About This Special Issue

The rapid advancements in robotics have significantly increased the demand for more sophisticated and adaptive manipulation capabilities. Traditional control and modeling techniques, while robust, often fall short in dealing with the complexities and uncertainties of real-world environments. An integration of data-driven methods into the modeling and control of robotic manipulators offers a promising avenue to address these challenges. More specifically, data-driven methods, powered by machine learning, provide new tools for handling the high-dimensional, nonlinear, and dynamic nature of robotic manipulation tasks. These methods enable robots to adapt to new and unforeseen circumstances through learning, improve performance by leveraging vast amounts of sensory data, and achieve higher precision and reliability in complex manipulation tasks.

As robotics continues to permeate various industries, including manufacturing, healthcare, and service sectors, the need for advanced manipulation capabilities becomes even more critical. Data-driven approaches promise to enhance these capabilities, leading to more intelligent and versatile robotic systems.

The primary objectives of this initiative are:

Data-Driven Models: Create accurate and robust models of robot dynamics and environments using machine learning techniques.
Data-Driven Control Algorithms: Design and implement control algorithms that leverage data-driven models to improve manipulation accuracy and efficiency.
Integrate Sensor Data: Utilize multimodal sensor data (visual, tactile, force) to enhance perception and control.

The main topics of this Special Issue include, but are not limited to, the following:

Reinforcement learning for control policies
Supervised and unsupervised learning in control systems
Transfer learning and domain adaptation in robotic control
Deep learning for control applications
Data-driven dynamic modeling of robots
Direct data-driven control strategies
Model identification and system parameter estimation
Predictive modeling for manipulation tasks
Integration of multimodal sensor data (vision, tactile, force, etc.)
Sensor fusion techniques for improved control accuracy
Perception algorithms for object recognition and scene understanding
Adaptive control based on learning algorithms
Model predictive control (MPC) using learned models
Robust and optimal control techniques enhanced by data-driven insights
Real-time control adaptations using machine learning
Data-driven Human-Robot Interaction and Collaboration

Submission Guidelines

Researchers and practitioners are invited to submit original research articles, letters, commentaries, reviews, and perspectives that address the aforementioned topics. All submissions will undergo a single-blind peer-review process with at least two review reports received to ensure the quality and relevance of the published work as the regular submission. Articles are published online immediately upon acceptance. The Article Processing Charge (APC) for publication is fully waived for this special issue.

Manuscripts should be prepared according to the journal's Instructions for Authors and submitted through the online submission system.

Mechatronics Technology

Special Issues

In Progress

Archive