Machine learning (ML) has significantly transformed robotics and industrial applications by enhancing automation, decision-making, and optimization processes. Modern ML methods have substantially improved performance in areas such as robotic grasping, locomotion, perception and control of robotic systems, navigation, planning, mapping, human-robot interaction, and localization. The rapid Advancement in ML algorithms, computational capabilities, and data accessibility presents immense opportunities for innovative solutions in robotics and industrial sectors.
The primary objective of this special issue is to showcase the latest advancements in ML techniques that are specifically tailored for robotics and industrial applications. By presenting innovative applications of ML across various industrial sectors, we aim to highlight the transformative potential of these technologies. Additionally, this issue seeks to address the challenges and limitations associated with integrating ML in real-world robotic and industrial applications, providing a comprehensive overview of current obstacles and potential solutions. There is an urgent need for new real-time algorithms and more explainable and interpretable models that can efficiently process data from sensors, preferably using unsupervised or semi-supervised approaches. Furthermore, we aim to showcase interdisciplinary approaches that combine ML with other emerging technologies such as the Internet of Things (IoT), edge computing, and 5G networks, thereby underscoring the synergy and enhanced capabilities resulting from these integrations.
This special issue aims to gather cutting-edge research, reviews, and case studies that explore the latest developments, challenges, and future directions in this dynamic field. The topics of interest include, but are not limited to:
ML for Autonomous Robotic Systems and Vehicles
- Autonomous robotic locomotion and advanced navigation
- Autonomous grasping and manipulation with mobile robots
- Multi-robot systems and networked robots
- Autonomous driving, planning, mapping, and localization
ML for Human-Robot Interaction:
- Simulation-based learning for robotics
- Learning from human demonstrations and gesture/emotion recognition
- Safety and collaborative task learning between humans and robots
- Bio-inspired and social robots, healthcare robotics
ML for Sensor Integration in Robotics:
- Utilization of sensors (EEG, ECG, IMU) in robotics
- Multi-modal sensor fusion
- Unstructured data mining for industrial applications
ML and Cognitive Computing:
- Context-aware and emotion-aware applications in robotics and industry
- Cognitive computing and affective computing (artificial emotional intelligence)
Industrial Applications of Machine Learning:
- Industrial process optimization through machine learning
- Predictive maintenance in manufacturing
- Robotics in industrial automation and quality control
- Industrial decision-making based on ML models
Interpretable ML and Explainable AI:
- Interpretable ML in robotics and industrial applications
- Synergistic benefits of integrating ML with emerging technologies
Integration with Emerging Technologies:
- Combining ML with IoT, edge computing, and 5G networks
Guest Editors:
Associate Prof. Zoran Najdovski Deakin University, Australia)
Dr. Siamak Pedrammehr (Deakin University, Australia)
Dr. Van Thanh Huynh (Deakin University, Australia)
Associate Prof. Tae Hee Lee (Jeonbuk National University, Republic of Korea)
Prof. Aysegul Ucar (Mechatronics Engineering Department, Firat University, Elâziğ, Turkey)
Dr. Mohammad Fotouhi (Delft University of Technology, Netherlands)
Submission Procedure:
Any new submission will be processed with single-blind peer review immediately.
To submit a paper, please go to ROBOMECH Journal's submission.
For submission guideline please check here.
When submitting your paper, please select “Advances in Machine Learning for Robotics and Industry Applications” under “Collection” to be included in this special call.