检索结果-内蒙古大学图书馆

Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Cedrique Rovile Njieutcheu Tassi Anko Börner Rudolph Triebel German Aerospace Center (DLR) Institute of Optical Sensor Systems Germany German Aerospace Center (DLR) Institute of Robotics and Mechatronics Germany

ISBN: (纸本)9781450398336

In the last decade, several approaches have been proposed for regularizing deeper and wider neural networks (NNs), which is of importance in areas like image classification. It is now common practice to incorporate several regularization approaches in the training procedure of NNs. However, the impact of regularization strength on the properties of an ensemble of NNs remains unclear. For this reason, the study empirically compared the impact of NNs built based on two different regularization strengths (weak regularization (WR) and strong regularization (SR)) on the properties of an ensemble, such as the magnitude of logits, classification accuracy, calibration error, and ability to separate true predictions (TPs) and false predictions (FPs). The comparison was based on results from different experiments conducted on three different models, datasets, and architectures. Experimental results show that the increase in regularization strength 1) reduces the magnitude of logits; 2) can increase or decrease the classification accuracy depending on the dataset and/or architecture; 3) increases the calibration error; and 4) can improve or harm the separability between TPs and FPs depending on the dataset, architecture, model type and/or FP type.

关键词： Calibration error Quality of uncertainty Ensemble Regularization strength Mixture of Monte Carlo Dropout (MMCD) Separating true predictions (TPs) and false predictions (FPs) Monte Carlo Dropout (MCD)

来源：评论

学校读者我要写书评

暂无评论

mechatronics Design and Bio-Motion Simulation of Trans-radial Arm Prosthesis Controlled by EMG Signals

Mechatronics Design and Bio-Motion Simulation of Trans-radia...

引用

Colombian Caribbean Conference (C3), IEEE

作者： Diego A. Zavala Molina Ricardo J. Silva Cabrejos José Cornejo Margarita Murillo Manrique Ricardo Rodríguez Ricardo Palomares Professional School of Mechatronics Engineering Universidad Ricardo Palma Lima Peru Universidad Tecnológica del Perú Lima Peru Research Group of Robotics and Mechatronics (GI-ROMA) Universidad Ricardo Palma Lima Peru

According to the National Institute of Statistics and Informatics (INEI), 32 % of the population in the country have some type of motor disability, which includes difficulty in carrying out activities of daily living using the upper extremities. This research proposes the design and simulation of an upper extremity prosthesis controlled by electromyography signals for a patient with a trans-radial amputation. The cover of the prosthesis was made of ABS plastic and its CAD design was made with SolidWorks software. A compartment in the forearm was considered for the placement of the battery and the electronic system in the hand. The EMAXX ES8MA II and TOWER MG995 servomotors were used to load a mass of 2.3 kg of the forearm and hand assembly and a mechanical system to reach the 10 N.m necessary to move the fingers of the hand. The Von Mises stress analysis was carried out by applying a torque of 50 N.m in the coupling of the forearm-hand system. The CoppeliaSim software was used to simulate the movement of the prosthesis with the dimensions extracted from a volunteer patient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-based Methods for Object Recognition with High-Resolution Tactile Sensors

arXiv

引用

arXiv 2023年

作者： Gandarias, Juan M. García-Cerezo, Alfonso J. Gómez-De-Gabriel, Jesús M. Robotics and Mechatronics Group Systems Engineering and Automation Department University of Málaga Escuela de Ingenierías Industriales Málaga Spain

Novel high-resolution pressure-sensor arrays allow treating pressure readings as standard images. Computer vision algorithms and methods such as Convolutional Neural Networks (CNN) can be used to identify contact objects. In this paper, a high-resolution tactile sensor has been attached to a robotic end-effector to identify contacted objects. Two CNN-based approaches have been employed to classify pressure images. These methods include a transfer learning approach using a pre-trained CNN on an RGB-images dataset and a custom-made CNN (TactNet) trained from scratch with tactile information. The transfer learning approach can be carried out by retraining the classification layers of the network or replacing these layers with an SVM. Overall, 11 configurations based on these methods have been tested: 8 transfer learning-based, and 3 TactNet-based. Moreover, a study of the performance of the methods and a comparative discussion with the current state-of-the-art on tactile object recognition is presented. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

AnyFace: A Data-Centric Approach For Input-Agnostic Face Detection

AnyFace: A Data-Centric Approach For Input-Agnostic Face Det...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Askat Kuzdeuov Darina Koishigarina Huseyin Atakan Varol Inst. of Smart Systems and AI Nazarbayev University Astana Kazakhstan Dept. of Robotics and Mechatronics Nazarbayev University Astana Kazakhstan

