检索结果-内蒙古大学图书馆

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

作者： Sohrab Allahyari Hamid Rahmanei S. Ali A. Moosavian Dept. of Mechanical Engineering Center of Excellence in Robotics & Control Advanced Robotics & Automated Systems (ARAS) Laboratory K. N. Toosi University of Technology Tehran

Four-wheel drive Mecanum robots have gained attention due to their ability to move in all directions, which allows them to work in tight and complex environments. For this reason, ensuring precise control of these robots along predefined trajectories is crucial. This work presents a comparative study on the effects of parametric uncertainties, external disturbances, measurement noises, and initial deviations on the trajectory-tracking performance of a 4-wheel drive Mecanum robot. First, the kinematic and kinetic models of the Mecanum robot are introduced. Then, the integral sliding mode control is designed, and proof of stability is provided. In addition, we explore other control strategies, including PID, feedback linearization, sliding mode, and adaptive sliding mode control, that are designed for this robot. Furthermore, the particle swarm optimization algorithm is hired for the controllers with a cost function as the total sum of average error, maximum error, and final error. Optimization has been done on all controllers to compare the results fairly. To appraise the effectiveness of the proposed control optimization methods, simulations are carried out in MATLAB/Simulink. The results reveal that the proposed ISMC method performs best in both defined scenarios compared to other controllers. However, it must be noted that the ISMC controller exhibits limitations when facing significant uncertainties in the dynamic model. This study underscores the effectiveness of our proposed control method and provides valuable insights into the practical implementation controller for the Mecanum robot in real-world applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking of Robotic Arms Using Learning Modified Transpose Jacobian

Trajectory Tracking of Robotic Arms Using Learning Modified ...

引用

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

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

In this research, the issue of trajectory tracking in task space of a robotic arm with rotational joints has been solved. For this purpose, a non-model based controller the modified jacobian-transpose is used which it’s performance has been improved by reinforcement learning. Traditionally, the settings of the error thresholds for this controller will require trial and error, but in this algorithm, reinforcement learning is used to adjust these parameters online and according to the conditions. The simulations for the desired trajectory indicate that the improvement of the trajectory tracking achieved by using proposed algorithm. Also, the superiority of this controller in noisy conditions compared to the reference Jacobian transpose controller has been shown.

关键词：

来源：评论

学校读者我要写书评

暂无评论

C2FNet: Coarse-to-Fine Keypoint Localization Network for Monocular 6D Object Pose Estimation

C2FNet: Coarse-to-Fine Keypoint Localization Network for Mon...

引用

Chinese Automation Congress (CAC)

作者： Jiahao Sun Xin Ma Yibin Li Center for Robotics School of Control Science and Engineering Shandong University Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan China

Estimating the 6D object pose from a singular RGB image is a fundamental task in the field of computer vision. Recent studies have demonstrated that keypoint-based methods exhibit remarkable efficacy. Such methodologies initially identify keypoints and subsequently deduce the object”s pose by addressing a Perspective-n-Point (PnP) problem. Nonetheless., the prevalent approach of directly regressing the 2D coordinates of keypoints renders these methods sensitive to occlusions. Instead., we inaugurate a coarse-to-fine keypoint localization network (C2FNet)., where we utilize the predicted keypoint offsets from the first stage as input to deformable convolutional networks (DCN) in the second stage., to further capture geometric features and enhance spatial relationships between keypoints., thus outputting accurate and robust keypoint coordinates. Experiments indicate that the proposed approach surpasses existing advanced methods in terms of performance on the LINEMOD and Occlusion LINEMOD datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition

arXiv

引用

arXiv 2023年

作者： Song, Chuanxin Wu, Hanbo Ma, Xin Center for Robotics School of Control Science and Engineering Shandong University China Engineering Research Center of Intelligent Unmanned System Ministry of Education China

