检索结果-内蒙古大学图书馆

21th Annual Conference on Towards Autonomous robotics, TAROS 20120

作者： Hardman, David George Thuruthel, Thomas Iida, Fumiya Bio-Inspired Robotics Lab Department of Engineering University of Cambridge Cambridge United Kingdom

ISBN: (纸本)9783030634858

Control of robots has largely been based on the assumption of a fixed morphology. Accordingly, robot designs have been stationary in time, except for the case of modular robots. Any drastic change in morphology, hence, requires a remodelling of the controller. This work takes inspiration from developmental robotics to present a piecewise morphology-controller growth/adaptation strategy that facilitates fast and reliable control adaptation to growing robots. We demonstrate our methodology on a simple 3 degree of freedom walking robot with adjustable foot lengths and with varying inertial conditions. Our results show not only the effectiveness and reliability of the piecewise morphology controller co-adaptation (PMCCA) strategy, but also highlight the need for morphological adaptation as a robot design strategy. © 2020, Springer Nature Switzerland AG.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Nature's All-in-One: Multitasking Robots inspired by Dung Beetles

arXiv

引用

arXiv 2024年

作者： Leung, Binggwong Gorb, Stanislav Manoonpong, Poramate Bio-inspired Robotics and Neural Engineering Lab School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology Rayong21210 Thailand Functional Morphology and Biomechanics Zoological Institute Kiel University Kiel24118 Germany Embodied AI and Neurorobotics Lab SDU Biorobotics The Mærsk Mc-Kinney Møller Institute The University of Southern Denmark Odense5230 Denmark

Dung beetles impressively coordinate their six legs simultaneously to effectively roll large dung balls. They are also capable of rolling dung balls varying in the weight on different terrains. The mechanisms underlying how their motor commands are adapted to walk and simultaneously roll balls (multitasking behavior) under different conditions remain unknown. Therefore, this study unravels the mechanisms of how dung beetles roll dung balls and adapt their leg movements to stably roll balls over different terrains for multitasking robots. We synthesize a modular neural-based loco-manipulation control inspired by and based on ethological observations of the ball-rolling behavior of dung beetles. The proposed neural-based control contains various neural modules, including a central pattern generator (CPG) module, a pattern formation network (PFN) module, and a robot orientation control (ROC) module. The integrated neural control mechanisms can successfully control a dung beetle-like robot (ALPHA) with biomechanical feet to perform adaptive robust (multitasking) loco-manipulation (walking and ball-rolling) on various terrains (flat and uneven). It can also deal with different ball weights (2.0 and 4.6 kg) and ball types (soft and rigid). The control mechanisms can serve as guiding principles for solving complex sensory-motor coordination for multitasking robots. Furthermore, this study contributes to biological research by enhancing our scientific understanding of sensory-motor coordination for complex adaptive (multitasking) loco-manipulation behavior in animals. © 2024, CC BY.

关键词： Modular robots

来源：评论

学校读者我要写书评

暂无评论

Real-Time Dynamic Robot-Assisted Hand-Object Interaction via Motion Primitives

arXiv

引用

arXiv 2024年

作者： Yuan, Mingqi Wang, Huijiang Chu, Kai-Fung Iida, Fumiya Li, Bo Zeng, Wenjun Bio-Inspired Robotics Lab Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Department of Computing The Hong Kong Polytechnic University Hong Kong Eastern Institute of Technology Zhejiang Ningbo China

Advances in artificial intelligence (AI) have been propelling the evolution of human-robot interaction (HRI) technologies. However, significant challenges remain in achieving seamless interactions, particularly in tasks requiring physical contact with humans. These challenges arise from the need for accurate real-time perception of human actions, adaptive control algorithms for robots, and the effective coordination between human and robotic movements. In this paper, we propose an approach to enhancing physical HRI with a focus on dynamic robot-assisted hand-object interaction (HOI). Our methodology integrates hand pose estimation, adaptive robot control, and motion primitives to facilitate human-robot collaboration. Specifically, we employ a transformer-based algorithm to perform real-time 3D modeling of human hands from single RGB images, based on which a motion primitives model (MPM) is designed to translate human hand motions into robotic actions. The robot’s action implementation is dynamically fine-tuned using the continuously updated 3D hand models. Experimental validations, including a ring-wearing task, demonstrate the system’s effectiveness in adapting to real-time movements and assisting in precise task executions. Copyright © 2024, The Authors. All rights reserved.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Online adaptive resistance control of an arm exercise exoskeleton 23rd

Online adaptive resistance control of an arm exercise exoske...

