An Artificial Sensory Neuron with Tactile Perceptual Learning. Issue 30 (7th June 2018)

• Record Type: Journal Article
• Authors: Wan, Changjin; Chen, Geng; Fu, Yangming; Wang, Ming; Matsuhisa, Naoji; Pan, Shaowu; Pan, Liang; Yang, Hui; Wan, Qing; Zhu, Liqiang; Chen, Xiaodong
• Is Part Of: Advanced materials. Volume 30:Issue 30(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-06-07
• Subjects: artificial intelligence -- artificial neurons -- electronic skin -- neuromorphic engineering -- perceptual learning; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.201801291
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: Sensory neurons within skin form an interface between the external physical reality and the inner tactile perception. This interface enables sensory information to be organized identified, and interpreted through perceptual learning—the process whereby the sensing abilities improve through experience. Here, an artificial sensory neuron that can integrate and differentiate the spatiotemporal features of touched patterns for recognition is shown. The system comprises sensing, transmitting, and processing components that are parallel to those found in a sensory neuron. A resistive pressure sensor converts pressure stimuli into electric signals, which are transmitted to a synaptic transistor through interfacial ionic/electronic coupling via a soft ionic conductor. Furthermore, the recognition error rate can be dramatically decreased from 44% to 0.4% by integrating with the machine learning method. This work represents a step toward the design and use of neuromorphic electronic skin with artificial intelligence for robotics and prosthetics. Abstract : A neuromorphic tactile processing system is built to mimic biological sensory neurons with sensing, refining, and learning. The spatiotemporal correlated tactile stimuli can be detected and integrated for pattern recognition. The recognition capability can be further enhanced by implementing perceptual learning processes. Such a system would endow robots and prostheses with artificial intelligence to extend their cognition and adaptability.