检索结果-内蒙古大学图书馆

Flydar: A Passive Scanning Flying Lidar Sensing System for SLAM Using a Single Laser

IEEE SENSORS JOURNAL 2022年第2期22卷 1746-1755页

作者： Tan, Chee How Bin Shaiful, Danial Sufiyan Tang, Emmanuel Soh, Gim Song Foong, Shaohui Singapore Univ Technol & Design Engn Prod Dev Pillar Singapore 487372 Singapore

This paper presents the Flying Lidar (Flydar) aerial robot for simultaneous localization and mapping (SLAM). The Flydar integrates a single laser and capitalizes on the rotating dynamics of a nature-inspired aerial robot for omnidirectional scanning. This paper presents a 2.5D SLAM approach using the Flydar and does not assume that the Flydar's hovering plane, and thus the laser scan, is parallel to the ground plane, which is a key assumption in our previous work. A quaternion-based filter performs active correction of the Flydar's laser scan due to its transient attitude. A dual-accelerometer approach was incorporated to estimate the Flydar's scan rate during high angular rates flight beyond the gyroscope dynamic range. The proposed attitude filter output was experimentally evaluated statically on a bench-top setup and dynamically in flight, with an rms inclination estimate error of up to 1.1 degrees and 0.38 degrees respectively. The attitude-corrected lidar scan was used to estimate the robot pose for 2.5D SLAM. The 2.5D SLAM was experimentally validated on the Flydar and demonstrated to be superior to pure 2D SLAM in loop closure, position estimate drift, and rms error. Significantly, the 2.5D SLAM using the Flydar reports a low rms Euclidean error of up to 0.083 m, which is a 32.0% error reduction compared with our previous work, which uses 2D SLAM.

关键词： Sensors Simultaneous localization and mapping Robots Laser radar Robot kinematics Estimation Accelerometers Aerial robotics lidar robotics and automation sensor applications

来源：评论

学校读者我要写书评

暂无评论

Efficient Global Optimization of Non-Differentiable, Symmetric Objectives for Multi Camera Placement

引用

IEEE SENSORS JOURNAL 2022年第6期22卷 5278-5287页

作者： Hanel, Maria L. Schonlieb, Carola-Bibiane Univ Cambridge Cambridge Image Anal Grp Dept Appl Math & Theoret Phys Cambridge CB3 0WA England

We propose a novel iterative method for optimally placing and orienting multiple cameras in a 3D scene. Sample applications include improving the accuracy of 3D reconstruction, maximizing the covered area for surveillance, or improving the coverage in multi-viewpoint pedestrian tracking. Our algorithm is based on a block-coordinate ascent combined with a surrogate function and an exclusion area technique. This allows to flexibly handle difficult objective functions that are often expensive and quantized or non-differentiable. The solver is globally convergent and easily parallelizable. We show how to accelerate the optimization by exploiting special properties of the objective function, such as symmetry. Additionally, we discuss the trade-off between non-optimal stationary points and the cost reduction when optimizing the viewpoints consecutively.

关键词： Cameras Optimization Robot vision systems Linear programming Sensors Three-dimensional displays Task analysis NETW networked sensor fusion and decisions OPTO imaging sensors APPL environmental monitoring and control robotics and automation OTHER global optimum multiple camera placement non-differentiable objective symmetric objective

来源：评论

学校读者我要写书评

暂无评论

A Novel Scheme for Controlling Intelligent Television by Using Intelligent Camera

A Novel Scheme for Controlling Intelligent Television by Usi...

引用

2024 lEEE International Conference on Advanced Information, Mechanical Engineering, robotics and automation, AIMERA 2024

作者： Zhou, Zhaoxiong China Mobile Internet of Things Limited Company Intelligent Hardware Products Department Chongqing China

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343335

Although the home intelligent camera contains many functions, its application scenarios are still very limited. Based on the widely used big data analysis method and the face recognition function of intelligent camera, this paper designs a novel scheme of using intelligent camera to control intelligent television. The scheme combines intelligent camera, intelligent television, cloud platform and mobile App. The face recognition function of the intelligent camera recognizes people watching intelligent television, and reports to the mobile App remotely through the cloud platform;users can set the duration and period of watching intelligent television through the mobile App, and can also talk with the intelligent camera through the mobile App or send a language prompt message through the mobile App. In addition, the cloud platform can use big data analysis technology to recommend the best intelligent television playback time and duration to the mobile App, so that children can learn and entertain at the same time. The experimental results also show that the scheme has the conditions for popularization. This scheme can effectively realize the control of the intelligent camera on the intelligent television. © 2024 IEEE.

