检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and Automation

作者： Saivimal Sridar Corey J. Majeika Phillip Schaffer Matthew Bowers Seiichiro Ueda Andrew J. Barth Jon L. Sorrells Jon T. Wu Thane R. Hunt Marko Popovic Robotics Engineering Program Worcester Polytechnic Institute United States

ISBN: (纸本)9781467380270

Hydro Muscles are linear actuators resembling ordinary biological muscles in terms of active dynamic output, passive material properties and appearance. The passive and dynamic characteristics of the latex based Hydro Muscle are addressed. The control tests of modular muscles are presented together with a muscle model relating sensed quantities with net force. Hydro Muscles are discussed in the context of conventional actuators. The hypothesis that Hydro Muscles have greater efficiency than McKibben Muscles is experimentally verified. Hydro Muscle peak efficiency with (without) back flow consideration was 88% (27%). Possible uses of Hydro Muscles are illustrated by relevant robotics projects at WPI. It is proposed that Hydro Muscles can also be an excellent educational tool for moderate-budget robotics classrooms and labs;the muscles are inexpensive (in the order of standard latex tubes of comparable size), made of off-the-shelf elements in less than 10 minutes, easily customizable, lightweight, biologically inspired, efficient, compliant soft linear actuators that are adept for power-augmentation. Moreover, a single source can actuate many muscles by utilizing control of flow and/or pressure. Still further, these muscles can utilize ordinary tap water and successfully operate within a safe range of pressures not overly exceeding standard water household pressure of about 0.59 MPa (85 psi).

关键词： artificial muscle soft actuators hydraulics pneumatics control robots

来源：评论

学校读者我要写书评

暂无评论

Inverse reinforce learning with nonparametric behavior clustering

arXiv

引用

arXiv 2017年

作者： Rajasekaran, Siddharthan Zhang, Jinwei Fu, Jie Department of Electrical and Computer Engineering Robotics Engineering Program Worcester Polytechnic Institute

Inverse Reinforcement Learning (IRL) is the task of learning a single reward function given a Markov Decision Process (MDP) without defining the reward function, and a set of demonstrations generated by humans/experts. However, in practice, it may be unreasonable to assume that human behaviors can be explained by one reward function since they may be inherently inconsistent. Also, demonstrations may be collected from various users and aggregated to infer and predict users behaviors. In this paper, we introduce the Non-parametric Behavior Clustering IRL algorithm to simultaneously cluster demonstrations and learn multiple reward functions from demonstrations that may be generated from more than one behaviors. Our method is iterative: It alternates between clustering demonstrations into different behavior clusters and inverse learning the reward functions until convergence. It is built upon the Expectation-Maximization formulation and non-parametric clustering in the IRL setting. Further, to improve the computation efficiency, we remove the need of completely solving multiple IRL problems for multiple clusters during the iteration steps and introduce a resampling technique to avoid generating too many unlikely clusters. We demonstrate the convergence and efficiency of the proposed method through learning multiple driver behaviors from demonstrations generated from a grid-world environment and continuous trajectories collected from autonomous robot cars using the Gazebo robot simulator. Copyright © 2017, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Design of interval type-2 fuzzy logic controllers for flocking algorithm

Design of interval type-2 fuzzy logic controllers for flocki...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Seung-Mok Lee Jong-Hwan Kim Hyun Myung Department of Civil and Environmental Engineering Robotics Program KAIST Daejeon South Korea Department of Electrical Engineering and Computer Science Robotics Program KAIST Daejeon South Korea

This paper presents a novel interval type-2 fuzzy logic control architecture for flocking system when the system has noisy sensor measurements. The traditional type-1 fuzzy logic controller (FLC) using precise type-1 fuzzy sets cannot fully model and handle the uncertainties of sensor data. However, type-2 FLC using type-2 fuzzy sets with a footprint of uncertainty (FOU) produces better performances under noisy environments. In this paper, therefore, we present a reactive control architecture for flocking algorithm that is based on interval type 2 FLC to implement the flocking behaviors consisting separation, obstacle avoidance, and velocity matching behaviors. The type-2 based control system could cope with the uncertainties of noisy sensor measurements and resulted in good performances that outperformed the type-1 FLC.

关键词： Collision avoidance Robot sensing systems Trajectory Fuzzy sets Fuzzy logic Noise measurement

来源：评论

学校读者我要写书评

暂无评论

A YOLOv7-Based Method for Detecting Buttons in Service Robots during Autonomous Elevator-Taking Tasks

A YOLOv7-Based Method for Detecting Buttons in Service Robot...