Exploring the semantic context in scene images is essential for indoor scene recognition. However, due to the diverse intra-class spatial layouts and the coexisting inter-class objects, modeling contextual relationships to adapt various image characteristics is a great challenge. Existing contextual modeling methods for scene recognition exhibit two limitations: 1) They typically model only one type of spatial relationship (order or metric) among objects within scenes, with limited exploration of diverse spatial layouts. 2) They often overlook the differences in coexisting objects across different scenes, suppressing scene recognition performance. To overcome these limitations, we propose SpaCoNet, which simultaneously models Spatial relation and Co-occurrence of objects guided by semantic segmentation. Firstly, the Semantic Spatial Relation Module (SSRM) is constructed to model scene spatial features. With the help of semantic segmentation, this module decouples spatial information from the scene image and thoroughly explores all spatial relationships among objects in an implicit manner, thereby obtaining semantic-based spatial features. Secondly, both spatial features from the SSRM and deep features from the Image Feature Extraction Module are allocated to each object, so as to distinguish the coexisting object across different scenes. Finally, utilizing the discriminative features above, we design a Global-Local Dependency Module to explore the long-range co-occurrence among objects, and further generate a semantic-guided feature representation for indoor scene recognition. Experimental results on three widely used scene datasets demonstrate the effectiveness and generality of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Sim-to-real: Quadruped Robot control with Deep Reinforcement Learning and Parallel Training

Sim-to-real: Quadruped Robot Control with Deep Reinforcement...

引用

IEEE International Conference on robotics and Biomimetics

作者： Han Jiang Teng Chen Jingxuan Cao Jian Bi Guanglin Lu Guoteng Zhang Xuewen Rong Yibin Li Center for Robotics School of Control Science and Engineering Shandong University China

ISBN: (纸本)9781665481106

In recent years, deep reinforcement learning methods provide a new realization idea for the motion control of the quadruped robot, which makes the neural network controller have the characteristics of strong adaptability and high stability. In this paper, we propose an end-to-end neural network framework that, contains an estimator network for estimating the robot's ontology states in addition to the critic and actor networks. These states serve as an important observation data for the critic and actor networks. In addition, in order to solve the disadvantage of high cost of neural network training time, we exploit the mechanism of parallel training and deploy the entire training process in GPU, which improves the speed of network convergence. Finally, we reconstruct the forward network on the CPU through the Eigen library, and transfer the model to the real robot, successfully implementing sim-to-real. We demonstrate our model on SDUQuad-48, and experiments show that the learned policy can achieve various dynamic motions with strong robustness.

关键词： Training Computational modeling Neural networks Graphics processing units Reinforcement learning Robustness Libraries

来源：评论

学校读者我要写书评

暂无评论

Dynamics Modeling of Continuum Robots Using Screw Theory for Real-time control

Dynamics Modeling of Continuum Robots Using Screw Theory for...

引用

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

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

Modeling the dynamics of continuum robotic arms is challenging due to the highly nonlinear nature and uncertain and complicated inherent structure. This affects the application of continuum arms in various aspects, such as inverse kinematics, path generation, optimization, and control. This paper deals with the dynamics modeling of continuum robotic arms using screw theory to develop a suitable model with high accuracy, speed, and low computational load to achieve real-time control. By using the representation of the Lie group of screws in the screw theory, which simplifies the mathematics of the problem, it is possible to achieve a real-time integrated representation of the dynamics of the deformation of the body of continuum robotic arms. This provides the possibility of accurately predicting the system behavior even in the presence of external forces acting on the end-effector. The experimentally validated results for circular and infinite motion trajectories show the model effectiveness in enhancing the trajectory tracking performance and ability to estimate configuration shape changes under external loads. The integration of this model in soft robotic arms has the potential to revolutionize their application in a wide range of industries and medical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weld Seam Extraction of Intersecting Pipelines Based on Point Cloud Entropy 11

Weld Seam Extraction of Intersecting Pipelines Based on Poin...

