Touchformer: A Transformer-based two-tower architecture for tactile temporal signal classification DOI
Chongyu Liu, Hong Liu, Hu Chen

и другие.

IEEE Transactions on Haptics, Год журнала: 2023, Номер 17(3), С. 396 - 404

Опубликована: Дек. 25, 2023

Haptic temporal signal recognition plays an important supporting role in robot perception. This paper investigates how to improve classification performance on multiple types of haptic datasets using a Transformer model structure. By analyzing the feature representation signals, Transformer-based two-tower structural model, called Touchformer, is proposed extract and spatial features separately integrate them self-attention mechanism for classification. To address characteristics small sample datasets, data augmentation employed stability dataset. Adaptations overall architecture training optimization procedures are made robustness model. Experimental comparisons three publicly available demonstrate that Touchformer significantly outperforms benchmark indicating our approach's effectiveness providing new solution

Язык: Английский

Recent Advances in Tactile Sensory Systems: Mechanisms, Fabrication, and Applications DOI Creative Commons

Jianguo Xi,

Huaiwen Yang, Xinyu Li

и другие.

Nanomaterials, Год журнала: 2024, Номер 14(5), С. 465 - 465

Опубликована: Март 4, 2024

Flexible electronics is a cutting-edge field that has paved the way for artificial tactile systems mimic biological functions of sensing mechanical stimuli. These have an immense potential to enhance human-machine interactions (HMIs). However, still faces formidable challenges in delivering precise and nuanced feedback, such as achieving high sensitivity emulate human touch, coping with environmental variability, devising algorithms can effectively interpret data meaningful diverse contexts. In this review, we summarize recent advances sensory systems, piezoresistive, capacitive, piezoelectric, triboelectric sensors. We also review state-of-the-art fabrication techniques Next, focus on applications HMIs, intelligent robotics, wearable devices, prosthetics, medical healthcare. Finally, conclude future development trends

Язык: Английский

Процитировано

16

Tactile-Sensing Technologies: Trends, Challenges and Outlook in Agri-Food Manipulation DOI Creative Commons

Willow Mandil,

Vishnu Rajendran, Kiyanoush Nazari

и другие.

Sensors, Год журнала: 2023, Номер 23(17), С. 7362 - 7362

Опубликована: Авг. 23, 2023

Tactile sensing plays a pivotal role in achieving precise physical manipulation tasks and extracting vital features. This comprehensive review paper presents an in-depth overview of the growing research on tactile-sensing technologies, encompassing state-of-the-art techniques, future prospects, current limitations. The focuses tactile hardware, algorithmic complexities, distinct features offered by each sensor. has special emphasis agri-food relevant technologies. It highlights key areas manipulation, including robotic harvesting, food item feature evaluation, such as fruit ripeness assessment, along with emerging field kitchen robotics. Through this interdisciplinary exploration, we aim to inspire researchers, engineers, practitioners harness power technology for transformative advancements By providing understanding landscape serves valuable resource driving progress its application systems.

Язык: Английский

Процитировано

25

A comprehensive review of robot intelligent grasping based on tactile perception DOI
Tong Li, Yuhang Yan,

Chengshun Yu

и другие.

Robotics and Computer-Integrated Manufacturing, Год журнала: 2024, Номер 90, С. 102792 - 102792

Опубликована: Июнь 7, 2024

Язык: Английский

Процитировано

8

Review on the Use of Brain Computer Interface Rehabilitation Methods for Treating Mental and Neurological Conditions DOI Creative Commons
Vladimir Khorev, Semen Kurkin, Artem Badarin

и другие.

Journal of Integrative Neuroscience, Год журнала: 2024, Номер 23(7)

Опубликована: Июль 5, 2024

This review provides a comprehensive examination of recent developments in both neurofeedback and brain-computer interface (BCI) within the medical field rehabilitation. By analyzing comparing results obtained with various tools techniques, we aim to offer systematic understanding BCI applications concerning different modalities input data utilized. Our primary objective is address existing gap area meta-reviews, which more outlook on field, allowing for assessment current landscape scope BCI. main methodologies include meta-analysis, search queries employing relevant keywords, network-based approach. We are dedicated delivering an unbiased evaluation studies, elucidating vectors research development this field. encompasses diverse range applications, incorporating use interfaces rehabilitation treatment diagnoses, including those related affective spectrum disorders. encompassing wide variety cases, perspective utilization treatments across contexts. The structured organized presentation information, complemented by accompanying visualizations diagrams, renders valuable resource scientists researchers engaged domains biofeedback interfaces.

Язык: Английский

Процитировано

7

In‐Sensor Touch Analysis for Intent Recognition DOI

Yijing Xu,

Shifan Yu,

Lei Liu

и другие.

