Article
Robotics
Jaehyun Yi, Byungchul Kim, Kyu-Jin Cho, Yong-Lae Park
Summary: This paper presents a novel design for a multi-fingered robotic gripper with underactuation and fiber-optically sensorized tendons for force sensing, inspired by the Golgi tendon organs found in biological muscles. The gripper consists of three rigid fingers, each with three joints, and uses active and passive tendons to enable flexion and extension. The active tendon is a fiber-optic tendon with an embedded fiber Bragg grating (FBG) for detecting tension, while the passive tendons retract the finger to its initial position. The gripper demonstrates the force-sensing capability of the sensorized tendons.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Computer Science, Theory & Methods
Youssef Amin, Christian Gianoglio, Maurizio Valle
Summary: This paper proposes a robotic gripper equipped with a tactile sensing system to extract information from manipulated objects. Real-time classification of physical properties on resource-constrained devices requires efficient preprocessing techniques and machine learning algorithms. The authors present a tactile sensing system mounted on the Baxter robot for classifying the hardness of objects. They utilize low computational cost preprocessing techniques and three machine learning algorithms for real-time, energy-efficient, and low-memory impact classification. Results demonstrate that convolutional neural networks achieve the highest accuracy (>98%), while support vector machine exhibits the lowest memory occupation (1576 bytes), inference time (<0.077 ms), and energy consumption (<5.74μJ).
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Robotics
Francois R. Hogan, Jean-Francois Tremblay, Bobak H. Baghi, Michael Jenkin, Kaleem Siddiqi, Gregory Dudek
Summary: This paper introduces and develops novel touch sensing technologies that enable robots to better sense and react to intermittent contact interactions. The Finger-STS sensor provides multimodal feedback for robot localization and guiding tasks.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Jiahua Dong, Yang Cong, Gan Sun, Tao Zhang
Summary: This study introduces a novel Lifelong Visual-Tactile Learning (LVTL) model for continuous robotic visual-tactile perception tasks, which fully explores latent correlations between different modalities and achieves significant improvements through specific mechanisms and optimization strategies.
PATTERN RECOGNITION
(2022)
Article
Robotics
Luca Scimeca, Josie Hughes, Perla Maiolino, Liang He, Thrishantha Nanayakkara, Fumiya Iida
Summary: Medical palpation is a diagnostic technique using touch to manipulate soft human tissue, particularly for diagnosing life-threatening conditions like cancer. Research shows that exploring soft body interactions requires complex palpation trajectories, and a probabilistic approach can efficiently search the robot's action space. This study advances robotic palpation and provides frameworks for understanding and utilizing soft body interactions.
Article
Robotics
Yu She, Shaoxiong Wang, Siyuan Dong, Neha Sunil, Alberto Rodriguez, Edward Adelson
Summary: This paper presents a novel perception and control framework for real-time cable following using robotic grippers equipped with vision-based tactile sensors. By combining two tactile-based controllers, the system successfully achieves cable gripping and alignment, preventing the cable from slipping out of the gripper.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2021)
Article
Multidisciplinary Sciences
Ningning Bai, Yiheng Xue, Shuiqing Chen, Lin Shi, Junli Shi, Yuan Zhang, Xingyu Hou, Yu Cheng, Kaixi Huang, Weidong Wang, Jin Zhang, Yuan Liu, Chuan Fei Guo
Summary: Researchers have developed a real-time artificial sensory system based on an iontronic slip-sensor, which can accurately recognize the texture of objects. The sensor can respond to both static and dynamic stimuli with high spatial and frequency resolution. When integrated into a prosthetic fingertip, the sensory system can accurately identify different textiles.
NATURE COMMUNICATIONS
(2023)
Article
Robotics
Vinicius Prado da Fonseca, Xianta Jiang, Emil M. Petriu, Thiago Eustaquio Alves de Oliveira
Summary: Identifying objects is a crucial step in robotic manipulation, and combining tactile sensors and machine learning models can help overcome the challenges posed by flexible robotic hands and unexpected object movements. This study explores tactile object identification through single grasping and brief exploratory procedures, demonstrating that single grasping can improve object recognition.
