检索结果-内蒙古大学图书馆

Leader-follower:Human-centered intention-guided controller for novel SuperLimb with application to load-carrying scenarios

引用

Science China(Technological Sciences) 2025年第1期68卷 321-334页

作者： Qinghua ZHANG Xianglong LI Hongwei JING Kerui SUN Yuancheng LI Sikai ZHAO Lele LI Haotian JU Ziqi WANG Rui WU Tianjiao ZHENG Jie ZHAO Yanhe ZHU The State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China The Learning Algorithms and Systems Laboratory School of EngineeringÉcole Polytechnique Fédérale de LausanneLausanne CH 101510587Switzerland

Supernumerary robotic arms(SuperLimb)are a new type of wearable robot that works closely with humans as a third hand to augment human operation *** conveyance of wearers'intentions,allocation of roles,and humancentered interaction considerations are the key points in the process of human-SuperLimb *** paper proposes a human-centered intention-guided leader-follower controller that relies on the dynamic modeling of SuperLimb with application to load-carrying *** proposed leader-follower controller takes the human as the leader and the SuperLimb as the follower,achieving effective information communication,autonomous coordination,and good force compliance between SuperLimb,humans,and the environment under human safety ***,the human-SuperLimb dynamic system is modeled to achieve force interaction with the environment and ***,to achieve the precise intention extraction of humans,pose data from five visual odometry sensors are fused to capture the human state,the generalized position,the velocity of hands,and the surface electromyography signals from two myoelectric bracelets sensors are processed to recognize the natural hand gestures during load-carrying scenarios by a designed Swin transformer ***,based on the real-time distance detection between human and mechanical limbs,the security assurance and force-compliant interaction of the human-SuperLimb system are ***,the human hand muscle intention recognition,human-robot safety strategy verification,and comparative load-carrying experiments with and without the proposed method are conducted on the SuperLimb *** showed that the task parameters are well estimated to produce more reasonable planning trajectories,and SuperLimb could well understand the wearer's intentions to switch different SuperLimb *** proposed sensor-based human-robot communication framework motivates future studies of other collaboration scenes fo

关键词： SuperLimb leader-follower human intention estimation human-robot safety human-robot communication

来源：评论

学校读者我要写书评

暂无评论

Transferring Shotcrete Skills to Robots

Transferring Shotcrete Skills to Robots

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Rui Wu Soheil Gholami Tristan Bonato Louis Munier Aude Billard Learning algorithms and systems laboratory Swiss Federal Institute of Technology Lausanne Switzerland

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Traditionally performed by skilled nozzle opera-tors, shotcrete remains a painful and risky task, where recurrent physical discomfort leads to severe and long-term health issues. When performed by novices or ill-trained workers, it can lead to waste. The shotcrete process guidelines advise operators on how to best maneuver the nozzle tool during spraying to reduce waste. This technique involves moving the nozzle with rhythmic circular movements while remaining at an optimal distance from the shotcrete surface. Adhering to these standards is challenging and adds to the operator's discomfort. To alleviate these issues, robotic solutions can be developed to partially or completely substitute the operator's work. This paper presents a first step towards modeling the technique employed by experienced nozzle operators and transferring them to control a robotic arm. We recorded the motion generated at the nozzle during a set of shotcrete operations by two expert nozzle operators and one novice. We analyze the pattern of motion and confirm that we model the shotcrete task and showcase its use for autonomous control of a mock-up of a shotcrete robot using expandable foam. Furthermore, we implement an intuitive shared control framework to support operators during shotcrete. The experimental results from quasi-real-world evaluations of our proposed framework on a seven-degrees-of-freedom robotic manipulator demonstrate the efficacy of our proposed control approach.

关键词： Analytical models Spraying Biomechatronics Manipulators Surface treatment Standards Guidelines

来源：评论

学校读者我要写书评

暂无评论

Dynamical System Approach to Navigation Around Obstacles

Dynamical System Approach to Navigation Around Obstacles

引用

European Control Conference (ECC)

作者： Aradhana Nayak Aude Billard Learning algorithms and systems laboratory (LASA) Ecole Polytechnique Federale de Lausanne (EPFL) Switzerland

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In this article, we propose a dynamical system to avoid obstacles which are star shaped and simultaneously converge to a goal. The convergence is almost-global in a domain and the stationary points are identified explicitly. Our approach is based on the idea that an ideal vector field which avoids the obstacle traverses its boundary up to when a clear path to the goal is available. We show the existence of this clear path through a set connecting the boundary of the obstacle and the goal. The traversing vector field is determined for an arbitrary obstacle (de-scribed by a set of points) by separating it into cluster of stars. We propose an algorithm which is linear in number of points inside the obstacle. We verify the theoretical results presented with various hand drawn obstacle sets. Our methodology is also extended to obstacles which are not star-shaped, and, those which exist in high dimensions.

