Article
Engineering, Electrical & Electronic
Haofeng Chen, Gang Ma, Peng Wang, Xiaojie Wang
Summary: This article introduced a bio-impedance analysis method based on human hand anatomy, which achieved high classification accuracy in hand gesture recognition with flexibility in electrode arrangement and fewer electrodes. Experimental results showed that compared to traditional electrical impedance tomography methods, the proposed method can better distinguish different gestures with higher accuracy.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Information Systems
Yajun Pang, Yujiang Gong, Xianan Hao
Summary: This paper proposes a static gesture recognition method based on point cloud sequences and an inverse kinematics model. The input point cloud sequences are divided into boundary points and inner points for marking, and inverse kinematics is used to estimate the position of joints that cannot be marked by curvature differences. Bending angles and fingertips position are selected as features, and recognition is completed using KNN. Experimental results show that the proposed method achieves an average recognition accuracy of about 96%.
Article
Robotics
Marc Peral, Alberto Sanfeliu, Anais Garrell
Summary: In this paper, an efficient and reliable deep-learning approach for hand gesture recognition in robot communication is presented. The approach utilizes visual information to extract hand landmarks and predict gestures, achieving high accuracy and real-time performance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Multidisciplinary Sciences
Shiqi Wang, Kankan Wang, Tingping Yang, Yiming Li, Di Fan
Summary: This paper proposes an improved 3D-ResNet sign language recognition algorithm with enhanced hand features, aiming to improve the accuracy of sign language recognition. The algorithm detects the hand regions using the improved EfficientDet network and enhances the detection ability with dual channel and spatial attention modules. Additionally, an improved residual module is used to extract sign language features. Experimental results show that the proposed algorithm achieves higher recognition accuracy compared to other algorithms.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Hardware & Architecture
Graziano Fronteddu, Simone Porcu, Alessandro Floris, Luigi Atzori
Summary: In this article, a dataset consisting of 27 dynamic hand gesture types is proposed. The dataset was collected from 21 subjects at full HD resolution. The subjects were carefully instructed and monitored to ensure the accuracy of the gestures.
Article
Computer Science, Artificial Intelligence
Derek W. Orbaugh Antillon, Christopher R. Walker, Samuel Rosset, Iain A. Anderson
Summary: A smart dive glove has been developed to recognize 13 hand gestures used in diving communication. Different classification algorithms were trained and evaluated, showing good performance in a dry environment but decreasing underwater, especially when divers need to focus on other tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Lesong Jia, Xiaozhou Zhou, Chengqi Xue
Summary: This paper presents a novel non-trajectory-based gesture recognition method (NT-GRM) based on hand skeleton information and a hidden Markov model (HMM). It can accurately and quickly recognize static and dynamic gestures with high recognition accuracy and speed.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Xin Wang, Dharmaraj Veeramani, Zhenhua Zhu
Summary: This article proposes a system for recognizing construction workers' hand gestures using wearable sensors on fingers. The system extracts motion data by synchronizing, normalizing, and smoothing finger motions and uses an enhanced fully convolutional neural network (FCN) for gesture recognition. The system achieved a precision and recall of 85.7% and 93.8% respectively in the system validation test. A pilot study demonstrated the feasibility of using the proposed system to interact with a robotic dump truck. Furthermore, the system was compared with vision-based recognition methods to assess their relative advantages and limitations quantitatively and qualitatively.
IEEE SENSORS JOURNAL
(2023)
Article
Chemistry, Analytical
Minjeong Yoo, Yuseung Na, Hamin Song, Gamin Kim, Junseong Yun, Sangho Kim, Changjoo Moon, Kichun Jo
Summary: In this paper, a hybrid hand gesture system combining an IMU-based motion capture system and a vision-based gesture system is proposed to improve real-time performance. The system utilizes real-time object detection and an estimated orientation sensed by a thumb-mounted micro-IMU to allow flexible drone operation.
