检索结果-内蒙古大学图书馆

20th International Conference on Electrical engineering, Computing Science and Automatic Control, CCE 2023

作者： Pantoja-Garcia, Luis Parra-Vega, Vicente Garcia-Rodriguez, Rodolfo Robotics and Adv. Manufacturing CINVESTAV Saltillo Mexico Universidad Politecnica Metropolitana de Hidalgo Postgraduate Program in Aerospacial Engineering Tolcayuca Mexico

ISBN: (纸本)9798350306767

Actor-Critic (AC) architecture has the salient feature, for the plethora of Reinforcement Learning schemes, that two intertwining neural networks (NN) collaborate to deploy a motor learning mechanism that oversees and evaluates the action to control a dynamical system as the robot manipulator. Since such NNs can be studied as dynamical systems to learn how to control the robot dynamics with a given performance, it has finally paved the way to deal with stability analysis, unfortunately, few works have addressed it. In this paper, we propose a Critic-NN whose approximation of the value function substantiates the decision making mechanism that collaborates to tune the Actor-NN action (approximation of inverse dynamics). The novel proposed design of the adaptation of the neural weights yields Lyapunov stability that provides explicit conditions for an attractive invariant set that render a stable regime using a quite simple NN with one hidden layer. Numerical simulations show the performance of the proposed approach. In addition, robustness is analyzed when the robot is subject to Liptchitz disturbances, interestingly showing relaunching of the learning mechanism when needed. Finally, a discussion on dealing with asymptotic stability, robustness issues, and the learning mechanism from a reward provided by the expert user is addressed. © 2023 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Actor-Critic Reinforcement Learning Controller for Constrained Robots 25

A Novel Adaptive Actor-Critic Reinforcement Learning Control...

引用

2022 IEEE International Conference on Automation/25th Congress of the Chilean Association of Automatic Control, ICA-ACCA 2022

作者： Pantoja-Garcia, Luis Garcia-Rodriguez, Rodolfo Parra-Vega, Vicente Robotics and Advanced Manufacturing Department Coah Saltillo25900 Mexico Universidad Politecnica Metropolitana de Hidalgo Aeronautical Engineering Program and Postgraduate Program in Aerospacial Engineering Tolcayuca43860 Mexico

ISBN: (纸本)9781665494083

Force-position control for robot manipulators has become a basic control regime for advanced applications such as interaction or cooperative tasks that imply contact to environment or external object. Thus, for many applications environmental information is evaluated continuously to generate adequate control actions to complete the task. There has been proposed techniques such as adaptive or intelligent control to cover some of these requirements, however it seems insufficient given the uncertainty involved when dealing with the environment. The emergence of deep learning has recently renewed interest in these tasks from the perspective of reinforcement learning algorithms. In this paper, an actor-critic scheme is proposed for simultaneous control of contact force and joint positions while moving along an environmental rigid surface. The critic stage evaluates information of the environment through an extended error manifold, trying to minimize the cumulative future rewards by a neural network. The actor stage, which receives environment information from the critic stage, is used to approximate inverse robot dynamics. Together with two continuous orthogonal sliding PID controllers gives rise to simultaneous tracking of position and force, with stability analysis. Numerical simulations show the performance of the proposed approach under several conditions. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stability Guaranteed Actor-Critic Learning for Robots in Continuous Time

Stability Guaranteed Actor-Critic Learning for Robots in Con...

引用

International Conference on Electrical engineering, Computing Science and Automatic Control (CCE)

作者： Luis Pantoja-Garcia Vicente Parra-Vega Rodolfo Garcia-Rodriguez Robotics and Adv. Manufacturing CINVESTAV Saltillo Mexico Postgraduate Program in Aerospacial Engineering Universidad Politecnica Metropolitana de Hidalgo Tolcayuca

关键词：

来源：评论

学校读者我要写书评

暂无评论

In-hand manipulation of a circular dynamic object by soft fingertips without angle measurement

引用

Science China(Information Sciences) 2021年第5期64卷 193-208页

作者： R.GARCIA-RODRIGUEZ V.PARRA-VEGA Aeronautical Engineering Program and Postgraduate Program in Aerospacial Engineering Universidad Politecnica Metropolitana de Hidalgo Robotics and Advanced Manufacturing Department Research Center for Advanced Studies (CINVESTAV)

A multi-fingered robotic hand with curved fingertips enables contact re-positioning without reattaching at the expense of fingertip rolling. This rolling stands for a characteristic that facilitates dexterous manipulation but results in an algebraically complex dynamic model subject to such constraints. The hemispherical shape of fingertips allows a dexterous manipulation when controlling the tangent forces, which are essential to rotate object. However, the measurement of the object angle in practice requires tactile-optical sensing. In this paper, considering robotic fingers with curved soft tips, we propose a feedback control that ensures optimal dynamical grasping of a circular rigid object. It is shown that the collaboration of the contact forces, to get a minimum pose of internal forces, and the tangential forces, to induce the conditions for assuring the grasp closure, is necessary to get a skillful manipulation. In this case, the orientation control of a circular object to the desired angle while avoiding direct measurement of the object angle is presented. Stability conditions of the system are presented in the sense of stability-in-the-manifold. Finally, representative simulations are shown and discussed.

关键词： optimal grasping manipulation soft-fingertips circular object stability-in-the-manifold

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Actor-Critic Reinforcement Learning Controller for Constrained Robots

A Novel Adaptive Actor-Critic Reinforcement Learning Control...

引用

IEEE International Conference on Automatica (ICA-ACCA)

作者： Luis Pantoja-Garcia Rodolfo Garcia-Rodriguez Vicente Parra-Vega Robotics and Advanced Manufacturing Department Research Center for Advanced Studies (CINVESTAV) Saltillo Coah Mexico Aeronautical Engineering Program and Postgraduate Program in Aerospacial Engineering Universidad Politecnica Metropolitana de Hidalgo Tolcayuca Mexico

ISBN: (纸本)9781665494090

关键词： Upper bound Uncertainty Force Reinforcement learning Robot sensing systems Stability analysis Trajectory

来源：评论

学校读者我要写书评

暂无评论

Adaptive actor-critic control of robots with integral invariant manifold

Adaptive actor-critic control of robots with integral invari...

引用

CHILEAN Conference on Electrical, Electronics engineering, Information and Communication Technologies (CHILECON)

作者： Luis Pantoja-Garcia Rodolfo Garcia-Rodriguez Vicente Parra-Vega Research Center for Advanced Studies (CINVESTAV) Saltillo Coah Mexico Aeronautical Engineering Program and Postgraduate Program in Aerospacial Engineering Universidad Politecnica Metropolitana de Hidalgo Tolcayuca Mexico

ISBN: (纸本)9781665408745

The actor-critic scheme stands for a powerful algorithm to design controllers for linear and non-linear systems subject to changing or highly uncertain dynamics. In particular, the actor-critic scheme that has succeeded is typically based on two neural network stages in a hierarchical architecture where the critic stage approximates the reward cost function. In contrast, the dynamic of the system is estimated by another neural network in the actor stage. This paper proposes an adaptive actor-critic robot learning on a lower dimension invariant error manifold as part of the Performance Evaluator. The proposed scheme guarantees an envelope of exponential convergence of tracking errors using a modified Lyapunov function, throughout integral sliding mode enforced for all time, where this becomes fundamental to drive also the learning of Reward function. Simulations show a non-linear dynamical robot learning tracking a time-varying trajectory under this Reinforcement Learning scheme.

关键词： Manifolds Heuristic algorithms Neural networks Reinforcement learning Cost function Robot learning Trajectory

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：