检索结果-内蒙古大学图书馆

Development of a Method for Detecting Cutting Points of Wilted Leaves Using 2D Image Keypoints and 3D Point Cloud

Journal of Institute of Control, robotics and Systems 2024年第11期30卷 1237-1244页

作者： Kang, Byeong Chang Jung, Ho Won Kim, Jong Hyeong Department of Mechanical Design and Robot Engineering Seoul National University of Science and Technology Korea Republic of Department of Mechanical System and Design Engineering Seoul National University of Science and Technology Korea Republic of

In agriculture, removing withered leaves is crucial for maintaining crop quality and preventing pests and diseases. This paper proposes a method for estimating the pose of wilted leaves and removing wilted leaves. While estimating precisely 3D location and pose information is essential for this task, most of previous methods for pose estimation have difficulty in processing time due to the complexity of feature extraction from 3D point cloud. The proposed method utilizes the YOLOv8 keypoint detection model to obtain image information, and YOLOv7 instance segmentation to isolate the region of interest. We calculate the 3D coordinates of the cutting point and the 3D rotation of the wilted leaf by applying RANSAC plane fitting and projection on 3D point cloud, simplifying the information required for the task. The method was validated using five types of model plant pots, achieving an average processing time of 98.584 ms and an accuracy of 3.83 mm. Additionally, the method recorded a 78% success rate in the removal of withered leaves. © 2024, Institute of Control, robotics and Systems. All rights reserved.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Vertical-Axis Rotary Triboelectric Nanogenerator with a Dual-Shaft design for Enhanced Performance

Vertical-Axis Rotary Triboelectric Nanogenerator with a Dual...

引用

IEEE SENSORS

作者： Jingu Jeong Soonjae Pyo Deparment of Mechanical Design and Robot Engineering Department of Mechanical System Design Engineering Seoul National University of Science and Technology Seoul Republic of Korea

ISBN: (数字)9798350363517

ISBN: (纸本)9798350363524

Triboelectric nanogenerators (TENGs) offer a promising avenue for renewable energy generation, particularly from wind sources. In this study, we present a structural modification approach to enhance the output performance of rotary-type wind-driven TENGs by introducing a dual-shaft mechanism. This design modification significantly improves energy harvesting efficiency and reliability across a wide range of wind speeds, especially under low wind speed conditions. Our dual-shaft TENG (DS-TENG) nearly doubles the frequency of contact-separation events compared to conventional configurations, resulting in substantially higher electrical output. Experimental results demonstrate that the DS-TENG consistently outperforms traditional designs across all wind speed ranges, with notable improvements in RMS voltage (108.72%) and current (119.82%). Fast Fourier Transform analysis further highlights the potential of the DS-TENG for reliable low wind speed anemometry. The versatility of the dual-shaft design enables its application in various rotary-type energy harvesters, offering a promising solution for sustainable energy harvesting in diverse environmental conditions.

关键词： Wind energy generation Voltage measurement Fast Fourier transforms Wind speed Contacts Nanogenerators Urban areas Stators Reliability engineering Triboelectricity

来源：评论

学校读者我要写书评

暂无评论

Integrated Walking Control Strategy With Model Predictive Control and Whole–body Control Using Deep Learning–based State Estimator

引用

Journal of Institute of Control, robotics and Systems 2024年第10期30卷 1139-1146页

作者： Jeon, Sanghyeon Kwon, Na-Hyun Ha, Seong-Min Kim, Jung-Yup Department of Mechanical Design and Robot Engineering Seoul Nat’l Univ. of Science and Technology Korea Republic of

This paper proposes a walking strategy that integrates Model Predictive Control (MPC) and Whole-Body Control (WBC) based on a single rigid body model. Additionally, it develops and utilizes a novel state estimator based on LSTM deep learning instead of the commonly used Kalman filter–based state estimator. MPC and WBC are methods that enable walking robots to perform various tasks without falling. Therefore, this study uses MPC based on a single rigid body model to derive the optimal ground reaction force. Subsequently, in WBC, constraints are added to satisfy robot dynamics equations and track the optimal ground reaction force. Finally, through WBC, the optimal joint torque is computed considering whole-body floating dynamics and optimal ground reaction forces. All of these computations are performed based on the newly developed deep learning–based state estimator. The proposed control strategy is validated through Gazebo simulation using a quadruped walking robot, Go2. © ICROS 2024.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

A High-throughput Uniform-Sized Droplet Generator with a Triangular Cross-Section Channel Fabricated by Simple Mems Process and Self-Alignment 22

A High-throughput Uniform-Sized Droplet Generator with a Tri...

