Deep Learning-Assisted 3D Pressure Sensors for Control of Unmanned Aerial Vehicles DOI
Junlai Jiang, Hao Gu,

Ruixiang Xu

et al.

ACS Applied Materials & Interfaces, Journal Year: 2025, Volume and Issue: unknown

Published: May 15, 2025

Accurately and reliably detecting recognizing human body movements in real time, relaying appropriate commands to the machine, have substantial implications for virtual reality, remote control, robotics applications. Nonetheless, most contemporary wearable analysis control systems attain action recognition by setting sensor thresholds. In routine usage, stringent trigger conditions facilitate inadvertent contact, resulting a poorer user experience. Here, we created intelligent gesture system utilizing multilayer microstructure composite thin film piezoresistive sensing array deep learning techniques. The exhibits ultrahigh sensitivity (ranging from 0-6 kPa 412.2 kPa-1) rapid response times (loading at 40 ms, recovery 30 ms). detected gestures are classified recognized via convolutional neural network, achieving accuracy of 97.5%. Ultimately, altitude an unmanned aerial vehicle is accomplished through wireless signal transmission reception. To achieve visualization complete gesture-controlled flight process, developed intuitive interface real-time display video surveillance. implementation this introduces novel mechanism human-machine interaction, expands applications robotic technology, offers innovative concepts practical pathways reality.

Language: Английский

Recent progress on artificial intelligence-enhanced multimodal sensors integrated devices and systems DOI
Haihua Wang, Mingjian Zhou, Xiaolong Jia

et al.

Journal of Semiconductors, Journal Year: 2025, Volume and Issue: 46(1), P. 011610 - 011610

Published: Jan. 1, 2025

Abstract Multimodal sensor fusion can make full use of the advantages various sensors, up for shortcomings a single sensor, achieve information verification or security through redundancy, and improve reliability safety system. Artificial intelligence (AI), referring to simulation human in machines that are programmed think learn like humans, represents pivotal frontier modern scientific research. With continuous development promotion AI technology Sensor 4.0 age, multimodal is becoming more intelligent automated, expected go further future. this context, review article takes comprehensive look at recent progress on AI-enhanced sensors their integrated devices systems. Based concept principle technologies algorithms, theoretical underpinnings, technological breakthroughs, pragmatic applications fields such as robotics, healthcare, environmental monitoring highlighted. Through comparative study dual/tri-modal with without using (especially machine learning deep learning), highlight potential performance, data processing, decision-making capabilities. Furthermore, analyzes challenges opportunities afforded by offers prospective outlook forthcoming advancements.

Language: Английский

Citations

2
A Flexible-Integrated Multimodal Hydrogel-Based Sensing Patch DOI Creative Commons
Peng Wang, Guoqing Wang,

Guifen Sun

et al.

Nano-Micro Letters, Journal Year: 2025, Volume and Issue: 17(1)

Published: Feb. 21, 2025

Abstract Sleep monitoring is an important part of health management because sleep quality crucial for restoration human health. However, current commercial products polysomnography are cumbersome with connecting wires and state-of-the-art flexible sensors still interferential being attached to the body. Herein, we develop a flexible-integrated multimodal sensing patch based on hydrogel its application in unconstraint monitoring. The comprises bottom hydrogel-based dual-mode pressure–temperature layer top electrospun nanofiber-based non-contact detection as one integrated device. core substrate exhibits strong toughness water retention, temperature, pressure, proximity realized different mechanisms no crosstalk interference. function verified simulated real-world scenario by robotic hand grasping objects validate practicability. Multiple patches locations pillow assembled intelligent Versatile human–pillow interaction information well their evolution over time acquired analyzed one-dimensional convolutional neural network. Track head movement recognition bad patterns that may lead poor achieved, which provides promising approach

Language: Английский

Citations

2
Human skin-inspired neuromorphic sensors DOI Open Access
Jianfeng Sun, Chenyu Zhang, Chenxi Yang

et al.

Soft Science, Journal Year: 2025, Volume and Issue: 5(2)

Published: March 21, 2025

Human skin-inspired neuromorphic sensors have shown great potential in revolutionizing machines to perceive and interact with environments. skin is a remarkable organ, capable of detecting wide variety stimuli high sensitivity adaptability. To emulate these complex functions, been engineered flexible or stretchable materials sense pressure, temperature, texture, other physical chemical factors. When integrated computing systems, which the brain’s ability process sensory information efficiently, can further enable real-time, context-aware responses. This study summarizes state-of-the-art research on principles computing, exploring their synergetic create intelligent adaptive systems for robotics, healthcare, wearable technology. Additionally, we discuss challenges material/device development, system integration, computational frameworks human sensors, highlight promising directions future research.

Language: Английский

Citations

0
Micro/Nano Self-Powered Device Based on Interface Regulation Strategy DOI
Yu Liu, Wenjun Dong, Y. Luan

et al.