引用

2023 International Conference on Advanced robotics and Intelligent Systems, ARIS 2023

作者： Chen, Ming-Hsin Huang, Wei-Hsiang Li, Tzuu-Hseng S. National Cheng Kung University Program on Ai Robotics AiRobots Lab. Tainan Taiwan Ncku AiRobots Lab. Dept. of Electrical Engineering Tainan Taiwan

ISBN: (纸本)9798350302714

This paper presents a novel visual algorithm based on YOLOv7, designed to enhance the robustness of automated elevator-taking service robots in detecting elevator buttons. Traditional solutions for elevator interaction, such as image processing methods, feature selection, or wireless communication protocols, have inherent limitations related to communication security issues and additional equipment costs. In order to overcome these challenges, our method leverages a physical robotic arm and the YOLOv7 object detection neural network to improve the accuracy of elevator button detection and enable effective robot-elevator interaction. To identify elevator buttons, we employ single-stage object detection algorithms along with multiple cameras to capture comprehensive environmental information during experimental trials. By utilizing these techniques, our proposed method ensures the safety and reliability of the automated elevator-taking process for service robots. Experimental results demonstrate the effectiveness of our algorithm in accurately detecting elevator buttons across various testing scenarios. Overall, our method offers a more suitable solution for service robots to autonomously navigate elevators and perform their intended tasks. © 2023 IEEE.

关键词： Elevators

来源：评论

学校读者我要写书评

暂无评论

RoboRover - A Jetson Nano Powered Robot Car for Object Following, Obstacle Avoidance, and Wall Following 14

RoboRover - A Jetson Nano Powered Robot Car for Object Follo...

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Huynh, Trinh Walter, James Aveta, Federica University of Michigan Robotics Department Ann ArborMI48109 United States Wentworth Insitute of Technology Electrical and Computer Engineering Program BostonMA02115 United States

ISBN: (纸本)9798350304138

An intelligent and self-sufficient robot is essential across a wide range of fields, including transportation, industry, space exploration, and defense. Mobile robots possess the capability to undertake diverse tasks such as handling materials, aiding in disaster scenarios, conducting patrols, and executing rescue operations. As a result, the development of an autonomous robot that can navigate through both unchanging and ever-changing surroundings has become important. The primary objective of mobile robot navigation revolves around ensuring the seamless and secure traversal of the robot through complex environments, starting from an initial position, and reaching a designated goal position. This paper presents the design and implementation of a Jetson Nano powered robot car which uses local sensors to interact with an unknown environment. Object following, obstacle avoidance, and wall following features are built for the car to navigate to reach its desired destinations. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Decisioning System for Wifi Access Point Installation using Genetic Algorithm

Design and Implementation of Decisioning System for Wifi Acc...

引用

2022 International Electrical engineering Congress, iEECON 2022

作者： Thitinaruemit, Aphirak Sitjongsataporn, Suchada Prongnuch, Sethakarn Mahanakorn University of Technology Electrical Engineering Graduate Program Faculty of Engineering and Technology Bangkok Thailand Faculty of Engineering and Technology Dept. of Electronic Engineering Bangkok Thailand Suan Sunandha Rajabhat University Faculty of Industrial Technology Dept. of Robotics Engineering Bangkok Thailand

ISBN: (纸本)9781665402064

This paper presents the design and implementation of a WiFi indoor localization system using genetic algorithm. The coverage capability of the wireless access point is an important parameter in the design to estimate the distance from the transmitted and received signals. The main purpose of this work is to find the effective number of wireless access points in the design area by using genetic algorithm. The Received Signal Strength (RSSI) is measured for the signal quality. The test area consists of the multiple classrooms on the same floor inside the building and the conditions are unobstructed and used the line-of-sight for transmitted and received signals. The experimental results by measuring the received signal through a laptop are indicated that RSSI = -35 dBm at a distance of 5 meters is a prominent indicator of signal quality that can be used to search a variety of information from internet inside the classroom. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization of fish-like locomotion using hierarchical reinforcement learning

Optimization of fish-like locomotion using hierarchical rein...

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Jeonghyeon Wang Jinwhan Kim Robotics Program Ocean Robotics & Intelligence (ORIN) Laboratory Department of Mechanical Engineering KAIST Daejeon Korea

With an interest in advanced marine propulsion systems, much research has been done on mimicking fish-like locomotion using flapping fins. This study aims to optimize the swimming pattern of fish-like locomotion based on hierarchical reinforcement learning. A simplified carangiform fish model is employed and a segmented tail motion is learned by Q-learning to maximize the average forward velocity by flapping the tail fin. The performance of the self-learned swimming pattern is verified and analyzed in terms of the flapping efficiency. The results show that the flapping angle limit of approximately 35 degrees is best in maximizing the forward moving velocity and the hierarchical reinforcement learning approach is effective in providing a reasonable solution for a large-scale problem.

