检索结果-内蒙古大学图书馆

Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 673-689页

作者： Cong Pan Junran Peng Zhaoxiang Zhang the Center for Research on Intelligent Perception and Computing(CRIPAC) National Laboratory of Pattern Recognition(NLPR)Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 the School of Future Technology University of Chinese Academy of Sciences(UCAS)Beijing 100049China the Huawei Inc. Beijing 100085China IEEE the Institute of Automation Chinese Academy of Sciences(CASIA)Beijing 100190 the University of Chinese Academy of Sciences(UCAS) Beijing 100049 the Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science&Innovation Chinese Academy of Sciences(HKISI CAS)Hong Kong 999077China

Monocular 3D object detection is challenging due to the lack of accurate depth *** methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB ***-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion ***,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with *** from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth *** we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each ***,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input *** method is the first Swin-Transformer-based backbone architecture for monocular 3D object *** experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

关键词： Monocular 3D object detection normalizing flows Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Handling qualities evaluation for spacecraft docking in low earth orbit

Handling qualities evaluation for spacecraft docking in low ...

引用

作者： Mueller, Eric Bilimoria, Karl D. Frost, Chad NASA Ames Research Center Moffett Field CA 94035 United States Automation Concepts Research Branch M/S 210-10 United States Autonomous Systems and Robotics Intelligent Systems Division M/S 269-1 United States

ISBN: (纸本)9781563479458

A new generation of spacecraft is now under development by NASA to replace the Space Shuttle and return astronauts to the Moon. These spacecraft will have a manual control capability for several mission tasks, and the ease and precision with which pilots can execute these tasks will have an important effect on mission risk and training costs. A simulation evaluated the handling qualities of a generic space vehicle based on dynamics similar to one of these spacecraft, NASA's Crew Exploration Vehicle, during the last segment of the docking task with a space station. This handling qualities evaluation looked at four different translational control systems, two of which are available in current space vehicles and two of which were adapted from aeronautical vehicle control system designs. These response types were flown with three levels of translation-into-rotation dynamic coupling arising from a longitudinal offset between the reaction control system thrusters and the vehicle's center of mass. The effect of variations in jet thrust was also measured for a single response type. The results indicate that greater translation-into-rotation coupling is strongly correlated with degraded handling qualities, but that different response types do not have a major effect on pilot workload, final docking performance, or overall handling qualities.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

AsynEIO: Asynchronous Monocular Event-Inertial Odometry Using Gaussian Process Regression

arXiv

引用

arXiv 2024年

作者： Wang, Zhixiang Li, Xudong Zhang, Yizhai Zhang, Fan Huang, Panfeng The Research Center for Intelligent Robotics Shaanxi Province Innovation Team of Intelligent Robotic Technology School of Automation Northwestern Polytechnical University Xi'An710072 China

Event cameras, when combined with inertial sensors, show significant potential for motion estimation in challenging scenarios, such as high-speed maneuvers and low-light environments. There are many methods for producing such estimations, but most boil down to a synchronous discrete-time fusion problem. However, the asynchronous nature of event cameras and their unique fusion mechanism with inertial sensors remain underexplored. In this paper, we introduce a monocular event-inertial odometry method called AsynEIO, designed to fuse asynchronous event and inertial data within a unified Gaussian Process (GP) regression framework. Our approach incorporates an event-driven frontend that tracks feature trajectories directly from raw event streams at a high temporal resolution. These tracked feature trajectories, along with various inertial factors, are integrated into the same GP regression framework to enable asynchronous fusion. With deriving analytical residual Jacobians and noise models, our method constructs a factor graph that is iteratively optimized and pruned using a sliding-window optimizer. Comparative assessments highlight the performance of different inertial fusion strategies, suggesting optimal choices for varying conditions. Experimental results on both public datasets and our own event-inertial sequences indicate that AsynEIO outperforms existing methods, especially in high-speed and low-illumination scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Semi-Closed-Loop Constant Force Control of a Multi-Modes Rigid-Flexible Underactuated Gripper 23rd

Semi-Closed-Loop Constant Force Control of a Multi-Modes Rig...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and Engineering, IFToMM CCMMS 2022

作者： Chen, Weilin Feng, Zihong Lu, Qinghua Wei, Huiling Qin, Xiaolu Mo, Jiacheng Tang, Yu Wei, Sheng School of Mechatronics Engineering and Automation Foshan University 33 Guangyun Road Guangdong Foshan528000 China Academy of Interdisciplinary Studies Guangdong Polytechnic Normal University Guangzhou510665 China Engineering Research Center for Intelligent Robotics Jihua Laboratory Foshan528200 China