Nano Energy, Journal Year: 2025, Volume and Issue: unknown, P. 110916 - 110916

Published: March 1, 2025

Language: Английский

Citations

0
All-Gel-Based Triboelectric Noncontact Sensor for Human Motion Perception DOI
Shanping Wang,

Haicheng Wan,

Yu Lv

et al.

ACS Applied Materials & Interfaces, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Flexible noncontact sensors are of great significance in contemporary applications. Nevertheless, conventional that rely on metal electrodes have limited flexibility, and their multilayer architectures likely to experience interfacial delamination during extended use. To tackle these problems, we introduce an all-gel-based flexible triboelectric sensor, which consists two parts, i.e., the gelatin/poly(vinyl alcohol) (PVA)/poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS)/graphene (G) electrode hydrogel PVA/cellulose/carbon nanotubes (CNT) aerogel. The not only features outstanding biocompatibility but also exhibits high conductivity. aerogel demonstrates excellent mechanical properties, such as good elasticity durability. This sensor can stably output a current 1.18 μA, charge 18.4 nC/cm2, voltage 3.7 V at stable state. It accurately reliably detect wide range human motions, elbow bending, knee movement, running, providing reliable approach for motion perception facilitating progress relevant fields.

Language: Английский

Citations

0
Metallic Ag with Suspended Network Structure Enhances the Power Generation Performance of NBT-Based Coupled Nanogenerators DOI
Wenlong Xu, Yudong Hou,

Kaibiao Xi

et al.

ACS Applied Materials & Interfaces, Journal Year: 2025, Volume and Issue: unknown

Published: April 24, 2025

Piezo-pyroelectric coupled nanogenerators (PPCNGs) capable of collecting vibration energy and thermal in complex environments are expected to provide a long-term power supply for multifunctional electronic devices. However, the piezoceramics as core PPCNGs limited their generation capabilities due low conductivity high internal resistance. In this work, it is proposed construct Na0.5Bi0.5TiO3-K0.5Bi0.5TiO3/Ag (NBT-KBT/Ag) composite ceramics with suspended network structure by introducing low-melting-point metal Ag second phase. The that can serve transmission path effectively reduces scattering phonons carriers ceramics, improves transport efficiency, achieves dual effects increasing reducing resistance ceramics. And output density PPCNG composed optimal components 736.4 nW/cm3, which 4.7 times unoptimized virgin components. Furthermore, possesses capability recognize object information through pressure temperature sensing. This work reinforces characteristics constructing structure. More importantly, simple efficient design strategy be extended material modification application smart

Language: Английский

Citations

0
Magnetic Cilia and Hair‐Follicle Architecture Enabled Dual‐Mode Bionic E‐Skin for High‐Sensitivity and Wide‐Linear‐Range Tactile/Touchless Perception DOI
Chenxi Lu, Qian Gan, Senjiang Yu

et al.

Advanced Functional Materials, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

Abstract Pressure/magnetism dual‐mode sensors for tactile/touchless perception are desired to adapt multifunctional applications. However, it remains a challenge possess high sensitivity and wide linear response range in both modes. Here, bionic e‐skin with magnetic cilia hair‐follicle architecture (MCHFA) is proposed achieve high‐sensitivity wide‐linear‐range pressure/magnetism (0–26 kPa: S = 2.72 kPa −1 , R 2 0.99; 26–400 0.60 10–171 mT: 2.8 T 0.94), where the mainly dominated by easy deformation of attributed gradient compressibility synergistic architectures hair‐follicle. Additionally, resolutions pressure (0.20%) magnetism (11.0%) obtained due These excellent characteristics dual modes endow MCHFA‐based sensor applications health monitoring human–machine interfaces, such as finger bending game rehabilitation training prevention senile dementia, noncontact coded lock taking advantage less risks cross infection personal information leakage.

Language: Английский

Citations

0
Deep Learning-Assisted 3D Pressure Sensors for Control of Unmanned Aerial Vehicles DOI
Junlai Jiang, Hao Gu,

Ruixiang Xu

et al.

ACS Applied Materials & Interfaces, Journal Year: 2025, Volume and Issue: unknown

Published: May 15, 2025

Accurately and reliably detecting recognizing human body movements in real time, relaying appropriate commands to the machine, have substantial implications for virtual reality, remote control, robotics applications. Nonetheless, most contemporary wearable analysis control systems attain action recognition by setting sensor thresholds. In routine usage, stringent trigger conditions facilitate inadvertent contact, resulting a poorer user experience. Here, we created intelligent gesture system utilizing multilayer microstructure composite thin film piezoresistive sensing array deep learning techniques. The exhibits ultrahigh sensitivity (ranging from 0-6 kPa 412.2 kPa-1) rapid response times (loading at 40 ms, recovery 30 ms). detected gestures are classified recognized via convolutional neural network, achieving accuracy of 97.5%. Ultimately, altitude an unmanned aerial vehicle is accomplished through wireless signal transmission reception. To achieve visualization complete gesture-controlled flight process, developed intuitive interface real-time display video surveillance. implementation this introduces novel mechanism human-machine interaction, expands applications robotic technology, offers innovative concepts practical pathways reality.

Language: Английский

Citations

0