引用

11th IEEE Data Driven control and Learning Systems Conference, DDCLS 2022

作者： Lu, Shuaibing Shi, Xiaorui Tian, Xincheng Liu, Yan Center for Robotics School of Control Science and Engineering Shandong University Jinan250061 China Engineering Research Center of Intelligent Unmanned System Ministry of Education Jinan250061 China SINOTRUK Jinan Power Co. Ltd

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

This paper presents a method for extracting intersecting pipelines weld seam based on point cloud. Firstly, the collected point cloud is filtered by PassThrough filter to extract the region of interest, and the intersecting pipelines model is reconstructed by using the camera calibration results and the pose of robot. Then VoxelGrid filtering and Moving Least Squares filtering are performed on the reconstructed model to smooth the error caused by camera and robot. The Fast Point Feature Histograms of point cloud is used to calculate the entropy map, and the weld seam region is extracted by threshold segmentation. Finally, an iterative algorithm for weld point extraction based on entropy is proposed. Through experimental verification, the algorithm can extract the weld points of the actual intersecting pipelines and obtain the real position of the weld points in the robot base coordinate frame, which has great application value in robot automatic welding area. © 2022 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Path Finding and Moving Stability-Focused Trajectory Planning for Mobile Robots

Towards Efficient Path Finding and Moving Stability-Focused ...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Hou, Muyang Lei, Zhenya Hu, Haidong Wang, Zhong Wang, Yong Xie, Le Wang, Hesheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Beijing Institute of Control Engineering Beijing100190 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Department of Automation Shanghai200240 China

ISBN: (纸本)9781665481090

Nowadays, mobile robots play an important role in a variety of service scenarios. They need to plan and track trajectories to accomplish tasks such as delivery or guided tours. In such tasks, there are two remaining challenges: on one hand, the time and memory consumption of present path planners are still significant;on the other hand, service robots, which have a higher center of gravity, demand greater moving stability than that of current trajectory planners provide. To address these two challenges. Firstly, we propose a safety boundary first A∗ which fully utilizes environmental obstacle information to create a safety boundary and searches in it to quickly find an initial path. Secondly, we formulate the trajectory optimization problem as a nonlinear optimization problem, where the smoothness, safety, feasibility, and moving stability of the robot are taken into account. Furthermore, to constrain the robot's lateral acceleration, we design a time allocation algorithm based on non-uniform B-spline, enhancing the quality of the resulting trajectory. Simulations and real-world experiments demonstrate that our algorithms significantly improve path search efficiency, enhance moving stability, reduce the difficulty of tracking, and improve the quality of task completion. © 2024 IEEE.

关键词： Trajectories

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

Robust Nonlinear Observer-based Adaptive Visual Servo control for a Multirotor

Robust Nonlinear Observer-based Adaptive Visual Servo Contro...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Long, Yu Zhong, Hang Qian, Zhenyu Liu, Min Zhang, Hui Jiang, Yiming Wang, Yaonan Hunan University College of Electrical and Information Engineering Changsha410082 China National Engineering Research Center for Robot Visual Perception and Control Changsha China Hunan University College of Robotics Changsha410082 China China China Highway Engineering ConsultingCorporation DATA CO. LTD Beijing100089 China

ISBN: (纸本)9798350372601

In this article, an robust nonlinear observer-based visual servo adaptive control strategy is investigated for a multirotor for stable tracking of targets. This article uses the Newton Euler equation to model the dynamics of the multirotor and describes the visual servo system model. In order to avoid being affected by various disturbances, this article designs disturbance observer and velocity observer to improve the robustness of the system. Based on nonlinear observers, this article designs a layered controller that includes a visual outer loop controller and an adaptive sliding mode geometric inner loop controller. To verify the feasibility of this algorithm, this article conducts simulation experiments using MATLAB and Simulink, and adds constant disturbances for verification. Both simulation experiments and experimental results in real environments show that the controller we designs has excellent stability and robustness. © 2024 IEEE.

关键词： Euler equations

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：