检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yoon, Jeonghyeon Park, Junhyun Park, Hyojae Lee, Hakyoon Lee, Sangwon Hwang, Minho The Department of Robotics and Mechatronics Engineering DGIST Daegu42988 Korea Republic of

In robot-assisted minimally invasive surgery (RAMIS), optimal placement of the surgical robot base is crucial for successful surgery. Improper placement can hinder performance because of manipulator limitations and inaccessible workspaces. Conventional base placement relies on the experience of trained medical staff. This study proposes a novel method for determining the optimal base pose based on the surgeon's working pattern. The proposed method analyzes recorded end-effector poses using a machine learning-based clustering technique to identify key positions and orientations preferred by the surgeon. We introduce two scoring metrics to address the joint limit and singularity issues: joint margin and manipulability scores. We then train a multi-layer perceptron regressor to predict the optimal base pose based on these scores. Evaluation in a simulated environment using the da Vinci Research Kit shows unique base pose score maps for four volunteers, highlighting the individuality of the working patterns. Results comparing with 20,000 randomly selected base poses suggest that the score obtained using the proposed method is 28.2% higher than that obtained by random base placement. These results emphasize the need for operator-specific optimization during base placement in RAMIS. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Resampling Strategies for Increasing Point Density in Narrow Passages for Probabilistic Roadmaps

Resampling Strategies for Increasing Point Density in Narrow...

引用

ASME/IFToMM International Conference on Reconfigurable Mechanisms and Robots, ReMAR

作者： Bartłomiej Bonar Tomasz Buratowski Department of Robotics and Mechatronics Faculty of Mechanical Engineering and Robotics AGH University of Krakow Kraków Poland

ISBN: (数字)9798350395969

ISBN: (纸本)9798350395976

This paper presents multiple point-sampling strategies for stochastic approach to path planning. Their main purpose is to increase points density in narrow corridors, which are often difficult areas to navigate using non-deterministic approach for path planning. At the same time, algorithms for distributing points over the area of narrow regions and reducing their number in open space are described as well as postprocessing algorithm distancing samples from obstacles. Simulation-based tests are performed to compare achieved results and estimate calculation times.

关键词： Navigation Gaussian distribution Probabilistic logic Vectors Path planning Computational efficiency Complexity theory

来源：评论

学校读者我要写书评

暂无评论

From AI to AGI - The Evolution of Real-Time Systems with GPT Integration

From AI to AGI - The Evolution of Real-Time Systems with GPT...

引用

IEEE Southeastcon

作者： Aarush Kaunteya Pande Preston Brantley Muhammad Hassan Tanveer Razvan Cristian Voicu Department of Robotics & Mechatronics Engineering Kennesaw State University Marietta Georgia

Generative artificial intelligence (AI), particularly ChatGPT, is revolutionizing various sectors, from exercise applications to accounting software, politics, and pharmaceuticals. As versatile aerial vehicles, drones have broad applications in videography, military operations, and surveying. However, their programming and optimal utilization often require extensive training. This research tackles these challenges by utilizing ChatGPT's sophisticated logic and prompt training features to enable drones to operate autonomously in various settings, ranging from everyday tasks to emergencies like search and rescue missions. Enhancing Microsoft Research's PromptCraft robotics, the project integrates innovative algorithms and GPT-4-Vision, improving command efficiency, speed, and accuracy. This integration also leverages additional sensor data feedback, allowing the drones to process user prompts with enhanced contextual understanding. Initial results show a significant improvement in command response times and accuracy, enabling the drones to interpret and execute complex voice commands in various environments. This paper presents a multimodal framework that enriches the capabilities of voice-controlled robotic systems and broadens the scope of AI applications in real-time systems, laying the groundwork for customized AI-driven systems, including robots tailored for diverse applications and the shift towards AGI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Realistic Sound with Prosthetic Hand: A Reinforcement Learning Approach 46

Generating Realistic Sound with Prosthetic Hand: A Reinforce...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Jeong, Taemoon Yamsani, Sankalp Hong, Jooyoung Park, Kyungseo Kim, Joohyung Choi, Sungjoon Korea University Department of Artificial Intelligence Seoul Korea Republic of University of Illinois Urbana-Champaign Department of Electrical and Computer Engineering ChampaignIL United States Department of Robotics and Mechatronics Engineering Daegu Korea Republic of