引用

22nd International Conference on Solid-State Sensors, Actuators and Microsystems, Transducers 2023

作者： Oh, Byeolnim Cho, Youngseo Park, Jaewon Cho, Younghak Kim, Hyun Soo Kwangwoon University Department Of Electronic Engineering Seoul Korea Republic of Seoul National University Of Science & Technology Department Of Mechanical Design And Robot Engineering Seoul Korea Republic of Korea University Division Of Environmental Science & Ecological Engineering Seoul Korea Republic of

ISBN: (纸本)9784886864352

In this study, a step emulsification (SE) device with an inverted triangular cross-section channel was developed for high-throughput monodisperse droplet generation. The SE device consisting of two different height channels (step ratio of sample solution and carrier oil channel heights = 1 : 4) was fabricated by simple, low-cost MEMS processes (e.g., anisotropic wet etching), and the triangular channel design for the sample solution was easily formed through a self-alignment process based on geometric similarity. The developed SE device successfully created the same size of droplets over a wide range of flow rate variations. The stable and robust droplet generation capability of the developed device allowed for massive production. © 2023 IEEJ.

关键词： Monodisperse droplet generation step emulsification triangular cross-section

来源：评论

学校读者我要写书评

暂无评论

GainAdaptor: Learning Quadrupedal Locomotion with Dual Actors for Adaptable and Energy-Efficient Walking on Various Terrains

arXiv

引用

arXiv 2024年

作者： Kim, Mincheol Kwon, Nahyun Kim, Jung-Yup Humanoid Robot Research Laboratory Department of Mechanical Design and Robot Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of

Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics, either directly manage joint torques or use proportional-derivative (PD) controllers to regulate joint positions at a higher level. In case of DRL, direct torque control presents significant challenges, leading to a preference for joint position control. However, this approach necessitates careful adjustment of joint PD gains, which can limit both adaptability and efficiency. In this paper, we propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency. The framework employs a dual-actor algorithm to dynamically adjust the PD gains based on varying ground conditions. By utilizing a divided action space, GainAdaptor efficiently learns stable and energy-efficient locomotion. We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains. Supplementary videos are available at https://***/view/gainadaptor © 2024, CC BY-NC-ND.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement of Piezoresistive Tactile Sensor Based on mechanical Metamaterial with Negative Poisson's Ratio

Performance Enhancement of Piezoresistive Tactile Sensor Bas...

引用

IEEE SENSORS

作者： Mingyu Kang Honggap Choi Keun Park Soonjae Pyo Deparment of Mechanical Design and Robot Engineering Seoul National University of Science and Technology Seoul Republic of Korea Department of Mechanical System Design Engineering Seoul National University of Science and Technology Seoul Republic of Korea

ISBN: (数字)9798350363517

ISBN: (纸本)9798350363524

This work proposes a piezoresistive tactile sensor based on a metamaterial with a negative Poisson's ratio, utilizing a more cost-effective and straightforward method compared to previous processes for fabricating microstructures. To demonstrate the impact of negative Poisson's ratio on piezoresistive sensor performance, comparison structures with a positive Poisson's ratio are designed, manufactured, and tested. The metamaterial-based sensor exhibits a high sensitivity at low pressures, which is 2.8 times higher than that of a body-centered cubic structure and 10 times higher than a simple cubic structure. Additionally, the fabricated sensor demonstrates excellent flexibility and minimal physical interference due to the integration of flexible electrodes and substrates. The sensor shows potential for various applications, including wearable devices, which have recently gained significant attention.

关键词： Performance evaluation Electrodes Sensitivity Tactile sensors Interference Metamaterials Microstructure Wearable devices Piezoresistance Substrates

来源：评论

学校读者我要写书评

暂无评论

Quadruped Walking Algorithm Integrating Balance Control Using Cartinverted Pendulum Model and Optimization-based Whole-body Inverse Dynamics Control

引用

Journal of Institute of Control, robotics and Systems 2024年第9期30卷 1024-1036页

作者： Han, Kyu-Chur Kim, Hyun-Seok Kim, Jung-Yup Department of Mechanical Design and Robot Engineering Seoul Nat’l Univ. of Science and Technology Korea Republic of Smart Robotics Team Hyundai-Rotem Co Korea Republic of

