Roboticists Make Robot AI More "Spontaneous" — By Implementing Chaotic Itinerancy

Inspired by the chaotic operation of animal brains, a team from the University of Tokyo have come up with a "chaotic neural network."

Researchers at the University of Tokyo have published a paper designed to showcase how artificially intelligent robots can be more "spontaneous" — by taking advantage of chaotic itinerancy.

“There is an aspect of high-dimensional chaos called chaotic itinerancy (CI) which can explain brain activity during memory recall and association," notes doctoral student Katsuma Inoue of the team's work. "In robotics, CI has been a key tool for implementing spontaneous behavioral patterns."

"In this study, we propose a recipe for implementing CI in a simple and systematic fashion only using complicated time-series patterns generated by high-dimensional chaos. We felt our approach holds potential for more robust and versatile applications when it comes to designing cognitive architectures. It allows us to design spontaneous behaviors without any predefined explicit structures in the controller, which would otherwise serve as a hindrance."

The team's proposed method for implementing chaotic itinerancy in a robotic AI resulted in what they describe as a "high-dimensional chaotic neural network," which they say enables improved autonomous operation and increased flexibility.

"Animal brains yield high-dimensional chaos in their activities, but how and why they utilize chaos remains unexplained. Our proposed model could offer insight into how chaos contributes to information processing in our brains," adds Associate Professor Kohei Nakajima of the work. "Also, our recipe would have a broader impact outside the field of neuroscience since it can potentially be applied to other chaotic systems too. For example, next-generation neuromorphic devices inspired by biological neurons potentially exhibit high-dimensional chaos and would be excellent candidates for implementing our recipe. I hope we will see artificial implementations of brain functions before too long."

The team's paper is available under open-access terms in the journal Science Advances.

Gareth Halfacree
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire:
Related articles
Sponsored articles
Related articles