检索结果-内蒙古大学图书馆

Position-aware pushing and grasping synergy with deep reinforcement learning in clutter

CAAI Transactions on Intelligence Technology 2024年第3期9卷 738-755页

作者： Min Zhao Guoyu Zuo Shuangyue Yu Daoxiong Gong Zihao Wang Ouattara Sie Intelligent Robotics Laboratory Faculty of Information TechnologyBeijing University of TechnologyBeijingChina Beijing Key Laboratory of Computational Intelligence and Intelligent Systems BeijingChina Laboratory of Biomechatronics and Intelligent Robotics(BIRO) Department of Mechanical and Aerospace EngineeringNorth Carolina State UniversityRaleighNorth CarolinaUSA

The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in *** effectively perform grasping and pushing manipu-lations,robots need to perceive the position information of objects,including the co-ordinates and spatial relationship between objects(e.g.,proximity,adjacency).The authors propose an end-to-end position-aware deep Q-learning framework to achieve efficient collaborative pushing and grasping in ***,a pair of conjugate pushing and grasping attention modules are proposed to capture the position information of objects and generate high-quality affordance maps of operating positions with features of pushing and grasping *** addition,the authors propose an object isolation metric and clutter metric based on instance segmentation to measure the spatial re-lationships between objects in cluttered *** further enhance the perception capacity of position information of the objects,the authors associate the change in the object isolation metric and clutter metric in cluttered environment before and after performing the action with reward function.A series of experiments are carried out in simulation and real-world which indicate that the method improves sample efficiency,task completion rate,grasping success rate and action efficiency compared to state-of-the-art end-to-end *** that the authors’system can be robustly applied to real-world use and extended to novel *** material is available at https://***/NhG\_k5v3NnM}{https://***/NhG\_k5v3NnM.

关键词： deep learning deep neural networks intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Path Tracing and Validation of Omni Wheeled Mini Robot Using Visual Feedback 11

Path Tracing and Validation of Omni Wheeled Mini Robot Using...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Ahamed, Aftaab Jayaraj, Karthik Fazil, Shibin Nikitha, S. Sudheer, P.A. National Institute of Technology Calicut Robotics Interest Group Mechatronics Robotics Laboratory India National Institute of Technology Calicut Mechatronics/Robotics Laboratory Mechanical Engineering Department India

ISBN: (纸本)9798350379136

Holonomic drives are gaining popularity in many fields due to their versatility in various industrial applications. The ability of the holonomic drive robots to move in all directions makes it distinct from other drive mechanisms. Open-loop control of omnidirectional bots can be achieved with relative ease whereas automating it is not as easy. When trying to create an automated system with lower cost, off the shelf components and hardware, other problems may arise as a result of the poor performance of the components. Here a three wheeled omnidirectional robot that can trace a predefined path without human intervention has successfully been developed. © 2024 IEEE.

关键词： Open loop control

来源：评论

学校读者我要写书评

暂无评论

Low-resistance, high-force, and large-ROM fabric-based soft elbow exosuits with adaptive mechanism and composite bellows

引用

Science China(Technological Sciences) 2023年第1期66卷 24-32页

作者： HUANG WeiCheng FENG Miao YANG DeZhi GU GuoYing Robotics Institute School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China Meta Robotics Institute Shanghai Jiao TongUniversityShanghai 200240China

