Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Ying Sun et al.
Summary: With the advancement of sensor technology and artificial intelligence, video gesture recognition technology using big data has made human-computer interaction more natural and flexible, providing enhanced interactive experiences in teaching, on-board control, electronic gaming, and more. A robust recognition algorithm based on multi-level feature fusion of a two-stream convolutional neural network is proposed to handle challenges like lighting changes, background clutter, rapid movement, and partial occlusion. Experimental results demonstrate that the proposed model can accurately track and recognize gestures, outperforming the single-channel model with improved detection accuracy and mean average precision (mAP). Furthermore, it achieves high recognition rates under occlusion and varying light intensities, showing satisfactory performance compared to other methods in various datasets.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Ying Liu et al.
Summary: This paper focuses on instance-level 3D target detection in complex indoor scenes. By constructing an indoor 3D target detection dataset and establishing a pixel-by-pixel key point voting network, combined with depth images, key point detection and pose optimization are achieved, and evaluation and visualization analysis are conducted.
APPLIED INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Xuefeng Dong et al.
Summary: Grasp detection is critical for a robot. Detecting object and corresponding grasp positions in a stacked environment is challenging. A new method called MMD is proposed to improve the accuracy of object and grasp position detection. MMD consists of a feature extractor and a multi-stage object predictor. The proposed MMD achieves better grasp detection performance, with a state-of-the-art 76.71% mAPg recognition precision on the VMRD dataset. Test experiments demonstrate the feasibility of the method on the Kinova robot.
Article
Engineering, Mechanical
Xiaofeng Zhang et al.
Summary: This paper presents a collision-free solution to the inverse kinematics problem of a mobile manipulator. The main contribution is a novel inverse kinematics solution framework combining unique domains. The problem is formulated as an optimization problem, and a simplified objective function is proposed using a kinematics decoupling method. The joint variables are decoupled and constrained, and an approach to initialize the variables is proposed. Furthermore, a solution framework for the manipulator body to avoid obstacles is presented, and CMA-ES algorithm is applied to optimize the framework. Simulation results demonstrate the effectiveness of the proposed method.
MECHANISM AND MACHINE THEORY
(2023)
Article
Mathematical & Computational Biology
Yang Zhang et al.
Summary: Object detection and grasp detection are crucial for unmanned systems operating in cluttered real-world environments. The proposed SOGD approach utilizes neural learning to predict the best grasp configuration for each detected object, overcoming the challenge of finding relationships between objects and grasp configurations. Experimental results demonstrate the superior performance of SOGD in predicting reasonable grasp configurations from cluttered scenes, outperforming state-of-the-art methods on public datasets.
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
(2023)
Review
Computer Science, Artificial Intelligence
Xin Liu et al.
Summary: The digital twin is a crucial technology for smart manufacturing and industrial digital transformation. This paper provides a systematic research on the basic components of the digital twin. By analyzing 117 articles from 2017 to 2022, it clarifies the definition, characteristics, and application areas of the digital twin, and explores the research methodology and application potential of its core components. The research results and future research recommendations are presented.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Information Systems
Gongfa Li et al.
Summary: This paper explores the integration of blockchain technology in the Internet of Medical Things (IoMT) and its impact on user security, convenience, and interoperability. It presents a novel approach to continuous dynamic gesture recognition by improving filters and models for surface electromyography (EMG) signals. The experimental results demonstrate the effectiveness of the proposed method in reducing false recognition rates and achieving accurate gesture recognition.
INFORMATION SCIENCES
(2023)
Article
Chemistry, Analytical
Zhongjie Zhang et al.
Summary: This paper presents a method for realizing an autonomous real-time 6D robotic grasping system on Kinova Gen3, integrating object detection, pose estimation, and grasping plan techniques. The system utilizes pixel-wise voting network (PV-net) for estimating the object's 6D pose, and a rapid analytical method on point cloud to judge the authenticity of the detected object. The system demonstrates stable and robust performance in various installation positions and heavily cluttered scenes.
Article
Robotics
Sheng Yu et al.
Summary: In this letter, a novel grasp detection neural network called Squeeze-and-Excitation ResUNet (SE-ResUNet) is developed. It can generate grasp poses from RGB-D images and predict the quality scores of each grasp pose. The experimental results show high accuracy and real-time performance, and the proposed method outperforms other methods in comparison study.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Hu Cheng et al.
Summary: This paper presents a vision-based grasping platform that uses a deep grasp detector to accurately predict grasp poses for various objects. Real-world experiments demonstrate the effectiveness of the system in robust and accurate grasping.