Advanced Functional Materials, Год журнала: 2024, Номер 34(52)

Опубликована: Сен. 2, 2024

Abstract Tactile intent recognition systems, which are highly desired to satisfy human's needs and humanized services, shall be accurately understanding identifying intent. They generally utilize time‐driven sensor arrays achieve high spatiotemporal resolution, however, encounter inevitable challenges of low scalability, huge data volumes, complex processing. Here, an event‐driven touch (IR sensor) with in‐sensor computing capability is presented. The merit enables the IR ultrahigh resolution obtain complete information intrinsic concise data. It achieves critical signal extraction action trajectories a rapid response time 0.4 ms excellent durability >10 000 cycles, bringing important breakthrough tactile recognition. Versatile applications prove integrated functions for great interactive potential in all‐weather environments regardless shading, dynamics, darkness, noise. Unconscious even hidden features can perfectly extracted accuracy 98.4% further auxiliary diagnostic test demonstrates practicability telemedicine palpation therapy. This groundbreaking integration sensing, reduction, ultrahigh‐accuracy will propel leapfrog development conscious machine intelligence.

Язык: Английский

Процитировано

7

Artificial Intelligence Assisted Nanogenerator Applications DOI
Shumao Xu,

Farid Manshaii,

Xiao Xiao

и другие.

Journal of Materials Chemistry A, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

This review examines the integration of artificial intelligence with nanogenerators to develop self-powered, adaptive systems for applications in robotics, wearables, and environmental monitoring.

Язык: Английский

Процитировано

7

Porous nanocomposites with enhanced intrinsic piezoresistive sensitivity for bioinspired multimodal tactile sensors DOI Creative Commons

Jianpeng Zhang,

Song Wei,

Caichao Liu

и другие.

Microsystems & Nanoengineering, Год журнала: 2024, Номер 10(1)

Опубликована: Янв. 26, 2024

Abstract In this work, we propose porous fluororubber/thermoplastic urethane nanocomposites ( PFTNs ) and explore their intrinsic piezoresistive sensitivity to pressure. Our experiments reveal that the of PFTN-based sensor pressure up 10 kPa increases 900% compared thermoplastic nanocomposite PTN counterpart 275% fluororubber PFN counterpart. For pressures exceeding kPa, resistance-pressure relationship PFTN follows a logarithmic function, is 221% 125% higher than PFN, respectively. With excellent thick film, single sensing unit with integrated electrode design can imitate human skin for touch detection, perception traction sensation. The range our multimodal tactile reaches ~150 Pa, it exhibits linear fit over 97% both normal shear force. We also demonstrate an electronic skin, made array units, capable accurately recognizing complex interactions including pinch, spread, tweak motions.

Язык: Английский

Процитировано

6

Artificial Intelligence enabled Biodegradable All-Textile Sensor for Smart Monitoring and Recognition DOI

Pengfei Zhao,

Yilin Song,

Zhipeng Hu

и другие.

Nano Energy, Год журнала: 2024, Номер 130, С. 110118 - 110118

Опубликована: Авг. 15, 2024

Язык: Английский

Процитировано

5

Design of a flexible tactile sensor for material and texture identification utilizing both contact-separation and surface sliding modes for real-life touch simulation DOI
Vasiliki Zacharia, Achilleas Bardakas, Andreas Anastasopoulos

и другие.

Nano Energy, Год журнала: 2024, Номер 127, С. 109702 - 109702

Опубликована: Май 8, 2024

Язык: Английский

Процитировано

4

Machine Learning-Enhanced Bacteria Detection Using a Fluorescent Sensor Array with Functionalized Graphene Quantum Dots DOI
Xin Zhang, Weiwei Zhu,

Lianghui Mei

и другие.

ACS Applied Materials & Interfaces, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

Pathogenic bacteria are the source of many serious health problems, such as foodborne diseases and hospital infections. Timely accurate detection these pathogens is vital significance for disease prevention, control epidemic spread, protection public security. Rapid identification pathogenic has become a research focus in recent years. In contrast to traditional large-scale equipment, fluorescent sensor array developed this study can detect within just five min cost-effective. The employs nitrogen- sulfur-doped graphene quantum dots (NS-GQDs) synthesized through simple hydrothermal process, making it environmentally friendly by avoiding toxic metal elements. Functionalized with antibiotics, spectinomycin, kanamycin, polymyxin B, NS-GQDs (renamed S-NS-GQDs, K-NS-GQDs, B-NS-GQDs) exhibit variable affinities different bacteria, enabling broad-spectrum without targeting specific species. Upon binding fluorescence intensity functionalized decreases significantly. exhibits distinct responses bacterial species, which be distinguished using various machine learning algorithms. results demonstrate that platform quickly accurately identify quantify showing excellent performance terms accuracy, sensitivity, stability. This makes promising tool great practical application prospects detection.

Язык: Английский

Процитировано

0