检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pulli, Tessa Thalhammer, Stefan Schwaiger, Simon Vincze, Markus Vision for Robotics Laboratory Automation and Control Institute TU Wien Austria Industrial Engineering Department UAS Technikum Vienna Austria

Robots are increasingly envisioned to interact in real-world scenarios, where they must continuously adapt to new situations. To detect and grasp novel objects, zero-shot pose estimators determine poses without prior knowledge. Recently, vision language models (VLMs) have shown considerable advances in robotics applications by establishing an understanding between language input and image input. In our work, we take advantage of VLMs zero-shot capabilities and translate this ability to 6D object pose estimation. We propose a novel framework for promptable zero-shot 6D object pose estimation using language embeddings. The idea is to derive a coarse location of an object based on the relevancy map of a language-embedded NeRF reconstruction and to compute the pose estimate with a point cloud registration method. Additionally, we provide an analysis of LERF’s suitability for open-set object pose estimation. We examine hyperparameters, such as activation thresholds for relevancy maps and investigate the zero-shot capabilities on an instance- and category-level. Furthermore, we plan to conduct robotic grasping experiments in a real-world setting. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning Subordinate control System Based on Neural Network for Nonlinear Electric Drivers of Lower Limbs of Exoskeleton

Self-Tuning Subordinate Control System Based on Neural Netwo...

引用

2022 Conference of Russian Young Researchers in Electrical and Electronic engineering, ElConRus 2022

作者： Belov, Mikhail P. Dang Truong, Dinh Khoa, Tran Dang Saint Petersburg Electrotechnical University Department of Robotics and Industrial Automation Leti Saint Petersburg Russia Le Quy Don Technical University Department of Control Engineering Hanoi Viet Nam

ISBN: (纸本)9781665409933

This article proposes a subordinate system control with a self-turning adaptation of the coefficients of the PID controller of position control loop by an analog neural network for nonlinear electric drive of lower limb exoskeleton (LLE) under the influence of uncertain parameters of the dynamic model, nonlinear elements (friction, elasticity of the dynamic model), and stochastic external disturbances. To correct the coefficients of traditional PID controllers, it is proposed to use a neural network (NN), which allows self-tuning the coefficients directly from its outputs based on errors of the control system with the possibility of self-determination of the Jacobian matrix of the neural network. The paper also produces the dynamics model of exoskeleton movement with five links of two legs and a body, considering nonlinear electric drives and external disturbances acting. The efficiency of the proposed control method with the joint motion angular response of exoskeleton is proved by results simulation in the environment Matlab/ Simulink. © 2022 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Prediction Horizon Requirements for Automated Driving: Optimizing Safety, Comfort, and Efficiency

arXiv

引用

arXiv 2024年

作者： Sánchez, Manuel Muñoz van der Ploeg, Chris Smit, Robin Elfring, Jos Silvas, Emilia van de Molengraft, René Department of Mechanical Engineering Robotics Group Japan Control Systems Technology Group Eindhoven University of Technology Eindhoven Netherlands Department of Integrated Vehicle Safety Helmond Netherlands VDL CropTeq Robotics Eindhoven Netherlands

Predicting the movement of other road users is beneficial for improving automated vehicle (AV) performance. However, the relationship between the time horizon associated with these predictions and AV performance remains unclear. Despite the existence of numerous trajectory prediction algorithms, no studies have been conducted on how varying prediction lengths affect AV safety and other vehicle performance metrics, resulting in undefined horizon requirements for prediction methods. Our study addresses this gap by examining the effects of different prediction horizons on AV performance, focusing on safety, comfort, and efficiency. Through multiple experiments using a state-of-the-art, risk-based predictive trajectory planner, we simulated predictions with horizons up to 20 seconds. Based on our simulations, we propose a framework for specifying the minimum required and optimal prediction horizons based on specific AV performance criteria and application needs. Our results indicate that a horizon of 1.6 seconds is required to prevent collisions with crossing pedestrians, horizons of 7-8 seconds yield the best efficiency, and horizons up to 15 seconds improve passenger comfort. We conclude that prediction horizon requirements are application-dependent, and recommend aiming for a prediction horizon of 11.8 seconds as a general guideline for applications involving crossing pedestrians. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Kinematic and Kinetic Analysis of 3-RRS Parallel Manipulator

Kinematic and Kinetic Analysis of 3-RRS Parallel Manipulator

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Sara Ashrafi S. Ali A. Moosavian Department of Mechanical Engineering Advanced Robotics and Automated Systems (ARAS) Lab. Center of Excellence in Robotics and Control K. N. Toosi University of Technology Tehran Iran

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

This paper presents the Kinematic and Kinetic properties of the 3-RRS parallel manipulator that has been designed and prototyped at the ARAS Lab, together with an extensive experimental setup. Inverse and forward kinematics of the mechanism are studied, which leads to the attainment of eight possible solutions in each case, of which just one is physically acceptable and maintains its consistency in both analyses. In addition, the Jacobian matrix of the manipulator is derived for various operational scenarios. In this most recent update, a linear actuator under the moving platform is added to cancel the effect of the mass of the plate and the ball for enhancing the responsiveness of the system. Dynamic and kinetic equations are updated based on reduced gravitational effects.