IEEE SENSORS JOURNAL
(2022)
Article
Automation & Control Systems
Hui Zhang et al.
Summary: Pose estimation is a critical technology in industrial robotics. This study proposes a practical robotic grasping method that uses 6D pose estimation with protective correction to address the challenges of rapid detection in complex multiscene environments. The method trains a deep object pose estimation network with a synthetic dataset and uses the perspective-n-point algorithm to estimate the 6-DoF pose. A corrected grasping pose algorithm is also proposed to prevent collisions caused by misrecognition.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Robotics
Olyvia Kundu et al.
Summary: The paper proposes a novel method to detect graspable handles for picking objects from a confined and cluttered space. The method combines color and depth curvature information to segment the target object from its background and imposes the geometrical constraints of a two-finger gripper to localize the graspable regions. The proposed approach overcomes the limitations of a poorly trained deep network object detector and provides a simple and efficient method for grasp pose detection that can be implemented online with near real-time performance.
Article
Engineering, Multidisciplinary
Ying Liu et al.
Summary: This paper proposes a method for determining the grasping posture of manipulator based on shape analysis and force closure, which simplifies the grasping of irregular or complex objects into basic shapes for planning. The best grasping posture is obtained by evaluating indicators, achieving rapid determination of grasping system and defining grasping quality.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Engineering, Multidisciplinary
Juntong Yun et al.
Summary: This paper proposes a hybrid control method of auto-dynamic bit based on bit control to achieve flexible grasping of manipulator in unknown environment. By analyzing constraint conditions, establishing dynamic model, and introducing an improved position controller, the study successfully verifies the control performance of the force/bit hybrid controller.
ALEXANDRIA ENGINEERING JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Michael Hegedus et al.
Summary: This algorithm discovers grasp pose solutions for multiple grasp types using partially-sensed point clouds of unknown objects. It introduces the use of histograms and voxel grid representations to guide the gripper orientation search and match finger contact points, resulting in robust and scalable grasp pose solutions.
Article
Computer Science, Artificial Intelligence
Yinghui Liu et al.
Summary: This paper proposes a method that combines data-driven grasp constraint learning with one-shot human demonstration to learn grasp constraints from human demonstrations. By presenting task constraints in a GMM-based gripper-independent form, the method learns task constraints from simulated data with self-labeled grasp quality scores. The learned task constraint model can be used to infer both the unknown grasping task and the probability density distributions of the task constraints on the object point cloud.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2022)
Article
Automation & Control Systems
Peng He et al.
Summary: In this paper, a self-triggered model predictive control (MPC) strategy is proposed for discrete-time semi-Markov jump linear systems to achieve a desired finite-time performance. By introducing the concept of multi-step semi-Markov kernel, the multi-step predictive states under system mode jumping are obtained. Meanwhile, a self-triggered scheme is used to automatically predict sampling instants and reduce the computational burden of on-line solving of MPC.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Engineering, Mechanical
Gongfa Li et al.
Summary: This paper proposes an instruction pose-based compensation method to address the problem of applying inverse kinematics after error compensation. The method compensates the pose error between the calibrated model and the nominal model to the instruction pose and solves the new instruction pose using the inverse kinematics algorithm of the nominal model. The experiments on calibrated robots demonstrate the correctness of the theoretical analysis. It is concluded that the calibrated robot can be simplified and the original robot's inverse kinematics can be obtained using the proposed method.
MECHANISM AND MACHINE THEORY
(2022)
Article
Computer Science, Artificial Intelligence
Rui Wang et al.
Summary: This paper investigates pattern analysis on the symmetric positive definite manifold and designs two Riemannian operation modules for neural networks. Experimental results demonstrate the effectiveness of the proposed approach.
Article
Biotechnology & Applied Microbiology
Juntong Yun et al.
Summary: This article proposes a real-time target detection method based on a lightweight convolutional neural network, improving target detection technology by reducing the number of model parameters and improving detection speed. Experimental results demonstrate the effectiveness and superiority of the proposed method in complex scenes, with tests on video and deployment on the Android platform also confirming its real-time performance and scalability.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Hu Cheng et al.
Summary: In this article, a novel deep model for robot grasp pose detection is proposed, which can generate grasp poses for unknown objects in unstructured environments. With the use of rotated bounding boxes and fully convolutional style generation, the model is able to generate a large number of grasps at the pixel level. Moreover, the detection accuracy is improved by extracting and combining low-level high-resolution features and high-level abstract features.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Environmental Sciences
Yuedong Ku et al.