关键词： Support vector machines Navigation Shape Level set Heuristic algorithms Stars Europe

来源：评论

学校读者我要写书评

暂无评论

learning Barrier-Certified Polynomial Dynamical systems for Obstacle Avoidance with Robots

arXiv

引用

arXiv 2024年

作者： Schonger, Martin Kussaba, Hugo T.M. Chen, Lingyun Figueredo, Luis Swikir, Abdalla Billard, Aude Haddadin, Sami Germany Albaida Libya School of Computer Science University of Nottingham United Kingdom Learning Algorithms and Systems Laboratory EPFL Switzerland

Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots’ resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating barrier certificates into an optimization problem to learn a stable and barrier-certified DS. Such optimization problem can be very complex or extremely conservative when the traditional linear parameter-varying formulation is used. Thus, different from previous approaches in the literature, we propose to use polynomial representations for DSs, which yields an optimization problem that can be tackled by sum-of-squares techniques. Finally, our approach can handle obstacle shapes that fall outside the scope of assumptions typically found in the literature concerning obstacle avoidance within the DS learning framework. Supplementary material can be found at the project webpage: https://***. io/abc-dsMSC Codes 68T40 Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE

arXiv

引用

arXiv 2024年

作者： Regol, Florence Chataoui, Joud Charpentier, Bertrand Coates, Mark Piantanida, Pablo Gunnemann, Stephan McGill University Canada International Laboratory on Learning Systems Canada MILA Quebec Institute for Learning Algorithms Canada Technical University of Munich Germany École de Technologie Supérieure Canada

Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in different ways, such as quantization which reduces the precision of weights and arithmetic operations, and dynamic networks which adapt computation to the sample at hand. In this work, we propose a more general dynamic network that can combine both quantization and early exit dynamic network: QuEE. Our algorithm can be seen as a form of soft early exiting or input-dependent compression. Rather than a binary decision between exiting or continuing, we introduce the possibility of continuing with reduced computation. This complicates the traditionally considered early exiting problem, which we solve through a principled formulation. The crucial factor of our approach is accurate prediction of the potential accuracy improvement achievable through further computation. We demonstrate the effectiveness of our method through empirical evaluation, as well as exploring the conditions for its success on 4 classification datasets. © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Linearization and identification of multiple-attractor dynamical systems through Laplacian eigenmaps

The Journal of Machine Learning Research

引用

The Journal of Machine learning Research 2022年第1期23卷 13290-13324页

作者： Bernardo Fichera Aude Billard Learning Algorithms and Systems Laboratory (LASA) École polytechnique fédérale de Lausanne Lausanne Switzerland

Dynamical systems (DS) are fundamental to the modeling and understanding time evolving phenomena, and have application in physics, biology and control. As determining an analytical description of the dynamics is often difficult, data-driven approaches are preferred for identifying and controlling nonlinear DS with multiple equilibrium points. Identification of such DS has been treated largely as a supervised learning problem. Instead, we focus on an unsupervised learning scenario where we know neither the number nor the type of dynamics. We propose a Graph-based spectral clustering method that takes advantage of a velocity-augmented kernel to connect data points belonging to the same dynamics, while preserving the natural temporal evolution. We study the eigenvectors and eigenvalues of the Graph Laplacian and show that they form a set of orthogonal embedding spaces, one for each sub-dynamics. We prove that there always exist a set of 2-dimensional embedding spaces in which the sub-dynamics are linear and n-dimensional embedding spaces where they are quasi-linear. We compare the clustering performance of our algorithm to Kernel K-Means, Spectral Clustering and Gaussian Mixtures and show that, even when these algorithms are provided with the correct number of sub-dynamics, they fail to cluster them correctly. We learn a diffeomorphism from the Laplacian embedding space to the original space and show that the Laplacian embedding leads to good reconstruction accuracy and a faster training time through an exponential decaying loss compared to the state-of-the-art diffeomorphism-based approaches.

