Deep Neural Network Based Electrical Impedance Tomographic Sensing Methodology for Large-Area Robotic Tactile Sensing

Park, Hyunkyu; Park, Kyungseo; Mo, Sangwoo; Kim, Jung

doi:10.1109/tro.2021.3060342

Cited by 71 publications

(36 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Park et al designed a large-area electrical impedance tomography-based tactile sensor, which can be used for contact contour detection. 75 These methods also show good performance in tactile exploration. Many object exploration and recognition approaches were developed according to tactile information and machine learning methods.…”

Section: Planning-level Perceptionmentioning

confidence: 97%

A review on sensory perception for dexterous robotic manipulation

Xia¹,

Deng

Fang

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Sensory perception for dexterous robotic hands is an active research area and recent progress in robotics. Effective dexterous manipulation requires robotic hands to accurately feedback their state or perceive the surrounding environment. This article reviews the state-of-the-art of sensory perception for dexterous robotic manipulation. Two types of sensors, such as intrinsic and extrinsic sensors, are introduced according to their function and layout in robotic hands. These sensors provide rich information to a robotic hand, which contains the posture, the contact information of objects, and the physical information of the environment. Then, a comprehensive analysis of perception methods including planning-level, control-level, and learning-level perceptions is presented. The information obtained from sensory perception can help robotic hands to make decisions effectively. Previously issued reviews mainly focus on the design of tactile senor, while we analyze and discuss the relationship among sensing, perception, and dexterous manipulation. Some potential research topics on sensory perception are also summarized and discussed.

show abstract

Section: Planning-level Perceptionmentioning

confidence: 97%

A review on sensory perception for dexterous robotic manipulation

Xia¹,

Deng

Fang

et al. 2022

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…than other types of sensors. Existing machine learning methods can be utilized in the sensor calibration for: 1) extending spatial resolution of limited sensing elements [127], [156]; 2) improving the adaptability of mass production long-term usage [157]; compensating hysteresis induced by the viscoelastic property of the polymeric substrate materials [158]; 4) decoupling multimode deformations [135]; and 5) enhancing measurement reliability of large-area sensor array [15], [159] or some specific transductions [160], [161].…”

Section: ) Machine Learning Assisted Sensingmentioning

confidence: 99%

Review of Robot Skin: A Potential Enabler for Safe Collaboration, Immersive Teleoperation, and Affective Interaction of Future Collaborative Robots

Pang

Yang

Pang

2021

IEEE Trans. Med. Robot. Bionics

View full text Add to dashboard Cite

The emerging applications of collaborative robots (cobots) are spilling out from product manufactories to service industries for human care, such as patient care for combating the coronavirus disease 2019 (COVID-19) pandemic and in-home care for coping with the aging society. There are urgent demands on equipping cobots with safe collaboration, immersive teleoperation, affective interaction, and other features (e.g., energy autonomy and self-learning) to make cobots capable of these application scenarios. Robot skin, as a potential enabler, is able to boost the development of cobots to address these distinguishing features from the perspective of multimodal sensing and self-contained actuation. This review introduces the potential applications of cobots for human care together with those demanded features. In addition, the explicit roles of robot skin in satisfying the escalating demands of those features on inherent safety, sensory feedback, natural interaction, and energy autonomy are analyzed. Furthermore, a comprehensive review of the recent progress in functionalized robot skin in components level, including proximity, pressure, temperature, sensory feedback, and stiffness tuning, is presented. Results show that the codesign of these sensing and actuation functionalities may enable robot skin to provide improved safety, intuitive feedback, and natural interfaces for future cobots in human care applications. Finally, open challenges and future directions in the real implementation of robot skin and its system synthesis are presented and discussed.

show abstract

“…To further evaluate the spatial resolution of the proposed large-area tactile sensor, a series of multitouch indentation tests was performed. In addition to the two-point discrimination test [21], which has been presented to examine a deep neural network-based EIT method for large-area tactile sensing, we proposed a comprehensive testing protocol including two-point, three-point and four-point discrimination tests for evaluating the tactile spatial acuity of our sensor. Since the sensitivity to intensity of the EIT-based sensor varies across the sensing area, the spatial performance of the sensor is location-dependent [35].…”

Section: B Multi-touch Indentation Testmentioning

confidence: 99%

A large-area flexible tactile sensor for multi-touch and force detection using electrical impedance tomography

Wang¹,

Chen²,

Gang³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, a large-area flexible tactile sensor for multi-touch and force detection based on EIT technology was developed. A novel design of a sensor material made of a porous elastic polymer and ionic liquid was proposed. The proposed conductive flexible materials combining elastic porous structures and conductive liquids provide continuous, linear changes in impedance with respect to touch forces. A deep learning scheme PSPNet based on MobileNet was adopted to postprocess the originally reconstructed images to improve the performance of tactile perception. By using this data-driven method, we can improve the spatial resolution of the tactile sensor to achieve a single-point position detection error of 7.5±4.5 mm without using internal electrodes.

show abstract

Deep Neural Network Based Electrical Impedance Tomographic Sensing Methodology for Large-Area Robotic Tactile Sensing

Cited by 71 publications

References 58 publications

A review on sensory perception for dexterous robotic manipulation

A review on sensory perception for dexterous robotic manipulation

Review of Robot Skin: A Potential Enabler for Safe Collaboration, Immersive Teleoperation, and Affective Interaction of Future Collaborative Robots

A large-area flexible tactile sensor for multi-touch and force detection using electrical impedance tomography

Contact Info

Product

Resources

About