This paper presents a walking strategy that enables stable locomotion on irregular ground and allows a quadruped robot to respond to external impact disturbances while walking. Initially, we designed a cart inverted pendulum model (CIPM) for dynamic control of the quadruped robot and converted the control commands derived from the LQR controller into ground reaction forces for balance control using quadratic programming (QP). Next, the derived ground reaction forces were converted into optimal joint torques that integrated the cost function and ground friction conditions through Whole-Body Inverse Dynamics Control (WBIDC) using a floating base dynamic model to realize the stable walking of the robot. To verify the algorithm, ground obstacles and an impact disturbance applicator were modeled on the walking path in the GAZEBO simulation environment, demonstrating successful performance of the quadruped robot walking algorithm presented in this paper. © ICROS 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Learning Quadrupedal Locomotion with Impaired Joints Using Random Joint Masking

Learning Quadrupedal Locomotion with Impaired Joints Using R...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Mincheol Kim Ukcheol Shin Jung-Yup Kim Department of Mechanical Design and Robot Engineering Humanoid Robot Research Laboratory Seoul National University of Science and Technology Seoul Republic of Korea Robotics Institute Carnegie Mellon University Pittsburgh PA US

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Quadrupedal robots have played a crucial role in various environments, from structured environments to complex harsh terrains, thanks to their agile locomotion ability. However, these robots can easily lose their locomotion functionality if damaged by external accidents or internal malfunctions. In this paper, we propose a novel deep reinforcement learning framework to enable a quadrupedal robot to walk with impaired joints. The proposed framework consists of three components: 1) a random joint masking strategy for simulating impaired joint scenarios, 2) a joint state estimator to predict an implicit status of current joint condition based on past observation history, and 3) progressive curriculum learning to allow a single network to conduct both normal gait and various joint-impaired gaits. We verify that our framework enables the Unitree’s Go1 robot to walk under various impaired joint conditions in real-world indoor and outdoor environments.

关键词： Legged locomotion Deep reinforcement learning Motion capture Indoor environment Quadrupedal robots Reliability History

来源：评论

学校读者我要写书评

暂无评论

Learning Quadrupedal Locomotion with Impaired Joints Using Random Joint Masking

arXiv

引用

arXiv 2024年

作者： Kim, Mincheol Shin, Ukcheol Kim, Jung-Yup The Humanoid Robot Research Laboratory Department of Mechanical Design and Robot Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of Robotics Institute Carnegie Mellon University PittsburghPA15217 United States

Quadrupedal robots have played a crucial role in various environments, from structured environments to complex harsh terrains, thanks to their agile locomotion ability. However, these robots can easily lose their locomotion functionality if damaged by external accidents or internal malfunctions. In this paper, we propose a novel deep reinforcement learning framework to enable a quadrupedal robot to walk with impaired joints. The proposed framework consists of three components: 1) a random joint masking strategy for simulating impaired joint scenarios, 2) a joint state estimator to predict an implicit status of current joint condition based on past observation history, and 3) progressive curriculum learning to allow a single network to conduct both normal gait and various joint-impaired gaits. We verify that our framework enables the Unitree's Go1 robot to walk under various impaired joint conditions in real-world indoor and outdoor environments. © 2024, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Aerial Dockable Multirotor UAVs: design, Control, and Flight Time Extension Through In-Flight Battery Replacement

引用

IEEE Access 2025年 13卷 96782-96799页

作者： Yeongin Song Hyunmin Kim Jeonghyun Byun Keun Park Murim Kim Seung Jae Lee Department of Mechanical Design and Robot Engineering Seoul National University of Science and Technology (SeoulTech) Seoul Republic of Korea Department of Aerospace Engineering Seoul National University Seoul Republic of Korea Human-Centered Robotics Research and Development Division Korea Institute of Robotics and Technology Convergence (KIRO) Pohang Republic of Korea

This paper presents the development and evaluation of the AirDock system, a novel aerial docking and in-flight battery exchange solution designed to extend the operational flight time of multirotor unmanned aerial vehicles (mUAVs). The proposed system enables seamless mid-flight battery replacement through an aerial docking mechanism and a rail-Car-based battery transfer and retrieval system. The AirDock platform utilizes a fully actuated multirotor design, allowing independent control of six degrees of freedom (DoF) motion to maintain a constant attitude during battery exchange operations, facilitating easy docking. In this research, a generalized control allocation algorithm is introduced to manage dynamic shifts in the center of mass (CoM) during inter-modular battery transportation, ensuring safe flight control and mitigating thruster overloading: a critical factor in avoiding flight failure. Both simulations and real-world experiments validate the system’s effectiveness, demonstrating stable aerial docking, reliable in-flight battery exchange performance, and extended flight durations for mission modules. These findings highlight the AirDock system’s potential to overcome the energy limitations of battery-powered UAVs, extending missions across various applications.

关键词： Batteries Propellers Propulsion Plugs Torque Hardware robots Quadrotors Couplings Buildings

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：