☆ 4.7 Article

Reinforcement learning to achieve real-time control of triple inverted pendulum

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Towards stabilization and navigational analysis of humanoids in complex arena using a hybridized fuzzy embedded PID controller approach

Abhijit Mahapatro et al.

Summary: This study focuses on path planning and stabilization of humanoids in uneven and dynamic environments. The work successfully improves the performance of humanoid robots in avoiding local minima and dead-ends during navigation. By integrating a PID controller with a fuzzy logic controller, the robot is able to stabilize itself on uneven surfaces and navigate through obstacle-rich terrains. Simulation and experimental tests demonstrate the effectiveness of the proposed controller, showing improvements in path length and computational time compared to previous techniques.

EXPERT SYSTEMS WITH APPLICATIONS (2023)

添加到收藏夹

Article Mathematics, Applied

IMPLICIT-EXPLICIT RELAXATION RUNGE-KUTTA METHODS: CONSTRUCTION, ANALYSIS AND APPLICATIONS TO PDES

Dongfang Li et al.

Summary: This paper proposes a linearly implicit and high order accurate scheme for time discretization of time-dependent partial differential equations. The scheme is monotonicity-preserving and conservative for the original problems and has been tested with numerical experiments to confirm its effectiveness.

MATHEMATICS OF COMPUTATION (2023)

添加到收藏夹

Article Automation & Control Systems

Reinforcement learning with multimodal advantage function for accurate advantage estimation in robot learning

Jonghyeok Park et al.

Summary: In this paper, a reinforcement learning framework with a multimodal advantage function is proposed to achieve high returns. The framework directly assesses the complex true advantage function with multi-modality, enhancing the sample-efficiency of RL. Practical techniques including mode selection and rounding off of actions are developed to further improve the learning performance.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Efficient Multitask Reinforcement Learning Without Performance Loss

Jongchan Baek et al.

Summary: We propose an iterative sparse Bayesian policy optimization (ISBPO) scheme as an efficient multitask reinforcement learning (RL) method for industrial control applications. The scheme preserves the previously learned knowledge and improves the sample efficiency of learning new tasks.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

添加到收藏夹

Article Computer Science, Information Systems

Enhanced the Control Strategy of a Triple Link Robotic System (Robogymnast)

Bdereddin Abdul Samad et al.

Summary: This research aims to optimize the performance of a Fuzzy Linear Quadratic Regulator controller in a triple-link 'Robogymnast' robotic system. The study explores the complex factors involved in swing-up control and presents a linearized mathematical model for the system. Two algorithms, Teaching-Learning-Based Optimization (TLBO) and Particle Swarm Optimization (PSO), were used to tune the hybrid controller for stability assessment. MATLAB Simulink was also employed for performance simulation. The work primarily focuses on applying a Linear Quadratic Regulator/Fuzzy Logic controller in acrobatic robots.

IEEE ACCESS (2023)

添加到收藏夹

Article Automation & Control Systems

Lyapunov-based continuous-time nonlinear control using deep neural network applied to underactuated systems

Rosana C. B. Rego et al.

Summary: Learning-based neural network control methods can be applied to handle complex nonlinear systems, providing better solutions and stability guarantees.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

添加到收藏夹

Article Automation & Control Systems

Quantization-Aware Pruning Criterion for Industrial Applications

Yoonhee Gil et al.

Summary: This study proposes a simple and effective quantization-aware neural network pruning method that can run deep neural networks on lightweight embedded industrial devices while achieving sparse and lightweight network structures.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Digital twins-based flexible operating of open architecture production line for individualized manufacturing

Jiewu Leng et al.

Summary: This paper proposes a digital twins-based open architecture production line design and flexible operating approach for individualized manufacturing. The approach enables flexibility in both the physical and software aspects of the production line, and utilizes digital twins for comprehensive characterization and flexible operation. It provides an effective solution for catering to different individualized requirements.

ADVANCED ENGINEERING INFORMATICS (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Implementation of deep learning methods in prediction of adsorption processes

Dorian Skrobek et al.

Summary: This article presents the application of deep learning methods to predict the mass of an adsorption bed. The research shows that the GRU network achieves the best agreement with the measurement results in predicting the mass of both fixed and fluidized beds.

ADVANCES IN ENGINEERING SOFTWARE (2022)

添加到收藏夹

Article Automation & Control Systems

Hindsight Intermediate Targets for Mapless Navigation With Deep Reinforcement Learning

Yoonsu Jang et al.