引用

23rd International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2020

作者： Xiong, Xiaofeng Manoonpong, Poramate Odense5230 Denmark Bio-Inspired Robotics and Neural Engineering Lab The School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology Rayong21210 Thailand

ISBN: (纸本)9781916449046

Resistance training is an effective means of strengthening musculoskeletal capabilities;thereby preventing musculoskeletal disorders (MSDs). However, most existing exoskeletons fail to provide active and affordable resistance training. To address this problem, we develop a resistance-as-needed (RAN) controller and an arm exercise (RISE) exoskeleton for resistance training. The exoskeleton is designed and manufactured in a portable, lightweight (0.425 kg), and 3D print manner. Such control adaptability and design portability are facilitated by the RAN controller whose implementation relies only on internal (e.g., joint position) sensing, rather than external (i.e., EMG, electromyography) sensing and physical compliant mechanisms (e.g., springs). The active resistance torque to the RISE exoskeleton is generated by the RAN controller, in which impedance gains Kp and Kd are online tuned. As a result, the RAN controller enables the RISE exoskeleton to produce more adaptive and effective resistance motions that lead to higher training efficiency, compared to conventional constant impedance controllers. The proposed RAN controller and designed RISE exoskeleton pave a way for providing portable and affordable resistance training. © CLAWAR Association Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A small soft-bodied crawling robot with electromagnetic legs and neural control for locomotion on various metal terrains

A small soft-bodied crawling robot with electromagnetic legs...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Naris Asawalertsak Worameth Nantareekurn Poramate Manoonpong The Bio-inspired Robotics and Neural Engineering Laboratory School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology Rayong Thailand the Embodied Artificial Intelligence and Neurorobotics Laboratory SDU Biorobotics The Mrersk Mc-Kinney Møller Institute University of Southern Denmark Odense M Denmark

Soft-bodied crawling animals (like caterpillars and inchworms) exploit their active soft bodies with passive adapt-ability to achieve efficient locomotion and move on multiple terrains. While several research studies have used this principle for robot development, most existing caterpillar/inchworm-inspired soft robots can still crawl on specific terrain (flat, inner, or outer pipes). To advance state-of-the-art soft robotic technology, we propose here a small soft-bodied crawling robot with electromagnetic legs and passive body adaptation. The robot is driven by neural central pattern generator (CPG)-based control. Due to the combination of its actively con-tractable/extendable body, passively adaptable interconnected body joints, and electromagnetic legs, the robot can successfully crawl on a variety of metal terrains, including a flat surface, step, slope, confined space, and an inner (concave surface) and outer (convex surface) pipe in both horizontal and vertical directions. Additionally, it can be steered to navigate through a cluttered environment with obstacles. Using the CPG-based control method, the robot's locomotion speed can be simply regulated by changing a single CPG-frequency control param-eter. This small soft robot has the potential to be employed as a robotic system for inner and outer pipe inspection and confined space exploration in the oil and gas industry.

关键词： Legged locomotion Service robots Navigation Oils Metals Soft robotics Inspection

来源：评论

学校读者我要写书评

暂无评论

n-LIPO: Framework for Diverse Cooperative Agent Generation using Policy Compatibility

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Charakorn, Rujikorn Manoonpong, Poramate Dilokthanakul, Nat Vidyasirimedhi Institute of Science and Technology Bio-Inspired Robotics & Neural Engineering Laboratory School of Information Science and Technology Rayong Thailand Mærsk Mc-Kinney Møller Institute University of Southern Denmark Embodied AI and Neurorobotics Laboratory SDU Biorobotics Odense Denmark King Mongkut’s Institute of Technology Ladkrabang Bangkok Thailand