关键词： TV Data analysis Face recognition Process control Speech recognition Big Data Cameras Mobile applications robotics and automation Mechanical engineering

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Service Robot Development in Fast-Food Restaurants

引用

IEEE ACCESS 2022年 10卷 31466-31479页

作者： Chen, Chin S. Lin, Chia J. Lai, Chun C. Natl Taipei Univ Technol Grad Inst Automat Technol Taipei 10608 Taiwan TECO Elect & Machinery Co Ltd TECO Grp Res Inst Taipei 11503 Taiwan Natl Yunlin Univ Sci & Technol Dept Elect Engn Touliu 64002 Yunlin Taiwan

Given the prospect of low birth rate and aging population among developed countries, which further resulted in the shortage of workforces, service robots have been gradually applied to real-life from past academic research. This paper introduces the development of a service robot that is designed for food service in fast-food restaurants with the innovative improvement of mapping, localization, and navigation. Moreover, this research took the initiative of integrating 3D point cloud map and 2D occupancy grid map (OGM) in order to build a PC-OGM. In another word, using the sensory fusion method allows the service robot to adapt to a more complicated environment as well as enhance its positioning. In terms of its navigation function, the adaptive motion controller is refined so the service robot could navigate through narrow aisles smoothly. Finally, friendly contact-free food service robots were evaluated at fast-food restaurants in order to gain feedback from diners and waiters. Their feedback was broken down into 3 categories, availability, reliability, and satisfaction, for further analysis. As COVID-19 assails the world, we also look into future possibilities of food service robot deployment among restaurants to keep food and surface free from the virus.

关键词： Service robots Robots Simultaneous localization and mapping Navigation Cameras Robot vision systems Business Service robot robotics and automation SLAM non-contact service system integration

来源：评论

学校读者我要写书评

暂无评论

Vision-Based UAV-UGV Collaboration for Autonomous Construction Site Preparation

引用

IEEE ACCESS 2022年 10卷 51209-51220页

作者： Elmakis, Oren Shaked, Tom Degani, Amir Technion Israel Inst Technol Technion Autonomous Syst Program IL-3200003 Haifa Israel

Construction site preparation tasks rely on experienced operators and heavy machinery for clearing debris, earthmoving, leveling, and soil stabilization. These actions require complex collaboration between human teams to survey the site, estimate the material condition, and guide the operators accordingly. In recent years there has been a critical labor shortage due to increasing demands in construction. Integrating autonomous systems can mitigate this gap by replacing traditional methods with robotic solutions. However, while ideal conditions for automatic systems are static and highly controlled, construction sites are dynamic and unstructured environments. The ability of autonomous systems to overcome these conditions during outdoor construction site preparation tasks relies on their capacity to map the material on-site and continuously perform localization. This study suggests a solution to these problems by collaborating between an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV). In this method, the UAV produces a material map and monitors the UGV's location relative to known static landmarks. These measurements are then sent to the ground vehicle and are added to the onboard sensors using the Extended Kalman Filter (EKF) approach. Thus, the UAV enhances the operation of the UGV by providing an accurate localization and mapping from the air and allowing it to perform a site-preparation task beyond mere sensing. This approach is examined with simulation and validated by outdoor experiments. Additionally, this method is integrated within Shepherd, a custom-developed plugin for computer-aided design applications.

关键词： Location awareness Task analysis Robots Collaboration Robot kinematics Autonomous aerial vehicles State estimation Autonomous systems multi-robot systems pose estimation robotics and automation system implementation

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Foreign Object Classification in Fenceless Robotic Work Cells Using 2-D Safety Cameras

引用

TEHNICKI VJESNIK-TECHNICAL GAZETTE 2022年第5期29卷 1491-1498页

作者： Ozkahraman, Merdan Livatyali, Haydar Univ Appl Sci Dept Mechatron Engn TR-32260 Isparta Turkey Yildiz Tech Univ Dept Mechatron Engn TR-34349 Istanbul Turkey

Production systems using robotic manipulators have become common in the last few decades, and the trend is towards fenceless cells that save from space. Thus, the safety and flexibility of these systems have become more critical. The safety systems are based on either sensor data or camera images. Although the flexibility of the camera-based systems is better, conventional image processing methods are sensitive to the working environment. Artificial intelligence may be a powerful tool for them to adapt to change requirements quickly and improve accuracy and stability. In this study, a low-cost 2-D camera-based safety system was designed and installed in an experimental fenceless robotic work cell. The system controller was coupled with three alternative deep learning (ResNet-152, AlexNet, SqueezeNet) and three machine learning modules (support vector machine, random forest and decision tree). These modules were trained using photo images of ten distinct foreign objects penetrating the alarm zone. To include the ever-changing conditions of the industrial environment, disruptive effects including camera vibrations, shadows, reflections, illuminance variations etc. are included by using multiple images up to 550 for each class. Using the restricted data used for training and testing the six systems, the SqueezeNet deep learning model gave the best accuracy of 95% without any over-fitting. Despite this, machine learning-based models have been found to have 100 times faster prediction time than deep learning-based ones. Thus, the safety system can be adapted quickly to any possible changes and noise that may arise from working conditions is prevented, and time losses that may occur in industrial production may be prevented.

关键词： artificial intelligence image classification robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Special issue on the 2020 "robotics: Science and Systems" conference

引用

AUTONOMOUS ROBOTS 2022年第1期46卷 1-3页

作者： Likhachev, Maxim Behnke, Sven Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Bonn Bonn Germany

来源：评论

学校读者我要写书评

暂无评论

Robotic Fiber Fabrication based on Solidification Force Control 5

Robotic Fiber Fabrication based on Solidification Force Cont...

