Heterogeneous Structure Omnidirectional Strain Sensor Arrays with Cognitively-Learned Neural Networks.

Mechanically stretchable strain sensors have gained tremendous attentions in bio-inspired skin sensation systems and artificially intelligent tactile sensors. However, high-accuracy detection of both strain intensity and direction with simple device/array structures is still insufficient. To overcome this limitation, we propose an omnidirectional strain perception platform utilizing a stretchable strain sensor array with triangular-sensor-assembly (three sensors tilted by 45 °) coupled with machine learning-based neural network classification algorithm. The strain sensor, which is constructed with strain-insensitive electrode regions and strain-sensitive channel region, can minimize the undesirable electrical intrusion from the electrodes by strain, leading to a heterogeneous surface structure for more reliable strain sensing characteristics. The strain sensor exhibited decent sensitivity with gauge factor of ∼8, a moderate sensing range (0 ∼ 35%), and relatively good reliability (3,000 stretching cycles). More importantly, by employing a multiclass-multioutput behavior-learned cognition algorithm, the stretchable sensor array with triangular-sensor-assembly exhibited highly accurate recognition of both direction and intensity of an arbitrary strain by interpretating the correlated signals from the three-unit sensors. The omnidirectional strain perception platform with neural network algorithm exhibited overall strain intensity and direction accuracy around 98±2% over a strain range of 0 ∼ 30% in various surface stimuli environments. This article is protected by copyright. All rights reserved.