Due to the lightweight and compliance, fabric-based pneumatic exosuits are promising in the assistance and rehabilitation of elbow impairments. However, existing elbow exosuits generally suffer from remarkable mechanical resistance on the flexion of the elbow, thus limiting the output force, range of motion(ROM), and comfortability. To address these challenges, we develop a fabric-based soft elbow exosuit with an adaptive mechanism and composite bellows in this work. With the elbow kinesiology considered, the adaptive mechanism is fabricated by sewing the interface of the exosuit into spring-like triangle pleats, following the profile of the elbow to elongate or contract when the elbow flexes or extends. The composite bellows are implemented by further sealing a single blade of bellows into two branches to enhance the output force. Based on these structural features, we characterize the mechanical performance of different soft elbow exosuits: exosuit with normal bellows-NB, exosuit with adaptive mechanism and normal bellows-AMNB, exosuit with adaptive mechanism and composite bellows-AMCB. Experimental results demonstrate that by comparing with NB, the mechanical resistance of AMNB and AMCB decreases by 80.6% and 78.6%, respectively;on the other hand, the output torque of AMNB and AMCB increases to 120.3% and 207.0%, respectively, at50 k Pa when the joint angle is 120°. By wearing these exosuits on a wooden arm model(1.25 kg), we further verify that AMCB can cover a full ROM of 0°–130° at the elbow with 500 g weight. Finally, the application on a health volunteer with AMCB shows that when the volunteer flexes the elbow to lift a weight of 500 g, the s EMG activity of the biceps and triceps is markedly reduced.

关键词： wearable robots rehabilitation robots soft robot applications soft actuators design

来源：评论

学校读者我要写书评

暂无评论

Tailoring the in-plane and out-of-plane stiffness of soft fingers by endoskeleton topology optimization for stable grasping

引用

Science China(Technological Sciences) 2023年第11期66卷 3080-3089页

作者： LI DeChen CHEN ShiTong SONG ZeNan LIANG JiaLong ZHU XiangYang CHEN FeiFei State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Meta Robotics Institute Shanghai Jiao Tong UniversityShanghai 200240China

The intrinsic compliance of soft materials endows soft robots with great advantages to achieve large deformation and adaptive interactions in grasping ***,current soft grippers usually focus on the in-plane large deformation and load capacity but ignore the effect of out-of-plane external loads,which may lead to instability in practical *** problem calls for stiffness design along multiple directions to withstand not only in-plane interacting forces with objects,but also unexpected outof-plane *** this paper,we design a new type of soft finger by embedding an endoskeleton inside the widely-used PneuNets actuator,and the endoskeleton layout is optimized to achieve a remarkable bending deflection and limited lateral deflection under combined external in-plane and out-of-plane *** on the multi-objective topology optimization approach,the key structural features of the optimized endoskeleton are extracted and *** multi-material soft fingers are fabricated by the silicone compound mold *** and dynamic experiment results validate that the soft gripper with endoskeleton embedded exhibits remarkably improved out-of-plane stiffness,without sacrificing the in-plane bending flexibility,and leads to more stable grasping.

关键词： soft robot soft gripper stable grasping topology optimization pneumatic actuator

来源：评论

学校读者我要写书评

暂无评论

Design of Fuzzy controller for position control of a magnetic catheter in uniform magnetic fields 11

Design of Fuzzy controller for position control of a magneti...

引用

11th RSI International Conference on robotics and Mechatronics, ICRoM 2023

作者： Bidgoli, Mohammadhossein Zahedi Pouya, Mohammad Hatami Pishkenari, Hossein Nejat Taheri, Alireza Sharif University of Technology Nano Robotics Laboratory Department of Mechanical Engineering Tehran Iran Sharif University of Technology Robotics Laboratory Department of Mechanical Engineering Tehran Iran

ISBN: (纸本)9798350308105

Magnetic catheters have gained popularity as a safer and more precise alternative to manually guided catheters, reducing X-ray exposure for medical professionals. However, achieving precise control of the catheter's tip remains a topic of debate. In this paper, we introduce a fuzzy controller designed to control the position of the magnetic catheter's tip with high accuracy in a controlled environment with a uniform magnetic field and a feeder mechanism, providing a 3DOF setup. We implemented the fuzzy controller using a dynamic Cosserat model of the magnetic catheter and conducted simulations to assess its performance. To evaluate the closed-loop system, two trajectory paths, one following a cubic pattern and the other a helical pattern, were provided as desired inputs to the closed-loop system using the proposed controller. Additionally, Gaussian-distributed noise was added to the feedback loop of the system. The Root Mean Square Error (RMSE) values for a catheter with a variable free length ranging from 3 to 5 cm for these two input trajectories were 0.96 mm and 0.86 mm, respectively. The simulation results indicated that the presented control system has the capability to accurately track various trajectories with high precision. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Bifunctional nanoprobe for simultaneous detection of intracellular reactive oxygen species and temperature in single cells