Face detection is a mandatory step in many computer vision applications, such as face recognition, emotion recognition, age detection, virtual makeup, and vital sign monitoring. Thanks to advancements in deep learning and the introduction of annotated large-scale datasets, numerous applications have been developed for human faces. Recently, other domains, such as animals and cartoon characters, have started gaining attention but still lag far behind human faces. The biggest challenge is the limited number of annotated face datasets in these domains. The manual labeling of large-scale datasets is tedious and requires substantial human labor. In this regard, we present an inputagnostic face detector to ease the annotation of various face datasets. We propose a simple but effective data-centric approach instead of building a specific neural network architecture. Specifically, we trained a face detection model, YOLO5Face, on human, animal, and cartoon face datasets. The experiments show that the model can achieve accurate results in all domains. In addition, the model achieved decent results for animals and cartoon characters different from the ones in the training set. This implies that the model can extract agnostic facial features. We have made the source code and pre-trained models publicly available at https://***/IS2AI/AnyFace to stimulate research in these fields.

关键词： Training Animals Face recognition Source coding Neural networks Detectors Data models

来源：评论

学校读者我要写书评

暂无评论

A Data-Centric Approach for Object Recognition in Hemispherical Camera Images

TechRxiv

引用

TechRxiv 2023年

作者： Balgabekova, Zarema Alaran, Muslim Varol, Huseyin Atakan Inst. of Smart Systems and AI Nazarbayev University Astana Kazakhstan Dept. of Robotics and Mechatronics Nazarbayev University Astana Kazakhstan

Object recognition is a machine learning problem that involves the correct classification and localization of objects in an image. Object recognition has found wide applications in Industry 4.0, surveillance, and autonomous driving. Prominent datasets such as Pascal VOC, ImageNet, and MS COCO have further spurred advances in object recognition. However, the images in these datasets were captured using ordinary perspective lenses. Unlike ordinary cameras, fisheye or hemispherical cameras have a wide FoV reaching 180◦. Due to this property, they can acquire wide panoramic images, thus, capturing more objects in a scene as compared to ordinary perspective lenses. In this work, we provide the first benchmark testing dataset of real fisheye images containing commonly-occurring objects in the human environment obtained with hemispherical cameras. The dataset comprises 1,000 images containing 39 classes with a total number of 14,218 object instances. We trained the YOLOv7 model on the original MS COCO and transformed FisheyeCOCO datasets and tested the obtained models with our dataset. The results indicate that training the model on the combination of original and transformed datasets improves the performance by 2.5% compared to using these datasets separately. © 2023, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Robot-Assisted Navigation for Visually Impaired through Adaptive Impedance and Path Planning

Robot-Assisted Navigation for Visually Impaired through Adap...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Pietro Balatti Idil Ozdamar Doganay Sirintuna Luca Fortini Mattia Leonori Juan M. Gandarias Arash Ajoudani HRI2 Lab Istituto Italiano di Tecnologia Genoa Italy Dept. of Informatics Bioengineering Robotics and System Engineering University of Genoa Genoa Italy Systems Engineering and Automation Department Robotics and Mechatronics Lab University of Malaga Malaga Spain

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper presents a framework to navigate visually impaired people through unfamiliar environments by means of a mobile manipulator. The Human-Robot system consists of three key components: a mobile base, a robotic arm, and the human subject who gets guided by the robotic arm via physically coupling their hand with the cobot’s end-effector. These components, receiving a goal from the user, traverse a collision-free set of waypoints in a coordinated manner, while avoiding static and dynamic obstacles through an obstacle avoidance unit and a novel human guidance planner. With this aim, we also present a legs tracking algorithm that utilizes 2D LiDAR sensors integrated into the mobile base to monitor the human pose. Additionally, we introduce an adaptive pulling planner responsible for guiding the individual back to the intended path if they veer off course. This is achieved by establishing a target arm end-effector position and dynamically adjusting the impedance parameters in real-time through a impedance tuning unit. To validate the framework we present a set of experiments both in laboratory settings with 12 healthy blindfolded subjects and a proof-of-concept demonstration in a real-world scenario.

关键词： Target tracking Navigation Robot kinematics End effectors Real-time systems Path planning Sensors

来源：评论

学校读者我要写书评

暂无评论

Controlled Adaptive Flight of a Convertiplane Type Tricopter in Conditions of Uncertainty for Monitoring Water Areas

Controlled Adaptive Flight of a Convertiplane Type Tricopter...

