4.6 Article

Deep Learning Framework for Controlling Work Sequence in Collaborative Human-Robot Assembly Processes

Related references

Note: Only part of the references are listed.
Article Computer Science, Interdisciplinary Applications

An integrated mixed reality system for safety-aware human-robot collaboration using deep learning and digital twin generation

Sung Ho Choi et al.

Summary: This study introduces a novel integrated mixed reality system using deep learning and digital twin generation to accurately measure minimum safe distance and provide task assistance for human operators. By tracking the shared workplace and providing user-centric visualization through smart MR glasses, the system ensures safe and effective human-robot collaboration.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2022)

Article Automation & Control Systems

New directions for inline inspection of automobile laser welds using non-destructive testing

Miguel Araujo Machado et al.

Summary: An innovative system for detecting surface and sub-surface welding defects in laser-brazed joints is presented, operating autonomously and integrated with a robotized arm. Customized eddy current probes were designed and experimentally validated for detecting pore defects with 0.13 mm diameter and sub-surface defects buried 1 mm deep. The integration of the system with the manufacturing process towards an Industry 4.0 quality control paradigm is also discussed.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

Article Mathematical & Computational Biology

Novel Hybrid Brain-Computer Interface for Virtual Reality Applications Using Steady-State Visual-Evoked Potential-Based Brain-Computer Interface and Electrooculogram-Based Eye Tracking for Increased Information Transfer Rate

Jisoo Ha et al.

Summary: A novel hybrid BCI system combining SSVEP-based BCI and EOG-based eye tracking was proposed to increase the accuracy and information transfer rate of a nine-target SSVEP-based BCI in VR environment, showing significantly improved performance compared to traditional SSVEP-based BCI systems.

FRONTIERS IN NEUROINFORMATICS (2022)

Article Computer Science, Artificial Intelligence

Surface Electromyography Signal Recognition Based on Deep Learning for Human-Robot Interaction and Collaboration

Nuno Mendes

Summary: The interaction between humans and collaborative robots has sparked interest in gesture recognition systems. This study proposes a two-step algorithm using sEMG devices to recognize hand gestures, with a focus on the segmentation and recognition steps using deep learning methods. Comparisons with other devices demonstrate the effectiveness of this system.

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS (2022)

Article Computer Science, Interdisciplinary Applications

Hybrid machine learning for human action recognition and prediction in assembly

Jianjing Zhang et al.

Summary: This paper presents a hybrid approach to context-aware human action recognition and prediction based on the integration of a convolutional neural network (CNN) and variable-length Markov modeling (VMM) to improve operational flexibility and productivity in human-robot collaboration.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2021)

Review Computer Science, Interdisciplinary Applications

Emerging research fields in safety and ergonomics in industrial collaborative robotics: A systematic literature review

Luca Gualtieri et al.

Summary: Human-robot collaboration is a key technology of Industry 4.0 that is currently transforming manufacturing shop floors. Safety and ergonomics are the main focus of research in the field of collaborative robotics, with emerging research fields and challenges attracting significant interest as well.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2021)

Article Chemistry, Analytical

Multisensor Inspection of Laser-Brazed Joints in the Automotive Industry

Miguel A. Machado et al.

Summary: The article discusses a multisensory customized inspection system for automobile laser brazing using potential drop method and eddy current testing. Numerical simulations show superior performance of a new four-point probe configuration. The dedicated inspection system effectively detects porosities, cracks, and lack of bonding defects.

SENSORS (2021)

Review Chemistry, Analytical

Human-Robot Perception in Industrial Environments: A Survey

Andrea Bonci et al.

Summary: The capability of perception is crucial for human-robot interaction in industrial environments. As industrial settings require higher levels of automation to meet fast-paced and cost-effective market demands, robots must be able to sense human presence and intentions to prevent decreases in productivity and safety hazards. Robots with enhanced perception and interaction capabilities will play an increasingly important role in collaborative and cooperative applications within shared industrial spaces.

SENSORS (2021)

Article Chemistry, Analytical

Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition

Aleksandr Laptev et al.

Summary: This study focuses on building an effective end-to-end ASR system in low-resource environments with a high OOV rate. It proposes a dynamic acoustic unit augmentation method based on Byte Pair Encoding with dropout (BPE-dropout) technique, which results in steady improvements in regular and personalized speech recognition tasks (at least 6% relative WER reduction and 25% relative F-score reduction) without additional computational costs. By utilizing BPE-dropout, the monolingual Turkish Conformer achieves competitive results with a 22.2% character error rate (CER) and 38.9% WER, approaching the performance of the best published multilingual system.

SENSORS (2021)

Review Chemistry, Multidisciplinary

A Review of Human-Computer Interaction and Virtual Reality Research Fields in Cognitive InfoCommunications

Jozsef Katona

Summary: Cognitive infocommunications is an emerging discipline that aims to merge human cognitive capabilities with digital devices' cognitive capabilities, leading to promising results such as more effective learning and the development of new learning environments. This field has already produced numerous technological innovations and plays a key role in understanding and supporting the merging of cognitive processes with ICT.

APPLIED SCIENCES-BASEL (2021)

Article Chemistry, Analytical

Image Generation for 2D-CNN Using Time-Series Signal Features from Foot Gesture Applied to Select Cobot Operating Mode

Fadwa El Aswad et al.

Summary: This paper presents a foot gesture approach for robot control and switching between different operating modes, utilizing statistical analysis and neural network technology. The study shows that a higher recognition rate can be achieved through specific representation of features.

SENSORS (2021)

Review Computer Science, Information Systems

Deep Learning in the Industrial Internet of Things: Potentials, Challenges, and Emerging Applications

Ruhul Amin Khalil et al.

Summary: Recent advances in IoT have led to a proliferation of interconnected devices and the use of various smart applications, with the application of deep learning algorithms in IIoT providing various new applications. This article introduces various DL techniques and their applications in different industries, as well as use cases and research challenges in smart manufacturing, smart metering, and smart agriculture in IIoT systems.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Engineering, Industrial

Repetitive assembly action recognition based on object detection and pose estimation

Chengjun Chen et al.

JOURNAL OF MANUFACTURING SYSTEMS (2020)

Article Computer Science, Interdisciplinary Applications

Deep learning-based mobile augmented reality for task assistance using 3D spatial mapping and snapshot-based RGB-D data

Kyeong-Beom Park et al.

COMPUTERS & INDUSTRIAL ENGINEERING (2020)

Article Robotics

Towards Efficient Human-Robot Collaboration With Robust Plan Recognition and Trajectory Prediction

Yujiao Cheng et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Computer Science, Artificial Intelligence

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Proceedings Paper Automation & Control Systems

Hand/arm gesture segmentation by motion using IMU and EMG sensing

Joao Lopes et al.

27TH INTERNATIONAL CONFERENCE ON FLEXIBLE AUTOMATION AND INTELLIGENT MANUFACTURING, FAIM2017 (2017)

Proceedings Paper Automation & Control Systems

Human behavior and hand gesture classification for smart human-robot interaction

Nuno Mendes et al.

27TH INTERNATIONAL CONFERENCE ON FLEXIBLE AUTOMATION AND INTELLIGENT MANUFACTURING, FAIM2017 (2017)