Bioinspired Co‐Design of Tactile Sensor and Deep Learning Algorithm for Human–Robot Interaction

Kong, Depeng; Yang, Geng; Pang, Gaoyang; Ye, Zhiqiu; Lv, Honghao; Zhao, Yu; Wang, Fei; Wang, Xi Vincent; Xu, Kaichen; Yang, Huayong

doi:10.1002/aisy.202270027

Cited by 18 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reproduced (Adapted) with permission. [124] Copyright 2022, Wiley-VCH. piezoelectric, and triboelectric mechanisms, and the related research has focused on improving the performance parameters (sensitivity, dynamic range, hysteresis, etc.)…”

Section: Prospectsmentioning

confidence: 99%

“…[117][118][119] However, efforts to assure cost-effective production and mechanical durability, while comprehensively increasing each performance, have been relatively insufficient. Improving the sensory performance through learning-based algorithms [120][121][122][123][124] and data analysis techniques [125][126][127][128] has also been pursued to recognize gesture, [123,124] speech, [122] object species, [129,130] and surface texture. [131] Conventional algorithms for the tactile sensors have focused on how to use the sensor as mentioned above, and there is a lack of approach to improving the intrinsic performance of the sensor.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Current Landscape of the Robotic Tactile Array Sensors and Algorithm‐Based Performance Enhancement

Cho,

Park,

Kim

et al. 2024

Adv Eng Mater

View full text Add to dashboard Cite

The automated robots utilizing the traditional rigid tactile sensors have achieved significant success in effective task execution. Advancing into the era of service robots and humanoids that should perform sophisticated works in daily life, recent research trends in robotic tactile sensors have been shifting from the conventional rigid sensors to flexible/stretchable sensors. Over the past decade, the flexible/stretchable tactile sensors with human skin‐like mechanical compliance and stimulation perceptions have seen considerable advances. However, there are many substantial remaining challenges to produce practically useful flexible/stretchable tactile sensors such as the signal hysteresis originating from sensor material and the limited spatial resolution resulting from excessive addressing lines and signal interferences. Incorporation of learning‐based algorithms and data analysis techniques have been introduced recently and made remarkable successes in improving the challenges. Because most robotic tactile sensors are fabricated by using the electronic sensing mechanisms or platforms, this article presents a concise overview on recent flexible/stretchable tactile sensors. This article introduces a brief discussion on the sensor performance parameters and sensing mechanisms, and the algorithmic approaches. In addition, it addresses existing challenges associated with current tactile array sensors and algorithms, then discusses prospects and proposes a research direction for immediate practical uses in robots.This article is protected by copyright. All rights reserved.

show abstract

Section: Prospectsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Current Landscape of the Robotic Tactile Array Sensors and Algorithm‐Based Performance Enhancement

Cho,

Park,

Kim

et al. 2024

Adv Eng Mater

View full text Add to dashboard Cite

show abstract

“…[ 13–15 ] Among them, strain sensors based on soft porous materials, such as polyurethane (PU) sponge, are of great application potential. [ 16 ] The sensing capability of the strain sensors is attributed to the addition of conductive materials, such as carbon nanotubes (CNT) and various metallic nanowires, [ 17 ] which are deposited on the scaffold of the porous material. [ 18 ] The deformation of the scaffolds under external stimuli contributes to the connection or disconnection of the conductive fillers, [ 19 ] thus achieving the changes in sensing signals, as demonstrated in Figure S1, Supporting Information.…”

Section: Introductionmentioning

confidence: 99%

Highly Stretchable and Sensitive Strain Sensor Based on Porous Materials and Rhombic‐Mesh Structures for Robot Teleoperation

Pang

Liang

et al. 2023

Advanced Sensor Research

View full text Add to dashboard Cite

Wearable sensors for human motion capture offer a promising human–robot interface to control robots in the teleoperation scenario, where robots could function as the second body of human operators to fulfill tasks remotely and accurately. In this paper, a novel strain sensor based on a soft polyurethane (PU) sponge and carbon nanotubes (CNT) is designed for motion capture of human joints. The unique 3D porous microstructure of the PU‐CNT sponge provides the sensor with high sensitivity. To bridge the gap between the high sensitivity and high stretchability of the strain sensor, a rhombic‐mesh structure with optimized geometric parameters, in conjunction with a pre‐compression design, is proposed for strain sensor prototyping, which endows the sensor with an extra elongation rate during the stretching process. The proposed PU‐CNT strain sensor manifests promising sensing performance with a stretchability of up to 300% and a maximum gauge factor of 3893, together with long‐term durability, low detection limit, and fast response capacity. Finally, the validation of the strain sensor is carried out by deploying the sensor on a human elbow to realize the teleoperation of a robot arm, which could be monitored through the digital twin model of the robot in a real‐time manner.

show abstract

“…Moreover, to enhance the reliability of signal recognition, machine learning algorithms are emerging as effective means to reveal correlations and subtle differences among multichannel datasets. [ 27,28 ] In order to acquire more intriguing functionalities, the trend of flexible tactile sensors is moving toward integrated flexible sensor systems, which generally refer to sensor array integration, multimodal flexible sensor integration, and integrated signal processing systems. [ 29 ]…”

Section: Introductionmentioning

confidence: 99%

A Multifunctional Flexible Tactile Sensor Based on Resistive Effect for Simultaneous Sensing of Pressure and Temperature

Zhu,

Luo,

Cai

et al. 2023

Advanced Science

View full text Add to dashboard Cite

Flexible tactile sensors with multifunctional sensing functions have attracted much attention due to their wide applications in artificial limbs, intelligent robots, human‐machine interfaces, and health monitoring devices. Here, a multifunctional flexible tactile sensor based on resistive effect for simultaneous sensing of pressure and temperature is reported. The sensor features a simple design with patterned metal film on a soft substrate with cavities and protrusions. The decoupling of pressure and temperature sensing is achieved by the reasonable arrangement of metal layers in the patterned metal film. Systematically experimental and numerical studies are carried out to reveal the multifunctional sensing mechanism and show that the proposed sensor exhibits good linearity, fast response, high stability, good mechanical flexibility, and good microfabrication compatibility. Demonstrations of the multifunctional flexible tactile sensor to monitor touch, breathing, pulse and objects grabbing/releasing in various application scenarios involving coupled temperature/pressure stimuli illustrate its excellent capability of measuring pressure and temperature simultaneously. These results offer an effective tool for multifunctional sensing of pressure and temperature and create engineering opportunities for applications of wearable health monitoring and human‐machine interfaces.

show abstract

Bioinspired Co‐Design of Tactile Sensor and Deep Learning Algorithm for Human–Robot Interaction

Cited by 18 publications

References 0 publications

Current Landscape of the Robotic Tactile Array Sensors and Algorithm‐Based Performance Enhancement

Current Landscape of the Robotic Tactile Array Sensors and Algorithm‐Based Performance Enhancement

Highly Stretchable and Sensitive Strain Sensor Based on Porous Materials and Rhombic‐Mesh Structures for Robot Teleoperation

A Multifunctional Flexible Tactile Sensor Based on Resistive Effect for Simultaneous Sensing of Pressure and Temperature

Contact Info

Product

Resources

About