引用

5th International Conference on Manipulation, automation, and robotics at Small Scales (MARSS)

作者： Bettahar, Houari Valisalmi, Teemu Linder, Markus Zhou, Quan Aalto Univ Sch Elect Engn Dept Elect Engn & Automat Espoo 02150 Finland

ISBN: (数字)9781665459730

ISBN: (纸本)9781665459730

In this paper, we propose a robotic fiber fabrication method based on solidification force control to achieve highly repeatable mechanical properties of fibers. Dextran material is used as the specimen in the experiments. It has been chosen because of its similar rheological behavior to silk protein at high mass concentrations. However, the viscosity of dextran material is very low at its liquid phase, so force control during fabrication is challenging. Here, we propose a novel approach that controls the mechanical properties of fiber by controlling the solidification force. We employ impedance control with force tracking to control the solidification force to carry out the threading experiments and examine the benefits of the proposed approach. The repeatability of the mechanical properties of the fabricated fibers has been studied and compared using three scenarios a) fiber fabrication without solidification force control, abbreviated as FFNC, b) fiber fabrication with solidification force control after 60 seconds of solidification from the beginning of the solidification force detection abbreviated as FFWC, and c) fiber fabrication with solidification force control immediately after the detection of the solidification force, abbreviated as FFSC. The experimental results show that fibers fabricated using FFSC scenario have the highest repeatability based on the coefficient of variation of properties of the fabricated fibers, where the obtained coefficient of variation of the toughness, stiffness, elongation, and strength are 12.8%, 13.6%, 14.8%, 12.7% respectively. The experimental results also showed that fibers' mechanical properties toughness, stiffness, elongation, and strength have a negative correlation with the fabrication pulling velocity.

关键词： robotics and automation artificial fiber threading bio-mimicking impedance control force control

来源：评论

学校读者我要写书评

暂无评论

Deep PID Neural Network Controller for Precise Temperature Control in Plastic Injection-moulding Heating System 9

Deep PID Neural Network Controller for Precise Temperature C...

引用

9th IFAC Symposium on Mechatronic Systems (MECHATRONICS) / 16th International Conference on Motion and Vibration Control (MoViC)

作者： Ding, Yan-Xiang Cheng, Stone Huang, Yu-Ting Hong, De-Yu Natl Yang Ming Chiao Tung Univ Dept Mech Engn Hsinchu Taiwan

In this paper, deep PID neural network (PIDNN) controller is used in a nonlinear thermal regulatory control problem. We have a hot runner system and a nozzle with round tip as controlled plants. The control goal is to regulate their temperature responses for tracking a constant set point stably and precisely without exactly knowing mathematic models of plants during entire process by using deep PIDNN controller. The parameters (or weights) of controller are updated on-line based on gradient descent rule with Adam optimizer Comparing to the results with PID control, deep PIDNN controller reduces overshoot, saves much power and enhance the control performance that temperatures almost fluctuate within +/- 0.2 degrees C tolerance of set point in steady state. Copyright (C) 2022 The Authors.

关键词： robotics and automation PID Neural Network Temperature Control Online Optimization Plastic Injection-moulding Process

来源：评论

学校读者我要写书评

暂无评论

Six-Axis Force/Torque Sensors for robotics Applications: A Review

引用

IEEE SENSORS JOURNAL 2021年第24期21卷 27238-27251页

作者： Cao, Max Yiye Laws, Stephen Baena, Ferdinando Rodriguez y Imperial Coll London Dept Mech Engn London SW7 2AZ England Imperial Coll London Mechatron Med Lab London SW7 2AZ England Imperial Coll London Hamlyn Ctr London SW7 2AZ England

Six-axis force/torque sensors are transducers capable of measuring three dimensions of force and three dimensions of torque, and have a wide range of applications in robotic systems. The sensing principle behind the greatest majority of these is based on detecting strains in an elastic structure, and there are multiple modalities for strain measurement, including resistive strain gauge, piezoelectric, capacitive, and optoelectronic techniques. Developed sensors can be evaluated based on a range of parameters, including decoupling error, nonlinearity error, and measurement isotropy, where the primary design challenge is to maximise the allowable sensing range while minimising measurement errors. This literature review describes the state of the art of the field, and includes all relevant research associated with the search term "six-axis force/torque sensor" spanning 2015 - June 2021. The published literature for each sensing technique is summarised and evaluated, and a generalised sensor selection framework is proposed to assist the reader with the selection procedure for a state of the art sensor. In the period considered, there have been no significant improvements with the sensors documented in terms of measurement errors. Researchers have instead focused on features such as fault tolerance, alternative sensing techniques, cost reduction, and miniaturisation. These trends are expected to continue, and moving forward, the most significant challenge in the field is expected to be the lowering of manufacturing costs, as trends indicate measurement performance has reached maturity.

关键词： Sensors Robot sensing systems Force Measurement uncertainty Force measurement Strain Strain measurement Force sensors robotics and automation sensor selection six-axis force sensors

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：