关键词： Learning (artificial intelligence) Learning systems Mathematical model Markov processes Robots Propulsion

来源：评论

学校读者我要写书评

暂无评论

A classification scheme for planar 4r, spherical 4r, and spatial rccc linkages to facilitate computer animation

A classification scheme for planar 4r, spherical 4r, and spa...

引用

ASME 1998 Design engineering Technical Conferences, DETC 1998

作者： Murray, Andrew P. Larochelle, Pierre M. Department of Mechanical and Aerospace Engineering University of Dayton DaytonOH45469-0210 United States Robotics and Spatial Systems Laboratory Mechanical Engineering Program Florida Institute of Technology Melbourne FL32901 United States

ISBN: (纸本)9780791880319

In this paper we develop a complete classification scheme for planar, spherical and spatial four-bar linkages. The goal of this classification is to note all of the subtleties of motion that an arbitrary set of four link lengths can define. A classification should exist only between the mechanisms that exhibit similar ranges of motion at both the input and output. In the planar case, three parameters being identified as either positive, negative, or zero are necessary to completely characterize all possible ranges of motion. In the spherical and spatial cases, four parameters being identified as positive, negative or zero are needed. The result is 27 classifications of planar mechanisms and 81 for spherical and spatial RCCC mechanisms. © 1998 by ASME.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning with Pedestrian Trajectory Prediction Model for Service Robot Navigation in Crowded Environments

Deep Reinforcement Learning with Pedestrian Trajectory Predi...

引用

2023 International Conference on Advanced robotics and Intelligent Systems, ARIS 2023

作者： Wang, Shih-Hao Wu, Yu-Hsiung Li, Tzuu-Hseng S. National Cheng Kung University Ms Degree Program on Ai Robotics AiRobots Laboratory Tainan Taiwan Ncku AiRobots Laboratory Dept. of Electrical Engineering Tainan Taiwan

ISBN: (纸本)9798350302714

Safety and effectiveness are crucial considerations in the navigation of robots within crowded environments. Previous research in this field has predominantly focused on an omniscient approach, designing environments with exceptional obstacle avoidance capabilities. However, this approach fails to address the constraints imposed by real-world applications' limited field of view. Additionally, constructing a robot with a complete field of view can be prohibitively expensive. To tackle these challenges, this paper presents a novel approach that combines a social spatial-temporal graph convolutional neural network (Social-STGCN) with reinforcement learning (RL) to enhance crowd avoidance navigation. This approach offers a more practical and cost-effective solution. Simulations conducted to evaluate our proposed method demonstrate its effectiveness by achieving higher success rates and lower collision rates compared to existing approaches. These results confirm the efficiency and safety of our algorithm for crowd avoidance navigation. In practical applications, we employ the Intel RealSense L515 camera to capture depth and RGB image data, enabling the utilization of the Deep SORT algorithm for pedestrian tracking and recognition. This facilitates the acquisition of accurate position and speed information. To validate the performance of our system, we conducted robot experiments in real-world scenarios, including indoor corridors and elevator lobbies. The results obtained from these experiments clearly indicate that our proposed system successfully accomplishes navigation tasks with improved safety and effectiveness. In summary, this paper introduces an effective crowd avoidance navigation algorithm. By leveraging the Social-STGCN and RL techniques, our algorithm enables robots to navigate tasks with enhanced safety and efficiency, even when their field of view is limited. © 2023 IEEE.

关键词： Air navigation

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Task State Estimation for Safer Automation of Oxy-Fuel Metal Cutting 19

CNN-Based Task State Estimation for Safer Automation of Oxy-...

引用

19th IEEE International Conference on Automation Science and engineering, CASE 2023

作者： Akl, James Kodate, Shreedhar Calli, Berk Worcester Polytechnic Institute Robotics Engineering Department WorcesterMA01609 United States Worcester Polytechnic Institute Data Science Program WorcesterMA01609 United States

ISBN: (纸本)9798350320695

The industrial operation of oxy-fuel metal cutting via gas torches involves tasks such as ignition, preheating, and combustion along the target surface. Automated oxy-fuel cutting systems are exposed to risks and anomalies that can lead to incorrect actions and safety hazards. In this paper, we develop a classifier for online task state estimation to assess the cutting robot's actions, detect anomalies, and reduce the risk of hazards. Using representative footage from our robotic cutting experiments, we curate an image dataset labeled with four types of cutting task states. Using deep learning methods, we design and train a convolutional neural network model for classifying the cutting task state from input images. The classifier architecture is optimized for rapid inferences during online estimation. After evaluation, our classifier achieves an overall accuracy of 93.8 % with high inference speeds on two types of representative hardware. Our 'Oxy-fuel Cutting Task State' (OCTS) dataset is available at ***/10.5281/zenodo.7734951. © 2023 IEEE.

关键词： Risk assessment

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：