检索结果-内蒙古大学图书馆

arXiv 2025年

作者： He, Yushen Zhao, Lei Deng, Tianchen Fang, Zipeng Chen, Weidong Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China

Service mobile robots are often required to avoid dynamic objects while performing their tasks, but they usually have only limited computational resources. So we present a lightweight multi-modal framework for 3D object detection and trajectory prediction. Our system synergistically integrates LiDAR and camera inputs to achieve real-time perception of pedestrians, vehicles, and riders in 3D space. The framework proposes two novel modules: 1) a Cross-Modal Deformable Transformer (CMDT) for object detection with high accuracy and acceptable amount of computation, and 2) a Reference Trajectory-based Multi-Class Transformer (RTMCT) for efficient and diverse trajectory prediction of mult-class objects with flexible trajectory lengths. Evaluations on the CODa benchmark demonstrate superior performance over existing methods across detection (+2.03% in mAP) and trajectory prediction (-0.408m in minADE5 of pedestrians) metrics. Remarkably, the system exhibits exceptional deployability - when implemented on a wheelchair robot with an entry-level NVIDIA 3060 GPU, it achieves realtime inference at 13.2 fps. To facilitate reproducibility and practical deployment, we release the related code of the method at https://***/TossherO/3D Perception and its ROS inference version at https://***/TossherO/ros packages. Copyright © 2025, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Automatic Saline Monitoring System Using IoT 56

Automatic Saline Monitoring System Using IoT

引用

56th International Carnahan Conference on Security Technology, ICCST 2023

作者： Patel, Raju Adhikari, Manoj Singh Shukla, Manoj Kumar Payal, Mohit Kumar, Palvai Manoj Verma, Yogesh Kumar School of Electronics Engineering SENSE Vellore Institute of Technology Chennai India School of Electronics and Electrical Engineering Lovely Professional University Punjab India Department of Robotics and Automation Pune India Graphic Era Hill University Electronic and Communication Engineering Dehradun India

ISBN: (纸本)9798350315875

The need for health prevention is raising every day as the earth's population rises. Thus, everyone in our planet must take adequate care of their health. Due to technical breakthroughs in the domains medical treatment has improved fast in recent years, using sensors, microcontrollers, and computers to ensure quick patient recovery in hospitals. Every patient should receive better care, better monitoring, and the proper amount of essential nutrients at the proper time. By using an Internet of Things (IoT) to remotely monitor the saline system, the suggested method makes it possible to regulate saline drip rate using an improved technique. The suggested system includes a sensor for determining when the saline liquid level in the saline container has decreased to a risky level and a mechanism for stopping the saline flow automatically once the saline bottle is fully empty or at a specific level. The patients will benefit much from this, especially at night. Additionally, because air bubbles in blood may instantly kill a patient, this technique eliminates the deadly chance of their getting into their circulation. Such a gadget will guarantee that patients won't suffer any damage. © 2023 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Formation Control and Sub-Swarm Generation of Multirotor UAVs

Formation Control and Sub-Swarm Generation of Multirotor UAV...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Muhammad Muzamal Shahzad Muhammad Haroon Asad Muhammad Haris Hammad Munawar Muhammad Haroon Yousaf Swarm Robotics Lab National Center of Robotics and Automation University of Engineering and Technology Taxila Taxila Pakistan Computer Engineering Department University of Engineering and Technology Taxila Taxila Pakistan

The research field of collective behaviors takes inspiration from natural self-organizing systems like honeybees, fish schools, social insects, bird flocks, and other social animals. These behaviors can be transformed into robots by replicating the same set of rules as found in the natural swarms. The deployment of aerial swarm robotics has become significant due to their multiple applications in surveillance, agriculture, and military. These applications lead to the development of aerial swarm robotic platforms to solve real-world problems. For example, a swarm of low-tech, cost-effective small UAVs can engage a high-tech target effectively. Similarly, a swarm of UAVs can perform surveillance and rescue missions in disastrous areas and build an emergency communication network through multiple UAV swarms. The critical part of swarm technology is multiple swarm intelligence algorithms that have been proposed and tested by various simulation platforms such as V-rep, Gazebo and MATLAB. Very few of them have been deployed on hardware to solve real scenarios that include formation control, navigation, pattern formation, and a few sub-swarm generation algorithms. Team connectivity is one of the essential aspects of a swarm network that emerges the collective intelligence of the group and ensures the readiness of the algorithm to deploy and solve real-world problems. Many researchers proposed the team connectivity algorithms in a single swarm network but still left the connectivity gap between the sub-swarms during a mission. This research work contributes toward designing a swarm intelligence algorithm to improve the connectivity techniques and team connectivity between the swarm agents and the sub-swarm groups.

