检索结果-内蒙古大学图书馆

Development of typical collision reactions in combination with algorithms for external impacts identification

IFAC-PapersOnLine 2019年第13期52卷 253-258页

作者： Mikhel, Stanislav Popov, Dmitry Mamedov, Shamil Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

This study is focused on the problem of robot interaction with dynamically changing environment for contact and non-contact operations. Robot reaction is based on classification the results, obtained from force sensors. Particular attention is paid to the problem of contact localization in the case of single and multi-contact collisions. Localization algorithms presented for simplified shapeless model of the robot and more complex model that's also consider real shape of the robot links. Numerical experiments for external force estimation and collision point identification are provided using Kuka iiwa model. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Robots Changing environment Collision reactions Contact localization External force estimation Localization algorithm Multi contact Numerical experiments Robot controls

来源：评论

学校读者我要写书评

暂无评论

Interactive mobile robot in a dynamic environment1

引用

IFAC-PapersOnLine 2018年第30期51卷 354-359页

作者： Rehman, Bakhtawar Yagfarov, Rauf Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia

In this work we introduced a robotic system to work in a sociable environment alongside humans. The robot is able to recognize information through sound and it is capable to speak in order to response or provide significant information. We implemented and compared different simultaneous localization and mapping (SLAM) algorithms available in Robot Operating System (ROS). We compared their results and showed performance in real time in an indoor environment using lidars as the core sensing module. Thus we came up with a mobile robot autonomously navigating in a dynamic environment capable of interaction and manipulation intelligently. © 2016

关键词： Indoor positioning systems Mobile robots Navigation robotics Dynamic environments humanoid Indoor environment interaction Interactive control Robot operating systems (ROS) Simultaneous localization and mapping algorithms SLAM

来源：评论

学校读者我要写书评

暂无评论

Control of actuators with linearized variable stiffness

引用

IFAC-PapersOnLine 2019年第13期52卷 713-718页

作者： Savin, Sergei Khusainov, Ramil Klimchik, Alexandr Innopolis University Center for Technologies in Robotics and Mechatronics Components 420500 Universitetskaya St 1 Innopolis Russia

In this paper, a new model of variable stiffness actuators (VSA) is presented. In the proposed model, the stiffness and deformation of the elastic element can be controlled independently. The structure of the model allows the use of optimal control methods, such as linear quadratic regulator, as is demonstrated in the paper. The model can be used in studying mechanical systems with VSA and in control design for such systems. In order to connect controllers designed for the proposed model with actual VSA, a map of control actions is needed. Such map is provided for the case of Qbmove bidirectional antagonistic VSA. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Stiffness Actuators Linearization Machine design Control actions Elastic element Linear quadratic regulator Mechanical systems Model based controls Optimal control methods Optimal controls Variable stiffness

来源：评论

学校读者我要写书评

暂无评论

Error Analysis in Solving the Inverse Problem of the Cable-driven Parallel Underactuated Robot Kinematics and Methods for their Elimination

引用

IFAC-PapersOnLine 2019年第13期52卷 1156-1161页

作者： Maloletov, Alexander V. Fadeev, Mikhail Y. Klimchik, Alexandr S. Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Volgograd State Technical University Volgograd Russia

An analysis of the geometry of a cable-driven parallel robot is carried out. The influence of the design of the guide rollers and the winding mechanisms on the errors in the determination of the cable length control laws was investigated. Two variants of the arrangement of the spools in the winch mechanisms are considered. The analysis of the magnitudes of the resulting errors is given, the conclusion is made that it is necessary to take into consideration the design of the guide rollers and the winding mechanism with the vertical position of the spool, and also the permissibility to ignore the influence of the winding mechanism with the horizontal position of the spool. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Inverse problems Cables Errors Inverse kinematics Reels Robots Rollers (machine components) Winding Cable driven robots Cable length Cable driven Geometric analysis Guide rollers Parallel robots Underactuated robot Vertical positions

来源：评论

学校读者我要写书评

暂无评论

Robust energy aware output controller for uncertain plant

引用

IFAC-PapersOnLine 2019年第13期52卷 259-264页

作者： Dobriborsci, Dmitrii Margun, Alexey Kolyubin, Sergey Control systems and Robotics faculty ITMO University St. Petersburg Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

Nowadays, safety guarantee during physical Human-Robot Interaction (pHRI) is important problem. Control over energy becomes very useful approach and provides possibility of safety conditions implementation but requires measurement of energy variables. In this paper we extend our previous results for discrete robust output control algorithm by insertion of energy aware mechanism in the structure of control system. It is proven earlier that this way make the controller aware of the energy that they inject into the plant. By combining this approaches we introduce here a robust discrete-time output controller for uncertain plant that provides exponential convergence of tracking error to the bounded area and passivity of the closed loop system. The proposed approach is validated through simulation and experiments using Ball-and-Plate setup. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Controllers Budget control Closed loop systems Human robot interaction Man machine systems Plates (structural components) Power management Robust control Energy aware Energy budgets Exponential convergence Output controllers Passive systems Physical humanrobot interaction (phri) Safety guarantees Uncertain plants

来源：评论

学校读者我要写书评

暂无评论

Exploration of underinvestigated indoor environment based on mobile robot and mixed reality 1st

Exploration of underinvestigated indoor environment based on...