Diverse training partners in multi-agent tasks are crucial for training a robust and adaptable cooperative agent. Prior methods often rely on state-action information to diversify partners’ behaviors, but this can lead to minor variations instead of diverse behaviors and solutions. We address this limitation by introducing a novel training objective based on "policy compatibility." Our method learns diverse behaviors by encouraging agents within a team to be compatible with each other while being incompatible with agents from other teams. We theoretically prove that incompatible policies are inherently dissimilar, allowing us to use policy compatibility as a proxy for diversity. We call this method Learning Incompatible Policies for n-Player Cooperative Games (n-LIPO). We propose to further diversify individual policies by incorporating a mutual information objective using state-action information. We empirically demonstrate that n-LIPO effectively generates diverse joint policies in various two-player and multi-player cooperative environments. In a complex cooperative task, two-player multi-recipe Overcooked, we find that n-LIPO generates a population of behaviorally diverse partners. These populations are then used to train robust generalist agents that can generalize better than using baseline populations. Finally, we demonstrate that n-LIPO can be applied to a high-dimensional StarCraft Multi-Agent Challenge (SMAC) multi-player cooperative environment to discover diverse winning strategies when only a single goal exists. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Learning Through Scene Observation for Selective Item Identification in Conveyor Belt Systems 21st

Self-supervised Learning Through Scene Observation for Selec...

引用

21th Annual Conference on Towards Autonomous robotics, TAROS 20120

作者： Scimeca, Luca Iida, Fumiya Bio-Inspired Robotics Lab. Cambridge University Department of Engineering Trumpington St CambridgeCB2 1PZ United Kingdom

ISBN: (纸本)9783030634858

Conveyor belts are core components in several industries. Often, workers need to operate on conveyor belts, selectively picking objects based on visual features following inspection. In such cases it is desirable to be able to selectively identify such items automatically. The need of tailored systems discourages solutions based on common data collection and labeling, as well as vision systems based on known object features. We device a novel framework to learn from existing human labor, without need of explicit data gathering or labeling. The framework autonomously detects, tracks and learns the visual features of salient objects in conveyor belt-based systems. The system is comprised of two cameras, a Convolutional neural Network and a novel training regime, devised to support learning on on-line visual feeds. We show the framework is capable of autonomously learning the visual features of the objects picked by human operators. The system trains entirely through visual observation of human labor and achieves detection accuracy of over 97% on a set of 7 different objects after only 10 min of operation, without any knowledge of the objects at priori. © 2020, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Variable Soft Finger Exoskeleton for Quantifying Fatigue-induced Mechanical Impedance

A Variable Soft Finger Exoskeleton for Quantifying Fatigue-i...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Xiaofeng Xiong Poramate Manoonpong SDU Biorobotics the Mærsk Mc-Kinney Møller Institute the University of Southern Denmark (SDU) Odense M Denmark Bio-Inspired Robotics and Neural Engineering Lab the School of Information Science and Technology Vidyasirimedhi Institute of Science and Technology Rayong Thailand

Interactive (mechanical) impedance and finger fatigues are important topics, which have not been well investigated. To tackle this problem, we developed a soft lightweight (0.25 kg) finger exoskeleton (TIE-EXO) for quantifying interactive impedance and finger fatigue. A resist-as-needed (RAN) controller was used to produce variable resistance in fingers’ exercises. The TIE-EXO’s feedback and RAN’s parameters were applied to quantify the relationship between interactive impedance and finger fatigue. This quantification was validated in the index and middle fingers of three subjects. This validation shows that the RAN control enables the TIE-EXO to produce online resistance adaptations to different subjects and finger fatigue. Moreover, it indicates a variation and invariance in finger impedance control. We argue that the proposed method provides a novel way for investigating interactive impedance and finger fatigue.

