检索结果-内蒙古大学图书馆

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Shakerimov, Aidar Sarmonov, Shamil Amirova, Aida Oralbayeva, Nurziya Zhanatkyzy, Aida Telisheva, Zhansaule Aimysheva, Arna Sandygulova, Anara Department of Robotics and Mechatronics School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan Graduate School of Education Nazarbayev University Astana Kazakhstan

ISBN: (纸本)9781450394222

In Kazakhstan, the ongoing Cyrillic-to-Latin alphabet shift raises challenges for early literacy development and acquisition in the Kazakh language. This paper proposes the QWriter system to help young children learn the Latin-based Kazakh alphabet and its handwriting. The system consists of a humanoid robot NAO, a tablet with a stylus, and a Reinforcement Learning (RL) agent that learns a child's mistakes and progress to maximize alphabet learning in the shortest period of time by adapting the order of practice words according to the child's mistakes. To evaluate the effectiveness of the QWriter system, we conducted a between-subject design experiment with 59 Kazakh children aged 6-8 years old and compared their learning performance with a human tutor and the CoWriting Kazakh robot system. The results did not support our assumption, we found that the proposed system received significantly higher likability scores than the baseline human tutor. © 2023 Owner/Author.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Target Tracking Control of Space-Manipulators on Lie Groups

Target Tracking Control of Space-Manipulators on Lie Groups

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Moghaddam, Borna Monazzah Chhabra, Robin Carleton University Autonomous Space Robotics and Mechatronics Laboratory Mechanical and Aerospace Engineering Department OttawaONKIS 5B6 Canada

ISBN: (纸本)9798350337020

We present a full-pose end-effector control approach on Lie groups for free-floating space manipulators with non-zero momentum while tracking a moving target during proximity operations. We model space-manipulators as open-chain multi-body systems with 1-degree-of-freedom joints where the configuration space of the spacecraft is isomorphic to the Special Euclidean group SE(3). We formulate the dynamics of the spacecraft-manipulator via the Lagrange-Poincare equations and the dynamics of its target via Euler-Poincare equations to avoid kinematic singularities associated with parametrization of their poses. This model reduces the phase space of the space-manipulator by exploiting its inherent independence of the spacecraft's pose. We consider the full pose of the end-effector relative to the target as the system output, which transforms the output-tracking control problem into an output-regulation problem. To avoid parametrization singularities of this output, we perform feedback linearization on the matrix Lie group SE (3) in the reduced phase space of the space-manipulator. We then propose a feedback/feedforward proportional-integral-derivative workspace controller, based on coordinate-free pose and velocity error functions defined on the matrix Lie group associated with the target's relative pose. We provide analytical proof of the almost-global stability of the presented controller when regulating the end-effector's pose relative to the target towards identity. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Base Placement of Surgical Robot: Kinematics Data-Driven Approach by Analyzing Working Pattern

arXiv

引用

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

Squid-inspired and wirelessly controllable display for active camouflage in aquatic-environment

引用

npj Flexible Electronics 2024年第1期8卷 900-909页

作者： Doyoung Kim Seung Won Seon Minkyung Shin Jihwan Kim Bogeun Kim Janghoon Joo Sang Uk Park Wooseok Kim Hee Kyu Lee Byeong Woon Lee Se Gi Lee Su Eon Lee Ji-Hun Seo Seung Ho Han Bong Hoon Kim Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan University2066Seobu-roJangan-guSuwon 16419Republic of Korea Department of Smart Wearable Engineering Soongsil UniversitySeoul 06978Republic of Korea Electronic Convergence Materials and Devices Research Center Korea Electronics Technology Institute(KETI)Seongnam 13509Republic of Korea Department of Materials Science and Engineering Korea UniversitySeoul 02841Republic of Korea Department of Robotics and Mechatronics Engineering DGISTDaegu 42988Republic of Korea