ISBN: (纸本)9798350371499

In this study, we tackle the complex task of enabling prosthetic hands to accurately reproduce sounds, a crucial aspect for distinguishing between different materials through auditory feedback. Sound identification, such as discerning a drywall tap from that on a brick wall, significantly enhances the functionality and user experience of prosthetic devices. However, achieving this level of auditory feedback in prosthetic hands poses considerable challenges. We utilize reinforcement learning (RL) techniques to train prosthetic hands in emulating human-like sound characteristics, focusing on key auditory signals like amplitude and onset timing. Our approach integrates a detailed analysis of these sound attributes to direct the prosthetic hand's movements for the sound generation that mimics natural human actions. We developed a tailored reward function incorporating amplitude, onset strength, and timing criteria to ensure the prosthetic hand's movements align closely with the intended human-like sound output. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Humanoid robotics Powered by Vision-Based LLM Zero Shot Interactions

Humanoid Robotics Powered by Vision-Based LLM Zero Shot Inte...

引用

IEEE Southeastcon

作者： Gabriel David Smith Kwasi Debrah-Pinamang Razvan Cristian Voicu Department of Robotics & Mechatronics Engineering Kennesaw State University Marietta Georgia USA

ISBN: (数字)9798331504847

ISBN: (纸本)9798331504854

Advancements in artificial intelligence (AI) have transformed robotics by enabling systems to autonomously execute complex tasks with minimal human involvement. Traditional methods, however, often depend on costly hardware, continuous monitoring, and intricate software integration, which constrain scalability and widespread implementation. This research presents an innovative approach that combines vision-based large language models (LLMs) with zero-shot prompting to autonomously program robotic systems, including a humanoid robot equipped with dual manipulators. The proposed system harnesses contextual image data to efficiently generate task-specific code, eliminating the need for iterative corrections. Training is conducted through OpenAI's Assistant feature, utilizing documents predominantly comprising images, while continuous operation is facilitated by a self-looping mechanism. Experimental results highlight the system's capability to perform manipulator tasks with notable accuracy, paving the way for scalable, adaptive, and dynamic automation. This study addresses both practical and theoretical challenges in automation, providing a cost-effective framework for next-generation robotic systems.

关键词： Training Accuracy Automation Large language models Scalability Humanoid robots Software Stereo vision Sensors Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

Development and Control of an Autonomous User-Tracking Golf Caddie Robot

引用

Journal of Institute of Control, robotics and Systems 2022年第2期28卷 102-108页

作者： Kim, Byeong-Soo Choi, Jung Hyun Lee, Chan Oh, Sehoon Machinery & Robot Industry Promotion Team Daegu Mechatronics & Materials Institute Korea Republic of Department of Robotics Engineering DGIST Korea Republic of Department of Robot Engineering Yeungnam University Korea Republic of

This study proposes an autonomous caddie robot system that can automatically track a golf player. The caddie robot is designed to operate in two modes: an autonomous human-tracking mode, and a power-assisted manual driving mode. Mode conversion can be autonomously performed through the driving mode determination algorithm based on the distance and angle between a user and the robot, and angle of inclination. When the latter is too steep for the robot to track the user, the user can utilize a manual mode to guide the robot with minimal force. This study seeks to provide insight into how the high-level controller of the mobile platform should be configured to track users in flat and sloping environments. Experimental results obtained from tests in the golf course verify that the robot can be successfully utilized in golf games. © ICROS 2022.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Parallel Elastic Actuators for Minimizing Required Torque and Power: Comparison with Series Elastic Actuators

Optimal Design of Parallel Elastic Actuators for Minimizing ...

引用

Annual Conference of Industrial Electronics Society

作者： Kyeongsik Shin Sehoon Oh Dept. Robotics and Mechatronics Engineering DGIST Daegu Republic of Korea

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

This paper proposes an optimal design methodology for Parallel Elastic Actuators (PEAs) that minimizes torque and power consumption for tasks with external conditions. Furthermore, the paper advocates for selecting an actuator based on a comparison of the dynamic characteristics of PEAs and Series Elastic Actuators (SEAs) for a specific task. However, the design of actuators may need to vary depending on the task and application, but the criteria for this are often unclear. To address the ambiguous design criteria, we analyze the dynamic characteristics of PEAs and SEAs under external conditions and utilize them for optimal design. By formulating cost functions for various tasks, we identify the most suitable actuator design for each task. This study establishes criteria for designing PEAs for tasks with external conditions and proposes a general framework for PEA design optimization.

