检索结果-内蒙古大学图书馆

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

作者： Hamed Ghasemi Elnaz Balazadeh Shayan Malekpour Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory University of Tehran Tehran Iran Department of electrical and computer engineering School of Electrical and Computer engineering University of Tehran Tehran Iran

This article presents two approaches based on deep learning for achieving autonomous navigation and subsequently, conducts an in-depth comparative analysis to elaborate their respective performance. Both methods leverage neural networks to facilitate navigation. The first approach employs a deep convolutional neural network to identify suitable areas for forward movement, while the second method utilizes the drone’s front camera to capture images, which are then processed by a generative network to generate corresponding depth images. Importantly, both approaches rely solely on an RGB camera, resulting in cost savings for the robot and reduced energy consumption. The training data used for classifying collision-free and appropriate paths were gathered from simulated environments closely resembling real indoor settings. The proposed model calculates the probability associated with each segment of the input image, enabling the selection of the most viable area for drone flight. Incorporating generative networks as a depth estimation module enhances flight accuracy, making navigation in uncharted environments more straightforward. The accuracy of depth estimation was evaluated using standard criteria, achieving an accuracy rate of $84 \%$. This result underscores the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scene Understanding in Pick-and-Place Tasks: Analyzing Transformations Between Initial and Final Scenes

Scene Understanding in Pick-and-Place Tasks: Analyzing Trans...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Seraj Ghasemi Hamed Hosseini MohammadHossein Koosheshi Mehdi Tale Masouleh Ahmad Kalhor Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (数字)9798350376340

ISBN: (纸本)9798350376357

With robots increasingly collaborating with humans in everyday tasks, it is important to take steps toward robotic systems capable of understanding the environment. This work focuses on scene understanding to detect pick-and-place tasks given initial and final images from the scene. To this end, a dataset is collected for object detection and pick-and-place task detection. A YOLOv5 network is subsequently trained to detect the objects in the initial and final scenes. Given the detected objects and their bounding boxes, two methods are proposed to detect the pick-and-place tasks which transform the initial scene into the final scene. A geometric method is proposed which tracks objects' movements in the two scenes and works based on the intersection of the bounding boxes which moved within scenes. Contrarily, the CNN-based method utilizes a Convolutional Neural Network to classify objects with intersected bounding boxes into 5 classes, showing the spatial relationship between the involved objects. The performed pick-and-place tasks are then derived from analyzing the experiments with both scenes. Results show that CNN-based method, by VGG-16 backbone, outscores the geometric method by roughly 12% in certain scenarios, with an overall success rate of 84.3%.

关键词： YOLO electrical engineering Accuracy Tracking Transforms Feature extraction Manipulators

来源：评论

学校读者我要写书评

暂无评论

Scene Understanding in Pick-and-Place Tasks: Analyzing Transformations Between Initial and Final Scenes

arXiv

引用

arXiv 2024年

作者： Ghasemi, Seraj Hosseini, Hamed Koosheshi, MohammadHossein Masouleh, Mehdi Tale Kalhor, Ahmad Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran

With robots increasingly collaborating with humans in everyday tasks, it is important to take steps toward robotic systems capable of understanding the environment. This work focuses on scene understanding to detect pick-and-place tasks given initial and final images from the scene. To this end, a dataset is collected for object detection and pick-and-place task detection. A YOLOv5 network is subsequently trained to detect the objects in the initial and final scenes. Given the detected objects and their bounding boxes, two methods are proposed to detect the pick-and-place tasks which transform the initial scene into the final scene. A geometric method is proposed which tracks objects’ movements in the two scenes and works based on the intersection of the bounding boxes which moved within scenes. Contrarily, the CNN-based method utilizes a Convolutional Neural Network to classify objects with intersected bounding boxes into 5 classes, showing the spatial relationship between the involved objects. The performed pick-and-place tasks are then derived from analyzing the experiments with both scenes. Results show that CNN-based method, by VGG-16 backbone, outscores the geometric method by roughly 12% in certain scenarios, with an overall success rate of 84.3%.MSC Codes computer Vision and Pattern Recognition (***), Systems and Control (***) © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AGILE: Approach-based Grasp Inference Learned from Element Decomposition

AGILE: Approach-based Grasp Inference Learned from Element D...

