Coexistence of chaos and stability. These visualizations of the system’s output show broad patterns of instability, but localized patterns of stability.
Credit: Inoue et al.
Autonomous functions for robots, such as spontaneity, are highly sought after.
Many control mechanisms for autonomous robots are inspired by the functions of animals, including humans. Roboticists often design robot behaviors using predefined modules and control methodologies, which makes them task-specific, limiting their flexibility. Researchers offer an alternative machine learning-based method for designing spontaneous behaviors by capitalizing on complex temporal patterns, like neural activities of animal brains. They hope to see their design implemented in robotic platforms to improve their autonomous capabilities.
Robots and their control software can be classified as a dynamical system, a mathematical model that describes the ever-changing internal states of something. There is a class of dynamical system called high-dimensional chaos, which has attracted many researchers as it is a powerful way to model animal brains. However, it is generally hard to gain control over high-dimensional chaos owing to the complexity of the system parameters and its sensitivity to varying initial conditions, a phenomenon popularized by the term “butterfly effect.” Researchers from the Intelligent Systems and Informatics Laboratory and the Next Generation Artificial Intelligence Research Center at the University of Tokyo explore novel ways for exploiting the dynamics of high-dimensional chaos to implement humanlike cognitive functions.
“There is an aspect of high-dimensional chaos called chaotic itinerancy (CI) which can explain brain activity during memory recall and association,” said doctoral student Katsuma Inoue. “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.”
Reservoir computing (RC) is a machine learning technique that builds on dynamical systems theory and provides the basis of the team’s approach. RC is used to control a type of neural network called a recurrent neural network (RNN). Unlike other machine learning approaches that tune all neural connections within a neural network, RC only tweaks some parameters while keeping all other connections of an RNN fixed, which makes it possible to train the system faster. When the researchers applied principles of RC to a chaotic RNN, it exhibited the kind of spontaneous behavioral patterns they were hoping for. For some time, this has proven a challenging task in the field of robotics and artificial intelligence. Furthermore, the training for the network takes place prior to execution and in a short amount of time.
“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,” said Associate Professor Kohei Nakajima. “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 Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Autonomous boats could be your next rideon November 16, 2020 at 10:00 pm
Five years in the making, MIT’s autonomous floating vessels get an upgrade in size and learn a new way to communicate aboard the waters The feverish race to produce the shiniest, safest, speediest ...
- PerceptIn to launch the micro-Robot Taxi Demonstration on Public Road in Japanon November 16, 2020 at 5:23 pm
Robot taxi demonstration Mopi (Mobility service by PerceptIn) concept at Mizukubo, Tenno ward, Hamamatsu city. This first public road operation is supported by Hamamatsu City and Macnica, Inc.
- ADLINK’s Edge AI Powers Autonomous Race Cars for Indy Autonomous Challengeon November 16, 2020 at 12:35 pm
ADLINK Technology is an official sponsor of the Indy Autonomous Challenge (IAC), scheduled for October 23, 2021.
- Multi-link catfish skull may hold key to better underwater robotson November 16, 2020 at 11:12 am
Even though they don't have flexible tongues, catfish are still able to rotate captured prey within their mouths. A new understanding of how they're able to do so could ultimately lead to more ...
- Robot dogs start security patrols at US military baseon November 16, 2020 at 10:11 am
Personnel will have the ability to "drive" the "computerized canines" using virtual reality headsets, according to the US Air Force.
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Spontaneous robotic behaviors
- Researchers Give Robotic AI Spontaneous Behavioron November 14, 2020 at 6:16 pm
Researchers and roboticists are continually trying to achieve autonomous functions in robots, and they often look toward the animal brain as a point of inspiration for control mechanisms. Because of ...
- Robotic AI learns to be spontaneous - Researchers use dynamical systems and machine learning to add spontaneity to AIon November 11, 2020 at 11:40 pm
“In robotics, CI has been a key tool for implementing spontaneous ... when it comes to designing cognitive architectures. It allows us to design spontaneous behaviors without any predefined explicit ...
- Robotic AI learns to be spontaneouson November 11, 2020 at 3:07 pm
Roboticists often design robot behaviors using predefined modules and control methodologies, which makes them task-specific, limiting their flexibility. Researchers offer an alternative machine ...
- Robotic AI learns to be spontaneouson November 11, 2020 at 11:54 am
"In robotics, CI has been a key tool for implementing ... It allows us to design spontaneous behaviors without any predefined explicit structures in the controller, which would otherwise serve ...
- Designing spontaneous behavioral switching via chaotic itinerancyon November 11, 2020 at 11:19 am
In robotics, approaches based on dynamical systems theory ... is a powerful option for modeling spontaneous behavior with the functional hierarchy realized through the dynamics. CI is a frequently ...