Achieving optimal camouflage in an aquatic environment necessitates the ability to modulate transmittance in response to the surrounding obscurity and potential *** adaptation involves a dynamic transition from transparency to a deep-blue color,especially in low-light or dark *** a strategy promotes a seamless assimilation with the surroundings,enabling the absorption of searchlights and,subsequently,diminishing the risk of detection by ***,the presence of sophisticated mechanisms that facilitates stable and efficient control of transmittance is imperative,enabling smooth transition between transparent and deep-blue hues within the aquatic *** study presents nature-inspired programmable camouflage system that integrates an electrochromic display as the primary transmittance change element and a wireless base module for power and data *** technology offers a robust and flexible construction,ensuring stable operation as demonstrated through mechanical-fatigue experiments and quantitative simulation.A custom circuit and a power-control software package enable active control of multiple electrochromic displays while submerged in water.

关键词： transparency submerged lights

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

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

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

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

Development of Novel Stewart Robot Equipped with 3D Printed Soft Actuators

Development of Novel Stewart Robot Equipped with 3D Printed ...

引用

IEEE Southeastcon

作者： Joe Gilmore Cecil Abidoye Devin Grace Razvan Cristian Voicu Turaj Ashuri Amir Ali Amiri Moghadam Department of Robotics & Mechatronics Engineering Kennesaw State University Atlanta Georgia

The Stewart platform, a parallel robot configuration, traditionally employs six rigid linear actuators to connect a base with a mobile platform. These actuators, typically prismatic and connected by spherical or universal joints, are arranged in alternating pairs, enabling six degrees of freedom in positioning and orientation. While this architecture has proven effective in applications requiring robust and rigid positioning systems, the advent of soft or compliant actuators presents new possibilities, especially in applications where safety is paramount, such as in medical robots involving human contact. This paper introduces a novel compliant Stewart mechanism, incorporating soft 3D-printed linear actuators designed to replace the rigid joints and legs in conventional rigid Stewart mechanisms. It explores the implementation of these soft actuators within the Stewart platform's framework, aiming to retain its six degrees of freedom (DOF) motion while enhancing safety and adaptability in sensitive environments. The results demonstrate the feasibility and potential of this approach, opening new avenues in robotic design for medical and other human-interactive applications where the combination of precision, safety, and adaptability is critical.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recursive Input-Output Linearization for Slow-Fast Realization of Nonholonomic Hamiltonian Control Systems

引用

IEEE Transactions on Automatic Control 2024年第6期70卷 3571-3586页

作者： Gzenda, Vaughn Chhabra, Robin Carleton University Autonomous Space Robotics Laboratory OttawaONK1S 5B6 Canada Toronto Metropolitan University Department of Mechanical Industrial and Mechatronics Engineering TorontoONM5B 2K3 Canada

In this paper, we study a slow-fast realization of nonholonomic Hamiltonian control systems mediated by strong friction forces which is viewed as a singular perturbation of the nonholonomic system. We propose a systematic decomposition of the perturbed dynamics into slow and fast directions using the kinetic energy metric and the geometry of friction forces. The (slow) invariant manifold is identified by a set of invariance conditions resulting in partial differential equations that generally do not have an analytic solution. We approximate the invariant manifold along with the control inputs with power series and show that using this approximation the invariance conditions admit an inherent recursion. Accordingly, we develop a recursive procedure to perform dynamic input-output linearization of the approximated slow system. We consider the output trajectory tracking problem using a PD control law on the Nth order approximation of the invariant manifold. Closed-loop stability analysis is performed on both the invariant manifold and the full phase space of the system. We prove that if the internal dynamics of the nonholonomic system is exponentially stable, then the perturbed system remains asymptotically stable. Moreover, we prove that the output error dynamics is uniformly bounded when applying the approximated control law, with bounds dependent on the control gains and strength of the friction force. Our approach is illustrated through a numerical case study on a differential robot. © 1963-2012 IEEE.

关键词： Kinetic energy

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：