引用

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

作者： MohammadHossein Koosheshi Hamed Hosseini Mehdi Tale Masouleh Ahmad Kalhor Mohammad Reza Hairi Yazdi Human and Robot Interaction Laboratory School of Mechanical Engineering University of Tehran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran School of Mechanical Engineering College of Engineering University of Tehran

humans, this species expert in grasp detection, can grasp objects by taking into account hand-object positioning information. This work proposes a method to enable a robot manipulator to learn the same, grasping objects in the most optimal way according to how the gripper has approached the object. Built on deep learning, the proposed method consists of two main stages. In order to generalize the network on unseen objects, the proposed Approach-based Grasping Inference involves an element decomposition stage to split an object into its main parts, each with one or more annotated grasps for a particular approach of the gripper. Subsequently, a grasp detection network utilizes the decomposed elements by Mask R-CNN and the information on the approach of the gripper in order to detect the element the gripper has approached and the most optimal grasp. In order to train the networks, the study introduces a robotic grasping dataset collected in the Coppeliasim simulation environment. The dataset involves 10 different objects with annotated element decomposition masks and grasp rectangles. The proposed method acquires a 90% grasp success rate on seen objects and 78% on unseen objects in the Coppeliasim simulation environment. Lastly, simulation-to-reality domain adaptation is performed by applying transformations on the training set collected in simulation and augmenting the dataset, which results in a 70% physical grasp success performance using a Delta parallel robot and a 2 -fingered gripper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Path Planning of Mobile robots Using IsoCost-Based Dynamic Programming

Optimal Path Planning of Mobile Robots Using IsoCost-Based D...

引用

Iranian Conference on electrical engineering (ICEE)

作者： Fatemeh Alvankarian Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran

This paper proposes an optimal local path planning algorithm for mobile robots by means of the so-called IsoCost-based dynamic programming. This algorithm explores and finds the optimal paths to the goal point from different start points in the environment of the robot while avoiding arbitrary numbers and forms of obstacles. The concept of IsoCost HyperSurface (ICHS) is first explained and it is shown that with a certain cost value, the ICHS corresponding to optimal path planning surrounds all other ICHSs corresponding to non-optimal path planning algorithms. Based on this geometric property, agents are initiated and planned to explore and reveal the optimal ICHSs using dynamic programming. The optimality of the proposed method is proved and the results of this method are compared with those of Modified Potential Field and Bug2 algorithms, indicating that the proposed method surpasses the other two algorithms in terms of the optimality of path length and execution time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grasp the Graph (GtG): A Super Light Graph-RL Framework for robotic Grasping

Grasp the Graph (GtG): A Super Light Graph-RL Framework for ...

引用

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

作者： Ali Rashidi Moghadam Mehdi Tale Masouleh Ahmad Kalhor Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran

This paper introduces Grasp the Graph, an innovative framework addressing challenges posed by processing point clouds with conventional neural networks for robotic grasping. Such challenges often lead to the conversion of point clouds to multi-view images or voxel grids, requiring large networks with millions of parameters. Grasp the Graph formulates robotic grasping as a one-step reinforcement learning problem and leverages graph representation and graph neural networks to efficiently process geometric relationships in point clouds. The lightweight design with only 67k parameters facilitates swift training and strong generalization to novel objects, offering the capability to propose multiple valid grasping candidates. Empirical testing demonstrates the effectiveness of the proposed approach, achieving a 90.4% success rate on test objects while being trained with only 10 objects. Even with a three-camera setup during training, reducing the cameras during evaluation minimally impacts performance, resulting in less than a 3% decrease. 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developing a Reinforcement Learning-Based Actor-Critic Neural Network Controller for General Form of Serial Chain robots with Torque Constraints

SSRN

引用

SSRN 2023年

作者： Bahrami, Vahid Masouleh, Mehdi Tale Kalhor, Ahmad School of Electrical and Computer Engineering University of Tehran Human and Robot Interaction Laboratory Tehran Iran

