We are entering an era where the artificial intelligence (AI) mirrors human perception—the cornerstone of true intelligence. While brain-inspired chips already excel at processing vision, sound, and touch, they've struggled to "taste" chemicals in wet conditions characteristic of the human mouth. This drawback prevents their potential life-saving uses in medical and environmental fields.

Now, a breakthrough by researchers at the Chinese Academy of Sciences has cracked this challenge. As reported in a recent Proceedings of the National Academy of Sciences of the United States of America (PNAS) publication, a research team led by Prof. YAN Yong from the National Center for Nanoscience and Technology (NCNST) developed an artificial gustatory system capable of precise flavor discrimination in aqueous environments.

They constructed a memristive device using layered graphene oxide (GO) membranes. What makes it special is that it combines two functions: adapting brain-like synapses (for learning) and detecting chemicals (as a sensor). Its functionalities arise from dynamic ion migration within the nanofluidic channels of the GO membrane. They discovered that the ion adsorption-desorption process within GO membranes produces a memory effect.

"When ions 'hesitate' within the graphene interlayer, they get 'stuck' temporarily through surface interactions. This prolonged interfacial interaction simultaneously enables both memory retention and sensing capabilities," said ZHANG Yuchun, one of the first authors of the paper. Capitalizing on the dual functionality, researchers developed an AI-based artificial taste perception system which, after training, could discriminate basic tastes (e.g., sour, bitter, salty, sweet) and complex flavors such as coffee and cola with accuracies above 90%.

"Conventional architectures suffer from significant energy and temporal overhead due to the von Neumann bottleneck between discrete sensing and processing units," explained lead researcher, Prof. YAN Yong. "Our device could compute where it senses, suggesting that neuromorphic in-sensor computing in liquid environments is possible. This would directly address the urgent need for the smarter, faster, and more energy-efficient systems."

This work creates new possibilities for applications ranging from medical therapy for reconstructing taste for taste-loss patients, to autonomous machines capable of 'tasting' their environment, representing a significant leap toward truly intelligent and sense-enabled artificial systems. It is expected to pioneer artificial taste systems that may outperform human capabilities provided the key challenges are addressed—maintaining computational performance while miniaturizing these devices for compatible complementary metal-oxide-semiconductors (CMOS) integration.

Schematic Diagram: Human vs. Graphene Oxide Tasting System (Image by YAN Yong et al)

Contact: YAN Yong

National Center for Nanoscience and Technology (NCNST)

E-mail: yany@nanoctr.cn