检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hannus, Eric Le, Tran Nguyen Blanco-Mulero, David Kyrki, Ville Intelligent Robotics Group The Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Institut de Robòtica i Informàtica Industrial CSIC-UPC Barcelona Spain

Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot’s physical limits. These limits are especially relevant in dynamic manipulation where high velocities and accelerations are typical. To address this problem, we propose a framework that first maps a dynamic demonstration into a motion that respects the robot’s constraints using a constrained Dynamic Movement Primitive. Second, the resulting object state is further optimized by quasi-static refinement motions to optimize task performance metrics. This allows both efficiently altering the object state by dynamic motions and stable small-scale refinements. We evaluate the framework in the challenging task of bag opening, designing the system BILBO: Bimanual dynamic manipulation using Imitation Learning for Bag Opening. Our results show that BILBO can successfully open a wide range of crumpled bags, using a demonstration with a single bag. See supplementary material at https://***/view/bilbo-bag. 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

Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints

Dynamic Manipulation of Deformable Objects using Imitation L...

引用

IEEE/RSJ International Conference on intelligent Robots and Systems (IROS)

作者： Eric Hannus Tran Nguyen Le David Blanco-Mulero Ville Kyrki Intelligent Robotics Group at The Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland CSIC-UPC Institut de Robòtica i Informàtica Industrial Barcelona Spain

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

关键词： Measurement Learning systems Translation Shape Imitation learning Dynamics Kinematics Hardware Manipulator dynamics intelligent robots

来源：评论

学校读者我要写书评

暂无评论

SPONGE: Sequence Planning with Deformable-ON-Rigid Contact Prediction from Geometric Features

SPONGE: Sequence Planning with Deformable-ON-Rigid Contact P...

引用

IEEE/RSJ International Conference on intelligent Robots and Systems (IROS)

作者： Tran Nguyen Le Fares J. Abu-Dakka Ville Kyrki Department of Electrical Engineering and Automation Intelligent Robotics Group School of Electrical Engineering Aalto University Finlnd MIRMI Technische Universität München München Germany

Planning robotic manipulation tasks, especially those that involve interaction between deformable and rigid objects, is challenging due to the complexity in predicting such interactions. We introduce SPONGE, a sequence planning pipeline powered by a deep learning-based contact prediction model for contacts between deformable and rigid bodies under interactions. The contact prediction model is trained on synthetic data generated by a developed simulation environ-ment to learn the mapping from point-cloud observation of a rigid target object and the pose of a deformable tool, to 3D representation of the contact points between the two bodies. We experimentally evaluated the proposed approach for a dish cleaning task both in simulation and on a real Franka Emika Panda with real-world objects. The experimental results demonstrate that in both scenarios the proposed planning pipeline is capable of generating high-quality trajectories that can accomplish the task by achieving more than 90% area coverage on different objects of varying sizes and curvatures while minimizing travel distance. Code and video are available at: https://***/sponge/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mergulhão Bot: Design and Prototyping of a Low-Cost Hybrid Vehicle for Oil Leakage Detection

Mergulhão Bot: Design and Prototyping of a Low-Cost Hybrid ...

引用

IEEE Latin American robotics Symposium, LARS

作者： Guilherme C. De Oliveira Enrique F. Garcia Julio Cesar S. Dos Santos Adir A. Pedroso Leonardo C. Pereira Paulo L. J. Drews NAUTEC - Intelligent robotics and automation group FURG - Federal University of Rio Grande Rio Grande Brazil CDTEC - Technological Development Center UFPEL - Federal University of Pelotas Pelotas Brazil

Unmanned vehicles are increasingly popular and their demand increases annually. Since their invention in the 1950s, these vehicles have been widely used in various applications which include environmental monitoring. Oil spill in the oceans is an example of a serious problem for marine ecosystems that can be investigated with these vehicles. Currently, government authorities are analyzing satellite images to detect oil spots, but when oil submerges in the ocean becomes imperceptible by satellites. This oil can be silently moving to coastal regions, without containment maneuvers. Unmanned vehicles may be an effective alternative to remote sensing in these cases. In this scenario, this work presents a new design of a hybrid vehicle to move on the ocean surface and be able to submerge water, called the Mergulhão Bot. The robot was mechanically modeled using OnShape software, simulations were performed using ROS, Gazebo, and the UUV Simulator package.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SPONGE: Sequence Planning with Deformable-ON-Rigid Contact Prediction from Geometric Features

arXiv

引用

arXiv 2023年

作者： Le, Tran Nguyen Abu-Dakka, Fares J. Kyrki, Ville Intelligent Robotics Group The Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Finland MIRMI Technische Universität München München80992 Germany