This paper presents a regulation control system for Serial Chain robots (SCRs) using Reinforcement Learning (RL) algorithms. The main challenge is the high dimensionality of the state and action spaces due to the multiple degrees-of-freedom in SCRs. Traditional optimal control methods rely on mathematical models and solving differential equations, while RL offers a computationally intensive alternative. In this study, a controller is proposed with key features: reduced reliance on robot dynamics knowledge, applicability to various robots (SCRs and Cable-Driven Serial Chain robots (CDSCRs)), and the ability to limit torque. This method avoids complex computations of Coriolis vectors by modifying variables in the robot's dynamics to achieve a zero equilibrium point for regulation error. Actor-critic Neural Network (NN) based on RL methods is used for the adaptation laws of the regulator torque, while a MLP-NN is employed for the desired steady-state torque. Stability of the controller designs is ensured using suitable Lyapunov functions. Simulations on a 4-DoF CDSCR, representing a finger segment of the human body, validate the proposed control method's effectiveness. © 2023, The Authors. All rights reserved.

关键词： robots

来源：评论

学校读者我要写书评

暂无评论

Developing a Reinforcement Learning-Based Actor-Critic Neural Network Controller for General Form of Serial Chain robots with Torque Constraints

SSRN

引用

SSRN 2023年

作者： Bahrami, Vahid Masouleh, Mehdi Tale Kalhor, Ahmad School of Electrical and Computer Engineering University of Tehran Human and Robot Interaction Laboratory Tehran Iran

关键词： robots

来源：评论

学校读者我要写书评

暂无评论

Enhancing Impulse Response-Based SSVEP Decoding Method by Incorporating Temporal Local Correlation 7

Enhancing Impulse Response-Based SSVEP Decoding Method by In...

引用

7th International Conference on Biological Information and Biomedical engineering, BIBE 2024

作者： Huang, Jiayang Wang, Jiaxi Yang, Pengfei Xiong, Bang Zhang, Zhi-Qiang School of Computer Science and Technology The Key Laboratory of Smart Human-Computer Interaction Wearable Technology of Shaanxi Province Xidian University China School of Electronic and Electrical Engineering Institute of Robotics Autonomous Systems and Sensing University of Leeds United Kingdom

ISBN: (纸本)9783800762910

Various training-based spatial filtering methods have been proposed to classify steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). However, many overlook the temporal instability of SSVEPs, leading to decreased classification performance. Therefore, we propose an SSVEP decoding method that calculates template signals and spatial filters using the subject's impulse responses and periodic impulses, incorporating the temporally local correlation coefficient in the SSVEP decoding process. Then, we employ a combined correlation coefficient for SSVEP classification. The proposed method addresses the temporal instability of SSVEPs, with template signals that exhibit strong individual characteristics. Utilizing a public benchmark dataset, we achieved a classification accuracy of 87.43% and an ITR of 256.1 bits/min at 1s time window, demonstrating the performance of this method. Compared to other classical spatial filtering methods, the proposed method demonstrates superior classification performance, which can enhance the practical usability of SSVEP-BCI systems. © VDE VERLAG GMBH.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

JoTyMo: Joint Type and Movement Detection from RGB Images of Before and After Interacting with Articulated Objects

JoTyMo: Joint Type and Movement Detection from RGB Images of...

引用

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

作者： Ehsan Forootan Hamed Ghasemi Mehdi Tale Masouleh Ahmad Kalhor Behzad Moshiri Human and Robot Interaction Laboratory Electrical and Computer Engineering Department University of Tehran

This paper presents a CNN-based network architecture aimed to classify and detect joint types within Articulated objects, specifically the Push-P joints, P-joints, R-joints and objects lacking joints. The movement modeling of the detected objects is explored by processing pre and post interaction RGB images within the SAPIEN PartNet-Mobility dataset. In order to achieve this, an architecture is proposed to leverage consecutive CNN encoders based on the VGG architecture, in order to classify joints based on pre and post-interaction images. Additionally, in order to detect the effect-point and movement vector, a convolutional encoder is applied for each joint type. Moreover, extensive evaluation is made to showcase the results, achieving 96% accuracy in joint classification and 94% accuracy in regression on the considered dataset. Elaborate details regarding network architectures, training procedures, and testing methodologies are available at source code repository.

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：