... visual inspection theory and application. Corresponding author Ge Ma m_ge@gzhu.edu.cn 04 07 2025 19 08 2025 28 10 2025 03 11 2025 © 2026 Emerald Publishing Limited 2026 Emerald Publishing Limited Licensed re-use rights only Deep learning Defect detection...

... versions. Potholes detection Accident-free navigation Deep learning Machine vision Artificial intelligence Automated guided vehicles (AGV) Unmanned Ground Vehicles (UGV) epitomize advanced systems that seamlessly integrate essential components such as efficient mapping, precise pose...

...-making. In addition, a MobileNet-based deep learning (DL) model is proposed for quality inspection of injection parts, fine-tuned using the TL approach. Findings Using the TL approach, the MobileNet-based DL model demonstrates exceptional performance, achieving validation accuracy of 99.1...

... applications. Figure 3 System components of the manufactured drone A data set was created by collecting images of damaged, dusty and normal solar panels to train the deep learning model. The images in the data set were obtained through the designed drone, and the photos of the solar panels...

... 05 2021 01 07 2021 16 08 2021 20 12 2021 © Emerald Publishing Limited 2021 Emerald Publishing Limited Licensed re-use rights only Deep learning Convolutional neural network Vision positioning Eye-in-hand Grasp detection Image processing...

...Zhengtuo Wang; Yuetong Xu; Guanhua Xu; Jianzhong Fu; Jiongyan Yu; Tianyi Gu Purpose In this work, the authors aim to provide a set of convenient methods for generating training data, and then develop a deep learning method based on point clouds to estimate the pose of target for robot grasping...

... performance (88.47% accuracy and lowest computational time) than other methods. Originality/value This study can provide theoretical and engineering guidance for hand pose recognition in surgery robot teleoperation and design a new deep learning model for accuracy enhancement. Hang Su can be contacted...

... ( C ∼ t ) decides which information will be viewed as the candidate updated information described in equations (3) and (4) : Deep learning 3D Long-term recurrent convolutional networks Human sub-assembly recognition Human-robot collaboration In recent years, mass...

... been proposed for better handling segmentation of 6 D point cloud. By introducing normal vectors, semantic segmentation could be accomplished precisely for close points with opposite normal, such as wing upper and lower surfaces. Combining deep learning skills with traditional methods, the proposed...

...Yupei Wu; Di Guo; Huaping Liu; Yao Huang Purpose Automatic defect detection is a fundamental and vital topic in the research field of industrial intelligence. In this work, the authors develop a more flexible deep learning method for the industrial defect detection. Design/methodology/approach...

... environment than the conventional method. Originality/value A new method of deep learning based biomimetic robot path planning is proposed. The authors designed a multi-layer CNN which includes max-pooling layer and convolutional kernel. Then, the first and second layers features can be extracted...