引用

Microsystems & Nanoengineering 2024年第6期10卷 161-172页

作者： Yanmei Ma Weikang Hu Jian Hu Muyang Ruan Jie Hu Ming Yang Yi Zhang Hanhan Xie Chengzhi Hu Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy EngineeringSouthern University of Science and TechnologyShenzhen 518000China Department of Electrical and Electronic Engineering Southern University of Science and TechnologyShenzhen 518000China

Living cells can rapidly adjust their metabolic activities in response to external stimuli,leading to fluctuations in intracellular temperature and reactive oxygen species(ROS)*** these parameters is essential for understanding cellular metabolism,particularly during dynamic biological *** this study,we present a bifunctional nanoprobe capable of simultaneous measurement of ROS levels and temperature within single *** nanoprobe features two individually addressable nanoelectrodes,with platinum(Pt)and nickel(Ni)coatings on both *** the tip,these two metal layers form a nano-thermocouple,enabling precise intracellular temperature measurements,while the Pt layer facilitates selective ROS *** dual functionality allows for real-time monitoring of cellular responses during synergistic chemo-photothermal therapy of cancer cells and zebrafish embryos subjected to mitochondrial toxic *** results demonstrate that the nanoprobe effectively measures increases in temperature and ROS levels in HeLa cells undergoing chemo-photothermal therapy,as well as in chemically stimulated zebrafish *** providing detailed analysis of submicrometer-scale temperature and ROS variations within living cells,this nanoprobe offers valuable insights into cellular processes and holds promise for early disease detection and drug development.

关键词： metabolism simultaneous holds

来源：评论

学校读者我要写书评

暂无评论

3-Dimentional path planning and movement control of red blood cell immersed in plasma medium among moving obstacles 12

3-Dimentional path planning and movement control of red bloo...

引用

12th RSI International Conference on robotics and Mechatronics, ICRoM 2024

作者： Mehrabani, Mahboube Rahnavard Ronizi, Ahmad Reza Korayem, Moharam Habibnejad School of Mechanical Engineering Iran University of Science and Technology Robotics Research Laboratory Tehran Iran

ISBN: (纸本)9798331529734

This research focuses on planning the 3-dimensional path and controlling the movement of red blood cells in a blood plasma medium among moving obstacles. This research evaluates the performance of genetic algorithm and fuzzy logic control in navigating red blood cells through such environments. Results show that both methods achieve high path efficiency, with genetic algorithm at 90.75% and fuzzy logic control at 88.31%. fuzzy logic control demonstrated faster computation times, making it suitable for fewer or unpredictable obstacles, while genetic algorithm is preferable for environments with many or predictable obstacles. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Optimal Control of a Magnetically Actuated Capsule Endoscope Using Electromagnetic Coils Considering Small Intestine Dynamics 12

Enhanced Optimal Control of a Magnetically Actuated Capsule ...