Summary: This study introduces a robot for sorting construction and demolition waste, which can finely classify a large number of objects before mixing, thus improving the level of resource utilization. By implementing a deep learning method for grasping detection, the accuracy of robotic grasping has been significantly increased, meeting the efficiency and accuracy requirements for CDW sorting under actual working conditions.
JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT
(2021)
Article
Engineering, Industrial
Reyes Rios-Cabrera et al.
Summary: This paper introduces a dynamic categorization method for fast detection of 3D objects, showing promising results in experiments and demonstrating a more flexible and efficient approach compared to traditional rigid categories.
INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION
(2021)
Article
Computer Science, Information Systems
Mingshuai Dong et al.
Summary: The MASK-GD algorithm proposes a method for reliable grasping detection of an object in complex scenes, using features from the MASK area to achieve grasp detection, and performs comparably with state-of-the-art algorithms on Cornell Grasp Dataset and Jacquard Dataset.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Theory & Methods
Du Jiang et al.
Summary: This paper proposes a multi-task semantic segmentation model in complex indoor environments using the improved Faster-RCNN algorithm, addressing issues of uneven lighting by enhancing fusion methods and algorithms. The model achieves high performance and efficiency in segmenting contours of different scale objects.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Automation & Control Systems
Qunchao Yu et al.
Summary: The study introduces a novel multilevel convolutional neural network for robotic grasping of unknown objects, achieving high-accuracy grasping through four levels of different structures and functions. The network accurately determines the optimal grasping position and finger position distribution, enabling high-accuracy grasping in complex environments.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Du Jiang et al.
Summary: A target object grab setting model is established based on the candidate region suggestion network to ensure stable gripping performance of a manipulator in a dynamic environment. The model's detection success rate is improved by adding small-scale anchor values for small area grabbing target position detection, and a 94.3% crawl detection success rate is achieved on multi-target detection data sets through color image and depth image information fusion. These methods effectively enhance the model's robustness and crawl success rate.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Nan Guo et al.
Summary: A novel lightweight general-purpose attention module is designed, which simultaneously considers channel attention and spatial attention and combines them through a nonlinear hybrid method to facilitate better network fine-tuning. The module allows for adjustable parameters in each attention branch, making it more flexible and adaptable while being applicable to existing deep architectures.
Article
Automation & Control Systems
Xingshuo Jing et al.
Summary: The paper introduces a novel domain adversarial transfer network for transferring grasping skills learned from simulated environments to the real world. By utilizing generative adversarial training and task-constrained grasp candidates, shared features are extracted to effectively reduce the domain gap between different domains.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2021)
Article
Automation & Control Systems
Tuan-Tang Le et al.
Summary: This paper proposes a novel real-time 3D object recognition and grasping solution with the potential to handle multi-object class scenes. Experimental results show high accuracy and efficiency, with significant improvements in performance metrics compared to existing methods.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2021)
Article
Robotics
Jie Wang et al.
Summary: The study introduces a new grasp detection method that improves accuracy through candidate grasp detection and spatial feature scoring. Experimental results demonstrate that the method has a high success rate when faced with new objects.
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
(2021)
Article
Engineering, Mechanical
Peng Cheng et al.
Summary: This work investigates the issue of asynchronous fault detection filtering for discrete-time piecewise homogeneous Markov jump systems. A novel asynchronous fault detection filter is proposed and validated through real-time experiments.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Shangchun Liao et al.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Jinrong Tian et al.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2020)
Article
Computer Science, Information Systems
Lin Zhao et al.
INFORMATION SCIENCES
(2020)
Article
Chemistry, Multidisciplinary
HyunJun Jo et al.
APPLIED SCIENCES-BASEL
(2020)
Review
Computer Science, Artificial Intelligence
Chunwei Tian et al.
Article
Agriculture, Multidisciplinary
Ning Guo et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Proceedings Paper
Automation & Control Systems
Dongwon Park et al.
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
(2020)
Article
Instruments & Instrumentation
Jianmei Wang et al.
SENSORS AND MATERIALS
(2019)
Article
Instruments & Instrumentation
Markus Ulrich et al.
TM-TECHNISCHES MESSEN
(2019)
Article
Chemistry, Multidisciplinary
Tong Li et al.
APPLIED SCIENCES-BASEL
(2019)
Article
Computer Science, Artificial Intelligence
Wentao Cheng et al.
NEURAL COMPUTING & APPLICATIONS
(2019)
Article
Computer Science, Theory & Methods
Xianye Bu et al.
INTERNATIONAL JOURNAL OF GENERAL SYSTEMS
(2018)
Article
Robotics
Ian Lenz et al.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2015)
Article
Robotics
Alexander Kasper et al.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2012)