ISBN: (纸本)9789811993978

Grasping force control is important to realize safe and reliable robotic manipulation. In this paper, a semi-closed-loop constant grasping force control strategy of the multi-modes rigid-flexible underactuated gripper is designed to eliminate the influence of full-closed-loop control system on the grasping dexterity. For the two-point grasping mode and enveloped grasping mode, the inverse static model of gripper were established based on the forward static models proposed in our previous research and the numerical fitting. A semi-closed-loop PID constant grasping force control strategy was designed using the established statics models. Matlab Simulink was utilized to verify the proposed control strategy. Further, the multi-modes grasping force control system was built, and the effect of deformation for the flexible linkages on the equivalent size of grasped object was considered to correct the proposed control strategy by the analysis of balance position and numerical fitting. Finally, the rapidity, accuracy and stability of corrected control strategy were verified by experiments. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Force control

来源：评论

学校读者我要写书评

暂无评论

Automated force controlled assembly utilizing a novel hexapod robotic manipulator

Automated force controlled assembly utilizing a novel hexapo...

引用

Proceedings of the Biannual World automation Congress

作者： D. Kozlowski R. Stoughton W.S. Newman R. Hebbar Intelligent System and Robotics Center Sandia National Laboratories USA Micro Dexterity Systems USA Center for Automation and Intelligent Systems Research Case Western Reserve University USA

Within industry many repetitive operations, such as pick and place, spot welding, and spray-painting, have been successfully automated. While the operations themselves are diverse, a common thread within nearly all of them is that the robot performing the task has very limited direct physical contact with its environment. From a control perspective, this means that the robot need only be controlled to follow a desired trajectory fairly precisely nteractive forces with the environment can be essentially ignored. Assembly tasks are fundamentally different in nature - while some degree of precision in positioning is needed (e.g., alignment and part pickup), successful completion is rather a function of the precision in controlling, often delicately, the forces of interaction with the environment. Common examples include gear and spline meshing, threading fasteners, "snap" fittings, etc. Humans perform these types of tasks relatively easily, as we quite naturally control our interactive forces, but typical industrial robots do not possess such compliance, and fail miserably at these tasks. Delicate, dexterous control of physical interaction forces is typically limited by manipulator mechanical architecture (serial robots have high friction and inertia), the inability to sense forces accurately, and the lack of control sophistication to achieve the desired performance when such force sensing is present. PARADEX (PARAllel DEXterous) is a novel hexapod manipulator designed specifically for these types of assembly applications. This robot offers high payload and stiffness while minimizing moving mass. It utilizes direct drive linear motors for actuation, thus limiting friction. The robot is controlled with a personal computer, a real time operating system, and a commercial off the shelf motion control board. It can be switched between precise position control and compliance control based upon whether the system is in free space or in contact with the environment. PARADEX de

关键词： Force control Robotic assembly Automatic control robotics and automation Manipulators Service robots Robot sensing systems Friction Motion control Control systems

来源：评论

学校读者我要写书评

暂无评论

CNN Based Reliable Classification of Household Chores Objects for Service robotics Applications

CNN Based Reliable Classification of Household Chores Object...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Ren C. Luo Hsien-Chang Lin Yu-Ting Hsu TU Berlin University Berlin Germany International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA) Taipei Taiwan

Household chores service is one of the desirable functions for a service robot. Object classification is the most important function when searching for objects. We consider that the major concern is that the robot should not misclassify the object. If the robot misclassifies household object images, it will then perform the household tasks with the wrong object. This may cause serious damages to a service robot and to the user. This concept gives us the insight that the precision of the classification must be very high by setting a confidence threshold so that it then can claim a reliable service robot. By exploring this concept, we develop a more convincing indicator, Classification Reliability, to reveal the reliability of deep learning model. Moreover, we develop a fine-tune rule base to continuously regenerate more proper training dataset for the CNN model to increase reliability. Experimental results demonstrate that the CNN model fine-tuned by our closed-loop system achieves the reliability which is higher than the other similar effects such as DenseNet on the CIFAR-10 dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Eye-to-hand and Eye-in-hand visual servo system for parallel robot conveyor object tracking and fetching

Hybrid Eye-to-hand and Eye-in-hand visual servo system for p...

引用

Annual Conference of Industrial Electronics Society

作者： Ren C. Luo Shih-Che Chou Xin-Yi Yang Norman Peng International Center of Excellence on Intelligent Robotics and Automation Research National Taiwan University Taipei TAIWAN Industrial Technology Research Institute Hsinchu TAIWAN

The objective of this paper is to develop conveyer object tracking and fetching system. The traditional visual servo system for parallel robot is based on Eye-to-hand method which suffers from the narrow field of view (FOV). The basic step of moving assembling is multiple objects tracking which needs broad work space and big FOV of the parallel robot. In this paper, a Hybrid Eye-to-hand and Eye-in-hand Visual Servo System for parallel robot is proposed. Via this hybrid system, the parallel robot can achieve (multiple) object tracking and fetching with priority planning we designed. The eye-to-hand visual system with low resolution camera provides the estimations of the velocities and poses of the workpieces. Also the fetching priority is planned with this system. All aforementioned information is transferred to the eye-in-hand visual servo system for further use. Once the object appeared in the FOV of eye-in-hand system in the estimated position, the high resolution camera of the system is employed to acquire the pose information of the object with high accuracy and track it frame by frame. The hybrid system is successfully demonstrated and implemented on parallel robot which not only broadens the working space of parallel robot but also achieves great efficiency and accuracy.