INTELLIGENT SERVICE ROBOTICS
(2022)
Article
Robotics
Youcan Yan, Jia Pan
Summary: The proposed approach combines autonomous robotic palpation with a tactile sensor to localize and segment artificial tumors in tissue, providing efficient tissue abnormalities detection during robot-assisted minimally invasive surgery (RMIS). By utilizing Bayesian optimization, the tumor can be quickly localized within 30 iterations, while sliding the sensor over the tissue surface enables precise segmentation of the tumor boundary from surrounding soft tissue with high sensitivity and specificity. Additionally, tumor depth estimation can be achieved with Gaussian Process regression, demonstrating robustness and efficiency in both simulation and experiments, which could benefit surgical tasks like tumor removal.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Robotics
Prajval Kumar Murali, Cong Wang, Dongheui Lee, Ravinder Dahiya, Mohsen Kaboli
Summary: This study proposes a novel deep active visuo-tactile cross-modal framework for object recognition by autonomous robotic systems. The framework leverages deep neural networks and active perception strategies to improve recognition accuracy and efficiency.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Engineering, Electrical & Electronic
Zhenning Zhou, Binhua Huang, Runzhi Zhang, Meng Yin, Chengliang Liu, Yiwen Liu, Zhengkun Yi, Xinyu Wu
Summary: With the advancement of robot technology in the medical field, the recognition of tumor depth in robotic palpation plays a significant role in robot-assisted minimally invasive surgery (RMIS). However, the lack of tactile feedback hinders the accurate perception of tumor depth. To solve this problem, this study investigates the recognition of tumor depth by using tactile array data acquired through autonomous robotic palpation. Various deep learning methods, including the 2-D convolutional neural network-long short-term memory (2-D-CNN-LSTM) architecture, are applied for the classification problem. The experimental results show the feasibility and high accuracy of the proposed methods, especially when using all the tactile data from the robotic fingers.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Robotics
Sohee John Yoon, Minsik Choi, Bomin Jeong, Yong-Lae Park
Summary: The performance of robotic grippers is directly related to their ability to grasp objects of different sizes and shapes. This article proposes a length-adjustable linkage mechanism for underactuated fingers to adapt to complex object geometries. Tactile sensing is achieved using hyperelastic soft sensors.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Robotics
Zeyu Lu, Haotian Guo, Wensi Zhang, Haoyong Yu
Summary: This article presents a robotic gripper with a reconfigurable mechanism and tactile sensors, which can perform various grasping configurations and achieve in-hand manipulation of everyday objects. The gripper obtained positive results in benchmark tests and could potentially benefit different robotic applications.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Prajval Kumar Murali, Anirvan Dutta, Michael Gentner, Etienne Burdet, Ravinder Dahiya, Mohsen Kaboli
Summary: This work presents a novel active visuo-tactile based framework for accurately estimating pose of objects in dense cluttered environments. It utilizes a novel declutter graph (DG) to describe the relationship among objects in the scene and proposes a translation-invariant Quatern ion filter (TIQF) for pose estimation. Active visual and tactile points are selected by maximizing the expected information gain. Experimental results show significant improvement in pose accuracy compared to the baseline.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Information Systems
Reina Ishikawa, Masashi Hamaya, Felix Von Drigalski, Kazutoshi Tanaka, Atsushi Hashimoto
Summary: This study developed a system that can predict fractures of fragile foods during robotic food manipulation, allowing the robot to control ingredients without causing irreversible damage. By using tactile sensing and a simple neural network, the system successfully identified the timing of fractures and supervised the robot operation to prevent breakage.
Article
Chemistry, Analytical
Manuel Fernandez-Carmona, Joaquin Ballesteros, Marta Diaz-Boladeras, Xavier Parra-Llanas, Cristina Urdiales, Jesus Manuel Gomez-de-Gabriel
Summary: Smart rollators can autonomously capture gait parameters and avoid complex setups, with the introduction of a low cost open-source modular rollator in this work. The system is based on commercial components and its software architecture runs over ROS2, allowing for further customization and expansion.
Article
Chemistry, Analytical
Manuel Sanchez, Jesus Morales, Jorge L. Martinez, J. J. Fernandez-Lozano, Alfonso Garcia-Cerezo
Summary: This paper presents a new synthetic dataset obtained from Gazebo simulations of an Unmanned Ground Vehicle (UGV) moving on different natural environments. The dataset includes labeled points and pixels from LiDAR and camera scans, and also provides ground-truth 3D pose for benchmarking and supervised learning purposes.
Article
Robotics
Jianzhuang Zhao, Alberto Giammarino, Edoardo Lamon, Juan M. Gandarias, Elena De Momi, Arash Ajoudani
Summary: This article proposes a hybrid learning and optimization framework for mobile manipulators, which can be applied to complex and physically interactive tasks. The framework utilizes a physical interface, GMM/GMR, and quadratic programming to achieve passivity in the controlled system.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Mattia Leonori, Juan M. Gandarias, Arash Ajoudani
Summary: This paper presents MOCA-S, a mobile collaborative robotic assistant with a low-cost capacitive tactile cover for measuring interaction forces on the robot base. Two expanded whole-body controllers are proposed and tested, demonstrating the potential for safe physical Human-Robot Interaction (pHRI).