Planning robotic manipulation tasks, especially those that involve interaction between deformable and rigid objects, is challenging due to the complexity in predicting such interactions. We introduce SPONGE, a sequence planning pipeline powered by a deep learning-based contact prediction model for contacts between deformable and rigid bodies under interactions. The contact prediction model is trained on synthetic data generated by a developed simulation environment to learn the mapping from point-cloud observation of a rigid target object and the pose of a deformable tool, to 3D representation of the contact points between the two bodies. We experimentally evaluated the proposed approach for a dish cleaning task both in simulation and on a real Franka Emika Panda with real-world objects. The experimental results demonstrate that in both scenarios the proposed planning pipeline is capable of generating high-quality trajectories that can accomplish the task by achieving more than 90% area coverage on different objects of varying sizes and curvatures while minimizing travel distance. Code and video are available at: https://***/sponge/. Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Optimization Design and Research on the Isolation Structure of Wheel-Leg Composite Robot

Optimization Design and Research on the Isolation Structure ...

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Peiyao Shao Ting Wang Shiliang Shao Guochen Ma Facai Guan Yongsheng Zhang Shenyang Aerospace Xinguang Group Co. LTD Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

In order to improve the comprehensive vibration reduction performance of the wheel-leg composite robot vibration reduction system and improve the smoothness of its operation, a new type of integrated leg structure wheel-leg composite robot was designed. Dynamic models of parallel and series vibration reduction systems containing two vibration isolation devices were established, and a simulink simulation model was established with road excitation as input. The changes in the vertical acceleration of the robot center of mass, the dynamic deflection of the robot system, and the dynamic load index of the rubber at the bottom of the robot between the two vibration isolation systems and the original vibration isolation system were investigated. The results showed that compared to the original vibration isolation system, The series vibration isolation system can enhance the comprehensive isolation system, verifying the rationality of the design of the isolation system for this wheel-leg composite robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Strictly Decentralized Approaches for Multi-Robot Grasp Coordination

Strictly Decentralized Approaches for Multi-Robot Grasp Coor...

引用

IEEE International Conference on automation Science and Engineering (CASE)

作者： Rajkumar Muthusamy Ville Kyrki Praveen Kumar Muthusamy Tarek Taha Irfan Hussain Yahya Zweiri Domenico Prattichizzo Dongming Gan Robotics Lab Dubai Future Labs Dubai UAE Department of Electrical Engineering and Automation Intelligent Robotics Group Aalto University Finland Khalifa University of Science and Technology Abu Dhabi UAE Department of Advanced Robotics Istituto Italiano di Tecnologia Genoa Italy Purdue University USA

Grasp coordination is crucial for performing cooperative object manipulation tasks. Planning cooperative grasps among a group of decentralized robots is a new line of coordination problem that requires robots to simultaneously handle complex and large shaped and sized objects, a new level of difficulty that is rarely addressed in the literature. In this paper, we propose grasp coordination approaches for a decentralized group of robots facing explicit communication and sensing limitations. In particular, a scenario where robots with incomplete knowledge about each other's embodiments further lose the ability to 1. observe others' grasps occluded by the object's shape 2. exchange direct messages due to potential communication degradation resulting from the real-time planning and execution constraints. To tackle such a scenario, we introduce two baseline and two probabilistic approaches that are specifically designed for strict decentralization. The approaches analyze cooperative grasps using traditional grasp quality metrics and estimate cooperative grasps based on the assigned robot's priority. Simulation experiments demonstrate that the probabilistic approaches exhibit superior performance over the baseline approaches, reaching performance close to optimal for both homogeneous and heterogeneous groups. These approaches provide solutions to simulated multi-robot grasp coordination scenarios that have the potential to translate to real-world environments such as logistics, manufacturing, and services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Ground Effect in a Hybrid Aerial-Aquatic Unmanned Vehicle

Exploring Ground Effect in a Hybrid Aerial-Aquatic Unmanned ...