引用

1st International Conference on Human Interaction and Emerging technologies, IHIET 2019

作者： Akhmetzyanov, Aydar Yagfarov, Rauf Gafurov, Salimzhan Ostanin, Mikhail Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

ISBN: (纸本)9783030256289

Mobile robots allow human to explore impassable or unsafe indoor locations remotely. There are a large number of scenarios where the implementation of mobile robots is the only way to successfully complete them. Herewith, human-robot interaction is the key factor that determines the efficiency of overall mission accomplishment. This paper presents a real-time approach for remote exploration of underinvestigated indoor environment conducted by human-robot interaction. The approach is based on the mobile robot and mixed reality. We have chosen a differential drive mobile robot platform called Plato and mixed reality glasses Microsoft Hololens for experimental investigation of the proposed approach. Our paper demonstrates the results of experimental investigations of the proposed approach. The results have shown that the proposed approach is helpful, intuitive and convenient for spatial understanding and improves natural interaction both with a mobile robot and remote environment. Moreover, our approach is able to significantly increase the speed of indoor environment exploration. © 2020, Springer Nature Switzerland AG.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Design of the Parallel Spherical Manipulator for Wrist Rehabilitation 3

Design of the Parallel Spherical Manipulator for Wrist Rehab...

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Valeria, Skvortsova Dmitry, Popov Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

ISBN: (纸本)9781728124704

This paper presents the most important steps of the wrist rehabilitation robot design. In this work, kinematic synthesis problem of a 3-RRR spherical parallel manipulator is considered including a solution for forward and inverse kinematic problems. In order to maximize dexterity of the parallel manipulator over its workspace, its design is developed by finding optimal link shape parameters. The CAD design for the prototype is obtained based on this optimization. © 2019 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Continuous Control in Deep Reinforcement Learning with Direct Policy Derivation from Q Network 2nd

Continuous Control in Deep Reinforcement Learning with Direc...

引用

2nd International Conference on Human Interaction and Emerging technologies: Future Applications, IHIET-AI 2020

ISBN: (纸本)9783030442668

The reinforcement learning approach allows learning desired control policy in different environments without explicitly providing system dynamics. A model-free deep Q-learning algorithm is proven to be efficient on a large set of discrete-action tasks. Extension of this method to the continuous control task usually solved with actor-critic methods which approximate a policy function with additional actor network and uses Q function to speed up policy network training. Another approach is to discretize action space which will not give a smooth policy and is not applicable for large action spaces. A direct continuous policy derivation from the Q network leads to optimization of action on each inference and training step which is not efficient but provides optimal and continuous action. Time-efficient Q function input optimization is required in order to apply this method in practice. In this work, we implement efficient action derivation method which allows using Q-learning in real-time continuous control tasks. In addition, we test our algorithm on robotics control tasks from robotics gym environments and compare this method with modern continuous RL methods. The results have shown that in some cases proposed approach learns smooth continuous policy keeping the implementation simplicity of the original discreet action space Q-learning algorithm. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stiffness Parameters Idenification for Walking Robot 3

Stiffness Parameters Idenification for Walking Robot

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Popov, Dmitry Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

ISBN: (纸本)9781728124704

This paper discusses the stiffness parameters identification for an anthropomorphic walking platform. The robot stiffness model build using a virtual joint model by introducing additional springs, then the parameters of these springs are determined using identification algorithms. Two variants of a model are considered: taking into account the links and joints compliance and only joints. Numerical experiments were performed on the AR-601M robot model. © 2019 IEEE.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Collision Localization in Collaborative robotics 2020

Transfer Learning for Collision Localization in Collaborativ...

引用

3rd International Conference on Applications of Intelligent Systems, APPIS 2020

作者： Popov, Dmitry Klimchik, Alexandr Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

ISBN: (纸本)9781450376303

In this work, the transfer learning paradigm is used to improve the performance of neural networks. These networks estimate the collision point between the robot and an external object, using two different approaches. One of them uses a neural network to predict collision point on the internal robot axis and the second uses classification in order to find a collision in points which are sampled on the robot surface. The neural networks are trained on two datasets, one dataset is generated in simulation, the other one captured from the real robot. Obtained results show, that using a pre-trained network allows to greatly increase the overall accuracy of collision localization. © 2020 ACM.

关键词： Collaborative robots

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：