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Yasuhiro Kato, Pietro Balatti, Juan M. Gandarias, Mattia Leonori, Toshiaki Tsuji, Arash Ajoudani
Summary: This letter presents a novel interaction planning method that uses impedance tuning techniques to respond to environmental uncertainties and unpredictable conditions using haptic information only. The proposed algorithm plans the robot's trajectory based on haptic interaction with the environment and adapts planning strategies as needed. Experimental results show that the method can successfully autonomously plan the robot's trajectory and achieve compliant interaction with an unknown environment.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Francisco Pastor, Francisco J. Ruiz-Ruiz, Jesus M. Gomez-de-Gabriel, Alfonso J. Garcia-Cerezo
Summary: This letter presents an autonomous method for placing a sensorized wristband on victims in a search-and-rescue scenario. The method includes a two-phase process of visual hand tracking and haptic force control, and the wristband design is also discussed. Experimental results demonstrate the success of the wristband placement and the overall performance of the system in a large-scale disaster exercise.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Chemistry, Analytical
Pablo Vera-Ortega, Ricardo Vazquez-Martin, J. J. Fernandez-Lozano, Alfonso Garcia-Cerezo, Anthony Mandow
Summary: This article addresses the importance of real-time bio-signal sensor monitoring for emergency responders in disaster scenarios. It proposes the integration of health monitoring sensors in an Internet of Cooperative Agents architecture for search and rescue missions. The article presents experiments, surveys, and a wearable sensor suite design to enhance emergency worker activity.
Article
Chemistry, Analytical
Francisco Pastor, Da-Hui Lin-Yang, Jesus M. Gomez-de-Gabriel, Alfonso J. Garcia-Cerezo
Summary: This paper presents a dataset of tactile and kinesthetic data obtained from a robot gripper that grabs a human forearm. A fusion approach is used to estimate the actual grasped forearm section, which achieves good results.
Article
Computer Science, Information Systems
Jorge L. Martinez, Jesus Morales, Jesus M. Garcia, Alfonso Garcia-Cerezo
Summary: The kinematic relationship between the instantaneous centers of rotation (ICRs) and differential-drive locomotion in skid-steer vehicles on level terrain has not yet been analyzed on sloped ground. This paper presents a dynamic simulation of a skid-steer vehicle on level ground, where pitch and roll are kept constant by substituting gravity with an equivalent external force. The variations in tread ICRs on inclined ground have been deduced and experimentally corroborated with a four-wheeled mobile robot.
Article
Automation & Control Systems
Manuel Toscano-Moreno, Anthony Mandow, Maria Alcazar Martinez, Alfonso Garcia-Cerezo
Summary: In this article, a new DEM-based asymmetric inclination-aware trajectory planner for ground vehicles is proposed. The planner considers path slopes and defines a non-linear velocity constraints function to optimize travel time. Extensive experimental analysis and comparison with state-of-the-art path planners show the performance of the proposed planner in inclination-aware trajectory planning.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Education & Educational Research
Francisco-Javier Granados-Ortiz, Ana Isabel Gomez-Merino, Jesus Javier Jimenez-Galea, Isidro Maria Santos-Raez, Juan Jesus Fernandez-Lozano, Jesus Manuel Gomez-de-Gabriel, Joaquin Ortega-Casanova
Summary: The number of students enrolled in engineering studies in Spain is declining due to the difficulty in passing subjects and a lack of active student participation. This study aims to provide a feedback tool and survey to assess student satisfaction with scientific-technological activities in industrial engineering. The assessment process involves peer-assessment, self-assessment, and hetero-assessment, followed by a validated survey. Results show that while students found the evaluation experience objective, only a minority considered it advantageous for their learning and self-training, suggesting a need for complementary improvements to the evaluation system.
EDUCATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Gonzalo J. J. Paz-Delgado, J. Ricardo Sanchez-Ibanez, Raul Dominguez, Carlos J. J. Perez-Del-Pulgar, Frank Kirchner, Alfonso Garcia-Cerezo
Summary: A coupled path and motion planner for mobile manipulation is proposed to ensure mission safety and high efficiency. The path planner generates a safe trajectory to reach the goal vicinity and control the final rover orientation. The motion planner generates the arm joints motion profile using a 3D tunnel-like cost volume to ensure self-collision avoidance.
Article
Engineering, Electrical & Electronic
Francisco J. Ruiz-Ruiz, Cristina Urdiales, Jesus M. Gomez-de-Gabriel
Summary: Physical human-robot interaction (pHRI) is an essential skill for robots expected to work with humans. This study proposes a new analytical model that utilizes the inherent compliance of a gripper to calculate external interaction forces, enabling adaptive and compliant grasping.
Article
Computer Science, Cybernetics
Wansoo Kim, Virginia Ruiz Garate, Juan M. Gandarias, Marta Lorenzini, Arash Ajoudani
Summary: The objective of this paper is to develop and evaluate a directional vibrotactile feedback interface as a guidance tool for postural adjustments during work. A vibrotactile device called ErgoTac is employed to develop different feedback modalities, and the most suitable one is evaluated through experiments. The results show strong evidence and intuitiveness of the developed feedback modality in providing guidance towards ergonomic working conditions.
IEEE TRANSACTIONS ON HAPTICS
(2022)
Article
Ergonomics
Maria del Carmen Rey-Merchan, Jesus M. Gomez-de-Gabriel, Juan-Antonio Fernandez-Madrigal, Antonio Lopez-Arquillos
Summary: This article examines the limitations of monitoring safety harness usage in the workplace using Bluetooth Low Energy devices and proposes integrating other technologies to improve effectiveness.
INTERNATIONAL JOURNAL OF OCCUPATIONAL SAFETY AND ERGONOMICS
(2022)