引用

IEEE Latin American robotics Symposium, LARS

作者： Vivian Misaki Aoki Paulo Jefferson Dias de Oliveira Evald Pedro Miranda Pinheiro César Bastos da Silva Dayana dos Santos Cardoso Mauro André Barbosa Cunha Paulo Lilles Jorge Drews Intelligent Robotics and Automation Group Federal University of Rio Grande Rio Grande Brazil State University of Campinas Brazil Automation and Control Research Group Sul-rio-grandense Federal Institute Pelotas Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

This paper presents the investigation of the ground effect on hybrid aerial-aquatic vehicles. The ground effect is the formation of an air bag, caused by the thrusters during the landing and taking off of a propeller-based vehicle. Aerial vehicles are influenced by the ground effect, which is a large factor of variation in the turbulence and air flow that can significantly interfere with the movements of the vehicle. Therefore, the inclusion of ground effect dynamics in the vehicle model is relevant for a better comprehension of the transition zone between both environments: air and water. Simulation results show that thrust force is highly influenced by ground effect when a vehicle is coming out of the water, impacting on the controller's performance.

关键词： Safety devices Attitude control Propellers Simulation Atmospheric modeling Dynamics Prototypes

来源：评论

学校读者我要写书评

暂无评论

Hydrone: Modeling of a Hybrid Unmanned Aerial Underwater Vehicle Considering Trans-Media Dynamics

SSRN

引用

SSRN 2024年

作者： de Oliveira Evald, Paulo Jefferson Dias Brião, Stephanie Loi Aoki, Vivian Misaki da Silva, César Bastos dos Santos Cardoso, Dayana Pinheiro, Pedro Miranda de Oliveira, Felipe Gomes André Barbosa Cunha, Mauro Jorge Drews, Paulo Lilles Intelligent Systems and Control Group Federal University of Pelotas RS Pelotas Brazil Intelligent Robotics and Automation Group Federal University of Rio Grande RS Rio Grande Brazil Department of Computer Engineering and Industrial Automation State University of Campinas SP Campinas Brazil Federal Institute of Education Science and Technology in Rio Grande do Sul RS Pelotas Brazil Institute of Exact Sciences and Technology Federal University of Amazonas Itacoatiara AM Amazonas Brazil Brazil

Research in mobile robotics is growing into applications for difficult-to-access environments, such as in rescue and transport missions. Furthermore, autonomous vehicles can perform data collection in complex approach areas. Therefore, the study of hybrid unmanned vehicles is relevant for several areas, since these vehicles can act in different domains. The developed vehicle, called Hydrone, is designed in a quadrotor-type structure and equipped with a set of aerial and underwater propellers, which are fixed and independent between them. In this sense, this work presents the mathematical modeling of an unmanned hybrid vehicle, which can navigate underwater and aerial environments. Furthermore, the modeling considers the ground effect due to the influence on the vehicle’s trajectory change and the dynamics of the transition zone between water-air and air-water. These dynamics are important to evaluate the controller’s performance. Numerical simulations consider both transitions (water-air and air-water) and they are performed to discuss the influence of acting forces on the vehicle stability and position-tracking performance using a classical control system. © 2024, The Authors. All rights reserved.

关键词： Hybrid vehicles

来源：评论

学校读者我要写书评

暂无评论

Volume-based Transition Zone Assessment of Hybrid Unmanned Aerial-Underwater Vehicles

Volume-based Transition Zone Assessment of Hybrid Unmanned A...

引用

IEEE Latin American robotics Symposium, LARS

作者： Vivian Misaki Aoki Paulo Jefferson Dias De Oliveira Evald Pedro Miranda Pinheiro César Bastos Da Silva Dayana Dos Santos Cardoso Mauro André Barbosa Cunha Paulo Lilles Jorge Drews Intelligent Robotics and Automation Group Federal University of Rio Grande Rio Grande Brazil Department of Computer Engineering and Industrial Automation State University of Campinas Campinas Brazil Automation and Control Research Group Sul-rio-grandense Federal Institute Pelotas Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Quadrotors have been used in diverse areas, such as agriculture, civil construction, fire monitoring, and so on. However, these vehicles cannot perform missions that require navigation in aquatic environments, such as inspection of underwater structures and water sample collection, due to their hardware limitations. Therefore, hybrid unmanned aerial-underwater vehicles emerge as a feasible solution to accomplish these missions. Although quadrotors have well-accepted mathematical models, hybrid vehicles have a small quantity of works dealing with this topic. Moreover, we identified a gap in transition zone representation. Therefore, this paper presents a method for transition zone modeling based on vehicle geometry. Simulation results support the better representation of the proposed transition model in comparison to a sigmoid model.

关键词： Underwater structures Navigation Simulation Force Inspection Mathematical models Hardware

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：