引用

12th RSI International Conference on robotics and Mechatronics, ICRoM 2024

作者： Jamali, Mahdi Zarifi Khameneh, Mohammadreza Sarkhosh, Mohammadhossein Pishkenari, Hossein Nejat Sharif University of Technology Micro/Nano Robotics Laboratory Department of Mechanical Engineering Tehran Iran

ISBN: (纸本)9798331529734

Active locomotion of capsule endoscopes has become a prominent progress in minimally invasive diagnostic procedures. Utilizing external magnetic fields for this purpose enables contactless actuation and enhanced maneuverability. This study presents an optimal control technique for magnetically actuated capsule endoscopes (MACE) within the small intestine, using a modified OCTAMAG setup. The objective is to minimize input currents while ensuring accurate path tracking, thereby preventing coil overheating and avoiding actuation inaccuracies. A correction force is also incorporated into the controller to stabilize it against external disturbances. The proposed method is evaluated using a path inspired by the small intestine and compared to conventional PID control. Results show that the optimal controller achieves superior path tracking while maintaining input currents within safe limits. Additionally, the disturbance rejection capabilities of the optimal controller are comparable to those of the PID. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Path planning of mobile robot based on reinforcement learning to reach faster training 12

Path planning of mobile robot based on reinforcement learnin...

引用

12th RSI International Conference on robotics and Mechatronics, ICRoM 2024

作者： Takzare, Niloofar Lademakhi, Naeim Yousefi Korayem, Moharam Habibnejad School of Mechanical Engineering Iran University of Science and Technology Robotics Resaerch Laboratory Tehran Iran

ISBN: (纸本)9798331529734

Recent advances in reinforcement learning have to its adoption for solving complex and challenging problems in robotics, which has been well received by researcher. One of the advantages of deep reinforcement learning (DRL) is its ability to be applied without prior knowledge of the system. Path planning of mobile robots and avoid obstacle are among the biggest challenges in mobile robotics. In this article, a reinforcement learning algorithm is proposed, which automatically learns an optimal state for controlling the robot using several action parameters and a proposed artificial potential new reward function. Therefore, the robot path planning finds its way to the goal with fast training and less time. The simulation has been performed for two command and proposed algorithms in the environment with and without obstacle. The results of the simulations showed that the robot is able to reach all the set goals faster with the proposed new reward function. Also, the path planning has been validation with the feedback linear control. The reason is that the feedback linearization method takes a smoother path than DQN, but the DQN algorithm with the proposed reward function learns much faster and reaches all the set target points. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Synergy Between Soft Feet and an Active Tail to Enhance the Climbing Ability of a Bio-inspired Climbing Robot

引用

Journal of Bionic engineering 2024年第2期21卷 729-739页

作者： Pongsiri Borijindakul Tachadol Suthisomboon Alihong Ji Zhendong Dai Poramate Manoonpong Institute of Bio-inspired Structure and Surface Engineering College of Mechanical and Electrical EngineeringNanjing University of Aeronautics and AstronauticsNanjing210016China Bio-inspired Robotics and Neural Engineering Laboratory School of Information Science and TechnologyVidyasirimedhi Institute of Science and TechnologyRayong21210Thailand

Lizards use the synergy between their feet and tail to climb on slopes and vertical *** use their soft adhesive feet with millions of small hairs to increase their contact area with the terrain surface and press their tails against the terrain to actively maintain stability during *** by this,we propose a bio-inspired climbing robot based on a new approach wherein the synergy between soft feet and an active tail with a soft adhesive tip allows the robot to climb stably on even and uneven terrains at different slope *** evaluate and compare the climbing performance of the robot on three different terrains(hard,soft,and fluffy)at different slope *** robot configurations are employed,including those with standard hard feet and soft feet in combination with an active tail-with and without a soft *** experimental results show that the robot having soft feet and a tail with the soft tip achieves the best climbing performance on all terrains,with maximum climbing slopes of 40°,45°,and 50°on fluffy,soft,and hard terrains,*** payload capacity depends on the type of terrain and the inclination ***,our robot performs multi-terrain transitions(climbing from horizontal to sloped terrains)on three different terrains of a *** approach can allow a climbing robot to walk and climb on different terrains,extending the operational range of the robot to areas with complex terrains and slopes,e.g.,in inspection,exploration,and construction.

关键词： Bio-inspired climbing robots Climbing robots Soft foot Active tail Soft terrain Terrain transitions

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：