关键词： dynamical system graph Laplacian clustering learning

来源：评论

学校读者我要写书评

暂无评论

learning Barrier-Certified Polynomial Dynamical systems for Obstacle Avoidance with Robots

Learning Barrier-Certified Polynomial Dynamical Systems for ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Martin Schonger Hugo T. M. Kussaba Lingyun Chen Luis Figueredo Abdalla Swikir Aude Billard Sami Haddadin Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich (TUM) Germany School of Computer Science University of Nottingham UK Omar Al-Mukhtar University (OMU) Albaida Libya Learning Algorithms and Systems Laboratory EPFL Switzerland

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

关键词： Shape Scalability Perturbation methods Polynomials Collision avoidance Dynamical systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs 13

ProtSTonKGs: A Sophisticated Transformer Trained on Protein ...

引用

13th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences, SWAT4HCLS 2022

作者： Balabin, Helena Hoyt, Charles Tapley Gyori, Benjamin M. Bachman, John Kodamullil, Alpha Tom Hofmann-Apitius, Martin Domingo-Fernández, Daniel Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany Bonn-Rhein-Sieg University of Applied Sciences Sankt Augustin53757 Germany Laboratory of Systems Pharmacology Harvard Medical School BostonMA02115 United States Fraunhofer Center for Machine Learning Germany Enveda Biosciences BoulderCO80301 United States

While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowl- edge graphs, their union can better exploit the advantages of such ap- proaches, ultimately improving representations of biology. Using mul- timodal transformers for such purposes can improve performance on context dependent classification tasks, as demonstrated by our previ- ous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce Prot- STonKGs, a transformer aimed at learning all-encompassing representa- tions of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark Prot- STonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of infor- mation, paving the foundation for future approaches that use multiple modalities for biomedical applications. Copyright © 2022 for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Configuration Exploration in Inverse Dynamics Acquisition of Robotic Manipulators

Efficient Configuration Exploration in Inverse Dynamics Acqu...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Farshad Khadivar Sthithparagya Gupta Walid Amanhoud Aude Billard Learning Algorithms and Systems Laboratory (LASA) Ecole Polytechnique Fédérale de Lausanne (EPFL) Lausanne Switzerland

The inverse dynamics of a robotic manipulator is instrumental in precise robot control and manipulation. However, acquiring such a model is challenging, not only due to unmodelled non-linearities such as joint friction, but also from a machine learning perspective (e.g., input space dimension, amount of data needed). The accuracy of such models, regardless of the learning techniques, relies on proper excitation and exploration of the robot’s configuration space, in order to collect a rich dataset. This study aims to provide rich data in learning the inverse dynamics of a serial robotic manipulator using supervised machine learning techniques. We propose a method, called Max-Information Configuration Exploration (MICE), to incrementally explore and generate information-rich data via computing parameters of a trajectory set. We also introduce a new set of excitation trajectories that explores robot’s configuration through imposed stable limit cycles in robot joints’ phase space while satisfying feasibility constraints and physical bounds. We benchmark MICE against state-of-the-art in terms of data quality and learning accuracy. The proposed methodology for data collection, model learning, and evaluation, is validated with a KUKA IIWA14 robotic arm where the results prove significant improvement over traditional approaches.

关键词： Trajectory tracking Robot control Limit-cycles Machine learning Mice Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

A Structured Prediction Approach for Robot Imitation learning

arXiv

引用

arXiv 2023年

作者： Duan, Anqing Batzianoulis, Iason Camoriano, Raffaello Rosasco, Lorenzo Pucci, Daniele Billard, Aude Robotics and Machine Intelligence Laboratory The Hong Kong Polytechnic University Hong Kong Learning Algorithms and Systems Laboratory École Polytechnique Fédérale de Lausanne Lausanne Switzerland Visual And Multimodal Applied Learning Laboratory Politecnico di Torino Turin Italy DIBRIS Università degli Studi di Genova Genoa Italy Laboratory for Computational and Statistical Learning IIT@MIT Istituto Italiano di Tecnologia Massachusetts Institute of Technology CambridgeMA United States Center Università di Genova Genoa Italy Dynamic Interaction Control research line Italian Institute of Technology Genoa Italy

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

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：