关键词： Resistance Automation Conferences Fingers Exoskeletons Fatigue Impedance

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Adaptive parallel reflex- and decoupled CPG-based control for complex bipedal locomotion” [robotics and Autonomous Systems 134 (2020) 103663]

引用

robotics and Autonomous Systems 2024年 172卷

作者： Chaicharn Akkawutvanich Frederik Ibsgaard Knudsen Anders Falk Riis Jørgen Christian Larsen Poramate Manoonpong Bio-Inspired Robotics & Neural Engineering Laboratory Information Science and Technology Vidyasirimedhi Institute of Science and Technology Rayong Thailand Embodied AI and Neurorobotics Laboratory SDU Biorobotics The Mærsk Mc-Kinney Møller Institute University of Southern Denmark Odense Denmark

来源：评论

学校读者我要写书评

暂无评论

Fully implantable and battery-free wireless optoelectronic system for modulable cancer therapy and real-time monitoring

引用

npj Flexible Electronics 2023年第1期7卷 119-130页

作者： Kiho Kim In Sik Min Tae Hee Kim Do Hyeon Kim Seungwon Hwang Kyowon Kang Kyubeen Kim Sangun Park Jongmin Lee Young Uk Cho Jung Woo Lee Woon-Hong Yeo Young Min Song Youngmee Jung Ki Jun Yu Functional Bio-integrated Electronics and Energy Management Lab School of Electrical and Electronic EngineeringYonsei University50 Yonsei-roSeodaemun-guSeoul 03722Republic of Korea Center for Biomaterials Biomedical Research InstituteKorea Institute of Science and Technology(KIST)Seoul 02792Republic of Korea Department of Fusion Research and Collaboration Biomedical Research InstituteSeoul National University HospitalSeoul 03080Republic of Korea School of Electrical Engineering and Computer Science(EECS) Gwangju Institute of Science and Technology(GIST)Gwangju 61005Republic of Korea PA1 Foundry BusinessSamsung Electronics1 Samsungjeonja-roHwaseong-siGyeonggi-doRepublic of Korea R&D Center DNA Lab PharmaresearchSeongnam 13486Republic of Korea KU-KIST Graduate School of Converging Science and Technology Korea UniversitySeoul 136-705Republic of Korea School of Materials Science and Engineering Energy Materials for Soft Electronics LaboratoryPusan National UniversityBusan 46241Republic of Korea IEN Center for Human-Centric Interfaces and Engineering and George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Wallace H.Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of MedicineAtlantaGA 30332USA Institute for Robotics and Intelligent Machines Parker H.Petit Institute for Bioengineering and BiosciencesInstitute for MaterialsNeural Engineering CenterGeorgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Electronic Engineering YU-Korea Institute of Science and Technology(KIST)InstituteYonsei University50Yonsei-roSeodaemun-guSeoul 03722Republic of Korea

Photodynamic therapy(PDT)is attracting attention as a next-generation cancer treatment that can selectively destroy malignant tissues,exhibit fewer side effects,and lack pain during *** PDT systems have recently been developed to resolve the issues of bulky and expensive conventional PDT systems and to implement continuous and repetitive *** implantable PDT systems,however,are not able to perform multiple functions simultaneously,such as modulating light intensity,measuring,and transmitting tumor-related data,resulting in the complexity of cancer ***,we introduce a flexible and fully implantable wireless optoelectronic system capable of continuous and effective cancer treatment by fusing PDT and hyperthermia and enabling tumor size monitoring in *** system exploits micro inorganic light-emitting diodes(μ-LED)that emit light with a wavelength of 624 nm,designed not to affect surrounding normal tissues by utilizing a fully programmable light intensity ofμ-LED and precisely monitoring the tumor size by Si phototransistor during a long-term implantation(2–3 weeks).The superiority of simultaneous cancer treatment and tumor size monitoring capabilities of our system operated by wireless power and data transmissions with a cell phone was confirmed through in vitro experiments,ray-tracing simulation results,and a tumor xenograft mouse model in *** all-in-one single system for cancer treatment offers opportunities to not only enable effective treatment of tumors located deep in the tissue but also enable precise and continuous monitoring of tumor size in real-time.

关键词： optoelectronic enable battery

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：