引用

2020 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2020

作者： Jatsun, S. Morocho, Luis Miguel Mosquera Emelyanova, O. Leon, Andres Santiago Martinez Department of Mechanics Mechatronics and Robotics Kursk Russia

ISBN: (纸本)9781728169514

Currently, monitoring of water areas is one of the most important fields of study in terms of environmental protection aimed at guaranteeing the health of the citizens of different regions of the world. Monitoring data process makes possible to efficiently identify and accurately determine the coordinates of dangerous zones, as well as to track and predict the state of the water areas in study. In order to solve such kind of problems, in this paper we propose the use of a Flying Laboratory (FL) equipped with a water intake device and a software and hardware complex to control, receive, store and display the telemetric information from the FL. This paper is devoted to the mathematical modeling and research of the movement of an unmanned aerial vehicle (UAV) type convertiplane-tricopter in the vertical longitudinal plane, taking into account the uncertainties of external wind parameters. To reduce the impact of these parameters on the control quality and compensate the lack of information at the design stage, an adaptive control method with a reference model represented by a first-order transfer function has been introduced. The use of an adapter allowed to minimize the tracking error, i.e. the difference between the output signal and the reference model. The use of an adaptive control method has minimized the tracking error. The introduced algorithms in the adaptive control system have become possible to provide the fastest suppression of external disturbances in comparison with the traditional PID control strategy for the case of linear description of the control object. © 2020 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Heterogeneous Digital Twin Framework with Dynamic Responsibility Allocation for Complex Task Simulation 22

Multi-Agent Heterogeneous Digital Twin Framework with Dynami...

引用

Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems

作者： Adrian Simon Bauer Anne Köpken Daniel Leidner German Aerospace Center (DLR) & Robotics and Mechatronics Center (RMC) Weßling Germany

ISBN: (纸本)9781450392136

To become helpful assistants in our daily lives, robots must be able to understand the effects of their actions on their environment. A modern approach to this is the use of a physics simulation, where often very general simulation engines are utilized. As a result, specific modeling features, such as multi-contact simulation or fluid dynamics, may not be well represented. To improve the representativeness of simulations, we propose a framework for combining estimations of multiple heterogeneous simulations into a single one. The framework couples multiple simulations and reorganizes them based on semantically annotated action sequence information. While each object in the scene is always covered by a simulation, this simulation responsibility can be reassigned on-line. In this paper, we introduce the concept of the framework, describe the architecture, and demonstrate two example implementations. Eventually, we demonstrate how the framework can be used to simulate action executions on the humanoid robot Rollin' Justin with the goal to extract the semantic state and how this information is used to assess whether an action sequence is executed successful or not.

关键词： environment models knowledge representation robotics digital twin simulation

来源：评论

学校读者我要写书评

暂无评论

Development of a Special Module for an Industrial Collaborative Robot for Assembling Standard Threaded Products

Development of a Special Module for an Industrial Collaborat...

引用

2020 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2020

作者： Porunov, M. Trifonov, A. Institute of Automation and Robotics Mstu stankin Department of Robotics and Mechatronics Moscow Russia

ISBN: (纸本)9781728169514

This article represents a device for the automatic screwing. This unit allows to transfer, start on, screw and tighten threaded items with a required force. This unit was tested on the robot KUKA LWR 4+. The unit is applying passive adaptation of the assembled threaded items. The control system is using overcurrent protection for the tightening torque. There are following restrictions for the unit construction: minimal size and weight, minimal price, simplicity of the fabrication, possibility to change the tool head. © 2020 IEEE.

关键词： Robotic assembly

来源：评论

学校读者我要写书评

暂无评论

Whole Body Control Formulation for Humanoid Robots with Closed/Parallel Kinematic Chains: Kangaroo Case Study

Whole Body Control Formulation for Humanoid Robots with Clos...

引用

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

作者： Sait Sovukluk Johannes Englsberger Christian Ott Automation and Control Institute (ACIN) TU Wien Vienna Austria German Aerospace Center (DLR) Institute of Robotics and Mechatronics Wessling Germany

This study extends the whole-body control (WBC) formulation for bipedal humanoid robots that include closed (parallel) kinematic chains in their structure. Along with general formulation, we also stress the implementation of this formulation on Kangaroo, which is a highly dynamic humanoid robot developed by PAL robotics. This 76-DOF robot includes 24 independent closed-kinematic chains in its structure and constitutes a good case study for our approach. We discuss the WBC formulation for various control structures, including inverse dynamics control (IDC) and Modular Passive Tracking Control (MPTC). As a test scenario, we employ a 3D spring-loaded inverted pendulum (SLIP) jumping trajectory with disturbance rejection as the desired CoM trajectory.

关键词：

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：