关键词： Pattern formation Service robots Navigation Surveillance Insects Swarm robotics Formation control

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Deepfake Text Detection Techniques on Social-media

Performance Analysis of Deepfake Text Detection Techniques o...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： Adamya Gaur Sanjay Kumar Singh Pranshu Saxena University School of Automation & Robotics Guru Gobind Singh Indraprastha University Delhi India Department of Information Technology ABES Engineering College Ghaziabad India

In the last few years, there has been remarkable progress in the domain of natural language generation & understanding. This has led to the development of enhanced text generation capability of machines that can generate spurious text or deepfake text. The technology may be exploited to change and shape public sentiment on social media. Therefore, mechanisms to detect deepfake text is a crucial task. The study emphasizes on detection of deepfake text on social media platform X (formerly Twitter). It presents the performance of machine learning classifiers Logistic regression (LR), XGB classifier, and AdaBoost classifier, utilizing feature engineering methods Term Frequency (TF) and Term Frequency-Inverse Document Frequency (TF-IDF). Deep learning methods such as Dense Neural Networks (DNN), Bi-directional Long Short-Term Memory (Bi-LSTM), and Convolutional Neural Networks (CNN)in addition to state-of-the-art models and variants such as Bi-Directional Encoder Representations from Transformers (BERT), DistilBERT & RoBERTa are also a part of study, leading to 89.17% accuracy in deepfake text detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Validation of Autonomous Vehicles Across Scales using an Integrated Digital Twin Framework

Towards Validation of Autonomous Vehicles Across Scales usin...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Tanmay Vilas Samak Chinmay Vilas Samak Venkat Narayan Krovi Department of Automotive Engineering Automation Robotics and Mechatronics Laboratory (ARMLab) Clemson University International Center for Automotive Research (CU-ICAR) Greenville SC USA

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Autonomous vehicle platforms of varying spatial scales are employed within the research and development spectrum based on space, safety and monetary constraints. However, deploying and validating autonomy algorithms across varying operational scales presents challenges due to scale-specific dynamics, sensor integration complexities, computational constraints, regulatory considerations, environmental variability, interaction with other traffic participants and scalability concerns. In such a milieu, this work focuses on developing a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs) to help support the streamlined development and validation of autonomy software stacks. Particularly, this work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs. We study the adoption of these autonomy-oriented digital twins to deploy a common autonomy software stack with an aim of end-to-end map-based navigation to achieve the ODD-specific objective(s) for each vehicle. Finally, we also discuss the flexibility of the proposed framework to support virtual, hybrid as well as physical testing with seamless sim2real transfer.

关键词： Navigation Heuristic algorithms Ecosystems Full stack Aerodynamics Digital twins Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Waste Sorting automation with Visual Sensor and RFID

Waste Sorting Automation with Visual Sensor and RFID

引用

International Conference on Advanced Electrical Engineering (ICAEE)

作者： Seif Eddine Seray Ishak Bey Isma Akli Department of Control and Power University of M'hammed Bouguerra Boumerdes Algeria Robotics and Industrial Automation Division Center for Development of Advanced Technologies Algiers Algeria

ISBN: (数字)9798350349351

ISBN: (纸本)9798350349368

The quantity of domestic wastes is constantly increasing, resulting on overload of wastes. Recycling became imperative for ecologic and economical considerations in order to apply circular economy rules. In general, humans are recruited in waste sorting plants for performing the dangerous and tedious sorting tasks. The automation is, thus, necessary. This paper deals with the problem of waste sorting automation. The proposed solution consists of waste recognition and classification using YOLOv8, and human presence detection using RFID (Radio frequency Identification) tags. The proposed solution is validated in simulation. The virtual robot performs a task in order to simulate the behavior of a real robot with high fidelity, depending on the information coming from the RFID tags and a visual sensor.