关键词： Parallel robots Cameras Estimation Robot vision systems Visualization Servomotors

来源：评论

学校读者我要写书评

暂无评论

Grasp envelopes: Extracting constraints on gripper postures from online reconstructed 3D models

Grasp envelopes: Extracting constraints on gripper postures ...

引用

IEEE/RSJ International Conference on intelligent Robots and Systems

作者： Todor Stoyanov Robert Krug Rajkumar Muthusamy Ville Kyrki AASS Research Center Orebro University Sweden Intelligent Robotics Group Department of Electrical Engineering and Automation Aalto University Finland

ISBN: (纸本)9781509037636

Grasping systems that build upon meticulously planned hand postures rely on precise knowledge of object geometry, mass and frictional properties - assumptions which are often violated in practice. In this work, we propose an alternative solution to the problem of grasp acquisition in simple autonomous pick and place scenarios, by utilizing the concept of grasp envelopes: sets of constraints on gripper postures. We propose a fast method for extracting grasp envelopes for objects that fit within a known shape category, placed in an unknown environment. Our approach is based on grasp envelope primitives, which encode knowledge of human grasping strategies. We use environment models, reconstructed from noisy sensor observations, to refine the grasp envelope primitives and extract bounded envelopes of collision-free gripper postures. Also, we evaluate the envelope extraction procedure both in a stand alone fashion, as well as an integrated component of an autonomous picking system.

关键词： Grippers Grasping Planning Manipulators Three-dimensional displays Robot sensing systems Grasp three-dimensional displays Manipulator sensing systems Grippers Manipulators envelopes body position ENVELOPE Environmental models integrating element

来源：评论

学校读者我要写书评

暂无评论

Human-like Walking of Biped Robot with Foot Rotation Using Passive Metatarsophalangeal Joint 12

Human-like Walking of Biped Robot with Foot Rotation Using P...

引用

12th International Conference on CYBER Technology in automation, Control, and intelligent Systems, CYBER 2022

作者： Dai, Xiaolin Liu, Yixiang Liu, Xinyu Zang, Xizhe Song, Rui Li, Yibin School of Control Science and Engineering Shandong University Jinan250061 China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan250061 China Jiangsu Automation Research Institute Lianyungang222000 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150080 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In the process of walking, humans are accompanied by the important action of foot rotation. The foot rotates taking the heel and toe as the axis of rotation when landing on and leaving the ground, respectively. Although having high similarity to humans, many biped robots do not reproduce this important feature. This paper describes a method for adding foot rotation into biped robots using the passive metatarsophalangeal joint. Firstly, the biomechanics of human metatarsophalangeal joint during walking is analyzed. Then, the control strategy based on finite state machine for human-like biped walking with foot rotation is proposed for a simplified biped robot model that is composed of eight joints. Finally, the simulation results of the walking gait of the biped robot in MATLAB demonstrate the effectiveness of the control strategy. © 2022 IEEE.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

The Accuracy Analysis of Tool center Point Calibration via Condition Number and Minimum Eigenvalue

The Accuracy Analysis of Tool Center Point Calibration via C...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Ziqi Gao Yingli Li Yang Luo Yunxiang Jiang Bi Zhang Xingang Zhao Lingkai Chen Yiwen Zhao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Lab Hangzhou China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China

The accuracy of TCP (tool center point) calibration is vital to the operation accuracy of the robot. In this paper, we analyzed the accuracy analysis of TCP calibration of the regression matrix via condition number and minimum eigenvalue. It is theoretically proved that a regression matrix with a large condition number and a small eigenvalue will aggravate the influence of the observation error of the measurement point on TCP calibration accuracy and increase the TCP calibration error. To verify our analysis, simulation calibration experiments were carried out and statistical analysis was carried out on the calibration results. The result shows that the mathematical expectation and the variance of calibration error at minimum, median, and maximum matrix CA condition number are 1.36mm (±0.60mm), 1.57mm (± 0.75mm) and 2.94mm (±2.26mm) respectively, and the mathematical expectation and the variance of calibration error at minimum, median, and maximum eigenvalue are 3.33mm (± 2.32mm), 1.54mm (±0.72mm) and 1.16mm (± 0.49mm), respectively.

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：