An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms

Dong, Ruyi; Du, Jing; Liu, Yanan; Heidari, Ali Asghar; Chen, Huiling

doi:10.3389/fninf.2023.1096053

Cited by 5 publications

(5 citation statements)

References 52 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DDPG is a combination of Deep Q Network and Deterministic Policy Gradient algorithms [34,35]. This algorithm works effectively for action domains in continuous space.…”

Section: Reinforcement Learningmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-based position control: reinforcement learning approach in spring mass damper systems

Demircioğlu,

Bakır

2024

Phys. Scr.

View full text Add to dashboard Cite

This work examines the use of deep Reinforcement Learning (RL) in mass-spring system position control, providing a fresh viewpoint that goes beyond conventional control techniques. Mass-spring systems are widely used in many sectors and are basic models in control theory. The novel aspect of this approach is the thorough examination of the impact of several optimizer algorithms on the RL methodology, which reveals the optimal control tactics. The research applies a Deep Deterministic Policy Gradient (DDPG) algorithm for continuous action spaces, where the actor and critic networks are important components in assessing the agent's performance. The RL agent is trained to follow a reference trajectory using the Simulink environment for system modeling. The study provides insights into the agent's learning approach and performance optimization by evaluating the training process using force-time graphs, reward graphs, and Episode Manager charts. Furthermore, the effect of different combinations of optimizers on the control performance of the agent is examined. The outcomes highlight the importance of optimizer selection in the learning process by revealing significant variations in training times. As a result, a better understanding of the relationship between various optimizers and control performance is provided by this study's novel application of reinforcement learning in mass-spring system control. The results raise the possibility of more potent methods for controlling complex systems and add to the expanding field of study at the interface of control theory and deep learning.

show abstract

“…DDPG is a combination of Deep Q Network and Deterministic Policy Gradient algorithms [34,35]. This algorithm works effectively for action domains in continuous space.…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…RL has great potential in the control of complex and non-linear systems and can be used effectively in real-world applications with variable dynamics and uncertainties. It has been applied to different control applications [34,35].…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-based position control: reinforcement learning approach in spring mass damper systems

Demircioğlu,

Bakır

2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…These algorithms include K-means clustering, hierarchical agglomerative clustering (HAC), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and principal component analysis (PCA) [114][115][116][117][118]. Reinforcement learning, a framework for sequential decisions in uncertain situations, uses algorithms like Q-learning, SARSA, Deep Q-Network (DQN), and Deep Deterministic Policy Gradient (DDPG) in applications like traffic control, algorithmic trading, and intelligent robotics [119][120][121][122][123]. Machine learning algorithms have a profound influence across various sectors, fostering creativity and enabling us to address complex problems with better effectiveness and insight.…”

Section: Machine Learning Advancesmentioning

confidence: 99%

“…pseudo labeling [112] applying pseudo-labels to samples in the unlabeled set by using a model trained on the combination of the labeled samples and any previously pseudo-labeled samples and iteratively repeating this process in a self-training cycle mostly used for image classification semi-supervised generative adversarial network (SGAN) [113] extract [123] explores the environment and makes action decisions intelligent robotics…”

Section: Machine Learning Algorithms Purpose Applicabilitymentioning

confidence: 99%

Machine Learning, Mechatronics, and Stretch Forming: A History of Innovation in Manufacturing Engineering

Grigoras,

Zichil,

Ciubotariu

et al. 2024

Machines

View full text Add to dashboard Cite

This review focuses on the complex connections between machine learning, mechatronics, and stretch forming, offering valuable insights that can lay the groundwork for future research. It provides an overview of the origins and fundamentals of these fields, emphasizes notable progress, and explores the influence of these fields on society and industry. Also highlighted is the progress of robotics research and particularities in the field of sheet metal forming and its various applications. This review paper focuses on presenting the latest technological advancements and the integrations of these fields from their beginnings to the present days, providing insights into future research directions.

show abstract

“…Thesis research by [7] with the title Development of GMAW (Gas Metal Arc Welding) Automatic System Prototype for Pipe Welding Based on Machine Vision. Research by [8] with the title Design of 5 Degrees of Freedom Robot Arm with Kinematics Approach. Research by [9] with the title Design and development of a robotic arm.…”

Section: Introductionmentioning

confidence: 99%

Integrated Robotic Arm Control: Inverse Kinematics, Trajectory Planning, and Performance Evaluation for Automated Welding

Huda,

Pebrianti,

Binti MD. Zain

2023

ajse

View full text Add to dashboard Cite

This research delves into the automated functionality of robotic arm manipulators, a hallmark of Industry 4.0, within the manufacturing sector. The study focuses on precise movement adhering to predetermined trajectories, addressing the vital aspects of inverse kinematics and trajectory planning in robotic arm control. Utilizing the Matlab robotic toolbox, the research conducts simulations of inverse kinematic and trajectory planning. An experimental setup involving a robotic arm controlled by an Arduino Mega 2560 microcontroller, embedded with the inverse kinematic algorithm and trajectory planning, is executed. Data acquisition involves inputting coordinates and orientation for automatic welding along a straight path. Joint angles are measured using rotary encoders and converted into Cartesian coordinates to determine the end-effector's position. Discrepancy analysis compares measured joint angles with simulation values, revealing error margins. Movement quality of the robotic arm is assessed through Capability Processes (CP) evaluation. Results indicate disparities between experimental and simulated values. At input coordinates (400mm, 0mm, 300mm), joint angle errors of 2.51º, 0.98º, and 1.48º are observed for joints 2, 3, and 5, respectively. Similarly, at input coordinates (300mm, 0mm, 300mm), joint angle errors of 1.17º, 1.5º, and 2.7º are registered for the same joints. Trajectory error analysis during straight welding reveals average errors of 2.25 mm and 10.57 mm along the x and y axes. Mean absolute errors for joints 2, 3, and 5 are 1.9º, 0.48º, and 1.91º. Keywords: Robotic Arm Manipulators, Inverse Kinematics, Trajectory Error Analysis

show abstract

An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms

Cited by 5 publications

References 52 publications

Artificial intelligence-based position control: reinforcement learning approach in spring mass damper systems

Artificial intelligence-based position control: reinforcement learning approach in spring mass damper systems

Machine Learning, Mechatronics, and Stretch Forming: A History of Innovation in Manufacturing Engineering

Integrated Robotic Arm Control: Inverse Kinematics, Trajectory Planning, and Performance Evaluation for Automated Welding

Contact Info

Product

Resources

About