关键词： Jacobian matrices Actuators Mechatronics System dynamics Dynamics Kinematics Kinetic theory Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Robustness Estimation of Large Deviations in Linear Discrete-Time Systems 17th

Algorithm for Robustness Estimation of Large Deviations in...

引用

17th International Conference on Informatics in control, Automation and robotics, ICINCO 2020

作者： Vunder, Nina Dudarenko, Natalia Institute of Control Engineering TU Braunschweig Hans-Sommer-Str. 66 Braunschweig Germany Department of Control Systems and Industrial Robotics ITMO University 49 Kronverksky Pr. Saint-Petersburg Russia

ISBN: (纸本)9783030924416

The paper presents the algorithm for robustness estimation of large deviations in free motion of linear discrete-time systems. A tracking discrete-time systems with the modal control law are discussed, where the modal control law is designed taking into account the value of delay and the deviation. Two cases of discrete-time systems with control signal delay are considered in the paper. The first case relates to predictable delay of control signal, and the second one relates to unpredictable delay of control signal. It is assumed that parameters of the system are linearly dependent on the uncertainties. The problem is solved with the state space approach and the sensitivity theory methods. An upper bound estimation of trajectory deviations for discrete-time systems is obtained. The estimation contains the condition number of the eigenvectors matrix of the system state matrix. Therefore, sensitivity functions of singular values of the eigenvectors matrix are used to calculate the robustness estimation of the deviations. Based on the obtained equations, an algorithm for the robustness estimation of large deviations in linear discrete-time systems with parametric uncertainties is proposed. The proposed method is compared with an alternative LMI based approach for the peak estimation problem. Advantages and disadvantages of both approaches are illustrated with examples. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Long-Range Vehicle Detection of LiDAR using Adaboost Classification*

Long-Range Vehicle Detection of LiDAR using Adaboost Classif...

引用

IEEE/SICE International Symposium on System Integration

作者： Na-Young Lim Jeon-Hyeok Lee Tae-Hyoung Park Department of Intelligent Systems & Robotics Chungbuk National University Cheongju South Korea Department of Control & Robot Engineering Chungbuk National University Cheongju South Korea

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

In recent developments, autonomous racing has garnered attention as it aims to overcome the limitations of standard autonomous driving systems. Achieving safe racing conditions necessitates both fast and long-range perception. However, current 3D LiDAR object detection methods face challenges with high computational costs and limited detection ranges. These issues make them unsuitable for racing scenarios. To address these challenges, this paper proposes a clustering-based long-range vehicle detection method that relies solely on LiDAR. First, the method removes ground points and foreground points and clusters the remaining points. Subsequently, these clusters are classified as vehicles using AdaBoost, generating 2D bounding boxes in the range view. Experimental results demonstrate superior performance, achieving a computational efficiency of 53 Hz and a long-range detection accuracy of over 80%, compared to voxel-based and range-based methods. This approach offers a viable solution for autonomous racing environments.

关键词： Laser radar Three-dimensional displays Accuracy Vehicle detection System integration Object detection Computational efficiency Faces Standards Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Determining Relative Positioning for Aerial Refueling Through DNN Bounding Box Geometry

Determining Relative Positioning for Aerial Refueling Throug...

引用

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

作者： Maheshwari, Akshat Lowe, Ryan Mwaffo, Violet Clement, Danielle Mottino, Sarah Costello, Donald H. Weapons Robotics and Control Department United States Naval Academy AnnapolisMD21402 United States Aeronautics Division Lockheed Martin Corporation Fort WorthTX United States MATRIX Lab A. Clark School of Engineering University of Maryland College ParkMD United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The Office of Naval Research (ONR) has initiated the Advanced Autonomous Air-to- Air Refueling System (A4RS) project to establish standards and explore the use of deep neural networks (DNN) for autonomous refueling tasks. This research aims to develop a monovision-based camera system integrated with a DNN to achieve accurate bearing and range measurements to a refueling drogue within the final 15-20 feet before contact. As part of this study, a pre-trained DNN was used to identify the drogue by placing a bounding box around it. A similar-triangle-based algorithm was then applied to determine the relative range to the center of the drogue (x, y, and z translations) from the camera. The derived ranges were then compared with the actual ranges to determine if the errors would be acceptable for use in autonomous aerial refueling of an uncrewed system. The research found that as the range decreased, the error decreased to acceptable levels (less than four inches when the camera was five feet from the drogue). The results also showed that the more misalignment with the drogue, the larger the errors were to reality. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Air to Air Refueling Convolutional Neural Network Unmanned Aircraft System Algorithm Performance Computer Vision Fixed Wing Aircraft Autonomous Systems robotics Data Acquisition System Obstacle Avoidance