Article
Automation & Control Systems
Yu Jiang, Xianglong Peng, Mingzhu Xue, Chong Wang, Hong Qi
Summary: This paper discusses the importance of AUV in ocean research and the impact of the underwater environment on AUV control and human-robot interaction. It introduces fuzzy control to address the parameter issue in the traditional control model, as well as the gesture recognition framework for controlling AUV.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jing Qi, Li Ma, Zhenchao Cui, Yushu Yu
Summary: As robots become more common in our daily lives, there is a growing interest in the development of vision-based hand gesture recognition for natural human-robot interaction. This paper analyzes hand gesture recognition using monocular and RGB-D cameras, discussing the process of data acquisition, hand gesture detection and segmentation, feature extraction, and gesture classification. Experimental evaluations and algorithms for human-robot interaction are examined, along with the advances necessary for improving current hand gesture recognition systems.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wee How Khoh, Ying Han Pang, Shih Yin Ooi, Hui Yen Yap
Summary: Dynamic signature recognition with a no-contact characteristic is solved through a multi-view spatiotemporal approach based on spectral histogramming. Microsoft Kinect sensor captures motion sequences, allowing for rich information retrieval and feature description. The proposed approach achieves multi-resolution analysis for robust dynamic signature recognition.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Refat Khan Pathan, Munmun Biswas, Suraiya Yasmin, Mayeen Uddin Khandaker, Mohammad Salman, Ahmed A. F. Youssef
Summary: Sign Language Recognition is a breakthrough for communication among the deaf-mute society, and this study proposes a cost-effective technique using image dataset to detect American Sign Language (ASL) with high accuracy by utilizing a convolutional neural network model and image processing methods.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Wee How Khoh, Ying Han Pang, Andrew Beng Jin Teoh, Shih Yin Ooi
Summary: Transfer learning in hand gesture-based signature classification shows robustness against forgery attacks, achieving high precision and recall rates, with low error rates in random and skilled forgery attacks.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Electrical & Electronic
S. L. Aarthy, V. Malathi, Monia Hamdi, Ines Hilali-Jaghdam, Sayed Abdel-Khalek, Romany F. Mansour
Summary: Recognition of hand gestures has significant benefits in improving human-robot interaction. The use of big data and machine learning has made it easier to accurately classify hand motions using EMG signals. However, the process of collecting and labeling the dataset is time-consuming. To address this, a strategy combining depth vision learning with EMG-based hand gesture detection was developed. The technique achieved automatic classification of EMG data without considering the hand motion sequence and demonstrated improved performance in recognizing hand gestures.
JOURNAL OF SENSORS
(2022)
Article
Nuclear Science & Technology
Sofia Coloma, Manuel Ferre, Fernando Arranz, Gioacchino Micciche, Daniel Sanchez-Herranz, Oriol Nomen, Jose M. Cogollor
Summary: The IFMIF-DONES project aims to test materials using high-energy deuterons to produce a neutron flux. The Beam Dump cartridge absorbs charged particle beams after shutdown, requiring remote handling due to high activation and radiation levels.
FUSION ENGINEERING AND DESIGN
(2021)
Article
Engineering, Mechanical
Alexandre Campos, Eliseo Cortes, Daniel Martins, Manuel Ferre, Aldo Contreras
Summary: A portable mechatronic rehabilitation system named SARPA has been developed for bedridden patients, offering flexibility in different training modes and body members. Traditional rehabilitation is limited by human strength, while mechatronic systems aim to optimize user comfort and treatment effectiveness.
JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING
(2021)
Article
Computer Science, Cybernetics
Gonzalo Garcia-Valle, Sandra Arranz-Paraiso, Ignacio Serrano-Pedraza, Manuel Ferre
Summary: The article presents a study on determining absolute and differential vibrotactile thresholds in different areas of the torso to develop reliable haptic patterns for enhancing user performance in human-machine interaction systems. Results suggest the possibility of setting a unique minimum vibration for creating haptic patterns and estimating upper or lower differential thresholds using a K-value.
IEEE TRANSACTIONS ON HAPTICS
(2021)
Article
Chemistry, Analytical
Isabel-Maria Alguacil-Diego, Alicia Cuesta-Gomez, Aldo-Francisco Contreras-Gonzalez, David Pont-Esteban, David Cantalejo-Escobar, Miguel Angel Sanchez-Uran, Manuel Ferre
Summary: This study investigates the usability and acceptance of a hybrid exoskeleton called ExoFlex for upper-limb passive rehabilitation in patients with rotator cuff injury. Seven participants aged between 50 to 79, including six women and one man, showed promising results in acceptance and usability, with an average score of 80.71 on the SUS test.
Article
Chemistry, Analytical
Paul Espinosa Peralta, Manuel Ferre, Miguel Angel Sanchez-Uran
Summary: This article presents a novel and robust solution for using robots in manufacturing and industrial maintenance sectors to detect and rotate fasteners. The vision system is based on an industrial camera, tunable liquid crystal lens, and active near-infrared reflectance illumination. Robust algorithms using segmentation neural networks and vision were developed to find the center and rotation of the hexagon fastener under different conditions. Extensive evaluation tests were conducted to validate tolerance errors, robotic forces, and implemented algorithms.