关键词： Visualization automation Software architecture Operating systems Robot vision systems Robot sensing systems Recycling RFID tags Middleware Sorting

来源：评论

学校读者我要写书评

暂无评论

PS-Loc: Robust LiDAR Localization with Prior Structural Reference

PS-Loc: Robust LiDAR Localization with Prior Structural Refe...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Rui Li Wentao Zhao Tianchen Deng Yanbo Wang Jingchuan Wang Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Prior structural reference like floor plan is readily accessible in indoor scene, which exhibits the potential of improving localization quality without the requirements of a previously-built high-precision map. This paper introduces a novel optimal transport-based framework for prior structural reference-based localization, aiming to improve the robustness for the robot localization. Leveraging the spacial relations of structures, a matching method based on optimal transport theory is proposed and it improves the robustness of matching results in dynamic scene and rapid rotation conditions. Additionally, this paper handles metric inaccuracies in the known structural reference by implementing an prior guided plane adjustment-based updating strategy. This strategy combines prior and observational information to jointly optimize the structural information within a sliding window. The performance of the framework is validated through real-world experiments, demonstrating superior accuracy and robustness to disturbances from dynamic occlusion and rapid rotation compared to common state-of-the-art SLAM and localization methods.

关键词： Location awareness Measurement Laser radar Simultaneous localization and mapping Accuracy Robustness Robot localization Intelligent robots Floors

来源：评论

学校读者我要写书评

暂无评论

Integrating occlusion awareness in urban motion prediction for enhanced autonomous vehicle navigation

Integrating occlusion awareness in urban motion prediction f...

引用

IEEE Symposium on Intelligent Vehicle

作者： Vinicius Trentin Juan Medina-Lee Antonio Artuñedo Jorge Villagra Centre for Automation and Robotics (CSIC-UPM) Arganda Del Rey Spain Computer Science and Engineering Department University of Puerto Rico Mayagüez USA

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to ensure safety while navigating through highly interactive and complex scenarios. Lack of visibility due to an obstructed view or sensor range poses a great safety issue for autonomous vehicles. The inclusion of occlusion in interaction-aware approaches is not very well explored in the literature. In this work, the MultIAMP framework, which produces multimodal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov chains, is extended to tackle occlusions. The framework is evaluated with a state-of-the-art motion planner in two realistic use cases.

关键词： Navigation Dynamics Probabilistic logic Safety Bayes methods Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Theoretical and Computational Investigation on Aerospike Nozzle Equipped with Exhaust Plumes for Supersonic Flow Regimes 1

引用

International Conference on Mechanical Engineering, INCOME 2023

作者： Bindal, Rohi Kattyayan, Shivansh Sonawane, Chandrakant R. Dhanwani, Payal Thombre, Simran Joshi, Vedant Mishra, Ankit Kumar Department of Computer Science Engineering Symbiosis Institute of Technology Maharashtra Pune India Department of Mechanical Engineering Symbiosis Institute of Technology Maharashtra Pune India Department of Aeronautical Engineering Bhagwan Arihant Institute of Technology Gujarat Surat India Department of Aerospace Engineering Sastra University Tamil Nadu Thanjavur India Department of Robotics and Automation Symbiosis Institute of Technology Maharashtra Pune India Department of Research and Development ASTROEX RESEARCH ASSOCIATION Uttar Pradesh Deoria India

ISBN: (数字)9789819738748

ISBN: (纸本)9789819738731

Aerospike nozzles are widely used in aerospace applications due to their high performance, low cost, and low maintenance. They have been widely used to improve the performance of aerospike engines. This paper presents a computational and numerical analysis of the flow behavior of an aerospike nozzles equipped with exhaust plumes under different operating conditions, contributing to the better study and understanding of fluid dynamics for the aerospike nozzles in the field of aerospace engineering. The study uses a three-dimensional, axisymmetric model to simulate the flow within the nozzle, and the results are later used in order to generate better contours and performance. An iterative test has been carried out which in turn used for optimization loop which involves changes in contour shape, spike height, or spike angle to achieve better flow expansion and reduce pressure losses. The paper also discusses the potential future research directions, such as investigating unsteady flow phenomena or exploring advanced turbulence models for more accurate predictions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Aerospace applications

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

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：