关键词： Industrial electronics Actuators Torque Power demand Gears Design methodology Cost function Numerical models Springs Design optimization

来源：评论

学校读者我要写书评

暂无评论

Design of the Interior Permanent Magnet Synchronous Motor for Electric Vehicles Using Grain-Oriented Electrical Steel

引用

Transactions of the Korean Institute of Electrical Engineers 2022年第7期71卷 939-944页

作者： Kwon, Min-Su Lim, Dong-Kuk Seo, Hyeon-Uk Dept. of Electrical Electronic and Computer Engineering University of Ulsan Korea Republic of Dept. of Robotics & Mechatronics Korea Institute of Machinery Materials Korea Republic of

In this paper, the interior permanent magnet synchronous motor (IPMSM) for electric vehicles (EVs) using grain-oriented electrical steel (GO) is proposed. It was confirmed through the B-H characteristic curve and the B-W characteristic curve that the GO has superior magnetic characteristic compared to the non-grain-oriented electrical steel (NO). In order to maximize the effect of GO, the GO was partially applied to the stator teeth that has a uniform magnetic flux direction through magnetic path analysis of the EV traction motor. It has been confirmed that the output and various characteristics of the motor have improved with the application of GO. In particular, the iron loss was decreased by 44.83% in no-load condition. Moreover, the average torque and the efficiency were increased by 5.26%, 0.29%, respectively and the iron loss was decreased by 42.45% in load condition. The result of this study shows that the partial application of the GO in IPMSM improves the performance of the motor, effectively © 2022 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Traction motors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Accessibility and Affordability of Mobile Robotic Platforms Through MMATR: A Modular Machine-Learning Autonomous Trainable Rover

Enhancing Accessibility and Affordability of Mobile Robotic ...

引用

IEEE Southeastcon

作者： Daniel Byers Mark Vladimir Ogloblin Brandon Nguyen M. Hassan Tanveer Matt Marshall Yusun Chang Department of Robotics & Mechatronics Engineering Kennesaw State University Marietta Georgia

Traditional mobile robotic platforms often prove cost-prohibitive for small enterprises, offering limited functionality constrained to pre-programmed tasks. The Modular Machine-Learning Autonomous Trainable Rover (MMATR) ad-dresses this gap by striving to democratize access to automated mobile robotics. Prioritizing cost-effectiveness, programma-bility, and user-friendliness, MMATR presents an accessible solution. This research outlines MMATR's primary goals: autonomous operation through embedded machine learning, user-friendly retraining facilitated by a Python GUI, extensi-bility via user-developed modules, and a generatively designed, consumer-sized 3D-printable chassis. MMATR integrates a diverse range of functionalities, including five ultrasonic sensors for autonomous navigation, a user-friendly Python GUI for retraining the embedded machine learning model, and the capa-bility to extend functionality through user-developed modules. This paper details the design, implementation, and potential applications of MMATR, contributing to the advancement of accessible and affordable mobile robotic platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network

arXiv

引用

arXiv 2024年

作者： Park, Junhyun Jang, Seonghyeok Park, Hyojae Bae, Seongjun Hwang, Minho The Department of Robotics and Mechatronics Engineering DGIST Daegu42988 Korea Republic of

Flexible continuum manipulators are valued for minimally invasive surgery, offering access to confined spaces through nonlinear paths. However, cable-driven manipulators face control difficulties due to hysteresis from cabling effects such as friction, elongation, and coupling. These effects are difficult to model due to nonlinearity and the difficulties become even more evident when dealing with long and coupled, multi-segmented manipulator. This paper proposes a data-driven approach based on Deep Neural Networks (DNN) to capture these nonlinear and previous states-dependent characteristics of cable actuation. We collect physical joint configurations according to command joint configurations using RGBD sensing and 7 fiducial markers to model the hysteresis of the proposed manipulator. Result on a study comparing the estimation performance of four DNN models show that the Temporal Convolution Network (TCN) demonstrates the highest predictive capability. Leveraging trained TCNs, we build a control algorithm to compensate for hysteresis. Tracking tests in task space using unseen trajectories show that the proposed control algorithm reduces the average position and orientation error by 61.39% (from 13.7mm to 5.29mm) and 64.04% (from 31.17◦ to 11.21◦), respectively. This result implies that the proposed calibrated controller effectively reaches the desired configurations by estimating the hysteresis of the manipulator. Applying this method in real surgical scenarios has the potential to enhance control precision and improve surgical performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Hysteresis

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：