来源：评论

学校读者我要写书评

暂无评论

Aerogel defect detection using terahertz waves

Aerogel defect detection using terahertz waves

引用

International Conference on Infrared and Millimeter Waves

作者： Yehao Ma Liran Shen Yuqi Cao Dibo Hou Guangxin Zhang Department of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Robotics Institute Ningbo University of Technology Ningbo China

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

Aerogel is known as super insulation materials and has already been applied to manufacture thermal protection parts of aerospace equipment. Terahertz (THz) wave has good penetration to non-metallic and non-polar materials. To explore its potential in aerogel defect detection, the absorption coefficient and refractive index of aerogel were studied. As a result, the absorption spectrum of aerogel has not obvious absorption peak, and THz wave has great penetration for aerogel. Additionally, two aerogel samples with different sizes of defects were imaged with two time domain parameters (pulse peak and pulse valley) and two frequency domain parameters (absorption coefficient and refractive index). The study is of key importance for THz wave in nondestructive testing for aerogel, offering a rapid and non-destructive detection method for aerogel defects.

关键词： Insulation Absorption Frequency-domain analysis Nondestructive testing Refractive index Aerospace materials Time-domain analysis Protection Defect detection Testing

来源：评论

学校读者我要写书评

暂无评论

Impact of whole-body vibrations on electrovibration perception varies with target stimulus duration

arXiv

引用

arXiv 2024年

作者： Vuik, Jan D.A. Pool, Daan M. Vardar, Yasemin Department of Cognitive Robotics Faculty of Mechanical Engineering Delft University of Technology Delft Netherlands Department of Control and Operations Faculty of Aerospace Engineering Delft University of Technology Delft Netherlands

Objective: This study explores the impact of whole-body vibrations induced by external vehicle perturbations, such as aircraft turbulence, on the perception of electrovibration displayed on touchscreens. Background: Electrovibration holds promise as a technology for providing tactile feedback on future touchscreens, addressing usability challenges in vehicle cockpits. However, its performance under dynamic conditions, such as during whole-body vibrations induced by turbulence, still needs to be explored. Method: We measured the absolute detection thresholds of 15 human participants for short- and long-duration electrovibration stimuli displayed on a touchscreen, both in the absence and presence of two types of turbulence motion generated by a motion simulator. Concurrently, we measured participants’ applied contact force and finger scan speeds. Results: Significantly higher (38%) absolute detection thresholds were observed for short electrovibration stimuli than for long stimuli. Finger scan speeds in the direction of turbulence, applied forces, and force fluctuation rates increased during whole-body vibrations due to biodynamic feedthrough. As a result, turbulence also significantly increased the perception thresholds, but only for short-duration electrovibration stimuli. Conclusion: The results reveal that whole-body vibrations can impede the perception of short-duration electrovibration stimuli, due to involuntary finger movements and increased normal force fluctuations. Application: Our findings offer valuable insights for the future design of touchscreens with tactile feedback in vehicle cockpits. © 2024, CC BY-NC-SA.

关键词： Turbulence

来源：评论

学校读者我要写书评

暂无评论

Comparing DNN Performance to Justify Using Transference of Training for the Autonomous Aerial Refueling Task

Comparing DNN Performance to Justify Using Transference of T...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Dillon Miller Violet Mwaffo Donald Costello Weapons Robotics and Control Engineering Department United States Naval Academy Annapolis Maryland United States

In an effort to modernize the fleet, the United States Navy is looking to significantly increase the number of unmanned aircraft deployed within a carrier air wing. Yet, no method to certify the autonomous refueling of uncrewed aerial platforms has been publicly released. Ongoing research efforts at the United States Naval Academy (USNA) are investigating certification evidence that will allow a deep neural network (DNN) to enable the autonomous aerial refueling task. This poster paper highlights an investigation into developmental flight test videos of an aircraft refueling from a KC-130 tanker and from a tanker configured F/A-18 jet. In this paper, we evaluate a KC-130 trained DNN and a F/A-18 trained DNN against a F/A-18 data set that was not used in training either DNN. This procedure was aimed at determining whether the resources required to gather training data on each tanker aircraft taken separately are justified or if the performance of the DNN trained on a similar aircraft dataset is sufficient for the task.

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：