Article
Chemistry, Analytical
Carlos Veiga Almagro, Renato Andres Munoz Orrego, Alvaro Garcia Gonzalez, Eloise Matheson, Raul Marin Prades, Mario Di Castro, Manuel Ferre Perez
Summary: This paper presents a novel grasping strategy that reduces the workload for operators by using a geometrical analysis and machine learning techniques to ensure the uniformity of grasping. It utilizes a monocular camera to recognize and isolate targets, estimate their spatial coordinates, and provide stable grasping points.
Article
Computer Science, Artificial Intelligence
Jose Luis Samper-Escudero, Sofia Coloma, Miguel Angel Olivares-Mendez, Miguel Angel Sanchez-Uran Gonzalez, Manuel Ferre
Summary: This article introduces a cable-driven exosuit called LUXBIT, which is a flexible exoskeleton that adapts to the user's anatomy by arranging the fabric fibers and sewing patterns. It incorporates a novel deformable mechanism that promotes natural lifting of the arm. LUXBIT is designed to assist bimanual activities in daily living and has been shown to reduce muscle activity in the upper limbs and prolong the ability to hold tiring postures.
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
(2023)
Proceedings Paper
Robotics
Paul Espinosa Peralta, Veronica Palomino-Diaz, Pablo Rodriguez Herrerias, Carlos Rodriguez del Castillo, Carmen Maria Pedraza Cubero, Juan Pablo Yuste, Paulino Aparicio Cillan, Rafael Mesia Lopez, Guillermo Aguila Rodriguez, Victor Pablo Fernandez Franco, Miguel Angel Sanchez-Uran, Manuel Ferre
Summary: This paper describes the prototype of ROSE, a robotic system for automatic spacer installation in overhead power lines. The system has been tested and evaluated at UPM and Red Electrica facilities. It autonomously navigates and installs spacers at a configurable distance in meters. The system is supervised by an operator who receives environmental data from video signals and sensors via WIFI. Two robotic arms perform rod manipulation and screw operations, while a vehicle transports components.
ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2
(2023)
Proceedings Paper
Robotics
Violeta Redondo Gallego, Maria del Valle Delgado Jimenez, Gioacchino Micciche, Martin Mittwollen, Jose M. Sebastian, Miguel A. Sanchez-Uran, Manuel Ferre
Summary: This paper presents the design of a gripper with spring-maintained resting position for its fingers. By properly applying forces during grasping and following the correct releasing path, the fingers can be displaced. This mechanism overcomes the limitation of conventional actuators in hazardous environments with high radiation levels, but requires redesigning the objects to be manipulated.
ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 1
(2023)
Article
Computer Science, Information Systems
David Pont-Esteban, Miguel Angel Sanchez-Uran, Manuel Ferre
Summary: This article presents a robust control architecture for upper-limb exosuits to address uncertainties and disturbances. The proposed controller, CPISDO, utilizes a combination of proportional-integral and sliding mode control, along with a disturbance observer, to achieve good tracking performance and disturbance rejection.
Article
Computer Science, Information Systems
David Pont-Esteban, Miguel Angel Sanchez-Uran, Aldo Francisco Contreras-Gonzalez, Manuel Ferre
Summary: This paper presents a software current limitation method based on a continuous DC motor model predictor, which dynamically saturates the maximum voltages applicable to the motor to maintain the current under the predefined threshold. The method achieves full-time current limitation and allows configurable current peaks. Both standalone motor tests and rehabilitation exoskeleton applications have validated the effectiveness of this method.
Proceedings Paper
Computer Science, Cybernetics
Jose Luis Samper-Escudero, Sofia Coloma, Miguel A. Olivares-Mendez, Miguel Angel Sanchez-Uran, Manuel Ferre
Summary: Flexible exoskeletons are lightweight robots that surround a user's anatomy, assisting or opposing motion, and promoting anatomical adaption through sewing patterns and fabrics. By stacking patches, pressures on the user and actuation misalignment are reduced, enhancing the transfer of assistance forces.
PROCEEDINGS OF THE 2021 IEEE INTERNATIONAL CONFERENCE ON HUMAN-MACHINE SYSTEMS (ICHMS)
(2021)