Summary: This article proposes a new approach called hindsight-intermediate-target-based RL (HIT-RL) to achieve autonomous mapless navigation. The method generates virtual intermediate targets to guide the mobile vehicle to the final destination and exhibits good navigation performance in practical environments.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

添加到收藏夹

Article Automation & Control Systems

Adaptive Reinforcement Learning Strategy with Sliding Mode Control for Unknown and Disturbed Wheeled Inverted Pendulum

Phuong Nam Dao et al.

Summary: This paper proposes a novel adaptive integral sliding-mode control technique to improve the tracking performance of a WIP system. The algorithm combines online adaptive reinforcement learning control with the high robustness of integral sliding-mode control law. The main objective is to establish a general structure of integral sliding mode control law that can ensure the system state reaches a sliding surface in finite time. Simulation results validate the performance of the proposed control structure.

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS (2021)

添加到收藏夹

Article Automation & Control Systems

Sparse Variational Deterministic Policy Gradient for Continuous Real-Time Control

Jongchan Baek et al.

Summary: The proposed SVDPG algorithm integrates Bayesian pruning with policy update in reinforcement learning to achieve efficient policy network compression and competitive performance in continuous control benchmark tasks. Additionally, SVDPG demonstrates superiority in low-computing power devices and reliability in real-world scenarios.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2021)

添加到收藏夹

Article Automation & Control Systems

On the design of stable periodic orbits of a triple pendulum on a cart with experimental validation

Benjamin Jahn et al.

Summary: This paper focuses on enhancing an inversion-based control approach for stabilizing a periodic orbit of a multi-link triple pendulum on a cart. By introducing a nominal trajectory and a linear-quadratic-Gaussian controller, the high performance and accuracy of the method are successfully demonstrated on an experimental setup.

AUTOMATICA (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Digital twins-based remote semi-physical commissioning of flow-type smart manufacturing systems

Jiewu Leng et al.

Summary: Digital twins technology enables semi-physical simulation to reduce the commissioning cost of manufacturing systems. This paper proposes a digital twins-based remote semi-physical commissioning approach, validated through a case study, to make the commissioning of smart manufacturing systems more sustainable by combining open architecture design paradigm with digital twins-based approach.

JOURNAL OF CLEANER PRODUCTION (2021)

添加到收藏夹

Article Energy & Fuels

Prediction of Sorption Processes Using the Deep Learning Methods (Long Short-Term Memory)

Dorian Skrobek et al.

ENERGIES (2020)

添加到收藏夹

Article Computer Science, Information Systems

Digital Twin-Driven Cyber-Physical System for Autonomously Controlling of Micro Punching System

Rongli Zhao et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Engineering, Mechanical

Vibration control of uncertain multiple launch rocket system using radial basis function neural network

Bo Li et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2018)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Fuzzy-logic control of an inverted pendulum on a cart

Ahmad Ilyas Roose et al.

COMPUTERS & ELECTRICAL ENGINEERING (2017)

添加到收藏夹

Article Engineering, Industrial

Current status and advancement of cyber-physical systems in manufacturing

Lihui Wang et al.

JOURNAL OF MANUFACTURING SYSTEMS (2015)

添加到收藏夹

Article Automation & Control Systems

Swing-up control of a triple pendulum on a cart with experimental validation

Tobias Glueck et al.

AUTOMATICA (2013)

添加到收藏夹

Article Robotics

Transformation Control to an Inverted Pendulum for a Mobile Robot With Wheel-Arms Using Partial Linearization and Polytopic Model Set

Hiroaki Fukushima et al.

IEEE TRANSACTIONS ON ROBOTICS (2013)

添加到收藏夹

Article Robotics

The Inverted Pendulum Benchmark in Nonlinear Control Theory: A Survey

Olfa Boubaker

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS (2013)

添加到收藏夹

Article Automation & Control Systems

Baggage Transportation and Navigation by a Wheeled Inverted Pendulum Mobile Robot

Toshinobu Takei et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2009)

添加到收藏夹

Article Automation & Control Systems

Swing-up of the double pendulum on a cart by feedforward and feedback control with experimental validation

Knut Graichen et al.

AUTOMATICA (2007)

添加到收藏夹

Article Automation & Control Systems

Swinging up and stabilization of a real inverted pendulum

N Muskinja et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.