werner, Lennart Nan, Fang Eyschen, Pol Spinelli, Filippo A. Yang, Hongyi Hutter, Marco Swiss Fed Inst Technol Robot Syst Lab CH-8092 Zurich Switzerland

ISBN: (纸本)9798350377712;9798350377705

Automation of hydraulic material handling machinery is currently limited to semi-static pick-and-place cycles. Dynamic throwing motions which utilize the passive joints, can greatly improve time efficiency as well as increase the dumping workspace. In this work, we use Reinforcement Learning (RL) to design dynamic controllers for material handlers with under-actuated arms as commonly used in logistics. The controllers are tested both in simulation and in real-world experiments on a 12ton test platform. The method is able to exploit the passive joints of the gripper to perform dynamic throwing motions. With the proposed controllers, the machine is able to throw individual objects to targets outside the static reachability zone with good accuracy for its practical applications. The work demonstrates the possibility of using RL to perform highly dynamic tasks with heavy machinery, suggesting a potential for improving the efficiency and precision of autonomous material handling tasks.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Drone System for Detecting, Tracking, and Following of a Mobile robot in ROS/Gazebo

Real-Time Drone System for Detecting, Tracking, and Followin...

引用

2025 International conference on Control, Automation, and Instrumentation, IC2AI 2025

作者： Salman, Ali Dika, Mohammad Diab, Hassan Owayjan, Michel Achkar, Roger American University of Science & Technology Faculty of Engineering and Computer Science Beriut Lebanon Nantes University Saint-Nazaire France

ISBN: (纸本)9798331529604

Surveillance drones equipped with video transmission capabilities play a crucial role in modern security systems, with the integration of OpenCV for object detection marking a significant advancement. This study evaluates the detecting accuracy by varying the distance between the drone and the target object, addressing gaps in current research through a detailed practical insight. This research explores key aspects of drone-based video surveillance, including object detecting, tracking and real-time following, aiming to enhance understanding and methodology in Computer Vision (CV) applications with Unmanned Aerial Vehicles (UAVs). The Simulation of a surveillance drone system in Gazebo simulator within the ROS2 framework. The drone is programmed to dynamically follow and track a mobile robot, enabling systematic analysis of the object detection algorithm's performance. The findings contribute to advancing the reliability and effectiveness of drone-based video surveillance systems for future innovations in security and monitoring applications. © 2025 ieee.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Enhancing robotic Grasp Failure Prediction Using A Pre-hoc Explainability Framework 20

Enhancing Robotic Grasp Failure Prediction Using A Pre-hoc E...

引用

ieee 20th International conference on Automation Science and Engineering (CASE)

作者： Acun, Cagla Ashary, Ali Popa, Dan O. Nasraoui, Olfa Univ Louisville Dept Comp Sci & Engn Knowledge Discovery & Web Min Lab Louisville Automat & Robot Res Inst LARRI Louisville KY 40208 USA Univ Louisville Next Generat Syst Grp Louisville Automat & Robot Res Inst LARRI Louisville KY 40208 USA

ISBN: (纸本)9798350358513;9798350358520

Enhancing the explainability of machine learning (ML) models is crucial for bridging their use gap for practical applications of robotic autonomy. The common standard for adding explainability has been to use a post-hoc explanation approach. However, post-hoc approaches have recently attracted criticism for their lack of transparency, specifically because the post-hoc methods learn a surrogate model after the predictive model has already been learned, which means that the explanations are not authentically explaining the model's behavior. This study aims to add explainability to the task of robot grasping failure prediction using Factorization Machines as the predictive model and using a novel pre-hoc explainability framework to learn an explainable Factorization Machine model. Unlike post-hoc methods, pre-hoc explainability starts with learning the explainable model before training the blackbox model and then provides guidance while learning the latter to make predictions that are faithful to the explanations through a regularization mechanism. Through a detailed case study, we explore the trade-off between prediction accuracy and explanation fidelity and show that our framework is able to make predictions that are more accurate than an explainable white-box model while simultaneously learning a model whose pre-hoc explanations achieve a high level of fidelity relative to the predictions. Results show that our framework can predict the robustness of the grasp with 83% accuracy while explaining that increased effort exerted in Joint 2 of Finger 3 contributes tremendously to producing grasp failure, which is in contrast to increased efforts exerted at Joint 2 of Fingers 1 and 2 and at joint 1 of Finger 3, that all lead to reducing grasp failure.

关键词： Prediction models

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：